Skip to yearly menu bar
Skip to main content
Main Navigation
NeurIPS
Help/FAQ
Contact NeurIPS
Create Profile
Code of Ethics
Code of Conduct
Journal To Conference Track
Diversity & Inclusion
Proceedings
Future Meetings
Press
Exhibitor Information
Privacy Policy
Downloads
My Stuff
Login
Sydney
Atlanta
Paris
Select Year: (2026)
2026
2025
2024
2023
2022
2021
2020
2019
2018
2017
2016
2015
2014
2013
2012
2011
2010
2009
2008
2007
2006
Earlier Conferences
Dates
Submit
Call for Papers
Main Track Handbook
Reviewing Guidelines
Call for Evaluations & Datasets
Evaluations and Datasets FAQ
Reviewing Guidelines
Call for Position Papers
Call for Reproducibility
Call for Tutorials
Call For Competitions
Competition Track Reviewing Guidelines
Call for Workshops
Call For Affinity Events
Call for Educational Resources
Call For Creative AI
Call for Social Events
Call for Journal Papers
Call for Expo
AI Reviewing Experiment
Attend
Hotels
Visa Information
Volunteering and Financial Assistance
Attending with Children
Organizers
Organizing Committee
NeurIPS Board
NeurIPS Foundation
Exhibitors
2026 Exhibitors
Portal
EAC Information
Layout:
mini
compact
topic
detail
×
No topics available
No sessions available
title
author
topic
session
shuffle
by
serendipity
bookmarked first
visited first
not visited first
bookmarked but not visited
Loading...
Enable Javascript in your browser to see the papers page.
ShiftRAG: Bypassing the Textual Bottleneck via Decoupled Learning and Continuous Soft Tokens
Multiple Instance Verification
See, Read, Compare: Candidate-Aware Verification for Agent Test-Time Scaling
Generalization at the Edge of Stability
Bayesian Backprop as Belief Propagation: Single-Pass Predictive Uncertainty
Local-Interaction Learning Dynamics: A Markov Random Field Framework for Convergence of Deep Neural Network Learning
Mechanistic Interpretability with Sparse Autoencoder Neural Operators
The Key to Going Linear: Analysis-Driven Transformer Linearization
Fourier Contour Learning for Efficient and Traceable Cardiac MRI Quantification
BiShield-TEE: On the (In-)Security of Unilateral Weight Obfuscation in On-Device TEE-Shielded LLM Partition
Object Detection Benchmarks are Incomplete: The Role of Label Errors and Annotation Uncertainty
Locality Sensitive Hashing for p-Exponential Kernels with Applications to Density Estimation
ZO-F2: Low-variance Fisher preconditioner via bilinear estimation for zeroth-order optimization
DiA: Directional Adapter
Auditing Privacy Leakage in Tabular Foundation Model Embeddings
Generating from Discrete Distributions Using Diffusions: Insights from Random Constraint Satisfaction Problems
Image2Sim: Scaling Embodied Navigation via Generative Neural Simulator
Universal Cross-Prompt Adversarial Attacks on Promptable Concept Segmentation
M$^\star$: Every Task Deserves Its Own Memory Harness
ProPolar: Progressive Polar Decomposition for Implicit Neural Representations
ER-Reason: A Benchmark Dataset for LLM Clinical Reasoning in the Emergency Room
MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods
Simulating Human Memory with Language Models
Playing ZendoWorld: Challenging AI Agents on Active Visual Concept Induction
ActionUNet: Improving Robustness of VLA Models with Efficient Multi-scale Fine-tuning
EmoTrack: Robust Depression Tracking from Counseling Transcripts across Session Regimes
Efficient Adjoint Matching for Fine-tuning Diffusion Models
Intent-Aware Caching for Efficient LLM Serving
Empirical Bayes Flow Matching for Continuous Cryo-EM Heterogeneity
Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models
Scaling Optimization-Oriented Hypernetworks for Implicit Neural Representations
Agentic-imodels: Evolving agentic interpretability tools via autoresearch
Rethinking State Tracking in Recurrent Models Through Error Control Dynamics
FedSOUL: Federated Continual Unlearning via Spectral Orthogonality
Graph and Simplicial Complex Prediction Gaussian Process via Hodgelet Representations
An Efficient Geometric Characterization of Robust Fair Learning
What MLLMs Learn about When they Learn about Multimodal Reasoning
Active Learning From Positive and Unlabeled Examples
FedPeel: Peeling Stabilized Layers for Robust Heterogeneous Federated Learning
Learning with Multiple Correct Answers - Regret Bounds under Different Feedback Models
Susceptibilities for Neural Networks Learning from Physical Data
TiRex-2: Generalizing TiRex to Multivariate Data and Streaming
Mult-DPO: Multinomial Direct Preference Optimization for Recommender Systems
Online Learning via Learned Latent Bayesian Tracking
Amortized-Precision Quantization for Early-Exit Vision Transformers
Designing Reinforcement Learning for Diffusion Models: A Unified Path-Space View
Contractive Monoids: The Algebra Behind Stable Residual Propagation in Deep Graph Neural Networks
MEME: Multi-Entity & Evolving Memory Evaluation
PhyTS: A Benchmark for Scientific Time Series
Long Video Instructional Editing in the Wild
Latent Refinement Decoding: Enhancing Diffusion Language Models by Refining Belief States
BONSAI: Bayesian Optimization with Natural Simplicity and Interpretability
Sparkle: Realizing Lively Instruction-Guided Video Background Replacement via Decoupled Guidance
Conformal Language Modeling via Posterior Sampling
Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation
From Patches to Trajectories: Privileged Process Supervision for Software-Engineering Agents
Dynamic Causal Structure Discovery for Autoregressive Visual Generation
LENS: Low-Frequency Eigen Noise Shaping for Efficient Diffusion Sampling
Prediction-Powered Inference Across Many Tasks for AI Evaluations and Social Science Research
BRAVO: Bridge Matching for Autoregressive Video Generation
Joint Optimization of Tool Creation and Use for Large Language Model Agents
Inverse Modeling for Laser Pulse Shape Design in Inertial Confinement Fusion
End-to-End Differentiable Diffusion Conditioning for Physics-Informed Optimization
Lyapunov-Driven Optimistic Learning for Online Scheduling with Multi-Stage Tasks
The Expressivity Boundary of Probabilistic Circuits: A Comparison with Large Language Models
FlashMol: High-Quality Molecule Generation in as Few as Four Steps
The Heavy Hitter Oracle: Enhancing Frequency Estimation in Skewed Data Streams
Sign-Based Optimizers Are Effective Under Heavy-Tailed Noise
HierSVA: A Synthesis Pipeline, Dataset, and Benchmark for LLM-Driven Hierarchical Hardware Formal Verification
When and Why SignSGD Outperforms SGD: A Theoretical Study Based on $\ell_1$-norm Lower Bounds
Step-dLLM: Adaptive Step-aware Sparse Attention for Efficient Diffusion LLM Inference
Group Distributionally Robust Optimization with Flexible Sample Queries
Beyond Row Alignment: Virtual-Camera-Aware Online Stereo Rectification
MixScentNet: A Multiscale Graph-based Framework for Predicting Scent Mixture Perception
When and Why Adversarial Training Improves PINNs: A Neural Tangent Kernel Perspective
Geometric Instability of Hidden-State Trajectories Predicts Reasoning Failures in Large Language Models
Beyond One-Size-Fits-All: Diagnosis-Driven Online Reinforcement Learning with Offline Priors
Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning
VCR: Learning Valid Contextual Representation for Incomplete Wearable Signals
STRIDE: Learnable Stepwise Language Feedback for LLM Reasoning
ReST-RL: Reinforcing LLM Reasoning through Unified Self-Training and Value-Guided Search
Agree to Disagree: Multimodal Autonomous Negotiation and Calibration for Entity Representation Learning
Vision Correlators: Correlation-Driven Visual Understanding with Hypergraphs
TIB: Sample-wise Tempered Information Bottleneck for Multimodal Attribution beyond Alignment Assumption
StatLUT: Statistical Feature-Driven Multimodal 3D LUT Generation for Photorealistic Style Transfer
The Limits of AI-Driven Allocation: Optimal Screening under Aleatoric Uncertainty
Efficient and Simple Data Mixing All The Time
When Is Rank-1 Steering Cheap? Geometry, Granularity, and Budgeted Search
OmniSelect: Dynamic Modality-Aware Token Compression for Efficient Omni-modal Large Language Models
Federated Distributionally Robust Neural Combinatorial Optimization with Convergence Guarantees
AnyBokeh: Physics-Guided Any-to-Any Bokeh Editing with Optical Fingerprint Transfer
MinerU2.5-Pro: Pushing the Limit of Document Parsing via a Calibrated Evaluation-Data Flywheel
EngramState: Loadable Tool Priors for Efficient Function Calling
AsyncOPD: How Stale Can On-Policy Distillation Be?
LOCO: Local Light-Aware Object Compositing with Spatially Varying Illumination-Augmented Data
HELICS: Biobank-scale Conditional Synthetic Genome Generation via Latent Flow Matching
EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts
A Solvable Model of Chain-of-Thought in In-Context Learning
Intrinsic Information Theoretic Analysis of ReLU Nets
FuncFormer: Circuit Representation Learning via the Flow of Functional Propagation
Learning to Inject: Automated Prompt Injection via Reinforcement Learning
Random-Effects Centroids for Domain Generalization
Consolidating Reasoning with Test-Time Learning
CruxBench: A Benchmark of Information Discovery
Local Sparsity Enables Unsupervised LLM Safety Detection
FairSplit: Decomposing the Embedding Space for Fair Classification
BAL: Bidirectional Autoregression in Latent Space for Learning Human Movement Representations
ViMU: Benchmarking Video Metaphorical Understanding
Asynchronous Agentic Poisoning
Decomposing Effects in Neural Causal Models
Merging RLVR-Trained Experts via Policy-Shift-Guided Spectral Alignment
Natural Jammers: When Non-Robust Features Become Antagonistic
Affine-invariant Cubic Newton with Weak Learners
C3H: Compression-to-Consensus Criteria Hijacking in Multimodal LLM Recommender Systems
SPHERE-JEPA: Spherical Prediction with Homogeneous Embeddings
Gradient Regularized Newton Boosting Trees with Global Convergence
ReVMap: Vectorized Global Mapping via Connectivity-Aware Local Map Fusion
A Subgoal-driven RL Framework for Improving Long-Horizon Web Agents
MonarchRT: Efficient Attention for Real-Time Video Generation
Where Do Long Captions Fail? Position-Aware Diagnosis and Reinforcement Learning for Detailed Image Captioning
MIRAGE: Mobile Agents with Implicit Reasoning and Generative World Models
Uncertainty-Aware Fuzzy Graph Contrastive Learning
Asymptotically Optimal Best Arm Identification with Fixed-Budget under Differential Privacy
A Mean-Field Framework for Inference-Time Distributional Control of Diffusion Models
AdaSRU: Adaptive Source-Free Recommendation Unlearning via Gradient-Constrained Optimization
What Remains in Sight? Autoregressive Video Decoding as Representation-Guided Context Rewriting
Learning to Surpass: Training Tool-Using Agents with Anchored Feedback
Clarification as Supervision: Reinforcement Learning for Vision-Language Interfaces
CUVET: A Partitioning Approach for Continuous Treatment Assignment At Scale
Scalable Fair Learning via Cramér-von Mises Regularization
LogSig-SSM: Time-Series Modelling with Multi-Scale Log-Signature Compression for State-Space Models
MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory
Training-Free 3D Editing via Feature-Divergence Localization and Trajectory Correction
Probabilistic Tiny Recursive Model
DSSP: Diffusion State Space Policy with Hierarchical Full-History Conditioning
Learning Augmented Exact Exponential Algorithms
CoffeeBench: A Benchmark for Long-Horizon Strategic Decision-Making in Multi-Agent Economies
QEC Model Zoo: Democratizing AI-enhanced Quantum Error Correction
FreeOcc: Decoupling Ego-Motion for Efficient 4D Occupancy Forecasting via Continuous Flow Matching
NormLift: From Lifted Features To Semantic Reliability In 3D Gaussian Splatting
Learning Optimal Transport Plans Via Autoregressive Token Regression
Metric Depth Estimation from Arbitrarily Degraded Low-Resolution Depth Prompts
XL-SafetyBench: A Country-Grounded Cross-Cultural Benchmark for LLM Safety and Cultural Sensitivity
Medical LLMs as Medical World Models: Unified Policy-Dynamics Learning with Test-Time Search
Med-Agentic: Distilling Agentic Medical Reasoning with Internalized Meta-Capabilities
Explicit Geometric Chain-of-Thought for Vision-Language-Action in Autonomous Driving
Unify-Agent: A Unified Multimodal Agent for World-Grounded Image Synthesis
Clearer Sight, Fewer Lies: Oriented Pickup Preference Optimization for Multimodal Hallucination Mitigation
MentalHospital: A Virtual Environment for Evaluating Psychiatric Clinical Encounters
Chatter Attack: Resource Consumption Attack for Large Language Models
Aegis: Generative Gradient Masking for Privacy-Preserving Medical Federated Learning
MLAIRE: Multilingual Language-Aware Information Retrieval Evaluation Protocol
Test time training enhances in-context learning of nonlinear functions
WASP: Weakly Aligned Spatiotemporal Pairs for Fetal Brain MRI-Ultrasound Learning
How Neural Reward Models Learn Features for Policy Optimization: A Single-Index Analysis
LoMo: Local Modality Substitution for Deeper Vision-Language Fusion
Exact Flow Linear Attention: Exact Solution from Continuous-Time Dynamics
Neural Continuous-Time Markov Chain: Discrete Diffusion via Decoupled Jump Timing and Direction
Modeling Whole-Slide Images as Dynamic Tumor Microenvironment Fields
Parallel Fixed-Point Spiking Neurons for Efficient Training of Spiking Neural Networks
Optimal Ansatz-free Hamiltonian Learning In Situ
Beyond Contraction: Geometry-Faithful Supervised Dimensionality Reduction for Data Visualization
PACE: Pareto-Adaptive Compression for Efficient Native MLLMs
Scaling Point-in-Time Language Models: Economic Evaluation of Embeddings
Computing All Optimal Partial $p$-Wasserstein Matchings on the Line
Can Complementary Signals Bridge Similarity Islands? Manifold-Augmented Graph Embedding for Multimodal Recommendation
Unsupervised Unlearnable Segmentation via Semantic Structure Disruption
Training Language Models via Neural Cellular Automata
From Small to Large: Cross-Scale Graph Domain Adaptation via Local-Global Structural Alignment
One Language-Free Foundation Model Is Enough for Universal Vision Anomaly Detection
TokenCLIP: Token-wise Prompt Learning for Zero-shot Anomaly Detection
PACE: Geometry-Aware Bridge Transport for Single-Cell Trajectory Inference
VecDBLens: A Modular Framework for Diagnosing Vector Databases Retrieval Pipelines
How to Train a Surgeon? Benchmarking Generalist Agents in Surgical Scene Understanding
UniDG: Universal Defect Generation via Defect-Context Editing
BrickAnything: Geometry-Conditioned Buildable Brick Generation with Structure-Aware Tokenization
One Avatar, Any Budget: Robust LoD for Dynamic Gaussian Avatars
Diff3R: Feed-forward 3D Gaussian Splatting with Uncertainty Aware Differentiable Optimization
Semantic Residual: A Paired-Oracle Decomposition of LLM Multi-Agent Systems under Lossy Channels
Incentivizing Medical Vision Capabilities from Large-Scale Multimodal Pre-training
Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field
Coherence-Aware Transition-Intent Fusion for LTL Planning under Uncertain Semantic Maps
NesyProAct: Proactive Neural-Symbolic Control for Web Agents
A Primal-dual Approach for Semi-Infinitely Constrained Reinforcement Learning
CausalBind: Causal Modeling and Learning for Protein-Molecule Virtual Screening
Recursive Multi-Agent Systems
Calibration Is Not Control: Intervention Advantage for LLM-Agent Oversight
SpRePE: A Spherical Geometry-Aware Position Embedding scheme for Vision Transformers
Do Less, Decide Better: Optimal Human Dispatching in AI-Assisted Decisions
SliceWorld: A Predictive and Controllable World-State Model for CT Report Generation
Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
Differencing the Diffusion Trajectory toward Uncertain Components for Time Series Forecasting
HoloGene: Learning to Lift Sliced Spatial Transcriptomics to Holistic 3D Gene Fields
A Unified Framework for Image-to-3D Part Generation via Variable Granularity
Variance-Averse n-Step Offline Reinforcement Learning for Sparse Long-Horizon Environments
KiteNorm: Variance Regularisation for Stable and Scalable Post-LN Transformers
MENDR: Manifold-Embedded Neural Data Representations for Channel-Agnostic EEG Foundation Modeling
Reward Is Not a Universal Interface for Generative Reinforcement Learning
AlphaQ: Calibration-Free Bit Allocation for Mixture-of-Experts Quantization
Kernel Selection is Model Selection: A Unified Complexity-Penalised Approach for MMD Two-Sample Tests
Learning from the Self-future: On-policy Self-distillation for dLLMs
Universal Adaptive Proximal Gradient Methods via Gradient Mapping Accumulation
Transferability for General Reasoning: An Automated Curriculum for Multi-Domain LLM RL
Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning
City-RAG: Stepping Into a City via Spatially-Grounded Video Generation
$\boldsymbol{f}$-OPD: Stabilizing Long-Horizon On-Policy Distillation with Freshness-Aware Control
Orthros: Phase-Aware Heterogeneous Attention for Efficient Transformers
LifeStream: Token Life-Cycle Modeling for Training-Free Online Video Understanding
BEACON: Cross-Domain Co-Training of Generative Robot Policies via Best-Effort Adaptation
MainFL: Intertemporal Data Valuation for Robust Auction-based Federated Learning
Shift-Aware Identity-Guided Latent Refinement for Referring Audio–Visual Segmentation
CellMSA: Context Modeling for Single-Cell Representation Learning
NARRA-Gym for Evaluating Interactive Narrative Agents
Structure-aware Reinforcement Learning for Protein Directed Evolution
SkillGen: Verified Inference-Time Agent Skill Synthesis
Towards Principled Efficient Rollout Allocation in Test-Time Training
VisInteract: Towards Dynamic Interactive Text-to-Visualization under Imperfect Queries
Dataset Mismatch Matters in Group Relative Policy Optimization for Reinforcement Learning from Verifiable Rewards
[Re] Boosting the Visual Interpretability of CLIP via Adversarial Fine-Tuning
AptaBench: A Benchmark for Aptamer-Small Molecule Binding
Safe Actions Can Form Unsafe Traces: Benchmarking and Shielding Compositional Emergent Risk in AI Agents
Posterior Sampling-based Online Learning for Episodic POMDPs
CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models
Credit Assignment with Resets in Language Model Reasoning
Load Balancing Mixture of Experts with Similarity Preserving Routers
Jump Start Your Policy Learning with Lessons from 145,000 Training Runs
Read It Back: Pretrained MLLMs Are Zero-shot Reward Models for Text-to-Image Generation
HireWatch: Evaluating LLM Compliance with U.S. Employment Law Under Contextual Pressure
Going Down Memory Lane: Scaling Tokens for Video Stream Understanding with Dynamic KV-Cache Memory
Retrieval Heads Meet Vision: Uncovering How VLMs Locate and Extract Visual Information
KV Cache Compression via Attention Output Distortion Minimization
RIZZ: Routing Interactions to Near Zero-Interference Zones for Continual Adaptation of Black-Box Agents
Unified Forensic Preference Learning for Generalizable Synthetic Image Detection
RETR: A Structure-Preserving RGB-Event Transformer for Robust 3D Lane Detection
Flux Attention: Context-Aware Hybrid Attention for Efficient LLMs Inference
DRILL: Training World Models to Improve Policies, Not Predict Pixels
VI-CuRL: Stabilizing Verifier-Independent RL Reasoning via Confidence-Guided Variance Reduction
The End Justifies the Mean: Linear Ranking Rules for Proportional Sequential Decisions
Positional versus Symbolic Attention Heads: Learning Dynamics, RoPE Geometry, and Length Generalization
Estimating and Orthogonalizing Unknown Pre-training Gradients for Continual Fine-tuning of Large Language Models
Where Should Society Draw the Line? A Social Choice Approach to Collective Consent
Teaching Large Language Models When Not to Know: Learning Temporal Critique for Ex-Ante Reasoning
MLLMEraser: Achieving Test-Time Unlearning in Multimodal Large Language Models through Activation Steering
GIFT: Representation Geometry Matters for Single-Domain Generalized Object Detection
Sharp Non-Asymptotic Analysis of the Penalized Challenger in $\beta$-EB-TCI for Bernoulli Bandits
Beyond Expected Values: Risk-Sensitive Planning with Distributional Monte-Carlo Tree Search
DAGA: Dynamic Attention-Guided Adaptation for Self-Supervised Vision Transformers
Learning Contextual Causal Dynamics for Robust Exploration in Reinforcement Learning
ROSE: Risk-Aware Orthogonal Subspace Navigation for Lifelong Knowledge Editing in Multimodal Large Language Models
FreeAct: Demonstration-Free Robot Adaptation via Action-Grounded Generated Videos
Drag as Evidence: Motion-Grounded Latent Recomposition for Drag-Based Editing
FUTON: Fourier Tensor Network for Implicit Neural Representations
Escaping Path Mirages in Offline Goal-Conditioned Reinforcement Learning
Focusing Influence Mechanism for Multi-Agent Reinforcement Learning
Addressing Exogenous Variability in Cooperative Multi-Agent Reinforcement Learning
MASTARS: Multi-Agent Sequential Trajectory Augmentation with Return-Conditioned Subgoals
An Axiomatic Analysis of DPO and NLHF as Reference-Dependent Probabilistic Voting Rules
Hypergraph Modeling of Transformer Attention for Hallucination Detection
FreqCa: Accelerating Image generation and editing via Frequency-Aware Caching
Integrating digital twins with randomized experiments
Enhancing Gaze Reasoning in Vision Foundation Models for Gaze Following
RTCBench: Evaluating Tool Use of Large Language Models Beyond Oracle Access
Large Language Models Enhanced Covariate-adjusted Response-adaptive Randomization Design
Agentic Reward Modeling: Verifying GUI Agent via Progressive Trajectory-Grounded Interaction
DPLC: Dirichlet Process Guided Long-tail Clustering
MUNI: Multimodal Unified Latent Diffusion for Coherent Any-to-Any Generation
Subliminal Learning as Trait-Direction Drift: A Mechanism and Targeted Control under SFT Distillation
MC-H: Multi-Granularity Clustering with Hyperspherical Determinantal Point Process
Drifting Field Policy: Wasserstein Gradient Flow on Policy Space for Offline-to-Online RL
Strong Helps Weak: Directional Cross-Modal Alignment Transfer in Multi-modal LLMs
Implicit Value Probing: Inferring Human Value Preferences via Strategic Multi-Turn Conversations
Random Matrix Theory of Early-Stopped Gradient Flow: A Transient BBP Scenario
Open-Vocabulary 3D Part Segmentation with Semantic Propagation Hawkes Process
Beckmann Transport Models: From Autonomous Flows to One-Step Maps
DDGE: Disentangled Dirichlet Geodesic Evaluation for Robust Few-Shot Learning
PAPO-VLA: Planning-Aware Policy Optimization for Vision-Language-Action Models
Bound-Conditioned Latent Inference for Progressive Image Compression
ReSMap: Recasting Satellite Priors for Robust and Accurate Online HD Map Construction
DifFRACT: Diffusion Feature Reconstruction and Attribution for Circuit Tracing
Retrieval-Augmented Diffusion Modeling for Stochastic Discount Factor Portfolios
When Less is More: The LLM Scaling Paradox in Context Compression
TimeOperator: A Function-to-Function Approach to Time Series Modeling
PDE-PFN: Prior-Data Fitted Neural PDE Solver
When Does Fine-Tuning Extract Stored Knowledge? A Relation-Covering Theory for One-Layer Transformers
Event based Multi-Velocity-Scale Imaging
MPDocBench-Parse: Benchmarking Practical Multi-page Document Parsing
How Long Does Infinite Width Last? Signal Propagation in Long-Range Linear Recurrences
Trainable Topology Supervision under Structurally Unreliable Pseudo Supervision
Entropy Guided Dynamic Patch Segmentation for Time Series Transformers
CASQRec: Collaborative-Adaptive Semantic Quantization for Multimodal Recommendation
Predictive Surprise as Self-Grounding Concept Bottleneck for Interpretable Time Series
Efficient Learning of Truncated Boolean Product Distributions: Influence to the Rescue
Training-free Spatially Grounded Geometric Shape Encoding
PrismFlow: Residual Dynamics for Flow Matching in Time-Series Generation
CAIRN: Cross-Room 3D Scene Understanding with Topology-Aware Large Multimodal Models
MSC-Mol: Modality-Synergy Contrasting for Multimodal Molecular Representation Learning
$R^2E$: A Role-driven Reward Evolutionary Framework for Automated Reward Function Design
Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memory
A Cross-Interaction Neural Architecture for Submodular Functions
From “Weak” Signals to Strong Models: Preference Delta Aggregation with LoRA Merging
Active Corpus Selection for Training Subgraph Retrievers Using OOD Queries
$h$-control: Training-Free Camera Control via Block-Conditional Gibbs Refinement
Humans Correct Their Judgements Through Debate, but Weaker AI Models Not
Missing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy Correction
ReGenHuman: Re-Generating Human Appearances for Realistic Full-Body Video Anonymization
Not All Instances Should Contribute Equally: Sparse Support Grounding via Unbalanced Transport for Heterogeneous MIL
Punctuation-aware Hybrid Trainable Sparse Attention for Large Language Models
OmniSimulator: Aligning Small Language Models for Authentic Heterogeneous Behavior Modeling
Evaluating Synthetic ECG Pretraining: When Can Patient-Free Simulators Substitute for Real ECG Data?
Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces
Consistency as a Testable Property: Statistical Methods to Evaluate AI Agent Reliability
Uni-Cheb: A Basis-Agnostic Learnable Chebyshev Filter for Multimodal Spectral Modulation
Truncate Bad, Upweight Good: BoN-Style Distillation via Rank-Based Classification
FrontierSmith: Synthesizing Open-Ended Coding Problems at Scale
Exact Posterior Score Estimation for Solving Linear Inverse Problems
How Post-Training Shapes Biological Reasoning Models
Two Drifts, One Principle: Conflict-Aware Spectral Consolidation for Multimodal Continual Learning
Ergodic Risk Measures: Towards a Risk-Aware Foundation for Continual Reinforcement Learning
UniGS: Unified Geometry-Aware Gaussian Splatting for Multimodal Rendering
CrystalREPA: Transferring Physical Priors from Universal MLIPs to Crystal Generative Models
When Can Digital Personas Reliably Approximate Human Survey Findings?
Mirror Descent-Ascent for mean-field min-max problems
Mechanistic Circuit Identification for Controllable Data Generation
quanda: An Interpretability Toolkit for Training Data Attribution Evaluation
What Probing Reveals about Autonomous Driving: Better Predictions Lead to Better Planning
COMET: Decoupled Distillation, Routing, and Capacity Control for Task-Agnostic Continual Vision--Language Learning
Simmer: A Scalable Pretraining Recipe for Video-Text Encoders
ARK: A Dual-Axis Multimodal Retrieval Benchmark along Reasoning and Knowledge
Select Smarter, Not More? Prompt-Aware Evaluation Scheduling with Submodular Guarantees
Group of Skills: Group-Structured Skill Retrieval for Agent Skill Libraries
A Memory Efficient Unified Algorithm for Online Learning of Linear Dynamical Systems
Continuous Personalized Diffusion Model via Spinor-Component Forward Geometry
Goal-Conditioned Supervised Learning for Multi-Objective Recommendation
CyBiasBench: Benchmarking Bias in LLM Agents for Cyber-Attack Scenarios
EntropyCache: Decoded Token Entropy Guided KV Caching for Diffusion Language Models
Automotive-ENV: Benchmarking Multimodal Models in Automotive Cockpit Environments
Learning to Align Generative Appearance Priors for Fine-grained Image Retrieval
3D Skew Normal Splatting
Operads for compositional reasoning in LLMs
Near-Optimal Regret in Adversarial Kernel Bandits
Tell Me What To Learn: Generalizing Neural Memory to be Controllable in Natural Language
PINNeval: A Comprehensive Evaluation Standard for Physics-Informed Neural Networks
AR1-ZO: Topology-Aware Rank-1 Zeroth-Order Queries for High-Rank LoRA Fine-Tuning
Democratizing Tool Learning with Environments Fully Simulated by a Free 8B Language Model
PDF-HR: Pose Distance Fields for Humanoid Robots
Delve into the Applicability of Advanced Optimizers for Multi-Task Learning
FedReCall: Recalling Client-Specific Directions in Federated LoRA Fine-tuning
CT-Lesion: A Multi-Region CT Dataset for Co-existing Lesion Segmentation and Detection
Modality-Aware Expert Pruning for MoE-Based Multimodal Large Language Models
EDEN: Emergent Dynamics in Evolutionary Neural-networks for Robust Continuous Control
Auditing Instruction Robustness in Vision-Language-Action Models via Diversity-Aware Red Teaming
Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space
Stable Long-Horizon PDE Forecasting via Latent Structured Spectral Propagators
CollabVR: Collaborative Video Reasoning with Vision-Language and Video Generation Models
RotMoLE: Enhancing Mixture of Low-Rank Experts through Rotational Gating Mechanism
Diagnosing and Mitigating Modality Interference in Multimodal Large Language Models
Alignment Collapse Under KV Cache Quantization: Diagnosis and Mitigation
ModelLens: Finding the Best for Your Task from Myriads of Models
Dynamic Context Modeling for Longitudinal Mental Health Monitoring under Distribution Shift
Just Ramp-Up: Debiasing Regression-based Estimator for A/B Tests under Network Interference
Leak-CURBER: A Leakage-Controlled Multimodal Evaluation Benchmark for Enzymatic Reaction Tasks
Beyond Right and Wrong: Evaluating Second-order Social Reasoning in Large Language Models
AgenTracer-v2: Agentic Failure Tracer for LLM Agentic Systems
EcoGym: Evaluating LLMs for Long-Horizon Plan-and-Execute in Interactive Economies
Search More, Think Less: Rethinking Long-Horizon Agentic Search for Efficiency and Generalization
RigPAPR: Rig-Based Animation of Static Neural Point Clouds from a Single-View Video
Continuous-depth Deep Gaussian Processes
The World is Not Mono: Enabling Spatial Understanding in Large Audio-Language Models
Boosting LLM Reasoning via Human-Inspired Reward Shaping
From Reasoning Chains to Verifiable Subproblems: Curriculum Reinforcement Learning Enables Credit Assignment for LLM Reasoning
Steering Visual Generation in Unified Multimodal Models with Understanding Supervision
One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning
DRIVE: Fine-tuning via Data Contribution- and Diversity-aware Weighting with Prior Regularization
BEAGLE: Behavior-Enforced Agent for Grounded Learner Emulation
Co-GRPO: Co-Optimized Group Relative Policy Optimization for Masked Image Generation
Disentangling Homophilic and Heterophilic Patterns for Multi-Domain Graph Foundation Models
HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning
SteerVTE: Seamless Video Text Editing with Style and Glyph Control
Spectral Energy Allocation Enables Source-Free Domain Adaptation in Time Series Forecasting
UltraVoxelGS: Voxel-First Feed-Forward Gaussian Splatting for 3D Ultrasound Reconstruction
Motion Forcing: Decoupling Ego and Object Motion via Sparse Inputs for Structured Video Generation
Detect, Explain, Interpret: An End-to-End Benchmark for Time Series Anomaly Detection, Explainability and Interpretability.
A Mechanistic Investigation of Theory of Mind in a Large Language Model
Retrieval Over Training: Similarity search-based Model Selection for Time Series Anomaly Detection
Literati: Towards Anytime Optimal Shape Generalized Trees via AO*
Free Heavy-Tailed Lunch for Muon: A Theoretical Justification of Empirical Success
Catch-Only-One: Non-Transferable Examples for Model-Specific Authorization
Extremely Sparse-View Computed Tomography from 2D Projections via Pose-Aware Diffusion Priors
Contrastive Retrieval Heads for Improved Attention-Based Reranking
Nerve-Skeleton Message Passing for Federated Optimization with Overlapping Parameters
Matrix Recovery Via Symmetric Rank-one Measurements With Random Unit-modulus Vectors
ARGUS: Stacked Multi-View Identity Mosaic Injection for Subject-Preserving Video Generation
Discriminative Score Function: Turning Pretrained Models into Functional Generative Priors
CORVUS: Context Optimization and Reduction Via Underlying Synchronization for LLM Coding Agents
Geometry-Adaptive Explainer for Faithful Dictionary-Based Interpretability under Distribution Shift
MoRe-DVC: Motion Retrieval-Augmented Generation for Detailed Video Captioning
Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning
Learning Causal Orderings for In-Context Tabular Prediction
Clean Data Can Still Carry Backdoors: Support-Persistent Backdoors for Model Reuse
End-to-End Training for Unified Tokenization and Latent Denoising
A Theory of Spatial Continuous Attractors in Hopfield Energy Landscapes
Traversal-Invariant Positional Encoding for Serialized Graphs
Generation Navigator: A State-Aware Agentic Framework for Image Generation
Simultaneous Individual, Group and Multigroup Fairness in Set Covering Problems
Patch4Patch: Restoring Structural Connectivity in Patch-based Vision Encoders
Metaphor Is Not All Attention Needs
Hierarchical World Models with Implicit Dynamics
GeoMIND: A Benchmark for Spatial Understanding in Robotic Manipulation
Neural Bayesian Filtering
Context Value Informed In-Context Reinforcement Learning
ManiFusion: Unlocking High-Throughput Generation via Superposition in Manifold Space
Velocity-Space 3D Asset Editing
Counterfactual Explanations for Time-Series Classification via Constrained Flow Matching
AURA: An Autonomous Retouching Agent with Photographic Visual Thinking
ML Configuration Artifacts Should Be Closed Under Review
MESS: Multi-Exposure Sequence Synthesis for Generalizable Image Enhancement
BiasTrojan: LLM Judgers Are Easily Distorted by Few Hundreds of Contrastive Biased Training Data
NSARM: Next-Scale Autoregressive Modeling for Robust Real-World Image Super-Resolution
Train-free Data Poisoning Attack against Retrieval-augmented Diffusion Models
GOLD: Geometric Optimized Latent Diffusion for Structure-Aware RNA Inverse Folding
Graph Mamba Operator: A Latent Simulator for Interacting Particle Systems
Is Your LLM-as-a-Recommender Agent Trustable? LLMs' Recommendation is Easily Hacked by Biases (Preferences)
Learning What to Forget: Improving LLM Unlearning via Learned Token-Level Importance
Tracing Psychometric Inference in Large Language Models
Visual Anchoring for Scenario-Guided Forecasting
The Adversarial Gait: Detecting Visual Adversarial Attacks against Vision-Language Models via Self-Targeted Gradient Characterization
Exposing Private Corpus Leakage in Multimodal RAG
Discovering Unseen Degradations to Adapt Open-World Image Restoration
SurvivalPFN: Amortizing Survival Prediction via In-Context Bayesian Inference
Extrapolative Weight Averaging Reveals Correctness–Efficiency Frontiers in Code RL
3R-Adapter: Retrieval, Rewiring, and Refinement for Efficient Adaptation of 3D Reconstruction Model
Reinforcement Learning for Code Optimization
Expected Harm: Rethinking Safety Evaluation of (Mis)Aligned LLMs
ATLAS: Adaptive Temporal Learning for Single-Cell Multi-Omics Alignment and Dynamics
Concept-Aware Wasserstein Routing with Vision-Language Guidance for Few-Shot WSI Classification
ViDiC: Video Difference Captioning
Mamba Can Learn Low-Dimensional Targets In-Context via Test-Time Feature Learning
Flow Matching from Viewpoint of Proximal Operators
EpistasisBench: Revealing Structural Limitations of Zero-Shot Protein Language Models
Topology-Aware Optimal Transport for Source-Free Test-Time Adaptation in Anomaly Segmentation
What the Geometry of Good Models Tells Us
KV-COBRA: KV Cache Compression via Co-Optimized Bit-Rank Allocation
Domain-Conditioned Class Imbalance: Why Global Class Balance Fails Across Domains
Distributional Estimation of 3D Object Orientation
HALMES: Knowing When to Intervene in LVLM Hallucination Mitigation
ElasticFit: Fit-Aware 3D Object Insertion via VLM Reasoning and Generative Adaptation
UniRAP: Towards Unified Part-level Physical Affordance Reasoning and Actionable Perception
Local Policy Manifolds for Efficient Multi-Objective Reinforcement Learning
CitySTAR: Agent-Driven Structured and Topology-Aware Reasoning for Open-Vocabulary Urban 3D Grounding
TrajLoc: Trajectory-Attention Localization for Multi-Object Motion Control
Score-based Variational Inference via Quantum Maximally Mixed States
The Web Doesn't Sit Still: Adversarial Self-Evolving Attacks on Search Agents
GeoPano: Towards Geometrically Accurate Panoramic 3D Reconstruction from a Single Panorama
DeltaMomentum: A Key-Value based Anisotropic Momentum Update via Delta Rule
Learning When to Think: Dual-Reference Offline Optimization for Adaptive VLM Reasoning
Hyper Hawkes Processes: Interpretable Models of Marked Temporal Point Processes
Supervision Recovery for Time Series Anomaly Detection via Counterfactual Pairing
ProCTI: Prototype-Refined Global Conditioning for Diffusion-Based Time Series Imputation
Memory-Efficient Federated Fine-Tuning of LLMs via Block-wise Progressive Training
VETime: Vision Enhanced Zero-Shot Time Series Anomaly Detection
Online Conformal Abstention for Factuality Control Under Adversarial Bandit Feedback
MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment
METIS: Multi-Source Egocentric Training for Integrated Dexterous Vision-Language-Action Model
Revitalizing Medical Time Series with Vision-Informed Retrieval: A Vision-Language Perspective
Decoupling Conversational Dynamics in Full-Duplex Spoken Models through Reinforcement Learning
JMed48k: A Multi-Profession Japanese Medical Licensing Benchmark for Vision-Language Model Evaluation
Driver Attention as Competitive Allocation: A Scene--Task-Aware Dual-Branch Framework
UniFunc3D: Unified Active Spatial-Temporal Grounding for 3D Affordance Segmentation
Anchoring Reasoning Distillation via Syntactic Constraints
Beyond Distribution Matching: Self-Supervised Representation Forcing for Few-Step Video Generation
SpecBlock: Block-Iterative Speculative Decoding with Dynamic Tree Drafting
Active Learning of Conditional Generative Models via the Transport Neural Tangent Kernel
Does This Gradient Spark Joy?
Delightful Distributed Policy Gradient
Cyclic Denoising Reveals Ultrastable Memories in Diffusion Models
ECG-Reasoning-Benchmark: A Benchmark for Evaluating Clinical Reasoning Capabilities in ECG Interpretation
Towards Error-Free EHRs: Reasoning-Intensive Consistency Verification Between Clinical Notes and Structured Tables in Electronic Health Records
Event-Centric Perception in Weak-Signal Physical Streams with Multimodal LLMs
Generalization Bounds for Neural Networks with Sparse Connectivity
Transfer Learning of Linear Regression with Multiple Pretrained Models: Benefiting from More Pretrained Models via Overparameterization Debiasing
What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion
Crosscoding Through Time: Sparse Feature Discovery Across Sequence Positions
PDE-SSM: A Spectral State Space Approach to Spatial Mixing in Diffusion Transformers
Learning CLI Agents with Structured Action Credit under Selective Observation
Preconditioned Flow Matching
Continuous Expert Assembly: Instance-Conditioned Low-Rank Residuals for All-in-One Image Restoration
Rubato: Transcribing Piano Music with Timestamps
PLANING: A Loosely Coupled Triangle-Gaussian Framework for Streaming 3D Reconstruction
DisRFM: Polar Riemannian Flow Matching for Structure-Preserving Graph Domain Adaptation
COSMIO: A Benchmark for Cross-Survey Modality Imputation
InfiniteVL: A Systematic Approach to Highly-Efficient, Ultra-Long Multimodal Understanding
BudSplat: Feed-forward 3D Gaussian Splatting under a Rendering Budget
S2MDF: A Plug-And-Play Layer for Intersection-Free Multi-Object Signed Distance Fields
Robust Reversible Recovery for Adversarially Protected JPEG Images
SEEK-VAU: Towards Evidence-Faithful Video Anomaly Understanding via Agentic Search
Frozen Memory Is Not Enough: Rethinking External Memory as Extraction
RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO
HARMONY: Hierarchical Anchor Retrieval on Manifold for Oblivious-source Acoustic Anomaly Detection
MoE-SpAc: Efficient MoE Inference Based on Speculative Activation Utility in Heterogeneous Edge Scenario
PINNBench: A Benchmark and Evaluation Study of Training Policy Selection in Hybrid PINN-Operator Solvers
Diversity Combining for Multi-Path LLM Reasoning
TreePII: Efficient Computation of Higher-Order Probabilistic Interaction Indices in Tree Ensembles
Near-Optimal Best-of-Both-Worlds Algorithms for Decoupled Exploration and Exploitation in Multi-armed Bandits
DyPSI: Dynamic Physics Sensing via Joint Field and Sensor-Trajectory Generation
SCTI: Self-Calibrated Trident Identification of Black-Box LLM Watermarks
Deep Generative Models for Phylogenetic Inference with Complex Evolutionary Processes
Generating the Wild: Individual-Consistent Image-to-Video Generation for Wildlife
Learning Weakly Communicating Average-Reward CMDPs: Strong Duality and Improved Regret
Quantifying and Optimizing Path Uncertainty in Masked Diffusion Models
LucidNFT: LR-Anchored Multi-Reward Preference Optimization for Flow-Based Real-World Super-Resolution
Look-ahead Variational Flow for Generative Online Reinforcement Learning
Bootstrapped Bipartite Actor-Critic for Diffusion RL
GEMS-3D: A Large-Scale 3D Gravity, Electrical, Magnetic, and Seismic Earth Simulation Dataset for Multimodal Geophysical Learning
DTGS: Physics-Embedded Dynamic Thermal 3D Reconstruction with Gaussian Splatting
Self-Adjoint Flow Policy Optimization
Policy Optimization in Tabular MDPs: Data-dependent Regret under Unknown Transitions
Spectral Asymptotics of Neural Network Jacobians: Convergency, Universality, and Phase Transition
Global Context Guidance for Diffusion Large Language Models
Sobolev Regularized MMD Gradient Flow
NestRL: A Nested Training Regime for Mutual Adaptation in Human–AI Teaming
What Was That Again? Certified Robustness for Automatic Speech Recognition
FuseAdapt: Adaptation-Space Fusion for Multi-Modal Semantic Segmentation with Missing Modalities
PRISM: Rethinking Atmospheric Scattering Reconstruction as a Unified Understanding and Restoration Model for Real-world Dehazing
3DABSeg: Adaptive 3D Ankle Bone Segmentation with Multiscale Feature Fusion Mixture-of-Experts
Data-Efficient Learning for Constraint Satisfaction Problems via Relational Biases and Hard Axiom Clamping
CoLa3D: Composable Latent 3D Decomposition
Adversarial Risk in the Generative AI Era Necessitates Dropping the Small Epsilon Ball
Instruct-Particulate: Scaling Feed-Forward 3D Object Articulation with Kinematic Control
Tio: Language Models with Parallel Streams of Thoughts, Inputs and Outputs
Holo4D: Holistic 4D Reconstruction as Geometric Control for Video Diffusion
PolarScale: A Physics-Grounded Benchmark for Radiometrically Consistent RGB-to-Stokes Estimation
Track4D: Representing Dense 3D Tracking for Video Diffusion Models
VisEditBench: A Benchmark for Vector-Format Diagram Editing with Visual Instructions
LaMo: Self-Supervised Latent Motion Priors for Physical Realism in Video Generation
Teaching Video Generators to Remember: Eliciting Dynamic Memory for Out-of-Sight State Evolution
FireMPC: A Multi-Source Pan-Canadian Wildfire Benchmark Revealing Spatiotemporal Generalization Gaps
EventPrune: Cascaded Event-Assisted Token Pruning for Efficient First-Person Dynamic Spatial Reasoning
LYNX: Learning Dynamic Exits for Confidence-Controlled Reasoning
CME–SpectrumBench: Can LLMs Analyze Condensed Matter Spectral Data?
Structure-Prompted Multimodal Protein Language Model for Preference-Aligned Fitness Prediction
The Road Ahead in Autonomous Driving: The KITScenes Multimodal Dataset
Text-Based AI Tools for Research Integrity Must Be Audited on Linguistic Fairness Before Deployment
Tethered Predictive-Inertial Proposals with Objective Verification for Diffusion-Prior Inverse Problems
MechParser: A Vision-Language Framework for Parsing Chemical Reaction Mechanism Diagrams
RA-ClipScore: Making Generative Model Evaluation More Interpretable
GeoCore-9B: Towards Geo-Aware Generative Foundation Models in Earth Observation
EIPO: Efficient Inter-Step Parallel Optimization
BlenderFORGE: Framework for Optimizing Reactive 3D-Graphics Editing Ability of MLLMs
ParaLin: Accelerating Parallel Diffusion Integrator via Intrinsic Partially Linear Structure
SLS-Bench: A Benchmark for Incident Log Summarization with Synthetic Observability Data
ParaPC-FM: Accelerating Parallel Sampling via Principled Initialization
Benign Reinforcement Learning Can Amplify Latent Backdoors
Less is More: Compact-Token Masked Feature Learning for Skeleton Representation Learning
PROTEUS: A Self-Evolving Red Team with Surface Expansion for Agent Skill Ecosystems
Towards a Unified Model for Flexible Job Shop Scheduling Problems
SchedDiff: Diffusion-Based Priority Refinement for Job Shop Scheduling
ParetoSlider: Diffusion Models Post-Training for Continuous Reward Control
Learning Implicit Bias in Generative Spaces for Accelerating Protein Dynamics Emulation
Beyond Visual Boundaries: Rethinking Scene Segmentation for Movie RAG
TRACER: Verifiable Generative Provenance for Multimodal Tool-Using Agents
Spherical Interpolation for Backward-Compatible Multimodal Representations
Mutual Predictability Decomposition: Learning Interpretable Cross-Set Structure via Bi-Directional Prediction
Retrieve What’s Missing: Coverage-Maximizing Retrieval for Consistent Long Video Generation
Advectra: Asymmetric Latent Transport for Non-Stationary Physics
METRO: Metric-Enhanced Token Routing Operator
Steering Away from Memorization: Reachability-Constrained Reinforcement Learning for Text-to-Image Diffusion
An Equivariance Principle for Optimizer Design: Symmetry-Compatible Updates for Embeddings, LM Heads, and MoE Routers
Graph Learning from Label Proportions using Topology-Aware Pseudo Labeling and Aggregation
Not All Layers Need Tuning: Selective Layer Restoration Recovers Diversity
Assessing Sample Quality in Conditional Generation under Compositional Shift
TMPO: Trajectory Matching Policy Optimization for Diverse and Efficient Diffusion Alignment
How I learned to stop worrying and love StopGrads: Stationarity, Convergence, and a case study on Flow Map Learning
Eliciting Zero-Shot Named Entity Recognition in Large Language Models via Instruction Semantic Elaboration
DrugSAGE: Self-evolving Agent Experience for Efficient State-of-the-Art Drug Discovery
SphereFlow: Missing Modality Imputation via Geometric Transport on Hypersphere
$R^3$: 3D Reconstruction via Relative Regression
WebSpline: Structure-Informed Splines for Real-Time 3D Gaussians from Monocular Videos
The Shape of a Program: Path Signatures for Trace-to-Program Induction
FAME: Forecasting Academic Impact via Continuous-Time Manifold Evolution
Natural Synthesis: Outperforming Reactive Synthesis Tools with Large Reasoning Models
Knowledge Localization in Mixture-of-Experts LLMs Using Cross-Lingual Inconsistency
Population-Aligned Persona Generation for LLM-based Social Simulation
Attack-Inference Aligned Universal Adversarial Attacks on Video Object Segmentation
SkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles
Seeing the World through Any Eyes
eSAM: Editing SAM3 Attention for Training-Free Referring Segmentation
UGO: Unified Architecture for General Multi-Object Tracking by Segmentation
Guidance For Prior Change via Density Ratio Estimation
Flow Perturbation++: Multi-Step Unbiased Jacobian Estimation for High-Dimensional Boltzmann Sampling
Re-examining Low Rank adaptation for private LLM fine-tuning
Mechanisms of Misgeneralization in Physical Sequence Modeling
Stabilizing the Dynamic Low-Rank Training
CausalDriveBench: Evaluating Causal Reasoning in Vision-Language-Action Models for Autonomous Driving
Multimodal Context-Aware Human Motion Generation with Language, Vision, and Object
TrunkFish: Making Model Width Incrementally Refinable
Spectrum-Adaptive Generalization Bounds for Trained Deep Transformers
Causal Discovery Under Hard Selection Bias: A New Robust Score-Matching Approach
HyperTree: Scalable Unsupervised Hierarchy Discovery in Hyperbolic Space
Neural Optimal Transport in Hilbert Spaces
StreamMind: Dynamic Streaming Cognition for Online Video Understanding
MotionGrounder: Grounded Multi-Object Motion Transfer via Diffusion Transformer
Resolution-Aware Structural Density Peak Clustering
Jointly Robust Fairness: Overcoming Simultaneous Label and Attribute Noise
Edge of Stability Selectively Shapes Learning Across the Data Distribution
Beyond Semantic Alignment: Geometric Incomparability in Multi-Oracle Soft Fusion
STParOpt: An End-to-End Framework for Execution-Aware Parallelism Inference and Optimized CUDA Migration
Large Discrete Policy: Advancing Explicit Behavior Modeling with Stochastic Iterative Scoring
How Finite-Rank Bottleneck Shape the Low-Rank Adaptation Landscape
Birth-Death Structural Learning for 3D Gaussian Splatting
ProxySearch: Decoupled Inference-Time Scaling for Diffusion Models via Asymmetric Noise-Rank Transfer
Align as You Couple: Learning Spatial Resolved Inference from H&E Images with Mollified Flow Matching
Not All Slots Are Equal: Non-Co-Progressive Markov Bridge for Bundle Construction
Delay-Embedded Representations for Robust Saccade Classification in Noisy Oculographic Signals
Structure-Semantic Co-optimized Latent Diffusion Model for Fast Visual Anagram Synthesis
GraDE: A Graph Diffusion Estimator for Frequent Subgraph Discovery in Neural Architectures
CondenseVLA: Learnable History Condensation for Efficient Multi-Frame VLA
Probing Visual Planning in Image Editing Models
Learning Neuronal Wiring Rules from Morphological Token Sequences
Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Model
Beyond Family Labels: A Taxonomic Ornstein-Uhlenbeck Prior for Avian 3D Shape Recovery
Constant Term Shrinkage for Federated Learning
When is Warmstarting Effective for Scaling Language Models?
Reproducing FACTER: Fairness via Conformal Thresholding and Prompt Repair
AVOC: Enhancing Hour-Level Audio-Video Understanding in Omni-Modal LLMs via Retrieval-Inspired Token Compression
Unified Synthesis of Compositional Speech and Sound from Free-Form Text Prompts
Generalized Influence Functions for Better Model Change Estimates
Freeing the Law with LOCUS: A Local Ordinance Corpus for the United States
Soft-Radial Projection for Constrained End-to-End Learning
Otter Weather: Skillful and computationally-efficient medium-range weather forecasting
Paleoinspired Vision: From Exploring Colour Vision Evolution to Inspiring Camera Design
DoG: Sniffing Out Overconfidence in LLM Agents via Post-hoc Trajectory Restructuring
CORAL: A Benchmark for Structure-aware and Brain-wide Neuron Reconstruction in Light Microscopy
Compact Representations of Impact-Based Fair-Ranking Policies
Tree-Guided Identify Then Exploit: A Unified Framework of Pure Exploration and Regret Minimization for Dueling Bandits
Breaking the Second Barrier: Sub-Second Timestamped Omni-Modal Captioning
LDM-is-AE: Latent Diffusion is an Intrinsic Auto-Encoder for End-to-End Image Generation
COLLAR: Cascaded Object-Level Latent Refinement for High-Fidelity Conditional Generation
A Theoretical Framework for Self-Play Theorem Proving Algorithms
Mitigating Overgeneralization in RND via Spectral Target Design
Efficient Reasoning via Constrained Optimization in Latent Space
Taming the Tails: Why Distributionally Robust Optimization Needs New Theory for Imbalanced Regression
Scalable Minimal-Change Learning for Controllable Image Editing
Slide P2V-Bench: A Cross-Domain Benchmark for Slide-Centric Scientific Paper-to-Presentation Video Generation
From Retrieval to Reasoning: Agentic Mechanism Prediction from Cell Painting Profiles
Epistemic Social Learning: Latent Behavioral Structure under Endogenous Multi-Agent Interaction
Squeezing Capacity from Multimodal Large Language Models for Subject-driven Generation
Proactive Instance Navigation with Comparative Judgment for Ambiguous User Queries
Symplectic Reck: In-Situ Learning of Gaussian Quantum Operations
Correct, Route, Calibrate: Efficient Preference Optimization from Noisy, Heterogeneous Human Feedback
Behavior-Discriminative Reward Shaping for Reward-Robust Reinforcement Learning
Symplectic Neural Operators for Learning Infinite Dimensional Hamiltonian Systems
Privately Clipping Heavy-Tailed Data
NAGO: Noise-Aware Generative Operator via Flow Matching
interwhen: A Generalizable Framework for Steering Reasoning Models with Test-time Verification
EvoInspect: A Unified Self-Evolving Multi-Agent Framework for Industrial Hardware Inspection
The Interplay of Data Structure and Imbalance in the Learning Dynamics of Diffusion Models
Deep Ensembles for Epistemic Uncertainty: A Frequentist Perspective
The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment
LSVD: Loss-Aware Low-Rank Approximation for Efficient Low-Precision Vision-Language Models
Distribution Corrected Decision Transformer for Offline Reinforcement Learning with Imbalanced Datasets
SAG-Sep: Sparse Augmented Graphs and Onion-Guided Search for Rounded Capacity Cut Separation
Next Forcing: Causal World Modeling with Multi-Chunk Prediction
Who Should Evolve? Uncertainty-Aware Role Bottleneck Inference for Multi-Agent LLM Training
PointForward: Feedforward Driving Reconstruction through Point-Aligned Representations
Trajectory Forcing: Exploiting Diffusion Trajectories for Autoregressive Long Video Generation
Point4D: Long-range 4D Motion Reconstruction
Utility-Driven Clustered Federated Learning via Class-wise Interaction Attribution
RxnOptBench: Benchmarking LLMs for Reaction-Condition Optimization in Organic Methodology
ProbMedTOD: A Bayesian Network Guided Task-Oriented Dialogue System for Patient History Taking
Bridging Safety and Performance in Autonomous Systems using Offline Reinforcement Learning
How Far Are VLMs from Privacy Awareness in the Physical World? An Empirical Study
Beyond Steering Vector: Flow-based Activation Steering for Inference-Time Intervention
FAUST: Federated Asynchronous Update with Staggered Timescales for Low-Communication Foundation Model Training
Exploring the Limits of Compositional Generalization in Vision-Language-Action Manipulation
MCSplat: Multi-View Photometric and Geometric Consistent Feed-Forward Gaussian Splatting for Driving Scenes
NLD4CO: Neural Langevin Dynamics for Combinatorial Optimization
Rectified Policy Rollouts with Hierarchical Expert Guidance for Neural Combinatorial Optimization
UECO: A Unified Encoder with Structure-Aware Attention Mixture via Iterative Edge Evolving for Neural Combinatorial Optimization
Understanding Schedule-Free Methods in Nonconvex Optimization: Rate Guarantees and Escaping Saddles
Thompson Sampling using Prior-fitted Diffusion Transformers
Budget-Conditioned Clipping Policies for Differentially Private Federated Learning
DoAtlas-1: A Causal Compilation Paradigm for Clinical AI
Experience Makes Skillful: Enabling Generalizable Medical Agent Reasoning via Self-Evolving Skill Memory
PoSafeNet: Structured Safety Learning via Compositional Projection
BarrierSteer: LLM Safety via Learning Barrier Steering
ExperiGen: Agentic Hypothesis Discovery from Observational Data
Baba in Wonderland: Online Self-Supervised Dynamics Discovery for Executable World Models
Leveraging Dale’s Principle as an Inductive Bias in Recurrent Neural Networks
3D Fresnel Volumizing for Efficient Implicit Velocity Field Reconstruction
CURE: Visual Reprogramming of Vision-Language Models under Limited Supervision
LEVDA: Latent Ensemble Variational Data Assimilation via Differentiable Dynamics
Private Online Prediction from Experts with Small Losses
FARE: Forensic Acceptance Region Estimation for Catching Bait-and-Switch Image Generators
A multi-scale information geometry reveals the structure of mutual information in neural populations
Can Pixels Alone Reveal Image Origin? Minimax Limits and Learnable Interfaces for Passive Provenance
PixelPonder: Dynamic Patch Adaptation for Enhanced Multi-Conditional Text-to-Image Generation
TriAxialKV: Toward Extreme Low-Precision KV-Cache Quantization for Agentic Inference Tasks
Variance-Adaptive Optimal Algorithm for Reinforcement Learning with MNL Function Approximation
On the Feasibility of Identity Manipulation for Diffusion-Based Face Privacy Preservation
HALO: Homotopy-Augmented Layer Optimization for Stable LLM Supervised Post-training
PCFBench: How Far Can Large Vision-Language Models Go in Physics-aware Photonic Inverse Design?
Visual Latents Know More Than They Say: Unsilencing Latent Reasoning in MLLMs
Hider–Seeker Self-Play: Geometry-Verifiable Process Rewards for Long-Horizon Visual Search
AdaKVQ: Adaptive Mixed-Precision KV Cache Quantization For Efficient Reasoning Models
AtmoZero: Self-Play Post-Training for Caption-Free Weather Time-Series Captioning
Prototype-Aligned Multi-View Graph Learning for EHR Prediction
MM-OptBench: A Solver-Grounded Benchmark for Multimodal Optimization Modeling
TailDiff: Elicitable Tail-Guided Diffusion for Risk-Sensitive Generation
Latent-Lens: Visual Perception in Small Language Models Through Latent Communication
PEARL: Solver-in-the-Loop Interactive Optimization Modeling from Natural Language
Optimal Subgroup Discovery at Every Support Threshold
Global Importance Estimation for KV Cache Eviction
Making LoRA Identifiable: Orthogonal Alignment for Continual Learning
Latent Reasoning in Continuous Space for Unified Multimodal Models
TagBO: LLM-Driven Task-Aware Graph Bayesian Optimization for Scientific Discovery
IIDiff: Learning Cross-Domain Frequency Transitions with Diffusion Mixture-of-Experts
GLARE: Generating Listening Heads with Appropriate REactions
ST-DiffEye: Diffusion-based Continuous Gaze Generation via Joint Scanpath-Trajectory Modeling
ES-Merging: Biological MLLM Merging via Embedding Space Signals
Diagnosing Math-Reasoning Failure Structure with Milestone Oracles
Rethinking Reward Models for Multi-Domain Test-Time Scaling
From SGD to Muon: Adaptive Optimization via Schatten-p Norms
Predicting Species Splits: A Challenging Fine-Grained Benchmark for Category Discovery
Identified-Set Geometry of Distributional Model Extraction under Top-K Censored API Access
D-PACE: Dynamic Position-Aware Cross-Entropy for Parallel Speculative Drafting
Precision-Pyramid: Towards real-time neural decoding for fault-tolerant quantum computing
A Biconvex Formulation for Stable Transport of Mixture Models with a Unique Solution
PRIM: Meta-Learned Bayesian Root Cause Analysis
Empirical regularities in subjective decision-making by LLMs
Robust Latent Space Bayesian Optimization with Marginalized Kernel
EditFlowSR: Revisable Expression Generation for Symbolic Regression
Recovery Guarantees for Posterior Sampling of One-Bit Compressed Sensing
MaSC: A Masked Similarity Metric for Evaluating Concept-Driven Generation
BDC-Merge: Cross-Architecture Model Merging via Dependency Alignment
Generative Actor-Critic with Soft Bridge Policies
Rosetta: Composable Native Multimodal Pretraining
Neptuna: A Comprehensive Machine Learning Framework for Benchmarking Complex Multiphase Flows
Think, Plan, Paint: Layout-Aware Reasoning for Controllable Image Generation in Unified Models
UNICOM: Unified Multimodal Modeling via Compressed Continuous Semantic Representations
Can VLMs Reason When to Stop for Human Safety?
HYDRA: Representation Harmonized Tokenization for Multimodal Generation and Understanding
OgBench: A Framework for Evaluating Graph Neural Networks on Omics Data
Not All Tasks Quantize Equally: Fisher-Guided Quantization for Visual Geometry Transformer
Interactive 4D Volumetric Liquid Forecasting under Moving-Solid Interaction
SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning
Instance-Optimal Estimation with Multiple LLM Judges on a Budget
Hydra-X: Native Unified Multimodal Models with Holistic Visual Tokenizers
TTB: Test-time MLP Baking for Efficient Rendering of Decoder-only View Synthesis Models
What Does the AI Doctor Value? Auditing Pluralism in the Clinical Ethics of Language Models
A Black-Box Reduction from Regret to Multi-Level Coverage
Beyond Hard Negatives: Grounded Positive Supervision for Compositional CLIP
Agent Explorative Policy Optimization for Agentic Multimodal Reasoning
LACE: Latent Alignment via Counterfactual Embeddings
Forgetting is Not Always Bad: A Neuro-Inspired Memory Repair Mechanism for Poisoned LLM Agents
Selection, Not Fusion: Radar-Modulated State Space Models for Radar-Camera Depth Estimation
POISE: Instance-Specific Prompt Tuning under Latent Mixture Target Distributions
Counterfactual Online Conformal Prediction Under Adaptive Logging
Improving the Optimization Landscape of Matrix Completion with $\epsilon$-close Surrogates
Towards Understanding the Power and Limits of the Muon Optimizer: A River-Valley Perspective
Estimating Continuous Treatment Effects with Recourse Data
Beyond Imputation: Mask-Adaptive Conformal Prediction via Tree Embeddings on General Missing Data Mechanisms
What Stops SGD on LLM Pre-Training: The Need for Large Learning Rate and How to Achieve it
Kernel Value Regression in Offline Reinforcement Learning
Fréchet Regression on the Bures-Wasserstein Manifold
PersonaManifold: Revealing and Exploiting Curved Geometry in LLM Persona Representations
AttnDiff: Attention-based Differential Fingerprinting for Large Language Models
A Novel Schur-Decomposition-Based Weight Projection Method for Stable State-Space Neural-Network Architectures
Understanding and Mitigating Structural Forgetting in Fine-Tuned Time Series Foundation Models
Benchmark Health Index: A Systematic Framework for Benchmarking the Benchmarks of LLMs
DSSNet: Deep Spectral Structure Profiling Network for Traffic Flow Prediction
ENACT: Single-Image Human-Scene Interaction Motion from Language via Foundation-Model Orchestration
Sampling-Based Safe Reinforcement Learning
ProteinOPD: Towards Effective and Efficient Preference Alignment for Protein Design
EpiStream: Utility-Aware Temporal Abstraction for Dense-Action Streams
Geometry-Aware Flow Matching for Sparse-View 3D Gaussian Splatting
Learning Reach-Set Geometry for Tighter Probabilistic Neural Network Verification
AbSpecAlign: Specificity Reward Alignment for Antigen-Conditioned Antibody Generation
VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon
Arbitrarily Conditioned Hierarchical Flows for Spatiotemporal Events
Do Coding Agents Deceive Us? Detecting and Preventing Cheating via Capped Evaluation with Randomized Tests
Importance-Weighted Operator Learning Under Probability Measure Shifts
FalconPerception-HD: High Density Perception via Reinforcement Learning
AutoformBot: Formalizing Mathematics at Scale
Harmless in Pieces, Harmful in Motion: Detecting Multi-Agent Jailbreaks
GVCC: Zero-Shot Video Compression via Codebook-Driven Stochastic Rectified Flow
Data-Free Reservoir Features for Efficient Long-Horizon Cold-Start Continual Learning
MoRe: Modular Representations for Principled Continual Representation Learning on Sequential Data
Long-Context Generation Is a Sampling Problem
XTC: Head-Aware Sampling by Excluding Top Choices
Enabling VLA Action Self-Verification via VLM Token Probability Bucketing
CivBench: A Long-Horizon Benchmark for Tool-Mediated Agents in Civilization VI
WTF?! Simulation-Free Reinforcement Learning with Wasserstein-Tilted Flow Maps
When Do Cosine Prototypes Mislead? A Whitening-Aware Benchmark for Frozen-Feature Image Classification
SAFE-FEC: Semantically Constrained Adversarial Frontier Evolution for Factual Error Correction
A Graph Foundation Model for Unified Clustering
Towards Universal Black-box Attacks on Graph Neural Networks
Split Then Select: Moment-Preserving Density Control for Generalized Primitive Splatting
Reason to Play: Behavioral and Brain Alignment Between Frontier LRMs and Human Game Learners
Reconsidering Positional Supervision in Masked Diffusion Language Model Training
How Selection Shapes Diversity in LLM Ecosystems
Tactile MNIST: Benchmarking Active Tactile Perception
Benchmarking Compositional Generalisation for Machine Learning Interatomic Potentials
From Squeezing to Grounding: Visual Guided DPO for Multimodal Hallucination Mitigation
High-Fidelity Boltzmann Samplingvia Physical Prior Lifted Continuous GFlowNets
SwiftFlow: An Efficient One-Step Policy Learning via Improved Mean Flow for Robotic Manipulation
Hypergraph Representation Learning with Hyperlink Random Effects
The Geometry of Forgetting: Temporal Knowledge Drift as an Independent Axis in LLM Representations
LoReC: Rethinking Large Language Models for Graph Data Analysis
State Copying Crowds Out Reasoning: Mechanistic Evidence for Delta Planning in Autoregressive Models
Neighbor-Aware Snapshot-Based Temporal Graph Learning
STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens
ROLLVERIFY: BRIDGING EFFICIENCY AND ACCURACY IN LONG-TAIL ROLLOUT REINFORCEMENT LEARNING
T-ReX: Learning Tile-Reuse Indexes for Structured Model Compression
Unleashing the Power of Intrinsic-Entropy-Driven Exploration for Off-Policy Generative RL
VideoSTF: Stress-Testing Output Repetition in Video Large Language Models
Neuronal Self-Adaptation Enhances Capacity and Robustness of Representation in Spiking Neural Networks
FiTS: Interpretable Spiking Neurons via Frequency Selectivity and Temporal Shaping
How Do Agentic LLMs Decide to Call Tools? A Scaffold Default Controlled by Suppression
On the Nature of Attention Sink that Shapes Decoding Strategy in Omni-LLMs
Who Says What: Symbolic Trimodal Binding Mechanisms in Audio-Visual LLMs
Lost in Translation, Found in Embeddings: Sign Language Translation and Alignment
When Symbol Names Should Not Matter: A Logistic Theory of Fresh-Symbol Classification
CrossSteer:Cross-Modal Safety Steering for Audio-Language Models
Real2Sim in HOI: Toward Physically Plausible HOI Reconstruction from Monocular Videos
From Matching to Reasoning: Query-Aware Long Video Summarization
Flow Matching Policy Optimization with Mirror Descent and Entropy Constraints
Seq-LoRA: Sequential Bayesian Low-Rank Adaptation for Large Language Models
DualWorldBench: Can Agents Plan Deliveries across Symbolic and Grounded Worlds?
FrameRouter: Frame Budget Routing for Long-Video Understanding on Video-MME-v2 and Beyond
KNOT: A Knowledge Entanglement Benchmark for Robust Unlearning Evaluation
CLUE: Closing the Loop on Conflict and Collapse in LLM Unlearning
SelfGuard: Self-Supervised Deviation Modeling for Multi-Modal Jailbreak Detection
Treating Hyperparameters as Interventions: Task-Invariant Representation Learning for Transferable HPO
Croissant Baker: Metadata Generation for Discoverable, Governable, and Reusable ML Datasets
META-PAP: Meta-learning for Prompt-aware Preference Pairing in LLM Alignment
Cool Graphs: Active Property Search Towards Quantum Nano-Refrigerators
PACE: Phase-Aware Chunk Execution for Robot Policies with Action Chunking
Plausibility Is Not Prediction: Contrastive Evidence for LLM-Based Cellular Perturbation Reasoning
Seeing Both the Forest and the Trees: Reusing Holistic 3D Priors for Part-Decomposed Generation
GeneZip: Region-Aware Compression for Long Context DNA Modeling
Generative Structure from Motion with Native 3D Diffusion
Beyond Pixel Space: Frequency-Domain Uncertainty Estimation for Structure-Aware Diffusion Guidance
Diffusion Tree Search for Inference Time Adaptation of Material Foundation Models
Towards Explainable Industrial Anomaly Detection via Knowledge-Guided Latent Reasoning
Improving Guidance-Free Visual Generation via Self-Contrastive Alignment for Likelihood Estimation
Hyperbolic Concept Embedding Model for Interpretable Medical Image Diagnosis
View Confidence Perception-Driven Incremental Prediction for Incomplete Multi-view Multi-label Learning
Voxel as Token: A New Perspective for Zero-shot Cross-subject Vision Decoding
EcoGEO: Trajectory-Aware Evidence Ecosystems for Web-Enabled LLM Search Agents
Proportionality in Ranking Compression
LOFT: Low-Rank Orthogonal Fine-Tuning via Task-Aware Support Selection
Manifold Drift in Flow Preference Optimization: A Root Cause of Reward Hacking
HiLoRA: Adaptive Hierarchical LoRA Routing for Training-Free Domain Generalization
Steering Frozen LLMs: Adaptive Social Alignment via Online Prompt Routing
TF-PRVR: Training-Free Partially Relevant Video Retrieval for Real-World Generalization
TAPIOCA: Why Task- Aware Pruning Improves OOD model Capability
FlashRelight: Portrait Video Relighting with Dynamic Lighting
EVA-Cap: Optimizing Audiovisual Video Captioning via Event-Centric Alignment
Filter Banks: from Low-Rank Representations to Deep Models for Efficient Time Series Forecasting
Reformulating Neural Operators in $d+1$ Dimensions for Embedding Evolution
Heterogeneous Graph Federated Learning with Structure-Aware Data-Free Distillation
AI Control for Sandbagging on Fuzzy Tasks
FlyingDrones: A Dataset and Benchmark for Optical Flow Estimation from UAV motion
LogicTree-RAG: Logic Tree-guided Retrieval-Augmented Generation for Long-form Patent Drafting
CODA: Cohort- and Drift-aware Foundation Model for Multimodal Clinical Reasoning
Communication-Efficient Personalized Adaptation via Federated-Local Model Merging
Are Your Reasoning Models Reasoning or Guessing? A Mechanistic Analysis of Hierarchical Reasoning Models
Efficient Computation and Best-Response Dynamics in Anonymous Two-Action Games with Linear Utilities
Git Context Controller: Manage the Context of Agents by Agentic Git
Latent Abstraction for Retrieval-Augmented Generation
MineEvolve: Self-Evolution with Accumulated Knowledge for Long-Horizon Embodied Minecraft Agents
Fixed-Point Reasoning: Stable and Adaptive Deep Looped Models
Toward Executable Multi-framework Front-end Code Generation with Self-Correction
Phase-wise MLLM Tuning for Multi-framework WebUI Code Generation
Permute-then-Adapt: Weak-to-Strong Contrastive Image--Text Adaptation
Memento No More: Coaching AI Agents to Master Multiple Tasks via Hints Internalization
Tree Rotary Positional Encoding for Extreme Length Extrapolation from Scratch
Out-of-Distribution Detection in Continual Learning
3A-VLA: Abstraction-Aligned Action Learning for Vision-Language Agents in 3D Game Worlds
OmniDex: Scaling Dexterous Hand Grasping to Diverse Cluttered Scenes
Adaptive Conditional Gradient Sliding: Projection-Free and Line-Search-Free Acceleration
FoMEMO: Towards Foundation Models for Expensive Multi-objective Optimization
LinuxArena: A Control Setting for AI Agents in Live Production Software Environments
From Outcome to Representation: Tracing Reasoning Mechanisms through Integrated Policy Gradient
Learning Robust Representations for Defending White-Box Adversarial Attacks in Continual Learning
Towards Multi-Human-Value Alignment via Value Localization in LLMs
Neural Proposals, Symbolic Guarantees: Neuro-Symbolic Graph Generative Modeling
CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Driving
Noisy Data is Destructive to Reinforcement Learning with Verifiable Rewards
Controlling Transient Amplification Improves Long-horizon Rollouts
RescueBench: Can Embodied Agents Save Lives in the Wild?
ArtCrafter: Feed-Forward Generation of Articulated 3D Object with Analytic Joint Derivation
SituRecBench: A Benchmark for Situated Recommendation in 3D Interactive Environments
CADMA: Capacity-Aware Recall Decomposition for Generative Model Assessment
CPSea2: Composing Terminal Geometries for Structurally Diverse Cyclic Peptide Binder Design
PriorVLA: Prior-Preserving Adaptation for Vision-Language-Action Models
Auto-Rubric as Reward: From Implicit Preference to Explicit Generative Criteria
GEM: Interpretable Language Models via Geometric Embedding Alignment
NEST: Nascent Encoded Steganographic Thoughts
Dream-Cubed: Controllable Generative Modeling in Minecraft by Training on Billions of Cubes
Synthetic Pre-Pre-Training Improves Language Model Robustness to Noisy Pre-Training Data
Neural Preconditioned Born Series: A Metric-Matched Framework for Learning-based Preconditioners
CCTimeBoost: Learning Time-Varying Relative Risk with Case-Control Boosted Trees
StableVQ: Practical Guidelines for Stable Vector-Quantized Tokenizer Training
Procedural Refinement by LLM-driven Algorithmic Debugging for ARC-AGI-2
Training-Free Open World Object Detection
TSFM Meets LLM: Context as Covariate
PF-SGS: Pose-Free Streaming 3D Gaussian Splatting for Large-Scale Scene Reconstruction
Symmetry-Guaranteed Prediction of High-Order Tensor Properties for Crystalline Materials via Irreducible Decomposition
FlowSteer: Towards Agents Designing Agentic Workflows via Reinforced Progressive Canvas Editing
CP-MLPs: A Tensor-Rank Theory of Tied and Untied MLP Blocks
Iris: Empowering Video MLLMs with High-Frequency Pose Priors via Spatiotemporal Binding
Provable Explanations for Any-Order Neural Additive Models
MatCurvs: Article Real-Coordinate Curve Extraction for Agent-Ready Materials Reasoning
LatentUM: Unleashing the Potential of Interleaved Cross-Modal Reasoning via a Latent-Space Unified Model
Segment and Select: Vision-Language Segmentation in 3D Scenarios
MaterialsPilot: An Execution-Feedback Framework for Generative Design of Complex Atomistic Architectures
PhotoFlow: Agentic 3D Virtual Photography Missions
MVVBench: Benchmarking 4D Reasoning in Vision-Language Models
BEAKER: An Expert-Curated Benchmark for Embodied Brains in Self-Driving Chemical Laboratories
Stitched Value Model for Diffusion Alignment
Accelerating Video Inverse Problem Solvers with Autoregressive Diffusion Models
Learning Spectral Compositional Koopman Operators for Global-to-Regional Weather Forecasting
Energy-Tweedie: Score meets Score, Energy meets Energy
DACE RL for Compute Efficient Reinforcement Learning in Small Model Reasoning
EGCA: A Spectral Perspective on Forward Process Design in Diffusion Models
Predicting What Changes: Causal Delta World Models for Risk-Aware LLM Agent Planning
Drive vs. Decay: On the Training Dynamics of Joint-Embedding Predictive Architectures
Does Compression Imply Generalization? A Minimum Description Length Perspective
Think Densely, Act Sparsely: Latent Expert Cognitive Chains for Vision-Language-Action Autonomous Driving
TANGO: RNA Topology and Geometry Co-Design
An Analytical Model of Compute-limited Multistage Training Pipelines
PGGT-Loc: Primitive-Grounded Geometry Transformer for Feed-Forward Camera Localization
Fast Reconstruction of Exact Maxwell Dynamics from Sparse Data
Simple Projection-Free Algorithm for Contextual Recommendation with Logarithmic Regret and Robustness
From Average Sensitivity to Small-Loss Regret Bounds under Random-Order Model
Agentic Abstention: Do Agents Know When to Stop Instead of Act?
Faster Dynamic Graph Clustering with Hierarchical Graph Contraction
Mitigating Confidence Miscalibration in Open-World Semi-Supervised Learning
Measuring Layer-wise Intrinsic Dimensionality of FFNs in LLMs via PCA
Class–Domain Discriminability Guided Representation Enhancement for Domain Generalization
SENSE: Semantic Neural Speech Synthesis from Brain Dynamics via Spatial Graph Encoding
FADE: Fractional Anomalous Dynamics Extrapolation for Training-Free Diffusion Transformers Acceleration
Nüwa.RNA: An RNA Foundation Model for Unified Representation with Deep Structure Infusion
SSDGExplainer: Structure-Semantic Dual-Guided Explainer for Graph Neural Networks
Spark: Path-Aware Experiential Self-Evolution for VLMs Spatiotemporal Reasoning
Boosting Graph Contrastive Learning via Manifold-Guided Representation Disentanglement
QB-Highlights: Quality-Guided Budgeted Highlight Detection in Videos with Dense Query-Relevant Moments
HumanoidArena: Benchmarking Egocentric Hierarchical Whole-body Learning
Breaking the Quality–Privacy Tradeoff in Tabular Data Generation via In-Context Learning
Stable Partial Order Constraints for Temporal Causal Structure Learning
Intervention-Guided Image-Free Classifier Expansion for Fine-Grained Recognition
Risk-Sensitive Deep Optimal Stopping
FracTS: Hierarchical and Autoregressive Time Series Generation
When Confidence Rises Too Early: Detecting Shortcut Reasoning via Premature Answer Commitment
HOPE: Hand-Object Pressure Estimation from Monocular Videos
COHE: Auditing Non-Transitivity in Sample Difficulty Proxies for Vision Models
Attack Selection In Agentic AI Control Evaluations Meaningfully Decreases Safety
Beyond the Node Barrier: Zero-Shot Strategy Planning for LLM Training on Super-Nodes
Online Decision-Focused Learning under Semi-Bandit Feedback
Forgetting Has Neighbors: Localized Collateral Forgetting in Machine Unlearning
Illusory Pattern Perception Drives Spurious Inference in Large Language Models
EchoPrune: Interpreting Redundancy as Temporal Echoes for Efficient VideoLLMs
EHRNote-ChatQA: A Benchmark for Evidence-Grounded Multi-Turn Clinical Question Answering over Longitudinal Discharge Summaries
BusterX: MLLM-Powered AI-Generated Video Forgery Detection and Explanation
CARVE: Counterfactual Video Editing for Auditing and Hardening Video Detectors
Diffusion-State Policy Optimization for Masked Diffusion Language Models
Point Tracking Improves World Action Models
AIM: Adaptive Interaction in Multi-Agent Debate for Multimodal LLM Inference
Sparsely Supervised Diffusion
Parameter Exploration for RLVR via Variational Learning
Cheap Talk, Real Stakes: Commitment and Exploitation in Human-LLM Strategic Interaction
Not All Features Are Created Equal: A Mechanistic Study of Vision-Language-Action Models
Kernel-based guarantees for nonlinear parametric models in Bayesian optimization
D-DOIT: Training-free Adaptation of Discrete Diffusion via Doob's h-Transform
Distill to Think, Foresee to Act: Cognitive-Physical Reinforcement Learning for Autonomous Driving
AdaPCLA: Curriculum Prior Internalization For Long-Tailed Longitudinal EHR Generation
RAIL: Rethinking Auditory Intelligence in Large Audio-Language Models with a CHC-Grounded Benchmark
TSQAgent: Rating Time Series Data Quality via Dedicated Agentic Reasoning
MIRA: Mutual Information guided calibration for Reliable Test-Time Adaptation
Marrying Optimal Transport and ODEs for Unified Continuous-Time 4D Reconstruction and Tracking
Bernoulli Flow Models: Self-Consistent Generative Modeling for Binary Data
A New Perspective on Target-Conditioned Structural Dynamics for Link Prediction in Dynamic Graphs
LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning
Video-Zero: Self-Evolution Video Understanding
Efficient Off-Policy RL for Video Generation via Forward-Consistent Reward Matching
MemReward: Graph-Based Experience Memory for LLM Reward Prediction with Limited Labels
SignRot: LLM Quantization with Massive Outlier-Aware Sign-Adjusted Rotation
Coarse-to-Fine Autoregression over Hierarchical Discrete Codes for Molecular Graph Generation
Memorization Is Folding: Topological Signatures of Noisy-Label Learning
How Hard Is It for Message-Passing GNNs to Simulate One Weisfeiler-Lehman Color-Refinement Step?
Standing on the Shoulders of Giants: Rethinking EEG Foundation Model Pretraining via Multi-Teacher Distillation
kVNN: Learnable Volterra Network Kernels
When Catastrophic Inheritance Meets Forgetting in Continual Adaptation of Foundation Models
VERITAS: Veracity-Enhanced Robust Identification of LLM-generated Text Against Style-shifts
OpenClawBench: Benchmarking Process-side Anomalies in Real-world Agent Execution Trajectories
MLLM-Edit: Benchmarking Image Forgery Detection and Localization under MLLM-based Editing
ADIS-Law: Unified Scaling Laws for Annealing-Phase Domain Injection in Large Language Models
MHWA: Multi-timescale Hierarchical World-Action Model
Online Evaluation of LLMs via Dyadic Designs
WaveletLoRA: Frequency-Aware Content-Style Decomposition for Personalized Image Generation
Geometry-Aware Online Scheduling for LLM Serving: From Theoretical Bound to System Practice
Variable-Length Generative Protein Design via Generalized Poisson Flow
LangFlow: Continuous Diffusion Rivals Discrete in Language Modeling
SemMSA: Latent Semantic-Aided Robust Multimodal Sentiment Analysis with Incomplete Data
SLiDE: Structured Linear Dynamics for Forecasting with Exogenous Inputs
Amortized Guidance for Image Inpainting with Pretrained Diffusion Models
ART for Diffusion Sampling: A Reinforcement Learning Approach to Timestep Scheduling
Re-evaluating Confidence Remasking in Masked Diffusion Language Models
MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents
From Infrastructure to Interface, the AI Value Chain Drives LLM Homogenization
Efficient Evaluation of LLM Performance with Statistical Guarantees
Should We Pay This Much for Robustness? Efficient Proxy Certificates with Marginal Guarantees
Agentick: A Unified Benchmark for General Sequential Decision-Making Agents
SimpliHuMoN: Simplifying Human Motion Prediction
FlowMoP: Stochastic Multi-Person Motion Prediction
MAGE: All-[MASK] Block Already Knows Where to Look in Block Diffusion LLM
Learning Deployable Causal Action Geometry under Temporal Non-Stationarity
Measure-to-measure Regression with Transformers
Split-and-scale Latent 3D Representations
MiroEval: Benchmarking Multimodal Deep Research Agents in Process and Outcome
SliMOO: Interpretable Multi-Objective Evolutionary Search for LLM Depth Pruning
INSPO : Unlocking Intrinsic Self-Reflection for LLM Preference Optimization
BitMTP: When Multi-Token Prediction Meets Low-Bit Large Language Models
OmniToM: Benchmarking Theory of Mind in LLMs via Explicit Belief Modeling
Energy Is All We Need: Beyond FLOPs in Model-Heterogeneous Federated Learning
Kernelized Activation Steering
The Mechanism of Weak-to-Strong Generalization: Feature Elicitation from Latent Knowledge
Focusable Monocular Depth Estimation
The Heel of RLVR: Benchmark Glory Should Not Outpace Honest Measurement
Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and Large Language Models
Not All Routing Drift Is Harmful: Trust-Region Projection for Class-Incremental Learning
ProEdit: Inversion-based Editing From Prompts Done Right
Expanding the Role of Diffusion Models for Robust Classifier Training
Open Vocabulary Domain Unlearning
When Depth Lies: Benchmarking Vision-Language Models on Mirror-Induced RGB-D Ambiguity
CAB: Accelerating Flow and Diffusion Sampling via Rectification and Corrected Adams-Bashforth
Model Immunization Beyond Condition Numbers: The Importance of Plateau Regions
PhysEval.Weather: An Evaluation Framework for Physical Consistency in ML Weather Models
AeroChem: Closed-loop Physics-Informed State Space Modeling for Long-term Chemically-Reactive Air Quality Forecasting
LUMOS: Tracing Parametric Knowledge from Training Data to Behavioral Outputs in LLMs
Conflict-Aware Logit Adapters for Utility-Preserving Anti-Distillation
Vision Transformers Learn Gestalt-Like Figure-Ground Cues from Natural Images
Cortically-Resolved Recurrent Architecture for fMRI
SeaPilot: Mobile Agent with Self-refining Environment Alignment
Worst-Case Regret Bounds for Combinatorial Bandits with Ranking Feedback
Layerwise LQR for Geometry-Aware Optimization of Deep Networks
Learning When to Trust LLM Priors: A Validated Framework for Semantic Prior Integration
DiffPTS: Rethinking Diffusion ELBO for Probabilistic Time Series Forecasting
TimeES: Probabilistic and Deterministic Time Series Forecasting via Evolutionary Spectra
TimeClaw: A Time-Series AI Agent with Exploratory Execution Learning
Channel Mixer: A Pretrainable Tokenizer for Scalable Multi-Channel Vision Transformers
Accelerating LLM Pre-Training through Flat-Direction Dynamics Enhancement
Escape the Context Manifold: Preventing DiT In-Context Editing via Conditional Flow Hijacking
Mitigating Reward Hacking via Task Representations
No Pose, No Problem in 4D: Feed-Forward Dynamic Gaussians from Unposed Multi-View Videos
Geometric Analysis of Neural Regression Collapse via Intrinsic Dimension
MemCode: Discrete Semantic Representations for Long-Term Agent Memory
Constrained Modulatory Reservoirs for Context-Dependent Computation
Realtime-VLA FLASH: Speculative Inference Framework for Diffusion-based VLAs
RB-LDC: Redundancy-Balanced Latent Coding for Robust Diffusion
Models Designed to Forget: Machine Unlearning via Key Deletion
StateLedger: Path-Addressed External Memory for Persistent Multi-Agent Systems
SPACE: Unifying Symmetric and Asymmetric Routing Problems for Generalist Neural Solver
MMSkills: Towards Multimodal Skills for General Visual Agents
Replicas-as-Variables: A Planner for Throughput-Optimal Routing in LLM Deployment
NIV: Neural Axis Variations for Variable Font Generation
MARBLE: an Agent Benchmark for Spatial Reasoning and Visual Abstraction
DiscoverPhysics: Benchmarking LLMs for out-of-the-box scientific thinking
Median-of-Means under Structured Heavy-Tailed Noise: High-Probability Bounds for Clipped Stochastic Optimization
REFLEX: RNA Ensemble Generation via Flexibility-Calibrated Stochastic Bridge
When Noise Meets Long-Tail: Feature-Threshold Dual Calibration for Robust Pseudo-Labeling
RVR: Retrieve-Verify-Retrieve for Comprehensive Question Answering
Training-Free Generative Sampling via Moment-Matched Score Smoothing
AsymPipe: Accelerating Large-scale DiTs Image Editing via Asymmetry-Aware Pipeline Parallelism
ScAn-Bench: Evaluating Scaling Analysis Methodology
Diffusion Meta-Prompting and Steering for Generalizable Foundation Model Adaptation
Approaching I/O-optimality for Approximate Attention
Pinpoint: Grounded Worldwide Image Geolocation via Cross-Source Retrieval and Reranking
MaRK: Markov-adapted Recurrent Kernels for Dynamic Operator Conditioning in State Space Models
Geometric Prompt-Trajectory Planning for Test-Time Scaling
On the Nonlinearity of Learning Rate Scaling for LLM Training
Diving-R1: Empowering Multimodal LLMs with Traceable Progressive Reasoning for Interpretable Diving Action Quality Assessment
Trajectory-Consistent Dropout for Uncertainty Decomposition in Hamiltonian Neural Networks
UnfoldArt: Zero-Shot Recovery of Full Articulated 3D Objects from Text or Image
DiversePlace: Diversity-Seeking Curriculum Reinforcement Learning for Macro Placement
Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR
STEP: Learning STructured Embeddings for Progressive Time Series
Local Guidance, Global Impact: Gaussian-Reshaped Trust Region Unlocks Behavior Transitions
Reranking with Intra-modal Visual Association for Text-to-Image Person Re-Identification
Lift, See, Act: Hierarchical Robot Policy Pretraining with 3D Foundation Models
Improving Quantized Zeroth-Order Optimization through Reconstructed Low-Rank Structures
Trie-Aware Transformers for Generative Recommendation
Commit Then Explore: Reasoning Models Diversify, Not Converge
EpicWorldModel: Exploration-driven Planning with Latent World Models
Self-Rewarded Multimodal Coherent Reasoning Across Diverse Visual Domains
Claude Coke: Prevent Automated Crime by Agents
Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
Probability-Conserving Flow Guidance
Reading Attribution from Attention: Evidence Heads as Latent Attribution Mechanisms in LLMs
Privacy Risk Scales with Effective Dimension in Federated Learning
BodyBench: Evaluating Adversarial Image Defenses Against AI Nudification Inpainting
AgentSSL: Can MLE Agents Leverage Unlabeled Data?
An In-Depth Analysis of Hallucination Detection Methods for Vision-Language Models
Linear Contextual Bandits with Quasi-Optimism
Spatial-temporal Attributes Enhanced Prompt Weighting and Fusion for Video Recognition
FENet: Functional Embedding Neural Network for Change-Point Detection in Functional Time Series
NNCoxKL: Risk-Set Distillation from Probability-Free Prognostic Teachers for Deep Cox Models
RipplePLM: Structural and Property Decoupling for Protein Mutation Effect Generation
Axiomatic Reinforcement Learning for Open Multi-Agent Systems from Shapley Axioms
Beyond Spatial and Temporal Priors: A Generalizable Approach for Dense Correspondence Matching
Reverse to Advance: Teleoperation-Cost Effective Hard Policy Learning from Reversed Easy Tasks
Combating Camouflage and Forgetting: Spatio-Temporal Dual Denoising for Money Laundering Detection
Frequency‑Aware Flow Matching for Continuous and Consistent Robotic Action Generation
Colored Noise Diffusion Sampling
Agentic Geometry Problem Solving via Human-like Parallel Bidirectional Reasoning
Learning inexact alternating minimization
Adaptive and Neutral Theory of Evolution Strategies for Large Language Models
SAVE: Sparsity-Aware Influence Estimation for Vocabulary-Expanded LLMs
CTM-AI: A Blueprint for General AI Inspired by a Model of Consciousness
Auto-Dreamer: Learning Offline Memory Consolidation for Language Agents
Symb-xMIL: Symbolic Explanations for Multiple Instance Learning in Digital Pathology
Commutator Memory: Sparse, Path-Local Reading and Steering in Language Models
Emergent Visual Thinking in Text-Only Reasoning through Multimodal Training
Signed-Permutation Coordinate Transport for RMSNorm Transformers
BioSafetyBench: Agentic Cascade Evaluation for the Bio-AI Ecosystem
Lookalike3D: Seeing Double in 3D
Exact Recovery of Lipschitz Orthogonal Coordinate Transformations via Constrained Normalizing Flows
Understanding Multimodal Failure in Action-Chunking Behavioral Cloning
Bidirectional Information Flow (BIF) - A Sample Efficient Hierarchical Gaussian Process for Bayesian Optimization
Thinking with Images as Continuous Policy: Numerical Visual Chain-of-Thought
BoxTuning: Object-Aware Visual Prompting for Multimodal Model Fine-Tuning
Variational Cover Modification Steganography
Self-Recognition Finetuning can Reverse and Prevent Emergent Misalignment
Real In, Real Out: What If We Only Use Real Data for Scene Text Editing?
Few-Shot Visual Concept Extraction for Steering Diffusion Transformers
Keep It CALM: Analyzing the Limits of Global Unsafety in Text-to-Image Generation
HiLoc: A Hierarchical Representation Method for Spatial Localization in Multimodal Large Language Models
LogSTOP: Temporal Scores over Prediction Sequences for Matching and Retrieval
Robust Concept Unlearning in Diffusion Models via Directional Stability Regularization
Beyond Stabilization: Dual-EMA Teachers for Global–Local Semantic Learning in Semi-Supervised Medical Image Segmentation
BReD: Block Replay Dithering for Stable Low-Bit EMA Optimizer States
A Unified Framework for Adversary-Aware Differential Privacy Bounds
Online Differentially Private Consistent Clustering
HIFC-IQA: Train-Free Cross-Domain Image Quality Assessment via Dual-Process Cognition
Toward Online Robust Zero-Sum Markov Games with Function Approximation
Every Sample Counts: Supervised Fine-Tuning of Language Models with Pointwise Constraints
Context as Low-Rank Weights: Bounded Parametric Dynamic Memory for Unbounded Context
Scattered by Design: Why Per-Output Pruning Resists Structured Compression
HyperNSDE: Personalized Neural SDEs for Joint Static—Longitudinal Clinical Data Generation
Brenier Meets Adversarial Training: Optimal Transport Geometry for Robust Learning
Modality-Depth Routing for Visual Reasoning in VLM Post-Training
Semantic-Statistical Prior Banks for Federated Low-Shot Learning under Non-IID Clients
Stabilizing Few-Shot Object Detection with Language-Conditioned Probabilistic Prototypes
Rubato: Signature Attention for Irregular Multivariate Time Series Forecasting
On the Runway Cascade of Transformers for Language Modeling
R-GRec: Relation-Guided Generative Recommendation via Collaborative Graph Supervision
Embedded-Arena: Building Hardware-in-the-Loop Coding Agents to Run AI on Microcontrollers
Fewer Tokens, Fewer Layers: Efficient Vision Token Pruning and On-Policy Distillation to Accelerate VLMs
Pref-DetectGPT: Unveiling Machine-Generated Text via Preference-Aware Curvature Measurement
Intervene3D: Intervention-Based Controlled Inference for Multimodal Perception under Partial Observability
MAMQ-Net: A Robust Framework Leveraging Multi-level Tamper-aware Queries and Complementary Representations of Tampering Features for Progressive Image Forgery Localization
Robust Multi-view Clustering against Imperfect Information
Allocentric Perceiver: Disentangling Allocentric Reasoning from Egocentric Visual Priors via Frame Instantiation
When Riemann flows with Wasserstein: Generative Modeling of Probability Distributions on Manifolds
Quantitative Assessment of Crystal Structure Prediction
Are Agents Ready to Teach? A Multi-Stage Benchmark for Real-World Teaching Workflows
Learning from Disagreement: Maximum Divergence Knowledge Distillation
Hearing is Believing? Evaluating and Analyzing Audio Language Model Sycophancy with SYAUDIO
HCInfer: An Efficient Inference System via Heterogeneous Error Compensation for Resource-Constrained Devices
ParallelKernelBench: Can LLMs Write Fast Multi-GPU Kernels?
NyoomFloat12: Accelerating LLM Inference via Lossless 12-bit Weight Compression
SwiftVLM: Efficient Vision-Language Model Inference via Cross-Layer Token Bypass
SynthHair: Leveraging MetaHumans for a High-Quality 4K Hair Matting Dataset
Learning Hierarchical Forward Processes For Discrete Diffusion Language Models
SBNO : Schrödinger Bridge Neural Operator for the Forward and Inverse Problems under Missing Information
A Model of Diverse Sampling from Language Models
Diffusion-warm sampling of the XY model enables fast thermalization at scale
PreCoMem: Predictive Cognitive Memory for Self-Evolving Long-Term Dialogue Agents
MIRA: Reinforcing Multimodal Reasoning via Deceptive Contextual Augmentation
Navigating by Old Maps: The Pitfalls of Static Mechanistic Localization in LLM Post-Training
What Cohort INRs Encode, and Where to Freeze Them
MM-SCALE: Evaluating Evidence-Grounded Moral Judgment in Vision-Language Models
Selective Safety Steering via Value-Filtered Decoding
Probabilistic Circuits for Irregular Multivariate Time Series Forecasting
Foundation Pareto Flow Policy for Multi-Objective Reinforcement Learning
ESSAM: A Novel Competitive Evolution Strategies Approach to Reinforcement Learning for Memory Efficient LLMs Fine-Tuning
H-GenPO: Hierarchical Generative Policy Optimization via the Option-Critic Framework
Agentic Neural Architecture Search
The Aleatoric-Epistemic Dichotomy of Uncertainty is Meaningful and Indispensable for Machine Learning
StyleRoute: Diffusion Style Transfer via Regional Routing and Conflict-aware Projection
LEAP: Library-driven Evolutionary Abstraction Paradigm for Large Language Models
CommunityKV: Efficient Long-Context Decoding via Graph Partitioning
VecUQ-OT: Aggregating Uncertainty Measures via Multivariate Ranks
[Re] FairDICE: A Fair Tradeoff in Multi-objective Offline RL
Locating and Repairing Domain Shift in VLM Trajectory Planning
REINS: A Self-Evolving Agent Harness for Real-Time Trajectory Planning
μLM: Rethinking Sub-100M Language Models through Memory-First Design
LittleLearner: Language Models Under Pedagogically-Controlled Knowledge Exposure
Human–AI Collaboration Requires a High-Order Dynamic Abstraction Substrate
PRISM:Disentangling Preference Distributions for Generative Ranking
Scenes as Objects, Not Primitives : Instance-Structured 3D Tokenization from Unposed Views
Follow the Regularized Leader Does Not Converge in Constrained Optimization
Position: Machine Learning Models for Reaction Transition States Deserve Better
RAPTOR: Ridge-Adaptive Logistic Probes
Virtual Task Prompting for Multi-Task Scene Understanding
AdaCal: Adaptive Calibration for Robust Sparse Attention in Long-Context LLMs
Counterfactual Instruction Grounding for Vision-Language-Action Models
Where to Connect? Boosting MLLMs via Dynamic Gated Pathways across ALL ViT and LLM Layers
RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution
Correctable Fork Tokens: Verifier-Anchored Selective Credit Assignment for Tool-Integrated RLVR
MMTA: Benchmarking Multimodal Temporal Analysis with Time Series, Text, and Vision
Evaluating the evidence trace of NeurIPS 2025 contributions with agentic code auditing
FEP-Agent: Grounding LLM Agent Self-Evolution in Active Inference with Semantic Memory
URDF-Anything+: End-to-End Generation for Simulation-Ready Articulated Assets
BrainVista: Modeling Naturalistic Brain Dynamics as Multimodal Next-Token Prediction
Rethinking Contrastive Loss in CLIP Post-training: A Complementary Framework with Frozen Text Encoder
Cannistraci-Hebb Channel-wise Dynamic Sparse Training of Convolutional Neural Networks with Contextual Modulation
Strong Post-Training from Permissive, Reasoning-Dominant, Web-Scale Pretraining
ITO: Multi-View Alignment and Training-Time Fusion for Image-Text Pretraining
Characterizing Memorization in Diffusion Language Models: Generalized Extraction and Sampling Effects
Class-Domain Incremental Learning with Extensible Multi-Center Modeling
ReFlex: Faithful Panorama Reconstruction from a Single Image with Reflections
ASAP: Fast Adaptive Sliding Agnostic Poisoning Attack on Federated Learning
RL-Guided Temporal Localization for Dual-Channel Retrieval in Long-Horizon Agent Memory
LLM-Auction: Generative Auction towards LLM-Native Advertising
ElegantVLA: Learning When to Think for Efficient Vision-Language-Action Models
Underlying Functional Structure of Reinforcement Learning
Continuous p-adic Optimization
Felid: A Flexible and Efficient Design for Transformer Fine-Tuning over Encrypted Data
Riemannian Optimization for Low-Rank Adaptation via Desingularization
Pixel-space Autoregressive Image Synthesis via Spectrum Serialization and Flow-based Refinement
BQ-LoRA: Binary-Quantized Low-Rank Adapters as Implicit Regularizers for Parameter-Efficient Fine-Tuning
ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow
Rethinking XAI Evaluation: A Human-Centered Audit of Shapley Benchmarks in High-Stakes Settings
Residual Paving: Diagnosing the Routing Bottleneck in Selective Refusal Editing
Efficient Test-Time Adaptation For Robot Policies
Learning to Recommend in Unknown Games
APS: Bias-Controlled Adaptive Prototype Simulation for Population-Scale LLM Agents
MUST: Stage-Adaptive Stability Control for Test-Time Scaling in Multimodal Reasoning
RaVF: Learning Radar Velocity Fields via Spatial-Doppler Guidance
MemeEconomy : Do LLM Agents Trade Ethics for Survival?
MESSENGER: Memory-Enhanced Sequential Scene Flow Estimation via Autoregressive Next-Frame Forecasting
Unified Resource-Grounded Coordination Protocol for Orchestrator-Free Heterogeneous Multi-Agent Systems
On Communication-Efficient Training of Ensembles in Federated Learning
HetCCL: Efficient LLM Training on Heterogeneous Vendor GPUs
UNIVERSE: Unified Video Action Models for Autonomous Driving with Flexible Mask-Modulated Modality Generation
Words Before Pixels: Selective Modality Routing for Vision-Language Model Unlearning
Polynomial-Time Algorithm for Thiele Voting Rules with Voter Interval Preferences
The Internal Growth Function: A More General PAC Framework for Scenario Decision Making
SAM 3D Animal: Promptable Animal 3D Reconstruction from Images in the Wild
SP$^2$ec: Adaptive Self-Speculative Decoding for Vision-Language Models
Mixture-Trained Merging for Unified Multi-Objective Models
Differentiating Network Design Objectives for Balancing Cost and Distance
ECHO: Continuous Hierarchical Memory for Vision-Language-Action Models
SCDBench: A Benchmark for LLM-Based Smart Contract Decompilers
MOSAIC-Bench: Measuring Compositional Vulnerability Induction in Coding Agents
A Unified Semismooth Newton Approach to Multitask and Multivariate Square-Root Lasso Problems
Position: Life-Logging Video Streams Make the Privacy–Utility Trade-off Inevitable
Learning to play with spikes. Characterizing, predicting, and engineering unsupervised plasticity rules for spiking reservoir computing
Multi-Constrained Randomized Smoothing Certificates
ProMo3D: Probing Motion Cues in Frozen 3D Foundation Models
DetectViT: Test-time Backdoor Detection for Vision Transformers via Inter-Head Attention Discrepancy
Trust Region Policy Distillation
Evaluating Test-Time Scaling of General LLM Agents
Need-Aware Multi-Objective Reinforcement Learning for Emotionally Intelligent LLM Agents
Position: Adopt Constraints Over Fixed Penalties in Deep Learning
Agentic AI Design Should be Mediated to Promote Social Welfare
From Local Skills to Long-Horizon Tasks: Progressive Skill Exploration for LLM Web Agents
Better Language Models Require Better Domain-Specific Inductive Biases
Towards Unified Memory Adaptation for LLM Agents: Textual, Latent, and Parametric Pathways
Dual-Pathway Circuits of Object Hallucination in Vision-Language Models
SIGA: Scientific Simulation Coding Agent Adapter- A Geophysics Case Study
HAPS: Hierarchical LLM Routing with Joint Architecture and Parameter Search
Perceive, Interact, Reason: Building Tool-Augmented Visual Agents for Spatial Reasoning
Long-Horizon Agency Belongs in the Harness, Not the Context Window Only
Treat Domain-Specific Languages as Design Variables in LLM Agents
Position: Machine Learning Conferences Should Introduce an Autonomous Research Track
Discovering Structurally Plausible and Interpretable Cognitive Models with Large Language Models
Equivariant Spherical Transformer for Efficient Molecular Modeling
Position: Robust Reasoning Requires Internal Time, Not Scale Alone
Take It or Leave It: Intent-Controlled Partial Optimal Transport
AI Evaluation Should Require Standardized Item-Level Data Releases
What Does the Brain See? Multiview Neural Representation to Demystify the Brain-Visual Alignment
Solver-Aware Decompositions for Programming-by-Example: When Dividing Requires Knowing how to Conquer
Embracing Evolution: A Call for Body-Control Co-Design in Embodied Humanoid Robot
Memory is Not Search: Towards Proactive, Lifelong Memory in AI
The Era of Agentic Organization: Learning to Organize with Language Models
Improving Neural Decoding Performance for Language BCIs by Explicitly Modeling Context-Induced Noise
Bilevel Optimization of Synthetic Trajectories for Multi-Turn LLM Fine-Tuning
Risks Create a Jagged Frontier of LLM Productivity Gains Across Computer Occupations
How Much Is One Recurrence Worth? Iso-Depth Scaling Laws for Looped Language Models
Denoise First, Orthogonalize Later: Understanding Momentum in Muon via Spectral Filtering
Bigger Isn’t Better: Why the Indiscriminate Scaling of Foundation Models Can’t Solve Biology
AlignDrive: Aligned Lateral-Longitudinal Planning for End-to-End Autonomous Driving
LLM Routing Through the Lens of Recommendation: A Roadmap for Efficient AI Orchestration
Simulating Students or Sycophantic Problem Solving? On Misconception Faithfulness of LLM Simulators
MorphSIG: Subject-Driven Image Generation via Decoupled Anchoring and Feature Transport
Geometry-Aware Subspace Perturbation for Heterogeneous Federated Learning
Semantic-Bridge Federated Learning: Bridging CLIP Semantics for Heterogeneous FL
Causality can systematically address the monsters under the bench(marks)
Mitigating Memorization Where It Happens
Lipschitz Dueling Bandits over Continuous Action Spaces
From Tokens to Tactics: Adversarial Text Optimization in an Axis-Aligned Rhetorical Strategy Space for Harmful Content Detection
Nearly Optimal Fixed-Confidence Best-Arm Identification with 1-Bit Feedback
Standardization of Post-Publication Code Verification is Possible with the Support of the Community
Outbidding and Outbluffing Elite Humans: Mastering Liar’s Poker via Self-Play and Reinforcement Learning
When the Merge Coefficient Stops Mattering: Proximity Regularized Merging for Continual LoRA Adaptation
Sampling Is Not Curiosity: Why LLM Agents Should Investigate
Beyond Training Time, Test-Time Coordination is Essential for Cooperative MARL
Signal-Adaptive Trust Regions for Gradient-Free Optimization of Recurrent Spiking Neural Networks
Agent Security is a Systems Problem
From Benchmark to Adoption: Coding Agent Evaluation Needs User-Level Harness
Fusion or Confusion? Multimodal Complexity Is Not All You Need
Large Language Model Failures from Hallucination to Homogenization Are Different Facets of Miscalibration
Mixture-of-Hierarchical Experts: Optimized Mamba Architecture for Vision Diffusion
RoPE Is Not a Proper Relative Position Embedding
PCEval: A Benchmark for Evaluating Physical Computing Capabilities of Large Language Models
AI Models Can Provably Hide Arbitrary Capabilities
Sport Is The Next Grand Challenge For Artificial Intelligence: Toward A Science Of Human Physical Skill
Do Image Editing Models Understand Lighting?
We Should Distinguish Unlearning From Untraining
Concise Reasoning Through the Lens of Lagrangian Optimization
Binding Mode Matters: Hotspot-Aware Drug Discovery via Explorative Preferences
Position: Neurosymbolic AI is a strong technical foundation for trustworthy, deployable AI by design
Hypergraph-guided Global Mean-field Negotiation For Multiview Evidential Classification
MixForensics: Blend Before You Encode for Generalizable AI-Generated Video Detection
Evidence Guided Dual Expert Memory with Joint Routing for VLLMs Online Correction
RGF: Recursive Generative Framework for the Edge-Cut Separable Problems
Rethinking Training Targets, Architectures and Data Quality for Universal Speech Enhancement
Co-optimization for Adaptive Conformal Prediction
Computer Use at the Edge of the Statistical Precipice
DAPS: Dependency-Aware Premise Selection for LLM Theorem Proving
Agentic AI Scientists Are Not Built For Autonomous Scientific Discovery
Tree Training: Efficient LLM Training on Tree-Structured Trajectories
Dynamics of the Transformer Residual Stream: Coupling Spectral Geometry to Network Topology
AT-SKM-Net: An Accelerated Trainable Sampling Kaczmarz-Motzkin Framework for Linear Hard-Constraint Feasibility on Dynamic Graphs
Slower Generalization, Faster Memorization: A Sweet Spot in Algorithmic Learning
DDACOM: Dual-Decoupled Adaptive Communication for Multi-Agent Reinforcement Learning under Dynamic Networks
A Theoretical Analysis of Why Masked Diffusion Models Mitigate the Reversal Curse
Video-FLAIR: Not Whether to Reason, But How
Not All Noise Is Harmful: Towards Perception Aware and Controllable RAW Image Joint Denoising and Demosaicing
VLMs Trace Without Tracking: Diagnosing Failures in Visual Path Following
Omni-Interactive Universal Embedder
MosaicMRI: A Diverse Dataset and Benchmark for Raw Musculoskeletal MRI
Generative Active Learning via Bayesian Acquisition for Improving the Efficiency of Synthetic Data
DialectLLM: A Dialect-Aware Dialog[ue] Generation Framework Beyond Standard American English
Adaptive Covariance and Multi-Layer Alignment for Out-of-Distribution Detection
Hearing the Unspoken: Simulator-Induced Asymmetric-View Policy Optimization for Proactive Task-Oriented Dialogue
EchoXFlow: A Beamspace Echocardiography Dataset for Cardiac Motion, Flow, and Function
LAQuant: A Simple Overhead-free Large Reasoning Model Quantization by Layer-wise Lookahead Loss
On Fitting Flow Models with Large Sinkhorn Couplings
Apple-$\pi$: Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence
Symplectic Normal Coordinates Flow for Generative Modeling of Hamiltonian Systems
SpatialBench: Is Your Spatial Foundation Model an All-Round Player
RADAR: Relative Angular Divergence Across Representations
Substrata: Know What You Don't Know
Residual Calibration via Local Feature-Space Refinement
INVITA-WheatFieldState: A Real-World Benchmark for Crop-State Estimation in Wheat Field Trials
Multiscale Microenvironment Vector Space Projection for Uncovering Diverse Pathological Biomarker
Leveraging Psychophysical Attentional Distribution for Gaze-Augmented Reward Modeling
Inferring Computational Structure from Neural Recordings with Gain-Modulated Linear Dynamical Systems
AcousticBench: Measuring Acoustic Perception in Large Audio Language Models
Reason in the Words You Speak: Idiolectal Paraphrasing Off-Policy Traces for Reasoning Distillation in VideoLLMs
GradTrack: Detecting Noisy Labels via Temporal Trajectories of Class-wise Gradient Misalignment
Mixture-of-Control: State-Aware Fine-Tuning for Transformer-based Models
Mind the Gap: The Divergent Rebound Dynamics of Diffusion and Autoregressive Model
Feature Information Dynamics in Diffusion
Differentially Private Model Merging
GOAT-AL: Pseudo Neural Collapse Guides Adaptive Coverage for All-Budget Active Learning
Return to Basics: Very Simple Graph Contrastive Learning via Noise Cancellation Principle
Adaptive Gated Simplicial Propagation for Node Classification in Multimodal Graphs
From Next-Token to Next-Block: A Principled Adaptation Path for Diffusion LLMs
Predicting Quantization Price for Selecting PTQ Configurations Before Deployment
probly: Uncertainty-Aware Machine Learning
When Graph Structure Provably Helps Classification: Non-Asymptotic Recovery Guarantees
Spectrally Decomposed Equivariant Graph Neural Networks for Interatomic Potentials
FracEncoder: Towards Adaptive Cognitive Trajectories via Fractional-Order Context Encoding
ROK-FORTRESS: Measuring the Effect of Geopolitical Transcreation for National Security and Public Safety
A Unified Neural Architecture for Variable-Wise Shape Constraints
Temporal Behavior Trees for Reinforcement Learning: Specifications as Rewards, Curricula, and Diagnostics
Task-Induced Riemannian Metrics for Vision Transformer Feature Spaces
OPPO: Bayesian Value Recursion for Token-Level Credit Assignment in Policy Optimization
TOPPO: Rethinking PPO for Multi-Task Reinforcement Learning with Critic Balancing
Diagnosing and Repairing Visual Collapse in Compact Medical Multimodal LLMs
Phase-Adaptive Fusion: Spatio-Temporal Modulation for VLA Models
On the Recoverability of Causal Relations from Bulk Gene Expression Data
Re:Cognize - A Framework for Open-Set Sequential Character Re-Identification
PHOEBI: An Open-World Benchmark for Bacterial Identification in Phase-Contrast Microscopy
RAG in a Trenchcoat: When Minimal Memory Is Enough for Agentic Systems, and When It Isn’t
SDS-LoRA: Overcoming Anisotropic Gradient Scaling in Low-Rank Adaptation
RECIPE: Learning to Rank Complete Precursor Sets for Inorganic Retrosynthesis
Phases of Muon: When Muon Eclipses SignSGD
BROS: Bias-Corrected Randomized Subspaces for Memory-Efficient Single-Loop Bilevel Optimization
FusionAudit: Pathway-Conditioned Robustness Auditing for Native Multimodal Models
Train the Agent, Not the Expert: Learning to Harness Heterogeneous Experts for Multi-Turn Visual Reasoning
Omni-Safety under Cross-Modality Conflict: Vulnerabilities, Dynamic Mechanisms and Efficient Alignment
Breaking Modality Heterogeneity in Low-Bit Quantization for Large Vision-Language Models
Not All Proofs Are Equal: Evaluating LLM Proof Quality Beyond Correctness
The Surprising Effectiveness of Video Diffusion Models for Hand Motion Reconstruction
Quantum Best Arm Identification with Limited Round of Adaptivity: Lower Bounds and Algorithms
SpikeSTAG: A Dendritic Compartmental Spiking Graph Network for Multivariate Time-Series Forecasting
Permanent and Transient Representations for Continual Reinforcement Learning
REACT: A Lightweight Reliability-Aware Framework for Spatio-Temporal Out-of-Distribution Prediction
Bridging the Gap: Position-Independent Cache Reuse for Hybrid SSM-Attention Architectures
Adaptive multiscale operator correction via learned spectral subspace and physics-informed optimization.
Detect Anything in Graphic Design: Element-Level Rewards for Autoregressive Detection
NEvo: Neural-Guided Evolutionary Video Synthesis for Dynamic Visual Selectivity
DAWN: Dependency-Aware Fast Inference for Diffusion LLMs
Bridging 1D, 2D, and 3D with Any-to-Any Multimodal Modeling
Sparse Layers are Critical to Scaling Looped Language Models
Learning Menu-Based Mechanisms for Truthful Budget-Feasible Procurement
Long-Term Risks of Risk-Based Allocation
Strategic Feature Selection and Regularization
Graph Cascades: Contagion-Based Mesoscopic Rewiring for Structure-Aware Graph Machine Learning
AI Alignment Can Build Moral Autonomy
Meta Inverse Prompting for Video Generative Models
Does 1/2-Tsallis-INF Also Work Well for Best-Arm Identification?
Generalized Laplacian in Spectral Seriation on Manifold Data
AgroOmni: A Large-Scale Multi-view Agricultural Dataset for Cross-Scale Multimodal Reasoning
CRISP: Compositional Reasoning over Images via Stackable Programs for VLMs
From Post-Hoc to Ante-Hoc: Consistently Explainable Semi-Supervised Time Series Classification
CRePE: Curved Ray Expectation Positional Encoding for Unified-Camera-Controlled Video Generation
DARE: Dual-Level Adversarial Learning with Domain-Aware Regularization for Whole Slide Image Classification
SCHTs: A Semi-Structured Dynamic Sparse Training Framework for Hardware-Efficient Deep Learning
Learning with Synthetic Data via SGD in High-Dimensional Linear Regression
A Hierarchical Tokenization Framework for Voxel-Level fMRI Representation Learning
On the Memorization of Consistency Distillation for Diffusion Models
PGMS: Pyramidal Gaussian Mixture Splatting for 3DGS Compression
Intrinsic-Preserving Schrödinger Bridge for Direct Part-Aware 3D Generation
ECLIPSE: A Spacecraft Rendezvous Trajectories Dataset with Controlled In-Orbit Lighting Conditions
MATO: Multi-objective Personalized Alignment with Test-time Optimization for Large Language Models
LLM Flow Processes for Text-Conditioned Regression
Data-Adaptive Mahalanobis Metric Learning for Cross-Head Attention in Transformers
Narrowing the Collaboration Gap, Probably
Control First, Robustness Next: Decoupled Representation Learning for Visual RL Generalization
Unified Noise Steering for Efficient Human-Guided VLA Adaptation
Pointillism: Probing-Based Model Compatibility for Robust Collaborative Machine Learning
Bayesian Decision Making around Experts
Scale-Invariant Empirical-Bayes Laplace Approximation for ReLU Networks
Less Evidence, Better Answering: Gain-Aware Minimal Evidence Subset Selection for Medical QA
RPFQ-ViT: Rotated Phase-Frame Quantization for Extremely Low-Bit Weights in Vision Transformers
A Reduction from Delayed to Immediate Feedback for Online Convex Optimization with Improved Guarantees
Grounding Driving VLA via Inverse Kinematics
Capacity-Constrained Online Convex Optimization with Delayed Feedback
Reliable Chain-of-Thought via Prefix Consistency
Q-ARVD: Quantizing Autoregressive Video Diffusion Models
WAXAL: A Large-Scale Multilingual African Language Speech Corpus
VESTA: Visual Exploration with Statistical Tool Agents
DialBandit: Adaptive Sequential Search with Tunable Evaluation Fidelity
SSD: Shell-Guided Spherical Diffusion for Molecular Geometry Generation
Settling Pure Differentially Private Covariance Estimation
Designing Cell-Type-Specific Regulatory DNA with Guided Discrete Diffusion
Reinforcing VLAs in Task-Agnostic World Models
Structured Unitary Tensor Network Representations for Circuit-Efficient Quantum Data Encoding
UniVer: A Unified Perspective for Multi-step and Multi-draft Speculative Decoding
Imperfect World Models are Exploitable
What to Forget in Unlearning? Forget Set Curation for Language Models
Binding Visual Features Point by Point
SEAD: Competence-Aware On-Policy Distillation via Entropy-Guided Supervision
RheoSampling: Resolving the One-Hot Dilemma in Stochastic Dynamic-Tree Speculative Decoding
Attention Alignment Between Humans and Vision-Language Models
Learning Sparse Semantic-Cortical Atoms for Multisubject Naturalistic fMRI Encoding
TROPT: An Open Framework for Unifying and Advancing Discrete Text Optimization
Multivariate Time Series Forecasting needs Cross Variable Loss
CodeMimicry: Exploiting Safety Generalization Lag in Large Language Models via Structured Code Completion
Tree-Structured Synergy of Large Language Models and Bayesian Optimization for Efficient CASH
Machine Unlearning in Low-Dimensional Feature Subspace
Online Localized Conformal Prediction
MIRAGE: Adaptive Multimodal Gating for Whole-Brain fMRI Encoding
Shepherd: A Runtime Substrate Empowering Meta-Agents with a Formalized Execution Trace
RealDev-QA: Trajectory-Level Diagnosis for Developer RAG Under Real-World Noises
PatchBench: Measuring Collateral Damage in Activation Patching
Accelerating Diffusion Language Models via Structured Suffix Modeling
SAME: Stability-Aware Embedding Extraction in Mixture-of-Experts Language Models
Direct Conditional Parameterization for N-Dimensional Splatting
Failing Forward: Adaptive Failure-Informed Learning for Vision-Language-Action Models
TRIAD: Benchmarking Omni-Modal Ambiguity in Multimodal Large Language Models
EEG-X: Toward Device-Agnostic and Noise-Robust Foundation Models for EEG
Understanding Layer Patching in Model Size Interpolation
Semantic-Level Invariant Representation Learning for Cross-Hospital Clinical EEG Modeling
Beyond FLOPs: Train-Full, Deploy-Partial Multi-Exit Inference via Selective Lightweight IC Ensemble
Inner Product Aware Quantization: Provably Fast, Accurate, and Adaptive Algorithms
Echo-SAM: Zero-Shot Learning of Unseen Structures via Medical Knowledge Graph Grounding
Graph Energy Matching: Transport-Aligned Energy-Based Modeling for Graph Generation
VISD: Enhancing Video Reasoning via Structured Self-Distillation
FerQ: Fermat Quotient Reformulation of High-Order Binary Optimization
Extending Myerson's Optimal Auctions to Correlated Bidders via Neural Network Interpolation
Proprio: Latent Self-Scoring and Inference-Time Refinement for Physically Plausible Video Generation
Support Mismatch as a Benchmark Failure Mode for In-Context Prediction
Semantically Complementary Spectral Views Learning for Graph-Level Anomaly Detection
Measuring and Decomposing Mode Separation via the Canonical Diffusion
Q-Residual Physics: Hamiltonian-Structured Quantum Residual Learning for Embodied Dynamics
Dispatchable Coordination Envelopes for Embodied Collaboration Under Sequential Uncertainty
Phase-DGS: Phase-Guided Dynamic Gaussian Splatting from Unsynchronized Multi-view Video
EvoDiagram: Agentic Editable Diagram Creation via Design Expertise Evolution
Q-CoMove: Differentiable Quantum Circuit Priors for Coordinated Motion in Multi-Component Embodied Systems
Fiedler-Regularized Causal Discovery for Sparse Connected DAGs
RAM-H1200: A Unified Evaluation and Dataset on Hand Radiographs for Rheumatoid Arthritis
Temporal Pair Consistency for Flow Matching
CSFlow: Aligning Flow Matching with Human Contrast Sensitivity
fNIRSAtlas: A Large-Scale Benchmark for Functional Near-Infrared Spectroscopy Classification
ALETHEIA: A Multi-Frequency Eddy Current Pulsed Thermography Dataset for Neural Operator Learning in Nondestructive Testing
Think-with-Rubrics: From External Evaluator to Internal Reasoning Guidance
The Cost of Mismatch: Noise Amplification in Zeroth-Order Reinforcement Learning
Scaling Causal Reasoning with Increasingly Complex Causal Simulators
Learn from your own latents and not from tokens: A sample-complexity theory
Zero-Violation Regret for Cooperative Markov Games with Coupled Instantaneous Hard Constraints
Surrogate Calibration for Transferable Adversarial Attacks against Black-Box MLLMs
AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization
Foresight-over-Graph: Reasoning Beyond Local Horizons for Knowledge Base Question Answering
Achieving Optimal Static and Dynamic Regret Simultaneously in Bandits with Deterministic Losses
OmniEgoCap: Camera-Agnostic Sequence-Level Egocentric Motion Reconstruction
Decomposed Graded Verifier for Generative World Modeling
TriTD: Tri-Partite Trajectory–Distribution Distillation for Real-Time Autoregressive Video Generation
Adaptively Incorporating Directional Hints into Zeroth-Order Optimization
Learning-to-Memorize: Dynamic Context Management for Long-Horizon Autoregressive Video Generation
Reliability-Coupled Manifold-Aware Diffusion for Missing-Modality Inference
Neural Spectral Capacity: An Architectural Quantity from Network Specification Alone
Rethinking Time Series Tokenization from a Frequency Perspective
Towards Self-Supervised, Generalizable and Decomposable 4D Driving Scene Reconstruction
TransMem: Transition-Aware Retrieval for Evolving Personal Memory
SeqDiCO: Sequence-oriented Diffusion for Scale-Generalizable Neural Combinatorial Optimization
Prompts to Proxies: Emulating Human Preferences via a Compact LLM Ensemble
MemPilot: Learning Transferable Latent Memory Mechanisms for LLM Reasoning
DriftWeight: Repulsive Drift in Mean-Flow Space for Neural Network Weight Generation
Permutation Sensitivity in t-SVD-based Multi-view Clustering
Towards Generalist Graph-Level Anomaly Detection
Reconciling Safety and Performance via Dual-Expert Offline Imitation Learning
AtlasULP: Domain-aware Universal Link Prediction via Relation Atlas
Improving Continual Video Instance Segmentation via Spatial-Temporal Balanced Mixture-of-Experts Adapters
Fix the Structural Bottleneck: Context Compression via Explicit Information Transmission
Test-Time Adaptation via Self-Reinforced Optimal Transport for Zero-Shot OOD Detection with Vision–Language Models
NeuroMem: A Neuroplastic Memory Framework for Lifelong Agents through Delayed Consolidation
Echoes in Filter Bubble: Diagnosing and Curing Popularity Bias in Generative Recommender Systems
PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion
DyJR: Preserving Local Policy Plasticity in Reinforcement Learning with Verifiable Rewards via Dynamic Jensen-Shannon Replay
Learning Minimal Sufficient Evidence Graphs for GraphRAG via Nash-Guided Optimization
RAM-Net: Linear-Time Sequence Modeling with Sparsely Addressable State
Predictive but Not Plannable: RC-aux for Latent World Models
Imagine Before You Draw: Visual Prompt Engineering for Image Generation
Q-Probe: Scaling Image Quality Assessment to High Resolution via Context-Aware Agentic Probing
BSO: Safety Alignment Is Density Ratio Matching
UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks
OmniSpace: Efficient Geometry Awareness for Autonomous Vehicles MLLMs
PreFT: Prefill-only finetuning for inference efficiency
DriveSpatial: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving
Can Large Language Models Develop Gambling Addiction?
TIGER-FG: Text-Guided Implicit Fine-Grained Grounding for E-commerce Retrieval
SDHilb: Schrödinger Dynamics-Guided Neural Network with Adaptive Multi-Scale Hilbert Transform for Time Series Forecasting
Geometry-Aware Representation Denoising for Multi-view Image Restoration and 3D Reconstruction
The Alignment Tax Concentrates in Output Projections
Mental-Models for Multi-Agent Systems
Auditing the Judge: Human-Grounded Bias Discovery, Quantification, and Mitigation in LLM Judges
HyrCap: Hybrid Rank-Calibration of Action Proposals for Temporal Event Understanding
Empowering Masked Diffusion Models to Self-Correct with Leave-One-Out Transformers
Beyond Drug Discovery: The Nanotechnology Molecular Optimization (NMO) Benchmark
When Further Realization Is Unnecessary: Amortized Reasoning for Long-Horizon LLM Agents
Geometric Latent Reasoning Induces Shorter Generations in LLMs
SD-LoRA: Training-Time Structural Distillation into LoRA for Few-Shot Vision-Language Adaptation
Batch-Conditioned Semantic Anchors for Robust Transductive Adaptation of Vision--Language Models
The Mask Is Not the Object: Volumetric Supervision for 3D Gaussian Segmentation
Rennala-NSGD: Asynchronous Stochastic Optimization Beyond Euclidean Geometry
Do We Need Asynchronous SGD? On the Near-Optimality of Synchronous Methods
ALIGN-Rec: Continual Recommendation under Heterogeneous Unlearning Requests
Active Memory Feedback Loop for Fast–Slow Dynamics in Liquid Neural Networks
DACA-GRPO: Denoising-Aware Credit Assignment for Reinforcement Learning in Diffusion Language Models
Fingerprinting Inference Systems of Large Language Models
Trajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated Distillation
MixRoute: Rethinking Single-Distribution Training for Generalizable Neural Routing
SimpleEvol: Efficient Intelligence Conversion via Less Human Prior in Automated Heuristic Design
Foundation Model Informed Acquisition Functions for Molecular Discovery
Constrained Look-ahead Guidance for Interference-Aware Flow Editing
Fast Sandwich Products in Clifford Algebra
Mix-Opt: Mixed Optimization for Memory-Efficient Personalization of Text-to-Image Diffusion Models
OpticalRAG: Pixel-Space Compression for Token-Efficient Retrieval-Augmented Generation
Independent Latents, Robust Neural Operators
GWScore: A structural diversity metric for consistent text-to-image generation
Hyperbolic Concept Bottleneck Models
ContinuLoc: Continuous Pose Inference over Neural Fields for UAV Geo-Localization
SFPR: Structural Fingerprinting for LiDAR-to-OpenStreetMap Place Recognition
MultiSTEVE-1s: A Model Zoo and Interpretability Suite for Instruction-Following Vision Agents
Provably Reliable Classifier Guidance via Cross-Entropy Control
TerraVis: Towards Evaluation of World-Grounded Visual Consistency in Text-to-Image Generation via MLLM Workflows
NeuroAtlas: Benchmarking Foundation Models for Clinical EEG and Brain-Computer Interfaces
SCOPE-RL: Stable and Quantitative Control of Policy Entropy in RL Post-Training
SynIB: Informational Bottleneck for Maximizing Synergy in Multimodal Learning
At FullTilt: Real-Time Open-Set 3D Macromolecule Detection Directly from Tilted 2D Projections
OntoPlan: An Ontology-Grounded Scene Representation and Agentic Framework for Scalable Robot Task Planning
CoT-Guard: Small Models for Strong Monitoring
Closed-Form Linear-Probe Dataset Distillation for Pre-trained Vision Models
PanoWorld: Towards Spatial Supersensing in 360◦ Panorama World
Dual-Rate Diffusion: Accelerating diffusion models with an interleaved heavy-light network
EEG Benchmarking Needs a Task Specification Layer: NeuroDoc for Rulebook-Guided, Executable Benchmark Construction
Correlation-Aware Contextual Bandits with Surrogate Rewards for LLM Routing
Theory of Mind and Persuasion Beyond Conversation: Assessing the Capacity of LLMs to Induce Belief States via Planning and Action
CORTEG: Foundation Models Enable Cross-Modality Representation Transfer from Scalp to Intracranial Brain Recordings
Delta-Adapter: Scalable Exemplar-Based Image Editing with Single-Pair Supervision
Unifying Partner and Environment Diversity to Improve Human-AI Coordination
Per-Starting-Point Plausibility and Diversity Bounds for Score-Based Diffusion Models
DDMS: Discriminative Distillation of Multi-view Foundational Features into Single-view Models
Focus Matters: Attention-Value Dynamics for Hallucination Mitigation in Vision-Language Models
Diffusion-Enhanced GFlowNet for Solving Vehicle Routing Problems
Overcoming Attention Distraction: Training-Free Latent Communication for Multi-Agent Systems
Inpainting physics: self-supervised learning for context-driven fluid simulation
Latent Video Prediction for World Modeling: An Evaluation Uncovering Intriguing Favorable Evidence
SSR3D-LLM: Structured Spatial Reasoning via Latent Steps for Fine-Grained Grounding in Unified 3D-LLMs
SkillCIR: Intent-Guided Skill Composition for Training-Free Composed Image Retrieval
ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents
Toward Better Geometric Representations for Molecule Generative Models
Not All Low-Confidence Tokens Are Equal: Calibrated Confidence for Efficient Test-Time Reasoning
Scaling Linear Mode Connectivity and Merging to Billion Parameter Pretrained Transformers
Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs
Do Sparse Autoencoders Learn Meaningful Concept Hierarchies?
DELTA: Robustly Training Label-Conditional Diffusion Models with Weak Annotations
RelaVPR: Relation-Based Knowledge Distillation for Efficient Visual Place Recognition
GeoPMR: Preserving Relational and Hierarchical Geometry in Multimodal Molecular Representation Learning
Triggering Generalist Reasoning via Predictive Uncertainty for Dual-System VLA
DTA-GT: Direction- and Topology-Aware Graph Transformer for Neural Network Representation Learning
The Confusion is Real: GRAPHIC – A Network Science Approach to Confusion Matrices in Deep Learning
$PAS^2$: Physics-Anchored Spectral Reasoning for Air Quality Forecasting
CounterStrike-1K: A Multi-Perspective Dataset of Professional Gameplay for World Modeling
Joint Certification for Attributed Graphs: Beyond Topology-Only Robustness
Guaranteed Nonconvex Low-Rank Tensor Estimation via Scaled Gradient Descent
Complex Schrödinger Bridges
Active Learning via Classifier Impact and Greedy Selection for Interactive Image Retrieval
ADMIT: Support-Gated Memory-Write Admission for Document QA Agents
Subject-Relative Micro-Motion and Sleep Dynamics for Near-Infrared Video Sleep Staging
CausalConflictBench: Can Multimodal Models Follow Local Mechanisms That Conflict with Commonsense?
Monitoring the Internal Monologue: Probe Trajectories Reveal Reasoning Dynamics
AEGIS: Almost Surely Safe Offline Reinforcement Learning
BrainCoT: A Multi-Task Zero-Shot Brain Signal Foundation Model with Neurometric-Anchored Chain-of-Thought Reasoning
Chasing Label Shifters: A Change-Aware Framework for Dynamic Graph Node Classification
Pretraining Curricula Enable Selective Fine-tuning
Understanding Model Reprogramming: A Reachability and Relabeling Perspective
The Kernel Reality Check: Benchmarking and Distilling Efficient Attention at Scale
Neural Operator-based Curriculum Learning for Physics-Informed Neural Networks
Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language Models
TRL-Bench: Standardizing Cross-Paradigm Representation-Level Evaluation of Tabular Encoders
HSCO-Bench: An Agent-Driven End-to-End Hardware-Software Co-design Benchmark for Systems-on-Chip
Isotropic Activation Functions Enable Deindividuated Neurons and Adaptive Topologies
Safety Reconstructed: Generative Modeling via Masked Diffusion Builds Strong Safety Guardrails
Resolving AdaBoost Cycling with LLMs: A Computer-Assisted Counterexample
Reinforcement Learning Agents Are Swimmers
Knowing When Multivariate Forecasts Are Wrong
AutoHoney: Automating, Deploying, and Evaluating Scheming Honeypots Across Production Codebases
WILD: Widely Linear Conditioning for Time Series Forecasting
Learning Energy-Based Models from Stochastic Interpolants using Spatiotemporal Differences
Drift-Resistant Navigation World Model with Anchored Epipolar Guidance
Reconfiguring Procedural Knowledge for Compositional Robot Skill Adaptation
C2G-BENCH: A Cyber-Physical Evaluation Benchmark for Hierarchical Reinforcement Learning in Grid-Interactive Hyperscale Data Centers
PaLoRA: Paced Low-Rank Adaptation for Continual Learning
Unveiling Fine-Grained Visual Traces: Evaluating MultiModal Interleaved Reasoning Chains in Multimodal STEM Tasks
Steering Fields: Adaptive Vector Fields for Safe Image Generation and Beyond
Rethinking Cross-Layer Information Routing in Diffusion Transformer
SymDrift: One-Shot Generative Modeling under Symmetries
EvoGround: Self-Evolving Video Agents for Video Temporal Grounding
Magnifying What Matters: Attention-Guided Adaptive Rendering for Visual Text Comprehension
Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps
Closing the Loop: Co-Evolving EM for Irregular Time Series Generation in Lifted Representations
Harnessing Image Diffusion Prior for Photo-Realistic Video Restoration
Evaluation of Visual Processing Should Be Human-Centered, Not Metric-Centered
MOSAIC: Scaling Long-Horizon Language Agents via Multi-Scale Adaptive Inference Control
Integrating Background Knowledge for Scalable Causal Discovery
TrioPose: Native Triple-Stream Diffusion Transformers for Pose-Guided Text-to-Image Generation
EndoSCOP-V: A Multi-Turn Video Understanding Evaluation Framework for Multimodal Models in Endoscopy Reporting and Clinical Reasoning
Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks
LPG: Balancing Efficiency and Policy Reasoning in Latent Policy Guardrails
MaskForge: Structure-Aware Adaptive Attacks for Jailbreaking Diffusion Large Language Models
PhySPRING: Structure-Preserving Reduction of Physics-Informed Digital Twins via Graph Neural Networks
Persona-Model Collapse in Emergent Misalignment
AppCIF-Bench: An Application-Level Complex Instruction Following Benchmark for Large Language Models
LookThere! Sparse Vision by Reinforced Selection
Attending on Attention ($A^2$): Smaller Self-Supervised ViTs Localize Better Than Larger Ones
LLM Alignment--Utility Asymmetry under Semantic-Preserving Transformations
Decomposed Representations Mitigate the Alignment–Specificity Trade-off in Multi-Omics
Leveraging Data Symmetries to Select an Optimal Subset of Training Data under Label Noise
Internal Safety Collapse in Frontier Large Language Models
Pixels to Tokens: Token Space Efficient Active Learning for Low-Budget Semantic Segmentation
OneCanvas: 3D Scene Understanding via Panoramic Reprojection
UxSID: Semantic-Aware User Interests Modeling for Ultra-Long Sequence
SOC-ICNN: From Polyhedral to Conic Geometry for Learning Convex Surrogate Functions
Beyond Prediction: Steering VLM Agents with Retrospective World Modeling
Preventing Error Cascades in Long-Horizon Multimodal Agents with Edge-Reliability Graph Memory
OpenMHC: Accelerating the Science of Wearable Foundation Models
S3Former: Sequential, Structural, and Statistical Fusion for Continuous-Time Dynamic Graphs
A Unified Theoretical Framework for Task Recognition and Task Learning in In-Context Learning
F2G-Pose: Geometry-Aware Foundation Feature Lifting for Direct RGB-D Category-Level Object Pose Estimation
HumanScore: Benchmarking Human Motions in Generated Videos
From Failure Taxonomy to Intervention: A Diagnostic Methodology for Industry-Scale AVLM in Video and Live-Streaming Platform Moderation
EasyLens: A Training-Free Plug-and-Play Subtle-Lesion Representation Amplifier for Medical Vision-Language Models
High-Dimensional Robotic Reinforcement Learning with Developing Synergies
From Cursed to Competitive: Closing the ZO–FO Gap via Input-to-State Stability
Learning Scenario Reduction for Two-Stage Robust Optimization with Discrete Uncertainty
Learning to Solve Compositional Geometry Routing Problems
Simplicity is Enough: ReAct Agents for Prompt Optimization
What Time Is It? How Data Geometry Makes Time Conditioning Optional for Flow Matching
SheafStain: Sheaf-Theoretic Schr\"odinger Bridge for Spatially and Biologically Coherent Virtual Staining
Diffusion Subgoal Planning for Long-Horizon Offline Goal-Conditioned Reinforcement Learning
Inside the Loop: A Mechanistic Study of Weight-Tied Transformers on Depth-Bound Algorithmic Tasks
Who Watches the Watchers? Semantically-Constrained Reinforcement Learning for Red-Teaming Provenance Intrusion Detectors
Conflict-Suppressed RAG: A Simple Decoding-Time Framework for Faithful Retrieval-Augmented Generation
DocPTBench: Benchmarking End-to-End Photographed Document Parsing and Translation
OpenSanctions Pairs: A Large-Scale Dataset for Pairwise Entity Matching
MemForest: Efficient Agent Memory Management via EventTree Partitioning and Progressive Merging
Capacity Allocation at the Source: Sparse Target Optimization for LLM Knowledge Editing
MMOU: A Massive Multi-Task Omni Understanding and Reasoning Benchmark for Long and Complex Real-World Videos
ChainFlow-VLA: Causal Flow Planning with Vision-Language Models
Individuals Matter: Improving Deep Multi-View Clustering via Explicit Single-View Enhancement
The Silent Hyperparameter: Quantifying the Impact of Inference Backends on LLM Reproducibility
PRISM: A Benchmark for Programmatic Spatial-Temporal Reasoning
LOTION: Smoothing the Optimization Landscape for Quantized Training
CryoAtlas: A Large Curated Dataset and Unified Benchmark for Cryo-EM Atomic Model Building
Beyond ViT Tokens: Masked-Diffusion Pretrained Convolutional Pathology Foundation Model for Cell-Level Dense Prediction
Align3D-AD: Cross-Modal Feature Alignment and Dual-Prompt Learning for Zero-shot 3D Anomaly Detection
CURE: Counterfactual Unsafe-token Re-masking for Diffusion Large Language Model Test-time Alignment
Semantic Consistency of Vision Tokens: A Vision-Centric Perspective on Multimodal Large Language Models
Cost-Aware Learning
Gaussian Splatting-based Volumetric Video Compression with Sparse 4D Anchors
No More, No Less: Task Alignment in Terminal Agents
Self-Rewarding Sequential Monte Carlo for Masked Diffusion Language Models
MARS: Enabling Autoregressive Models Multi-Token Generation
PRIME: A Modular Approach for Private Synthetic Data
Emergence of a Shared Canonical Object Frame from In-the-Wild Videos
RL Excursions during Pre-training: How early is too early for on-policy learning?
RoboProcessBench: Benchmarking Process-Aware Understanding in Visual-Language Robotic Manipulation
Noise-Level KL Rates for Multi-Marginal Schrödinger Bridge Surrogates
Pluralistic AI Alignment Requires Inference-Time Multi-Objective Control
MuEdit: An efficient multi-task editing method towards inter-domain knowledge conflicts
Walking the Hypercube: Unbiased Quantum Partition Functions Without the Matrix
RelFlexformer: Efficient Attention Transformers for Integrable Relative Positional Encodings
LinearARD: Linear-Memory Attention Distillation for RoPE Restoration
MUSS: A Multi-scale and Sequence-based Model for Single-cell Gene Regulation
Beyond Self-Play and Scale: A Behavior Benchmark for Generalization in Autonomous Driving
ORCA: Hunting Compositional Failures in Text-to-Image Diffusion
Towards Scalable Context-Aware Single-Cell Spatial Transcriptomics Prediction from Histology Images
Learning to Generate Multiple Objects from Dense and Occluded Layouts
Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads
MICE: Multi-animal Interaction Context Encoder — A Hierarchical Foundation Model for Mouse Behavior
RSSA: Robust Semantic and Spatial Aligner for Collaborative Perception
Beyond Augmented-Action Surrogates for Multi-Expert Learning-to-Defer
QDMouse4M: A Multi-View 3D Mouse Spontaneous Behavior Dataset with Quantum-Dot Markers
GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction
EVOCHAMBER: Test-Time Co-evolution of Multi-Agent System at Individual, Team, and Population Scales
Ultra-DPO: Reimagining LLM Alignment as a Semi-Supervised Task
Follow the Mean: Reference-Guided Flow Matching
Test-Time Scaling with Diffusion Language Models via Reward-Guided Stitching
Differentiable Retrieval-Augmented Generation for Predicting Cellular Responses to Gene Perturbation
TriBet: Relative E-values for Online Machine-generated Text Detection
USAD: Uncertainty-aware Statistical Adversarial Detection
SVoT: State-aware Visualization-of-Thought for Spatial Reasoning via Reinforcement Learning
Identifying Latent Neural Dynamics with Recognition-Parameterized Gaussian Process Dynamical Systems
AirIAD: Agentic Iterative Reasoning for Industrial Anomaly Detection
Rethinking Post-Training Recipes for Multimodal Time-Series Forecasting
Dynin-Robotics: Omnimodal Unified Diffusion Vision-Language-Action Model
JRDB-AVR: An Active Visual Reasoning Benchmark for Real-World Embodied Environments
Rethinking in Spikes: Mitigating Hallucinations in MDLMs with Step-Aware Decoding
LR-V2X: Loss Resilient Collaborative Perception under Low-Bandwidth Communication
GATE-AD: Graph Attention Network Encoding for Few-Shot Industrial Visual Anomaly Detection
Which Pairs Should We Compare for DPO?
Tunable Latent Generative Priors for Compressed Sensing and Inverse Problems
Federate the Router: Learning Language Model Routers with Sparse and Decentralized Evaluations
WaveGen: Truly End-to-End Waveform Generation via Internal Spectral Trajectory Learning
Raw-Routed Mixture of Adapters: A Causal Intervention for Routing Collapse in Time Series Foundation Models
Does Mixed Label Imbalance Matter to Minority Collapse in Imbalanced Learning?
Closing the Gap on the Sample Complexity of 1-Identification
Steer-to-Detect: Probing Hidden Representations for Detection of LLM-Generated Texts
Efficient, Accurate and Stable Gradients for Neural ODEs
Trajectory-Matching Meta Pseudo-Labeling for Semi-Supervised Learning
Strong Stochastic Flow Maps
Learning Semantic Consistency for Open-Vocabulary Dense Perception
From Articulated Kinematics to Routed Visual Control for Action-Conditioned Surgical Video Generation
DriveWAM: Video Generative Priors Enable Scalable World-Action Modeling for Autonomous Driving
Edge of Stochastic Stability: Revisiting the Edge of Stability for SGD
CORAL: Learning Amyloid Fibril Ligand Docking with Cooperative Binding Rewards
Learning to Read Out: Unembedding Dynamics in Language Model Pretraining
Semiparametrically Efficient Inference for Kernel Measures of Noise Heterogeneity
LLMs as MDP Designers: A Dependency-Aware Agentic Framework for Automated Robot Policy Generation
Representation Preconditioning for Efficient Diffusion Model Training
Transformers in the Dark: Navigating Unknown Search Spaces via Bandit Feedback
Duality Models: An Embarrassingly Simple One-step Generation Paradigm
Glob3R: Global Structure-from-Motion with 3D Foundation Models
Brain Economy-Aligned Graph Transformers
A Private Empirical Defense Against Privacy Audits
Remember Your Trace: Memory-Guided Long-Horizon Agentic Framework for Consistent and Hierarchical Repository-Level Code Documentation
Soft Contamination Means Benchmarks Test Shallow Generalization
A Characterization of Latent Variable Causal Models Consistent with Observational Data
JuICE: A Benchmark for Evaluating LLM-Judge in Identifying Cultural Errors
Neural Causal Models under Markov Equivalence
Slowly Annealed Langevin Dynamics: Theory and Applications to Training-Free Guided Generation
SOAR: Semantic Organ-Aware Pretraining for 3D CT Image Understanding
FLIP: Fast and Accurate Global Lipschitz Estimation for Large Feedforward Networks
VAMIRec: Value-Aware Memory Intervention for Continual Recommendation
HeMeR: Heterogeneous Memory Reconciliation for Embodied Agents via Structured KV Reuse
AgentWeave: Efficient Distributed Agent Serving via Flow Decomposition
Untrusted Content Masking for Web Agents with Security Guarantees
Relation-Aware Graph Foundation Model
CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents
Benchmarks Are Not Atomic: Composition-Aware LLM Evaluation using BenchHub
DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation
Adaptive Generate-Rank-Verify: Inference-Time Search with Costly Verification
DUET: Unified Dual-Space Emotion Control for Diffusion and Flow-Matching Driven Text-to-Speech
Speech Tokenizers are Vulnerable: Transferable Semantic Attack and Robust Tokenizer
PhyProbe: Rethinking Physical Consistency Evaluation in Generated Videos
QUEST: Q-Learning for Uncertainty-Guided Efficient Search Teams
The AI Observatory: A Public Measure of Real-World AI Use
Audio-Visual Flamingo: Open Audio-Visual Intelligence for Long and Complex Videos
Latent Riemannian Flow Matching for Geometry-Grounded 3D Foundation Models
Beyond Sparse Captions: Aligning Slide-Level Text and Patch-Level Vision in Pathology
Discrete Neural Interlingua for Ontology-Agnostic EHR Modeling
FedIBS: Federated Vision-Language Adaptation via Intrinsic Bias Selection
The Implicit Bias of Hyperbolic Representation Learning for Multiclass Data: A Busemann Risk Perspective
Data Density Scaling Laws for Image Self-Distillation
VIPER: An Expert-Curated Benchmark for Vision-Language Models in Veterinary Pathology
GridProbe: Posterior-Probing for Adaptive Test-Time Compute in Long-Video VLMs
Causal heteroscedastic structure learning from incomplete temporal data
TopoPrune: Robust Data Pruning via Unified Latent Space Topology
EO-WM: A Physically Informed World Model for Probabilistic Earth Observation Forecasting
It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs
NeSyKC: Neurosymbolic Knowledge Compilation For Lifelong Learning Embodied Agents
Rare-Class Signal Suppression in Long-Tailed Multi-Expert Fine-Tuning
Vision Token Pruning via Query-Vision Interaction Decomposition
FrameSelect: A Unified Library for Video Frame Selection and Evaluation
Benchmarking Open-Ended Multi-Agent Coordination in Language Agents
QT-Net: Rethinking Evaluation of AI Models in Atomic Chemical Space
Unsupervised Domain Adaptation for Semantic Segmentation Based on Instance Spatial Geometry
Agreement without Coverage: Conditional Agreement is Non-Identifying in Variable-Support Structured Extraction
Geometry Meets Physics: Data-Efficient Pre-Training for Unstructured Neural PDE Solvers
Codebook-Guided Cross-Modal Knowledge Distillation for Structurally Heterogeneous Features
FinAl: Fine-grained Alignment for Detail-Preserving Medical Vision-Language Pretraining
HyperTransport: Amortized Conditioning of T2I Generative Models
Can Model Merging Improve Aggregation in DiLoCo?
BridgeMVS: Bridging Multi-View Stereo and Monodepth via Bidirectional Dynamic Fusion
H2G: Hierarchy-Aware Hyperbolic Grouping for 3D Scenes
Forest-Guided Semantic Transport for Label-Supervised Manifold Alignment
Enhancing LLMs with Cognitive-Affective Personality Inference for Simulating Human Social-Psychological Behavior
Nahual: A Sequence Model for Language and Atoms
AmbiguousWorld: Benchmarking and Resolving Ambiguous Instructions in Video World Models
HAI: Hierarchical Anchored Interaction for Multi-View Bimanual World Models
GeoSym127K: Scalable Symbolically-verifiable Synthesis for Multimodal Geometric Reasoning
Click3R: Interactive Stereo 3D Reconstruction with Sparse Correspondence Clicks
TreeWalker: Partial Evaluation for Grouped Tree-Ensemble Inference
Separating Common and Unique Directions for Model Merging
Path-independent Flow Matching for Multi-parameter Generative Dynamics
Graph Learning Should Move Beyond Restrictive Views of Spectral and Message-Passing GNNs
Deriving Hyperparameter Scaling Laws via Modern Optimization Theory
When and How to Canonize: a Generalization Perspective
scShapeBench: Discovering geometry from high dimensional scRNAseq data
Dynamic Physical Adversarial LED Patterns via Reinforcement Learning
Rethinking the State Update Gate for Long-Sequence Recurrent 3D Reconstruction
EmoPhone: A Multi-Wave Dataset for In-the-Wild Mobile and Wearable Affect Sensing
FreDRec: Frequency-Decoupled Knowledge Distillation for Multimodal Recommendation in Missing Modalities Scenarios
OopsWorld! Operation-Grounded Seamless World Generation
Revisiting Incremental Learning: A Three-Interface Diagnosis of Stability and Plasticity
Primal-Dual Representation Learning for Low-Rank Constrained MDPs
Decomposing and Reshaping Scaling Laws through Token Learning Times
Decomposing Temporal and Job-Induced Dynamics for Probabilistic Computing Workload Forecasting via Graph-Conditioned Dual-Branch Diffusion
Advancing Entropy-Level Credit Assignment in RLVR via Proximal Entropy Policy Optimization
CSLA: Sparse-Linear Attention with Learnable Routing and Quantization-aware Training
Self-Correction as Transition Geometry: Internalizing Reasoning via Lifted State Policy Optimization
MICA: Activation Checkpointing for Double-Backward Training of Machine Learning Interatomic Potentials
Robust Residual Correction via Selective Deployment for Time Series Forecasting
Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning
NORA: Evaluating Grounded Reasonableness in Visual First-person Normative Action Reasoning
BFS-PO: Best-First Search for Large Reasoning Models
DIAL: A Bounded-Monotone Adapter with Closed-Form Residual $L_\infty$ Bounds for Scalar-Controlled Refusal Modulation
Mixture of Probes: Learning with Privileged Modalities in Multimodal LLMs Through Probing
Geometry-Aware Post-Hoc Uncertainty Quantification in Operator Learning
FlowR2A: Learning Reward-to-Action Distribution for Multimodal Driving Planning
Teaching VLMs What to Say, Not How to Reason: Rethinking Counterfactual Reasoning in Autonomous Driving
Decoupled Optimization for Teacher-Student Semi-Supervised Learning via a Pioneer Student
FAVLA: A Force-Adaptive Multi-Rate VLA model for Contact-Rich Robotic Manipulation
Stable Alpha: Adversarial Invariant Representation Learning for Nonlinear Asset Pricing under Temporal Distribution Shifts
LiveOption: Evaluating LLM Agents in Structured Option Trading with Nonlinear Payoffs
ForceLDM: A Force-aware Latent Dynamics Model for Contact-Rich Manipulation
Why Cross-Skeleton Retargeting Is Non-Identifiable: Structural Limits of Generative Motion Models
Evolutionary foraging in grids: Intermittent search emerges as an optimal strategy
Outlier-Robust Multi-Output Gaussian Processes
Parallel Rollout Approximation for Pixel-Space Autoregressive Image Generation
MedPsy: State‑of‑the‑Art Small Medical Language Models for Efficient Edge Deployment
Explanation Multiplicity in SHAP: Characterization and Assessment
Embodied Neurocomputation: A Framework for Interfacing Biological Neural Cultures with Scaled Task-Driven Validation
Compute Efficiency and Serial Runtime Tradeoffs for Stochastic Momentum Methods
UltraFlash: Accelerating Megapixel Visual Synthesis
PoseBridge: Bridging the Skeletonization Gap for Zero-Shot Skeleton-Based Action Recognition
M$^3$: Reframing Training Measures for Discretized Physical Simulations
Z-Cache: Accelerating Diffusion Transformers via Self-Reflection
FlashControl: One-Step Controllable Generator via Distillation-Friendly Single-Stream Teachers.
Advancing Affordance-Grounded Creative Tool Use in Large Multimodal Models
Identification and Bounding of Joint Expectation over Potential Outcomes
Programmatic Reasoning with Structural Schema: A Unified Framework for Multi-Table Inference
A Foundational Model System for Datacenter Machine Repairs
SALT: When More Rollouts Don’t Help in Group-Based Policy Optimization and How to Make Them Matter
Modeling quantum neural network gradient with reinforcement learning
Where Reusable Computation Becomes Detectable: Solution-Frame Path Triage for Modular-Arithmetic Grokking
LAPrune: Logits-Aligned Scoring Proxy for KV Pruning via Vector Quantization
DIAGNO: Diagonal Spherical Neural Operators for Heterogeneous Earth Dynamics Modeling
Reading the Finetuning Prior: Verbatim Content Recovery via Contrastive Decoding Diffing
Sparsely Wired Mortal LLM Inference
Interleaved Latent Thinking and Adaptive Termination for Efficient Reasoning LLMs
Distributionally Robust Mixture-of-Experts Training
Decentralized Multi-Goal Multi-Agent Pathfinding with Spatial Prior and Neighbor Intent Prediction
Complexity of Differentially Private Selection via Federated APIs
OmniTraffic: A Controllable Generation Pipeline and Benchmark for Spatio-Temporal Traffic Reasoning
How Far Is Too Far? Object Recognition Declines Monotonically with Semantic Distance
Online Bayesian Recalibration of Brain–Computer Interfaces with Language Model Potentials
Cross-Family Universality of Behavioral Axes via Anchor-Projected Representations
AlloGen: Conformation-Selective Binder Design with Differential State Scoring
A Diagnostic Benchmark for Layered Layout and Template-Variant Reasoning
Sequential Behavioral Watermarking for LLM Agents
Auditing Correlated Failures in Frozen-Feature Pretrained-Encoder Pools for Medical Segmentation
Auditing Capsule Vision 2024: Within-Split Train-to-Validation Re-Exposure and a Kvasir-Channel Sensitivity Diagnostic
Contrastive Distribution Matching for Amortized Sequential Monte Carlo in Discrete Diffusion
Offline Reinforcement Learning for Plasma Control in Nuclear Fusion: Codebase and Benchmark
Bridging Structure and Language: Graph-Based Visual Reasoning for Autonomous Road Understanding
Is a Linear Probe Evidence of a Linear Representation?
Caterpillar GNN: Replacing Message Passing with Graph-Level Aggregation
CausalMix: Data Mixture as Causal Inference for Language Model Training
Emergent Low-Rank Training Dynamics in MLPs with Smooth Activations
MinPath: Learning Efficient LLM Reasoning via Minimal Dependency Paths
Choosing Before Acting: Comparative Value Estimation for Long-Horizon Tool-Use Agents
Fractional Power-of-Two Quantization for Efficient and Effective Multiplier-Free LLM Inference
Few-shot Task Learning via Compositional Concept Inference
Skill-Level Effects in Behavioral Cloning: When Low-Skill Data Improves Performance
DiffRisk: Diffusion Representation Learning with Informative Missingness for Health Risk Prediction
Refinement as a Service: Algorithmic Predictor Refinement
Task Success Is Not Enough: Side-effect-Aware Evaluation of Tool-Using Language Model Agents
Practical Estimation of the Bayes Optimal Fairness-Accuracy Tradeoff with Soft Labels
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information
FlowTrack: Controlling Edit-Signal Execution in Inversion-Free Flow Video Editing
A Matter of Interest: Understanding Interestingness Judgments of Math Problems in Humans and Language Models
VESPO: Variational Sequence-level Soft Policy Optimization for Off-Policy LLM Training
Sparse Updates Generalize Better Than Optimization: Stability Analysis for Randomized Subspace Descent
C3: Long-Horizon Character Consistency via Causal-Continuous State Dynamics and Memory Rewriting
Full-Duplex Speech-Motion Model for Dyadic Interaction
Saddle-to-Saddle Dynamics in Self-Supervised Shortcut Learning
DISTMOE: Rehearsal-free Routing in Mixture-of-Experts for Distributed Instruction Tuning
TALON: Confidence-Aware Speculative Decoding with Adaptive Token Trees
Frontier Coding Agents Use Metaprogramming to Adapt to Unfamiliar Programming Languages
EsoLang-Bench: Evaluating Large Language Models via Esoteric Programming Languages
C3P: Contrastive promoter-protein pretraining yields representations capturing bacterial gene regulation
Information bottleneck dynamics during learning across artificial and biological neural systems
$\text{PartConcepts}$: A Unified Mechanism for Fine-Grained Part Localization and Generation
ComPose: When to Trust Hands for Object Pose Tracking
Generalization Without Compression Penalty: A Stability Analysis of Error Feedback
SCOPE: Self-Play via Co-Evolving Policies for Open-Ended Tasks
When Are Multimodal Predictions Biologically Supported? A Diagnostic Evaluation Framework
PhysDNet: Physics-Driven Gradient Amplification for Real-Time Image Dehazing
EgoHMP: Achieving Precise Human Motion Prediction in 3D Scenes via Egocentric Cues
Revisiting The Power of Closed-Form: Robust Deep Image Prototype Discovery via Scale Mixtures
Seeing Speech: Learning Visible Articulatory Dynamics for Speech-Driven 3D Facial Animation
From Sample to Subset Construction: Coverage-Aware Curation of Robot Demonstrations
MemPoison: Uncovering Persistent Memory Threats and Structural Blind Spots in LLM Agents
Training-Based Backdoors Are Not Cryptographic
Brain-OF: An Omnifunctional Foundation Model for fMRI, EEG and MEG
Privacy Meets Hierarchy: Differentially Private Distributed Trilevel Learning
MolSpecFlow: Modality-Incomplete Molecular--Spectral Learning for MS/MS
Single Shot HDR Recovery via a Video Diffusion Prior
Live Music Diffusion Models: Efficient Fine-Tuning and Post-Training of Interactive Diffusion Music Generators
Past as State, Present as Attention: Persistent-State Blockwise Flow Matching for Long-Horizon Co-Speech Motion Generation
Generation-Drift-Guided Block Pruning for Large Language Models
Contrastive Adversarial Training for Robust Graph Neural Networks under Label Poisoning
Explanation Mechanism Influences Human Reliance on Reinforcement Learning Agents
Concord-SLAM: Cross-Render Concordance for Boundary-Native Semantic Gaussian SLAM
Koopman Generative Operators for Efficient Probabilistic Time-Series Forecasting
Position: Telic Errors Make VLMs Unreliable Annotators in Sensitive Contexts
Trapping Attacker in Dilemma: Examining Internal Correlations and External Influences of Trigger for Defending GNN Backdoors
Graph-Enhanced Attribute-Aware Modeling for Cloth-Changing Person Re-Identification
PISCO: Precise Video Instance Insertion with Sparse Control
ViTeX-Bench: Benchmarking High-Fidelity Video Scene Text Editing
How does feature learning change the function space evolution?
Derived Fields Preserve Fine-Scale Detail in Budgeted Neural Simulators
Posterior-First Neural PDE Simulation: Inferring Hidden Problem State from a Single Field
$\mathrm{Bounded\mbox{-}RS}$: A Bounded Evaluation Protocol and Testbed for Representational Systematicity
Scalable Adaptation of 3D Geometric Foundation Models via Weak Supervision from Internet Video
Stay Fair! Ensuring Group Fairness in Diffusion Models Across Guidance Scales
The Commit-Abstain Circuit: Why Language Models Hallucinate Instead of Abstaining
Optimal Transport Reweighting for Robust Learning under Spurious Correlations and Label Noise
Why Are LLMs Confidently Wrong? Correcting Overconfident Errors via Causal Head Intervention
Nonparametric Estimation of a Factorizable Density using Diffusion Models
One-Time Soft Alignment Enables Resilient Learning without Weight Transport
UniCon3R: Unified Contact-aware 4D Human-Scene Reconstruction from Monocular Video
Diffusion Models without Classifier-free Guidance
Why Geometric Continuity Emerges in Deep Neural Networks: Residual Connections and Rotational Symmetry Breaking
Adaptive Compression and Targeted Perturbation: A Unified Framework for Generalized Audio Deepfake Detection
AHPA: Adaptive Hierarchical Prior Alignment for Diffusion Transformers
Focal Reward: Balanced Reinforcement Learning under Rubric-Based Rewards
Time–Frequency Non-Stationary Modeling for Multivariate Time Series Forecasting
PANDA: Prior-guided Attentional Dual-path Architecture
HACO: Hedged Agent Computing for Reliable LLM Systems
Multiclass Classification with Rare Useful Features: Fundamental Limits and the Optimality of Diversity Pursuit Higher Criticism
Tool Verification for Test-Time Reinforcement Learning
ImageNet FID is a Pass Check, Not a Finish Line
AgentBrew: Offline Tool-Use Agent Learning from Raw Real-World Trajectories
Benchmark Shadows: How Data Regimes Shape Parameter Footprints and Generalization
Continuous Latent Diffusion Language Model
Emergence of Physical Intelligence via Controllable Information Production
Spectral Progressive Diffusion for Efficient Image and Video Generation
Proper Scoring Rules for Agentic Uncertainty Quantification
CTRL: Continual Test-Time Reinforcement Learning for Large Language Models
Inter-domain Inference for Gaussian Process Variational Autoencoders
World–Value–Action Model: Implicit Planning for Vision–Language–Action Systems
Curvature-Guided Parameter Initialization for Multi-Task Learning
AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation
KuaiRecV2: Benchmarking Large-Scale Continual Learning for Diversified and Multi-task Recommendation
Edit the Bits, Diff the Codes: Bitwise Residual Editing for Visual Autoregressive Models
Mental Imagery That Matters: Curing Latent Collapse in Multimodal Reasoning
MedCache: Training-Free Spatially Aware Caching for Accelerated Medical Video Generation
Lemon: Evidence-Risk-Aware Adaptive Organization for Long-Horizon LLM Agents
Watching Itself Watch: Self-Auditing Visual Reliance for Video Reasoning
Flipping Bits, Not Gradients: Sharpness-Aware Minimization Directly on the Boolean Hypercube
The Price of Locality in Label Privacy: Optimal Rates for Classification and Regression
Failure Profiling and Reachable Trajectory Selection for Reasoning Distillation
Diff-Kalman: Difference-Driven Learning for Structure-Preserving Kalman Filtering
PotARCin: Multi-Dimensional Evaluation of Skill Acquisition in Abstract Reasoning Tasks
Geometric Velocity Regularity for Flow Matching on Manifold-Concentrated Data
Sparse Koopman Autoencoders Identify Local Dynamical Regimes in Multibasin Systems
LoopNav: Benchmarking Spatial Consistency in World Models
MANGO:Multi-Angle Neural Gated Operators for Chirp-Perturbed PDEs
World from Motion: Generative Dynamic Gaussian Reconstruction from Monocular Video
AffectGPT-RL: Revealing Roles of Reinforcement Learning in Open-Vocabulary Emotion Recognition
Animation2Code: Evaluating Temporal Visual Reasoning in Video-to-Code Generation
FaithfulFaces: Pose-Faithful Facial Identity Preservation for Text-to-Video Generation
Information Propagation via Sign-Flip Dynamics
MorphoHELM: A Comprehensive Benchmark for Evaluating Representations for Microscopy-Based Morphology Assays
Wasserstein Gradient Flows and Forward-Only Diffusion Are Not Enough for Multimodal Sampling
Toward the Goldilocks Blind Compression of Quantum States
ExComm: Exploration-Stage Communication for Error-Resilient Agentic Test-Time Scaling
When LLM Routers Overpay: Strong-Model Over-Selection under Loose Budgets
A Simple Unigram Cross-Entropy Lens on the Lexical Imprint of Pre-training Data
WaterDescatterGS: Diverse Underwater 3D Scene Reconstruction Using Gaussian Splatting
Vermeer: Autoregressive generative modeling of microscopy predicts protein localization
Pose-Free Feed-Forward 3D Inpainting via Learnable Mask Attention and Support Token Refinement
On Nash Equilibria in Participatory Budgeting with Donations and Beyond
Exact Gaussian Moment Matching for Residual Networks: a Second-Order Method
Min-p, Max Exaggeration: A Critical Analysis of Min-p Sampling in Language Models
Topological Invariance and Breakdown in Learning Dynamics
Echoes of Error: Residual-Directional Local Rollout Consistency for Timeseries Forecasting
Exact Topological Compliance: Generating Persistence-Equivalent Graphs
Discrete Langevin-Inspired Posterior Sampling
Dynamic Regulatory Graph Learning for Histology-to-Spatial Transcriptomics
ManipShield: A Unified Framework for Image Manipulation Detection, Localization and Explanation
A Compass for Useful Data: Online Data Selection via Alignment-Gated Fisher Geometry
OTel: Open Telco AI Datasets, Benchmarks, and Models
Understanding the Out-of-Distribution Generalization of Chain-of-Thought Reasoning in LLMs
MathCD: A Benchmark Dataset for Cognitive Diagnosis with Semantic Information
PMO-Dock: Benchmarking Docking, Specificity, and Generalization in Molecular Optimization
pyCD: A Unified Benchmark for Reliable Evaluation of Cognitive Diagnosis Models
CrafterDojo: A Suite of Foundation Models for Building Open-Ended Embodied Agents in Crafter
Beyond a Single Score: An Audit of Aesthetic Evaluation in Text-to-Image Pipelines Across Subcultural Visual Languages
RoLL: Robust Low-Rank Learning via Nesterov Momentum
Task-Aware KV Cache Compression for LLM Agents via Utility-Driven Step Pruning
Inexact Bregman Sparse Newton Method for Efficient Optimal Transport
MIRAGE: Duality-Inspired MILP Augmentation for Representation Learning
SR-Prominence: A Crowdsourced Protocol and Dataset Suite for Perceptually-Weighted Super-Resolution Artifact Evaluation
Character Mixing for Video Generation
Learning Fine-Grained Vision-Language Alignment from Discriminative Part Descriptions
Forecasting Microbial Dynamics: Evaluation Protocol and Prior-Spectrum Benchmark
RECAP: Looking Once Is Not Enough for Vision-Language Reasoning
Random-Projection Tree Stein Variational Gradient Descent
Outlier-robust Diffusion Posterior Sampling for Bayesian Inverse Problems
Towards On-Policy Data Evolution for Visual-Native Multimodal Deep Search Agents
ARES: How Reliable Are LLM User Simulators for Recommender A/B Testing?
Fisher Decorator: Refining Flow Policy via A Local Transport Map
TraceTriage: A Benchmark for Cost-Aware Stop-or-Continue Decisions in Delayed-Outcome Workflows
Rethinking Forward Processes for Score-Based Nonlinear Data Assimilation in High Dimensions
DIGS: Distribution-Informed Gaussian Splatting for Training-Free Open-Vocabulary 3D Segmentation
GraphInstruct: A Progressive Benchmark for Diagnosing Capability Gaps in LLM Graph Generation
Panoptic Saliency Ranking
Tools as Continuous Flow for Evolving Agentic Reasoning
Beyond Selection: Token Parameterization for Extreme Visual Token Compression
A Single Deep Preference-Conditioned Policy for Learning Pareto Coverage Sets
Are Text-to-Image Models Inductivist Turkeys? A Counterfactual Benchmark for Causal Reasoning
Quality-Diversity Optimization as Multi-Objective Optimization
Machine Unlearning in Diffusion LLMs
Spectral Unlearning: Transformer Structure-Preserving Updates for Language Model
Retain-Neutral Surrogates for Min-Max Unlearning
SARL: Label-Free Reinforcement Learning by Rewarding Reasoning Topology
PitchBench: Measuring Pitch Hearing in Audio-Language Models
AirMPA: A Meteorology-to-Pollution Adapter for Global Air Quality Forecasting
Are LLM Safety Judges Policy-Invariant? A Three-Principle Stress-Test
How Hard is it to Rig a Benchmark? A Social Choice Analysis of Leaderboard Robustness
AET-Bench: Pixel-Accurate Atomic Tomography Is Not Atom-Accurate
ImmuVis: Hyperconvolutional Foundation Models for Imaging Mass Cytometry
Ferrogen: Generative Pipeline for Guided Search of Novel Ferroelectric Material for Logic and Memory
mmLIP: mmWave Radar-Language Interactive Pretraining via Point Confidence
SODA: Selective Optimization with Deferred BN Alignment for Efficient Dataset Distillation
Flexible Flows for Biological Sequence Design
RadarMAE: Injecting Physical Inductive Biases into Masked Autoencoders for Advanced Radar Object Detection
The Quiet Prompt: Erasing Ineffable Styles from Diffusion Models via Concept Leakage-aware Negative Guidance
Revisiting B2T: Discovering and Mitigating Visual Biases through Keyword Explanations
InterLV-Search: Benchmarking Interleaved Multimodal Agentic Search
MedMisBench: Measuring Epistemic Resilience of LLMs Under Misleading Medical Context
DRAGON : A Benchmark for Evidence-Grounded Visual Reasoning over Diagrams
GOLIATH: Gradient Inversion of Tabular Diffusion Models
Are LLMs Good at Feature Engineering? Evidence from a Controlled Synthetic Benchmark
TrustFlow: Adaptive Trust Calibration for Language Model Guided Reinforcement Learning
Hack-Verifiable Environments: Towards Evaluating Reward Hacking at Scale
Periodic Complex Stochastic Processes for Retrieving Atomic Structures of Unknown Matters
HiGraph: A Large-Scale Hierarchical Graph Dataset for Malware Analysis
Learning to Group and Order: Cross-Instance Self-Supervised RL for Vision-Centric MLLMs
AutoSaddler: Automatic Harness Optimization with Durable Updates from Agent Execution Traces
GramStatTexNet: Efficient, Interpretable, and Neuro-Inspired Texture Analysis-by-Synthesis
A Scientific Claim Stability Framework for Evaluating MRI Morphometry Pipelines
Bridging the Modality Bottleneck in Pathology MIL through Virtual Molecular Staining
NanoFold: Designing Reproducible Protein Structure Benchmarks through Principled Sampling
Do LLMs Feel Social Pressure? Locating and Steering Social Desirability Bias in LLMs
Q-Focus: Let the Question Guide What to See in Long Videos
Heteroscedastic TrueSkill: Modeling Match Noise and Player Consistency
AgriManager: A Framework and Benchmark for LLM-RL Generalization in Agricultural Management
AnyMo: Geometry-Aware Setup-Agnostic Modeling of Human Motion in the Wild
Unpacking the Evaluators: How Configuration Shapes the Evaluation of Alignment in Explainable AI
Spectral-Aligned Pruning for Universal Error-Correcting Code Transformers
Many Benign Errors are Better than A Few Severe Ones: Evaluating Hallucination Severity
When Does Sequential Detection Collapse to a Scalar? A Necessary and Sufficient Characterisation
The Text Uncanny Valley: Non-Monotonic Performance Degradation in LLM Information Retrieval
Autoregressive Appearance Prediction for 3D Gaussian Avatars
Integrating Strengths of Different Multi-Agent Workflows via Step-Aware Hybrid Topology Planning
NavAble: A Large-Scale Dataset and Synthetic Data Generation Pipeline for Blind Navigation
Intrinsic Selection and Particle Resampling for Inference-Time Scaling Beyond Domain Verifiability
Detecting Hidden ML Training With Zero-Overhead Telemetry
TELEVAL: A Benchmark Designed for Spoken Language Models in Chinese Interactive Scenarios
Reinforcement Learning for Exponential Utility: Algorithms and Convergence in Discounted MDPs
EvalAwareBench: A Benchmark for Measuring Evaluation Awareness in Frontier Language Models
How Data Scales in Agentic Reinforcement Learning: Laws and Synthesis Strategies
AccelEval: A Whole-Program Benchmark for LLM-Generated CPU-to-GPU Code Acceleration
In-Expectation Convergence of Stochastic Gradient Methods under Heavy-Tailed Noise
On the Last-Iterate Convergence of Clipped Gradient Methods
ARTIS: Agentic Risk-Aware Test-Time Scaling via Iterative Simulation
Superplatforms Are Strategically Compelled to Counteract AI Agents
RecMem: Recurrent Memory Compression for Long-Sequence Recommendation
PHMForge: Evaluating LLM Agents on Industrial Prognostics through MCP-Native, Algorithm-Grounded Tools
SMMBench: A Benchmark for Source-Distributed Multimodal Agent Memory
What kills $v$-prediction? A Patch-wise PCA Perspective on Pixel-Space Flow Matching
DELTA-TTS: Adapting Autoregressive Model into a Diffusion Language Model for Text-to-Speech
Platonic Task Arithmetic
TSNBench: Benchmarking LLM Proficiency in Time-Sensitive Networking
Offloading Score: Measuring AI Reliance through Counterfactual Workflows
D-VLA: A High-Concurrency Distributed Asynchronous RL Framework for Vision-Language-Action Models
Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security
Matchability-Aware Conformal Prediction for Open-Ended Language Model Generation
Curriculum Learning for Safety Alignment
Instrumental Choices: Measuring the Propensity of LLM Agents to Pursue Instrumental Behaviors
Build-and-Find: An Effort-Aware Protocol for Evaluating Agent-Managed Codebases
SWE-Chain: Benchmarking Coding Agents on Chained Release-Level Package Upgrades
AgenticVBench: Can AI Agents Complete Real-World Video Production Tasks?
Optimized Minimal 4D Gaussian Splatting for Efficient Dynamic Scene Representation
BayesRAG: Probabilistic Mutual Evidence Corroboration for Multimodal Retrieval-Augmented Generation
Two Phase Rapid Simulation Based Inference with Differentiable Simulators
TrustMod-SM: A Multi-Axis Benchmark for Evaluating Trustworthiness of LLMs in Social Media Content Moderation
Next-Latent Prediction Transformers Learn Compact World Models
Rest-Tuning: Data-Efficient Adaptation of EEG Foundation Models to Individuals via Resting-State Signals
MvFFN: Multi-view Floor-Plan Feed-Forward Network for Unposed Wide-Baseline Panorama Layout Reconstruction
PCBInnoBench: Benchmarking LLM Agents on Real-World PCB Design
MedEvoEval: Evaluating Continual Evolution of Doctor Agents through Simulated Clinical Episodes
UFO: A Unified Flow-Oriented Framework for Robust Continual Graph Learning
URSA: Chemistry-Aware Benchmark for Utilitarian Retrosynthesis Assessment
Payoff-Aware Prediction of Population Game Dynamics
Automated Kernel Discovery Towards Understanding High-dimensional Bayesian Optimization
Flow Map Language Models: One-step Language Modeling via Continuous Denoising
PatchKV: Weight Space Compensation of KV Cache
IndustryCode: A Benchmark for Industry Code Generation
Density-Ratio Losses for Post-Hoc Learning to Defer
MemDLM: Memory-Enhanced DLM Training
PAMod: Modeling Cyclical Shifts via Phase-Amplitude Modulation for Non-stationary Time Series Forecasting
K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs
A Theoretical Analysis of Backdoor Learning as Simplicity-Biased Optimization Dynamics
Distribution Shift in Missing Data Imputation: A Risk-Based Perspective and Importance-Weighted Correction under MAR
MyoChallenge 2025: A New Benchmark for Human Athletic Intelligence
Performance-Driven Policy Optimization for Speculative Decoding with Adaptive Windowing
HIRaD: Hidden Interaction Inference from Predictive Radar Dynamics
EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective
InQuant: In-Place Mixed-Precision KV Cache Quantization via Saliency-Aware Neighbor-Slot Reuse
DriveDreamer-Policy: A Geometry-Grounded World-Action Model for Unified Generation and Planning
Measuring What Matters: Synthetic Benchmarks for Concept Bottleneck Models
SO(3)-Equivariant Learning on CAD Boundary Representations
SoDeArena: A Socially-Situated Reasoning Benchmark for Large Language Models
Token Filtering: Online Attention Pruning via KV Similarity for Efficient LLM Inference
Distributed Online Convex Optimization with Compressed Communication: Optimal Regret and Applications
OS-Omni: A Cross-Platform Benchmark for Generalist Computer-Using Agents
Hyperbolic Displacement-Constrained Adaptation for CLIP-Based Class-Incremental Learning
Bonobo: Efficient Library-Scale Generation for De Novo Antibody Design
A Geometric Perspective on Reward Function Updates in Inverse Reinforcement Learning
Variational Approach to Optimal IPS Estimator for Multi-logger Off-Policy Evaluation
Decomposing the modulation of interactions between neuronal populations
Inference-Time Self-Aligned Drifting for Few-Step Flow Matching
Beyond Ground Truth: Evaluating Non-Verifiable Reasoning in LLMs through Moral Robustness
AgentHop: A Diagnostic Benchmark for Agentic Multi-Hop Scientific Question Answering
How to make the most of your masked language model for protein engineering
CAPER: Clause-Aligned Process Supervision for Text-to-SQL
From Perception to Punchline: Empowering VLM with the Art of In-the-wild Memes
BIRD-RL: Scaling Agentic Reinforcement Learning over Stateful Data-Centric Environments
OroPrecipBench: a km-scale benchmark for spatial precipitation downscaling over complex terrain
Impossibility of Distribution-Free Predictive Inference for Individual Treatment Effects
PAC Reasoning: Controlling the Performance Loss for Efficient Reasoning
CoMet: Context and Multiplicity Decomposition for Multimodal Uncertainty Estimation
Seen-Constrained Model-Order Selection for Unknown-$K$ Generalized Category Discovery
In-Context Learning Can Help Vision Language Models Overcome Training Prior
Reinforced Fast Weights via Next-Sequence Prediction
Deformable 2D Gaussian Splatting
No Free Alignment: Observability-Aware Alignment for Multimodal Heterogeneous Learning
When Does Graph Retrieval Become Answer-Supporting Evidence? A Diagnostic Audit of GraphRAG
PAVE: Prefill-Conditioned Activation Editing for Hallucination Mitigation in LVLMs
When evolution cheats: Frozen-weights Baselines reveal static-solvers interference in evolved plastic spiking neural networks
Improving Self-Supervised Vision Transformers with Cross Distillation
Capturing Membrane Dynamics and Spike Timing of Human Neurons at Scale using Neural Operators
Sustainability in the Loop: AI Model Development Should Be Multi-Objective
Mind the Gap: Dataset and Fine-grained Evaluation for Inline Audio Descriptions
Compositional Generalization Certificates via the Van Kampen Theorem
RobustStress: Stress-Testing AI-Generated Text Detectors under Gradual Perturbations
MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarios
SWE-GPU-Bench: Can Language Models Solve Real-World GPU Software Engineering Tasks?
ToPA: Block-wise Toeplitz Adaptation for Expressive and Efficient Fine-Tuning
Strategic Evaluation: Incentivizing AI Capability Coverage with Private Benchmarks
S²MoE: Shared-Subspace Mixture of Sparse Experts
SafeDrug: A Benchmark Dataset for Safety-Critical Pharmacological Reasoning in LLMs
Evaluating Neural Data Tokenizers: A Framework for Assessing Learned Representations of Spiking Activity
Bayesian Test-Time Inference of Task-Aligned Similarity from Weak Interactive Feedback
SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere
ClinMAS: A Knowledge-Grounded Multi-Agent Simulation Framework for Evaluating Clinical Reasoning in LLMs
Beyond Single-Shot Conditioning: Test-Time Condition Refinement for Diffusion-Based Image Restoration
Which Way Did It Move? Diagnosing and Overcoming Directional Motion Blindness in Video LLMs
SudoBench: A Contextual Authorization Benchmark for LLM Agents
TRACE: Trajectory-Aware Conceps for Explainable Video Understanding
M3-AD: Reflection-aware Multi-modal, Multi-category, and Multi-dimensional Benchmark and Framework for Industrial Anomaly Detection
Towards Better Generalization in Lifelong Person Re-Identification with Flatness-Aware Learning
Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents
TIGER: Bridging the Multimodal Reasoning-Access Gap via Modality Counterfactuals
SIGMA: Semantic-Difference Instruction-Grounding Mask Annotator for Text-Driven Image Manipulation Localization
Parallel-in-Time Training of Recurrent Neural Networks for Dynamical Systems Reconstruction
HERO: A Heterogeneity-Aware Benchmark Library for Federated Continual Learning
An Enigma of Artificial Reason: Investigating the Production-Evaluation Gap in Large Reasoning Models
Asymptotically Exact Negative Guidance of Diffusion Models via Positive-Unlabeled Learning
MultiTalk: Scaling Full-Duplex Speech Models to Long, Multi-Party, Bilingual Conversation
The Dynamic-Probabilistic Consistency Gap in Chaotic Surrogate Modeling
Identifying Structural Biases from Causal Mechanism Shifts
FLAG: Flow Policy MaxEnt-RL by Latent Augmented Guidance
Thinking with Imitation: Adaptive Reinforcement-Imitation Learning for Tool-Augmented Scientific Reasoning
LiFi: LiDAR Generation from Multi-View Images via Geometric and Semantic Collaborative Guidance
FedAdaVR: Adaptive Variance Reduction for Robust Federated Learning under Limited Client Participation
GLINT: Sparsely Gated Vision-Language Alignment for Fine-Grained Radiology Representations
Root Cause Analysis of Measurement and Mechanistic Anomalies
Causal Discovery under Time-Varying Delays
On the Selectivity of Generative Models in Structure-Based Drug Design
A systematic evaluation of vision-language models for observational astronomical reasoning tasks
RobustPruner: Decoupled Relevance and Uncertainty for Efficient Visual Token Pruning in MLLMs
SayNext-Bench: Why Do LLMs Struggle with Next-Utterance Anticipation?
Rethinking Learning from Label Proportions via Moment Matching
DynaFLIP: Rethinking Robotics Perception via Tri-Modal-Dynamics Guided Representation
Information Parity for Code: The Scope of Transfer in Multilingual Code Models
Generalization Analysis of Biased Stochastic Gradient Methods for Minimax Problems
Look-Before-Move: Narrative-Grounded World Visual Attention in Dynamic 3D Story Worlds
PICID: A Modular Evaluation Infrastructure for Reproducible PHM Across Tasks and Domains
Beyond the Dirac Delta: Mitigating Diversity Collapse in Reinforcement Fine-Tuning for Image Generation
Blur Issue Matters for Thermal Novel View Synthesis: A Floating Gaussian Suppression Approach
GCD: Correcting Hidden-State Bias in Off-Policy Agentic RL
HOPSE: Scalable Higher-Order Positional and Structural Encoder for Combinatorial Representations
GUITAR: Structured Failure Diagnosis of GUI Agents via State Transitions
Rebalancing Reference Frame Dominance to Improve Motion in Image-to-Video Models
AdapToPASS: Ambiguity-aware Adaptive Spherical Transformer for Panoramic Semantic Segmentation
FutureSim: Replaying World Events to Evaluate Adaptive Agents
Next-Token Prediction Enables Scalable Learning of Sleep Physiology
Spectral Feedback for Test-Time Alignment of Protein Diffusion Models
FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systems
What Comes Next and Why: Interpretable Next-Event Prediction with Neuro-Symbolic Rules
A Matched-Budget Audit Framework for Recaptioned Image-Text Supervision Distributions
Error-Guided Bellman Calibration for Semi-Offline Value Estimation
Video-Mirai: Autoregressive Video Diffusion Models Need Foresight
Latency-Conditioned Selection Bias in RLHF
New Coresets for Fair Clustering
OpenView: Empowering MLLMs with Out-of-view VQA
ResFusion: Medical Image Fusion Driven by Implicit-Forward Diffusion and Time-aware Joint Optimization
Permutation-Invariant Spectral Learning via Dyson Diffusion
MedHEB: Benchmarking Medical Embeddings Across Heterogeneous Clinical Evidence
DIS-Bench: Evaluating LLMs on System Testing via Directed Input Synthesis
VistaQA: Benchmarking Joint Visual Question Answering and Pixel-Level Evidence
V-CAST: Video Curvature-Aware Spatio-Temporal Pruning for Efficient Video Large Language Models
Past, Future, All at Once: Breaking Stability-Plasticity Dilemma via Post-hoc JANUS Rectification
CEO-Bench: Can Agents Play the Long Game?
Generating Physically Consistent Molecules with Energy-Based Models
Large Language Model Selection with Limited Annotations
AI Construct Lexis: An Ontology of the Hidden Assumptions in AI Evaluation
MedKIT: Evaluating Knowledge Integration and Generalization in Large Language Models
Market Regime Council for Dynamic Credit Assignment in Multi-Agent LLM Decision Systems
StakeBench: Evaluating Language Understanding Grounded in Market Commitment
From Walls to Synergy: A Joint LLM-Evolution Framework for MILP Solvers
CapTrack: Multifaceted Evaluation of Forgetting in LLM Post-Training
Learning-Augmented Approximation for Unrelated-Machines Makespan Scheduling
DataComp-VLM: Improved open datasets for Vision-Language Models
Instruction Anchor: Dissecting the Mechanistic Dynamics of Modality Arbitration
Walking Through 3D Spaces: Spatial Routing for Referring 3D Gaussian Splatting Segmentation
ProtoVis-Nav: Prototypical Visual Imagination for Visual-Spatial Aligned UAV Navigation
ViewRec3D: Learning to Recommend 3D Viewpoints for AI Photography
Quantized Reasoning Models Think They Need to Think Longer, but They Do Not
SwitchLingua V2: Agent-Driven Code-Switching via Digital Clones
Forecasting Downstream Performance of LLMs With Proxy Metrics
PhysTC: A Physics-Enhanced Dataset and Architecture for High-Precision Tropical Cyclone Forecasting
BELLS-O: Evaluating the Operational Trade-offs of LLM Supervision Systems
Online Causal Configuration for Networked Systems via Doubly Robust Steady-State Learning
Neural Scaling Laws in Particle Jets
PSD: Pushing the Pareto Frontier of Diffusion LLMs via Parallel Speculative Decoding
Orthogonal Uplift Learning with Permutation-Invariant Representations for Combinatorial Treatments
Attention Itself Could Retrieve. RetrieveVGGT: Training-Free Long Context Streaming 3D Reconstruction via Query-Key Similarity Retrieval
Never Go Full Batch: Stochastic TMLE for Large-Scale Debiased Inference
The Alignment Curse: Modality Alignment Supercharges Audio Attacks via Text Transfer
FLARE: Full-Modality Long-Video Audiovisual Retrieval Benchmark with User-Simulated Queries
JEDI: Real-Time Jailbreak Defense for LLMs via In-Generation Detection and Intervention
Reconstruction or Semantics? What Makes a Latent Space Useful for Robotic World Models
Accelerated Image Editing via Consistency-Aware Source Token Pruning
Efficient Gradient-Aware Asynchronous Reinforcement Learning for LLM Post-Training
Provable Pruning for Efficient 3D Gaussian Splatting via Coresets
GoT: A Game-Theoretic Approach to the Game of Twenty Questions
Barycentric Guidance: Turning Foundation Image Editors into Continuous Affective Controllers
The Fractured Interlingua: Geometric Bottlenecks in Cross-Lingual Knowledge Editing
APPSolver: Adaptive Patch Partitioning for Point-Wise Ship Flow Prediction on Unstructured Meshes
Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models
KnowVis: A Dual-View Benchmark for Diagnosing World-Knowledge Grounding in Text-to-Image Models
SynGeo: Synergizing Seeing and Proving through Revisable Geometric States
EviAttr-OW: Evidential Attribute Reasoning for Open World Object Detection
FinReasoning: A Hierarchical Benchmark for Reliable Financial Research Reporting
VisualWorldBench: A Fine-Grained Multi-Task Benchmark for Evaluating Visual World Knowledge in MLLMs
When Prompt Internalization Breaks: Continuous Experience Internalization in Large Language Models
Feedforward Novel View Synthesis for Heterogeneous Cameras
VEHBench: A Stage-Local Diagnostic Benchmark for LLM-Assisted Vibration Energy Harvester Design
Latent Process Generator Matching
Learning Rate Transfer for Hybrid Transformer-SSM Architectures
MobileMoE: Scaling On-Device Mixture of Experts
Branching Flows: Discrete, Continuous, and Manifold Flow Matching with Splits and Deletions
PG-LRF: Physiology-Guided Latent Rectified Flow for Electro-Hemodynamic PPG-to-ECG Generation
Control-Augmented Autoregressive Diffusion for Data Assimilation
$\pi$-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows
Hyperbolic Graph Neural Networks Under the Microscope: The Role of Geometry–Task Alignment
Stage Light is Sequence$^2$: Multi-Light Control via Imitation Learning
One Step is Enough: Multi-Agent Reinforcement Learning Based on One-Step Policy Optimization for Order Dispatch on Ride-Sharing Platforms
Stochastic Optimization with Random Search
Castle-in-the-Air: Probing the Foundational Visual Deficits of MLLMs via Bottom-Up Cognitive Factors
CS-Dialogue: A 104-Hour Dataset of Spontaneous Mandarin-English Code-Switching Dialogues for Speech Recognition
RadOmni: Advancing Foundation Model for Non-contrast CT with Omni Radiology Knowledge
U-Bench: A Comprehensive Understanding of U-Net through 100-Variant Benchmarking
Revisiting Diffusion Fine-Tuning for Unsupervised Domain Adaptation
Stabilizing Extrapolation in Looped Transformers via Learned Stochastic Stopping
HIDRA: Hierarchical Dual-Routing Attention for Replay-Free Lifelong Imitation Learning
SimVLA: Attributing Gains in VLA Models Through Controlled Ablation
To Copy or Not to Copy: Controlling Speculative Decoding via Intrinsic Model Signals
Towards Characterizing Scientific Image Utility and Upgradability
DeepfakeGenome: Toward Next-Generation Deepfake Attribution
Towards Reliable VLM Judges: State-Conditional Invariance and Presentation-Aware Diagnostics
Reward-free Pretraining for Reinforcement Learning via Occupancy Coverage Maximization
HalluWorld: A Controlled Benchmark for Hallucination via Reference World Models
DirectUV: Image-Conditioned UV Texture Generation with Surface-Aware Positional Encoding
Seg3DParts: Segmentation-Grounded Controllable Part-Level 3D Generation
A Reproduction Study of Weight-Based Mechanistic Interpretability in Bilinear MLPs
LPS-Bench: Benchmarking Safety Awareness of Computer-Use Agents in Long-Horizon Planning under Benign and Adversarial Scenarios
EPIC: Efficient Predicate-Guided Inference-Time Control for Compositional Text-to-Image Generation
Multi-Scale Representation Learning for Single-Cell Multi-Omics
Opening Up a New Layer: A Deeper Look into "Interpreting CLIP with Hierarchical Sparse Autoencoders"
RVLoss: Runoff Vote Loss for Self-Supervised LiDAR Scene Flow Estimation
Revisiting RegressionMSR: A Reproducibility Study
SaaSBench: Exploring the Boundaries of Coding Agents in Long-Horizon Enterprise SaaS Engineering
Posterior-Tracking for Best-Arm Identification in Bernoulli Bandits
Geometry-Aware Self-Supervised Electrophysiology Representation Learning
Adaptive Joint Testing of Policies in Discounted Markov Decision Processes
Mechanism Design for AI Overviews: Creator Incentives and Long-Term Profit
Visual Text Compression as Measure Transport
Model Distribution-Aware Multimodal Dataset Distillation
Revisiting Embodied Chain-of-Thought for Generalizable Robot Manipulation
SpatialVAM: Spatial-Aware Multi-View Video Diffusion as a Data-Efficient Robot Policy
Knowledge-Level Consistency Reinforcement Learning: Dual-Fact Alignment for Long-Form Factuality
Temporal Backtracking Search for Test-time Generative Video Reasoning
RepoZero: Can LLMs Generate a Code Repository from Scratch?
Remember with Confidence: Uncertainty Quantification for Spatio-temporal Memory with Probabilistic Guarantees
EditBridge: Towards Faithful and Efficient Ultra-High-Resolution Image Editing
Modelling Opinion Dynamics at Scale with Deep MARL
VeriTrip: A Verifiable Benchmark for Travel Planning Agents over Unstructured Web Corpora
HAPACT: A Benchmark For Human-Centric Physical Impact Localization in Movies
Anchor3DGS: Feed-Forward 3D Gaussian Splatting with Compact Anchor-Based Representation
Towards Generalizable 3D Anomaly Detection via Relational Inconsistency Modeling
How You Move Tells What You'll Do: Trajectory-Conditioned Egocentric Prediction
Beyond Outcome: Trajectory-Driven Prompt Optimization via Multi-Dimensional Rewards
Decide Before You Record: Heterogeneity-Guided Pre-Acquisition Stimulus Selection for Cross-Day Neuroprostheses
State-Resolving Attention for Length-Extrapolating Transformers
Safety-Aware Latent Space Reasoning in Large Language Models
PhysVista: Benchmarking Physical Intelligence in VLMs via a Perception-Reasoning-Assessment Loop
Learning to Deaggregate: Large-scale Trajectory Generation with Spatial Priors
Harnessing Agentic Evolution
A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compression
EgoForce: Robust Online Egocentric Motion Reconstruction via Diffusion Forcing
Breadcrumbing Search Agents: Per-Turn Scheming Over Long-Horizon Trajectories
Curvature-Dependent Lower Bounds for Riemannian Online Convex Optimization
Probabilistic Recursive Reasoning
SWE-Git-Bench: A Focused Worktree-Level Benchmark for Real Merge Conflict Resolution
Latent Action Reparameterization for Efficient Agent Inference
Isharah-Selfie: Continuous Sign Language Recognition Dataset for One-handed Signing
BabyTheorist: A Benchmark for Learning to Theorize the World from Observation Alone
Are Multimodal Benchmarks Really Useful? Item-Level Multimodal Benchmark Diagnosis via Structure-Response Co-Calibration
Context-Aware Generative Imputation for Robust Multimodal Learning in Missing Modality Scenarios
Orthogonal Updates for the Win: Towards Accelerated Adaptive Minimax Optimization
Symplectic Parallel Scan: A Neural Hamiltonian Framework for Accelerated Scientific Simulation
The BAMBI Dataset: Multimodal Nadir UAV-Recordings of Forest Wildlife
Topological Out-of-Domain Generalization in Dynamical Systems Reconstruction
From Table to Cell: Attention for Better Reasoning with TABALIGN
Dual-Space Preconditioning for Variational Inequalities and Root-Finding Problems
Discovering What You Can Control: Interventional Boundary Discovery for Reinforcement Learning
Distilling What Matters: Confidence-Aware Selective Distillation for Large Language Models
Gauge-Symmetric Dual Lagrangian Frameworks for Born-Oppenheimer Molecular Dynamics
Learning Scene-Grounded Interaction Priors for Scene-Aware Human Motion Prediction
Horizontal Diffusion Models: Score-based Generative Modeling on Frame-Connection Geometry
A Regularization-Based Approach to Public Belief State Search for Adversarial Games
ALTER: An Allen's Algebra-Based Evaluation Framework for Temporal Reasoning of LLMs
From Views to Worlds: Active Exploration over 3D Worlds for Vision-Language Models
SciResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery
DocScope: Benchmarking Verifiable Reasoning for Trustworthy Long-Document Understanding
Remembering What Matters: From Markovian to Subtask-Causal Memory in VLA Policies
Order Matters: Competition-Guided Query Ordering for RNN-Based Object Detection
LoRIF: Low-Rank Influence Functions for Scalable Training Data Attribution
PepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry Prediction
Screening Lipid Nanoparticles through Structure-Ratio Alignment
Anatomy-Preserving Unpaired Medical Image Translation via Shared Latent Anchoring
WovenAnchor Matcher: Specialized Intra- and Inter-Image Context Modeling for Feature Matching
Exemplar2VQA: A Scalable Exemplar-Driven Visual Question Answering Generation Framework via Multi-Agent Coding
OpenVTON-Bench: A Large-Scale High-Resolution Benchmark for Controllable Virtual Try-On Evaluation
From Pixels to Concepts: Do Segmentation Models Understand What They Segment?
AegisFlow: Training-free Non-myopic Path-safe Guided Flow Matching
Importance-Aware OBS Pruning for Diffusion Models
CyCLeGen: Cycle-Consistent Layout Prediction and Image Generation
Feasible Policy Optimization for Safe Reinforcement Learning
SDAE: Semantic-Diversity-Aware Exploration for Efficient Reinforcement Learning in Large Language Models
Learning Data-free Universal Adversarial Perturbation with Hybrid Priors and Gradient-Guided Sharpness Regularization
Deep Heteroskedastic Regression: Post-Hoc Variance Estimation from Latent Representations
Heteroscedastic Variational Last Layers
Reliability-Budgeted Edge–Cloud Adaptation for Continual Multimodal Dehazing on UAV
Variational Monte Carlo for Quantum Excited States via Nested Low-Rank Approximation
Looking Through the Mirror: Minimax-Optimal Regularized Regrets in Online Learning and Bandits
Dual Feature-Relational Alignment for Transferable Targeted Attacks on MLLMs
WorldAct: Activating Monolithic 3D Worlds into Interactive-Ready Object-Centric Scenes
Holistic Scaling Laws for Optimal Mixture-of-Experts Architecture Optimization
AIR: Rethinking Image-Text Offset Alignment in Multimodal Contrastive Representation Space
Search-Tree Scaling in Parallel Monte Carlo Tree Search
Iterative Latent Refinement for Value Learning in Offline Goal-Conditioned RL
SGNNBench: A Holistic Evaluation of Spiking Graph Neural Networks on Large-scale Graphs
Can 4D Foundation Models Remember?
Unveiling Entropy-Performance Decoupling in Agentic RL for Tool-Integrated Reasoning
MedMemoryBench: Benchmarking Agent Memory in Personalized Healthcare
ClawBenchPro: Benchmarking How Well Agent Harnesses Work
Data-Free Metrics Are Not Invariant Under Functionality-Preserving Reparametrisations
IPIBench: Evaluating Interactive Proactive Intelligence of MLLMs under Continuous Streams
Beyond Structural Agnosticism: Stable-Rank-Guided LoRA for Structure-Aware Fine-Tuning
Beyond Decoupled PEFT: Geometry-Aware Low-Rank Adaptation via Riemannian Reparameterization
Uncertainty-Aware Listwise Reinforcement Fine-Tuning for Fine-Grained Visual Classification
Map-Guided Caching: A Global Perspective for Efficient Diffusion Transformer
Parameterized Stripe Attention for Efficient Video Generation
Who Called? V33DA: A Physically Verified Multimodal Benchmark for Vocal Attribution in Zebra Finch Groups
DiPO: Disentangled Perplexity Policy Optimization for Fine-grained Exploration-Exploitation Trade-Off
iCATS: Fast Video Generation via Interaction-Aware Sparse Attention and Timestep-Adaptive Sparsity
Less Supervision, Better Generalization: Weakly Supervised Fake Region Localization in Diffusion-Edited Images
Learning Hierarchical Patch Splitting Policies for Faster Vision Transformers
A Principled Optimal Transport Framework for Frame Selection in Long Video Understanding
Relevance Is Not Necessity: Selecting the Necessary API Set for Tool-Using LLMs
SLIDERS: Systematic Reviews via Automated Evidence Synthesis and Reconciliation
SkipSR: Faster Super-Resolution with Token Skipping
Improved Regret Analysis For Parallel Gaussian Process Bandit Optimization
Position-aware eXplanation: A Model-Agnostic Framework for Positional Attributions
Transporting Quantiles to Codebook: Scalable Vector Quantization without Codebook Collapse
CodecSplat: Ultra-Compact Latent Coding for Feed-Forward 3D Gaussian Splatting
GraphWrit3R: End-to-End Writing of Scene Graphs for Multi-Modal 3D Scenes
Effective Knowledge Conflict Detection via Joint Agentic Optimization
Peer review should constrain evaluative authority
T$^2$-Splat: Adaptive Topology Mesh Splatting with Texture Residuals
Context-Aware Autoregressive Image Generation for Emerging Reasoning Properties
Pushing Biomolecular Utility-Diversity Frontiers with Supergroup Relative Policy Optimization
SRL-MPC: Shape-Aware Reinforcement Learned Model Predictive Control
Tensorion: A Tensor-Aware Generalization of the Muon Optimizer
The SuperActivator Mechanism: Transformers Concentrate Reliable Concept Signals in the Tail
Riemannian Admissibility Flow for Offline-to-Online Safe Reinforcement Learning
Plausible Biomolecular Structure Prediction via Physics-informed Reinforcement Learning
From Groups to Rings: Causal Evidence for Algebraic Decomposition in Grokked Transformers
Interaction Value Inference for Multi-Agent Reinforcement Learning via a Hierarchical Agent-Centric World Model
A Retained-Signal Interface for LLM Watermark Robustness under Paraphrase
GNES: Neural-Guided Evolutionary Program Search for Interpretable Multi-Agent Control
PULSE: Identifying Demonstration-Utility Features with Sparse Autoencoders
Learning Transferable Cross-Day Representations for Few-Shot Neural Decoding
Coordinating Hundreds of RL Agents through Scalable Inference-Time Search
Geometric Gain Graph: Zero-Token Graph Construction for Multi-Hop RAG
VocalGrad: Evaluating Acoustic Perception in Audio Language Models
Metropolis-Adjusted Diffusion Models
When does the noise schedule matter? A spectral classification of diffusion training objectives
S&P: Towards Scalable and Powerful Graph Learning with Hierarchical Structural Acquisition
V-LUMEN: Visual Lookup Memory for Embedding Scaling in Vision-Language Models
$SE(2)$-Aware Conditional Distribution Transport for Vehicle Trajectory Generation
ExpLang: Improved Exploration and Exploitation in LLM Reasoning with On-Policy Thinking Language Selection
Incremental Multiple Oracle
Second-Order Complexity of Neural ODE Inference
Second-Order Complexity Theory for Risk, Explanation, and Calibration in Machine Learning
Foundations of Categorical Equivariant Deep Learning
Diverse Representative Rashomon Sets for Sparse Generalized Additive Models
Releasing Anchors from Cross-View Correspondence: Probabilistic Multi-View Anchor Graph Clustering
GenRec: Knowing Where to Reconstruct and Where to Generate
G$^2$TR: Generation-Guided Visual Token Reduction for Separate-Encoder Unified Multimodal Models
Neural-Behavioral Representation of Natural Whole-body Movement in Monkeys
Traffic STGNNs across Sensor, City, and Time Shifts: Routing Concentration Tracks Sensitivity to Sensor Dropout
Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering
LLM Active Alignment: A Nash Equilibrium Perspective
Efficient Lookahead Encoding and Abstracted Width for Learning General Policies in Classical Planning
CausalTab: Pretraining Across Causal Environments for Tabular Causal Discovery
Extended Wasserstein-GAN Approach to Causal Distribution Learning: Density-Free Estimation and Minimax Optimality
Accelerating Neural Network Training with Augmented Koopman Dynamics
Training-Induced Escape from Token Clustering in a Mean-Field Formulation of Transformers
Minimax Optimal Estimation of Transport-Growth Pairs in Unbalanced Optimal Transport
CITE: Anytime Valid Statistical Inference in LLM Self-Consistency
One-Layer Transformers Provably Learn In-Context K-Nearest Neighbor Prediction with Chain-of-Thought
Conditional Counterfactual Mean Embeddings: Doubly Robust Estimation and Learning Rates
Grassmannian Geodesic Steering: Rank-Preserving Subspace Control for Inference-Time Alignment of Language Models
DeGlare: Self-Supervised Specular Removal for Industrial Metallic Surfaces via Multi-Illumination Priors
GenCOPE: Syn2Real Generalized Category-Level Object Pose Estimation for Robotic Picking
MUTE: Multi-Level Alignment Uncoupling Against Talking-Head Exploitation for Voice Protection
SNACK: A Sequential Notation Framework for Probabilistic Graph Generation
LangMap: A Human-Verified Benchmark for Hierarchical Open-Vocabulary Goal Navigation
Decoding the Critique Mechanism in Large Reasoning Models
Offline Constrained Reinforcement Learning under Partial Data Coverage
Neural Circuit Architectural Priors for Rat Locomotion
Direct Conditioning of Audio Diffusion Transformers on fMRI Reveals Cortical Contributions to Sound Reconstruction
LoopWeaver: Weaving Feedback Loops into Hierarchical Generation under Constraints
WorldMemArena: Evaluating Multimodal Agent Memory Through Action–World Interaction
Trustworthy AI Must Account for Interactions
Learning Visual Speech Representations via Cross-Modal Distillation and Joint Face-Lip Modeling
Njord: A Probabilistic Graph Neural Network for Ensemble Ocean Forecasting
Universal Time Series Generation with Neural Controlled Differential Equations
MMGraph-Agent: Agentic Multimodal RAG via Cache-Inspired Multimodal Knowledge HyperGraphs
Revisiting "Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editing"
Physics-Informed Video Generation via Mixture-of-Experts Latent Alignment
PRISM: Prior Relational Information for Self-supervised Modeling to Enhance Solubility OOD Generalization
Differentiable Belief-based Opponent Shaping
$\alpha$Depth: Learning Single-Pass Soft Boundary Decomposition for Stereo Conversion
ProAlign: Progressive Positional and Prototype-Guided Alignment for Aerial-Ground Person Re-Identification
How Do Language Models Compose Functions?
DELTAVID: Enhancing Fine-Grained Spatiotemporal Perception with Cross-Video Differences
Global convergence of adjoint-optimized neural PDEs
Complex Optimization Modeling via Multiagent Fine-Tuning and Skill-Augmented Reasoning
Incorporating Hierarchical Semantics in Sparse Autoencoder Architectures
Network of Theseus (Like the ship)
Distribution-Adaptive Policy Optimization
OT-Robust3DVLA: A Wasserstein Barycenter is the Right Inductive Bias for Robust Multi-View 3D Vision-Language-Action Policies
The Optimization Prior: Instilling depth for shallow networks, detail for coarse networks
CSBench: A Comprehensive Benchmark for Evaluating Project-Level System Construction in Computer Science
FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization
The Sparsity Whisperer
Knowledge Transfer Scaling Laws for 3D Medical Imaging
GPA: General Principled Framework for Linearizing Softmax Attention via KV Cache Approximation
CacheMAS: Cache Communication for Single-Pass, Jointly-Optimized Multi-Agent Systems
Confidence-Based Diffusion Sampling with Geometric Readiness Awareness for Accelerated Structure-based Drug Design
Diagnosing and Correcting Bias in MLLM for Long Video Understanding
DiPhon: Diffusion on Graphons for Scalable Graph Generation
Diffusion-Time Concept Manifolds: Sparse Autoencoder Groups for Interpreting Denoising Language Models
Conservatism Controllable Compositional Guidance for Offline Safe Reinforcement Learning
What Do SAE Features Encode? Evidence from Human Neural Activity
View-Spectral Reconciliation Learning for Text-based Multispectral Aerial–Ground Person Re-Identification
Crafter: Towards Automated Reproducible Machine Learning via Agentic Code Generation
Seeing Through the Chain: Understanding and Mitigating Hallucinations in Multimodal Large Reasoning Models
Learning What's Real: Disentangling Signals and Measurement Artifacts in Multi-Sensor Data, with Applications to Astrophysics
StitchEdit: Stitching Depth Priors into Image Editors via Per-Layer Gradient Probing
Rethinking Diffusion Decoding via Structural Commitment
Probe Before You Edit: Probing-Guided Molecular Optimization for LLM Agents in Structure-Based Drug Design
ROTATE: Regret-driven Open-ended Training for Ad Hoc Teamwork
How Data Augmentation Shapes Neural Representations
SePO: Self-Evolving Prompt Agent for System Prompt Optimization
Visual-to-Executable Procedural Reconstruction of Buildings.
Breaking Curse of Dimensionality for Mutual Information Estimation with Vine Copulas
REGATE: Confidence-Calibrated Integration of Temporally-Aligned Exogenous Texts for Dynamic Graphs
Intrinsic Muon: Spectral Optimization on Riemannian Matrix Manifolds
E0: Expressive Fine-Grained Discrete Action Prediction for Vision-Language-Action Models via Tweedie Discrete Diffusion
PepDDG: Peptide–Protein Binding ΔΔ𝐺 Prediction via Information Channel Decomposition
What Transformer FFNs Never See: Theory, Diagnosis, and Lightweight Remediation
Continually Evolving Skill Knowledge in Vision Language Action Model
ASAP: Assembly-Source Aligned Pseudocode Refinement For Binary Decompilation
Does the Question Really Matter? Training-Free Data Selection for Vision-Language SFT
BootstrapAgent: Turning Repository Setup into Reusable Agent Knowledge
From Non-Convex to Strongly Convex: Curvature-Adaptive FTPL for Online Optimization
Reasoning-based Spatial Prior (RSP): Learning Spatial Priors from Multimodal LLMs for Object Detection
Efficient Dataset Distillation for Pre-Trained Self-Supervised Models via Statistical Flow Matching
Uniform Stability and Generalization Error of GD and SGD on Fixed-Point Parameters
Convergence Analysis of Newton's Method for Neural Networks in the Overparameterized Limit
RelGS: Relation-Aware Gaussian Splatting for Open-Vocabulary 3D Scene Understanding
GEAR-Align: Grounding-Evidence-Aware Gradient Routing for Multimodal Alignment
IRCasDiff: Two-Stage Cascaded Diffusion for Compound Infrared Face Reconstruction
GameVerse: A Minute-Scale Gameplay Dataset for Long-Horizon Interactive World Modeling
Opt-Arena: Evaluating, Selecting, and Generating Optimization Modeling Data via Tripartite Graphs
SurgVista: Long-Horizon Surgical World Modeling with Plausible Instrument-Tissue Dynamics
LeCellModel: Interpretable Density Estimation over the Gene Expression Manifold
EverAnimate: Minute-Scale Human Animation via Latent Flow Restoration
Hyperspherical Local Margin Retraction for Zero-Shot Instance-Wise Machine Unlearning
The VLM as Sensor: Bayesian Active Search for Long Video Understanding
ExpRFT: Exponential Reward-Weighted Fine-Tuning for Offline RL in Multi-Turn Dialogue
Planning Persuasion, Not Utterances: Profile-Conditioned Open-Loop Search for Dialogue Strategy
RUBRIC-MME: Real-User Behavior-grounded Rubric for Multimodal Interaction Capability Evaluation
RAPDrive: Shared-Latent Hybrid Decoding for Reasoning and Planning in Autonomous Driving
Learning Reveals Invisible Structure in Low-Rank RNNs
ExtraVAR: Stage-Aware RoPE Remapping for Resolution Extrapolation in Visual Autoregressive Models
FacEDiT: Talking Head Video Editing via Facial Motion Infilling
Hint Tuning: Less Data Makes Better Reasoners
Strategic Causal Policy Learning: Welfare, Safety, and Fairness Thresholds
Comp$^2$VLM: A Hybrid Framework Combining Quantization and Lossless Compression for Efficient Vision-Language Models
CSO: Refining Robotic Policies via Skill Distribution Alignment and Skill-Grained Optimization
Hear, Localize, and Reason: Spatially Aware Scene Understanding for Audio-visual LLMs
Depth through Recurrence: Towards Ultra-Efficient On-Device ASR
StoSplat: Ray-Aligned Stochastic Preconditioning for Feed-Forward 3D Gaussian Splatting
Delayed homomorphic reinforcement learning for environments with delayed feedback
Inter-Agent Influence: Evaluating Persuasion, Deception and Coercion in Multi-Agent Systems
Transferring Visual Explainability from Self-Explaining to Prediction-Only Vision Transformers via Task Arithmetic
When Medical VLMs Stop Understanding: MedTEC-Bench for Probing Semantic Specificity
Multi-Nonsmooth-Nonconvex-Objective Optimization
Safe-Fair MACPO: Burden-Fair Constrained Policy Optimization for Safe Multi-Agent Reinforcement Learning
Consistency-Preserving Concept Erasure via Unsafe–Safe Pairing and Directional Fisher-weighted Adaptation
SH$^2$: A Mathematician-Curated benchmark for Assessing Research-level Math Capabilities of LLMs
Retriever-Free Retrieval-Augmented Reasoning via Corpus-Traversing MCTS
Can AI Agents Synthesize Scientific Conclusions?
MVPISplat: Multi-View Photometric Inconsistency for Defending 3D Gaussian Splatting Attacks
Two is better than one: A Collapse-free Multi-Reward RLIF Training Framework
Trivialized Generative Models on Lie Groups
Gram-Calibrated Anchoring for Class-Incremental Learning
LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL
IntegrityBench: Can LLMs Be Trusted as Co-Scientists? A Research Integrity Benchmark
Decoupling is the Key: Scaling Deep Value Networks in Reinforcement Leanring
ROAD: Rule-Grounded Context-Aware Open-World Driver Anomaly Detection
STRABLE: Benchmarking Tabular Machine Learning with Strings
Cauchy Scientific Networks: Loss–Architecture Alignment and Its Limit
GenEvolve: Self-Evolving Image Generation Agents via Tool-Orchestrated Visual Experience Distillation
CWAGraph: Retrieving What Was Never Explicitly Identified in Graph-Based RAG
CREF: Forecasting Benchmarks for the Age of Agents
fev-bench: A Realistic Benchmark for Time Series Forecasting
Stage-wise Attention-Guided Region Sequencing for Adversarial Attacks on Large Vision-Language Models
WavCIL: Wavelet Coefficient-Domain Invariant Learning for Dynamic Graph OOD Generalization
Gaussian Mixture Models in Hilbert Spaces via Kernel Methods
BASTION: Budget-Aware Speculative Decoding with Tree-structured Block Diffusion Drafting
The Geometry of Alignment Collapse: When Fine-Tuning Breaks Safety
Subprocess-Constrained Markov Decision Processes
SAGE: Semantically Disentangled Representation Learning through Latent Geometry Constraint and Large Language Model
Evidence-RL: Towards Evidence-intensive Visual Reasoning
AgenticOCR: Parsing Only What You Need for Efficient Retrieval-Augmented Generation
SympFNO: Structure-Preserving Fourier Neural Operators for Physical Surrogate Modeling
Learning in Policy Transparency Games: Wedge Structure and Adaptive Certification
A Scalable Multi-Task Model for Virtual Sensors
Strengthen Out-of-Distribution Detection via Adaptive Mahalanobis Gap
FrameVGGT: Coherence-Preserving Memory for Bounded Streaming Geometry
Observations Drift, Structures Remain: Structural Pretraining with Time Alignment for Electromagnetic Signals
SMI: Statistical Membership Inference for Reliable Unlearned Model Auditing
STEMFly: Enhancing UAV Vision-Language Navigation via Sensor Grounding, Temporal Diversity and Episodic Memory
Tokens-per-Parameter Coverage Is Critical for Robust LLM Scaling Law Extrapolation
Prospective Coding Improves Learning in Deep Continuous-Time Recurrent Networks
Volatility-Whitened Probabilistic Residual Modeling for Long-Term Time Series Forecasting
Structure-Semantic Guided Closed-Loop Medical Anomaly Detection via Multi-Agent Collaboration
IdealCache: Rethinking Cache Scheduling in Diffusion Transformers via Ideal Trajectories
Learning Global Temporal Dynamics in Sparse Networks via Cycle Counts
Understanding the Surprising Generalization Properties of Tabular Foundation Models
QWaveNet: Quantum-Enhanced Wavelet Network for Time Series Forecasting
FISC: Time-Series Forecasting via First-Layer Statistical Calibration Constraints
DARTS: Targeting Prognostic Covariates in Budget-Constrained Sequential Experiments
Test-Time Graph Anomaly Detection via Shifted Augmentation with Dynamic Objective Scheduling
TailFix: Mitigating Error Accumulation and Correcting Tail Deterioration in Long-Horizon Forecasting
DSR-TSF: Spectrum-Driven Dynamic Routing for Efficient Long-Horizon Time Series Forecasting
BucpTSF: Breaking the Uniform Computation Paradigm in Time-Series Forecasting
Readiness-Aware Sample Selection for Noisy Labels with Class Imbalance
MemArena: An Ego-Centric Benchmark for On-Device Agentic Personal Memory Assistants at Scale
GenRM-Flow: Generators are Process-aware Reward Models in Flow Matching
Disentangling Channel Semantics in Vision Transformers via Token Decorrelation and Composition-Aware Modulation
Coarse-to-Fine Compositional Diffusion for Long-Horizon Planning
Towards Direct Evaluation of Harness Optimizers via Priority Ranking
SWE Atlas: Benchmarking Coding Agents Beyond Issue Resolution
Cylindrical Geodesic Flow Matching for Quasiperiodic Physiological Signal Transformation
Déjà View: Looping Transformers for Multi-View 3D Reconstruction
ColorConceptBench: A Benchmark for Probabilistic Color-Concept Understanding in Text-to-Image Models
Benchmarking Optimizers for Large Language Model Pretraining
ZetaEvolve: Learning to Search through History-Conditioned Potential Value
Selective Critique for Cost-Aware LLM Agents in Long-Horizon Decision Making
The Alien Space of Science: Sampling Coherent but Cognitively Unavailable Research Directions
Mirror, Mirror on the Wall: Can VLM Agents Tell Who They Are at All?
When Trackers Fail: VLM-Guided Verification and Recovery for Robust Video Object Segmentation
GADMVP: Adaptive Few-Shot Graph-Level Anomaly Detection with Multi-View Structured Prompting
Benchmarking Vietnamese Legal Knowledge of Large Language Models
RePercENT: Scaling Disentangled Representation Learning Beyond Two Modalities
LensDesigner: A Self-Improving Agent for Optical Lens Design
Trust, but Don’t Verify: Epistemic Blind Spots in LLM Source Evaluation
OceanCBM: A Concept Bottleneck Model for Mechanistic Interpretability in Ocean Forecasting
Learning to Sample From Diffusion Models via Inverse Reinforcement Learning
Distribution Matching Distillation without Fake Score Network
Words That Make Language Models Perceive
Uncertainty Quantification for Large Language Diffusion Models
Can We Model the Artifacts Explicitly? Disentangle Artifacts via Pairwise Edit Relations for Image Manipulation Localization
GMOS: Grounding Moving Object Segmentation in 3D Space and Time
AtomMOF: All-Atom Flow Matching for MOF-Adsorbate Structure Prediction
EMERGE: A Benchmark for Updating Knowledge Graphs with Emerging Textual Knowledge
Spectral Reversal: Counteracting Singular Value Bias for Graph Prompting
Sharper Regret Bounds for Shampoo
One More Time: Revisiting Neural Quantum States from a Reinforcement Learning Perspective
As the Story Unfolds: Watching a Film and Identifying Characters as a Human Does
Multi-Level Alignment Framework for Long-Term Olfactory Neural Decoding
ActO: Extracting Action Representations from MLLM Embeddings for Video World Models
ASAT: Adaptive Scoring and Thresholding with Human Feedback for Robust Out-of-Distribution Detection
MedHorizon: Towards Long-context Medical Video Understanding in the Wild
Structured Transforms for Low-Overhead Quantization of Language Models
Atom-level Protein Representation Learning Improves Protein Structure Prediction
scTrilemma: Balancing Identity, Invariance, and Reconstruction in Single-Cell Representation Learning
VLAN: Vision-Language Accessible Navigation
RobustGenBench: A Benchmark for Robust Generalization to Adversarial and Common Perturbations, with Applications to Vision and Vision-Enabled Large Language Models
OccStress: Stress-Testing the 4D Occupancy Forecasting Chain
SAGE: Semantic Ambiguity Guided Capacity Expansion for Retrieval-Augmented Generation
Logit-Conditioned Diffusion Decoding for Frozen Discrete-Token VLMs
LibriBrain100: One Hundred Hours of Broad and Deep MEG Data for Neural Speech Decoding at Scale
Think, then Score: Decoupled Reasoning and Scoring for Video Reward Modeling
Position: A Safe LLM and a Safe Harness Do Not Make a Safe Agent
Towards Scalable Egocentric HOI for Humanoids: Benchmarking Whole-Body Dexterous Interaction with Tactile Prediction
VL-DocIR: A Benchmark for Vision-Based Long Document Retrieval
TACT: Mitigating Overthinking and Overacting in Coding Agents via Activation Steering
MMLongCite: A Benchmark for Evaluating Faithfulness of Long-Context Vision-Language Models
Read, Parse, Describe: Unified Document Parsing with Visual Element Description Generation
Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents
ViCO: A Training Strategy towards Semantic Aware Dynamic High-Resolution
Resilient Semi-Supervised Inference with Heterogeneous Unlabeled Data
Teacher-Aware Evolution of Heuristic Programs from Learned Optimization Policies
FAST-Brain: A Flow-Aligned Spatio-Temporal Surrogate Brain Model
One Adapter For All: Towards Generalizable Many-To-One Domain Adaptation In Heterogeneous Collaborative Perception
STAR-Math: Multi-Agent Mathematical Reasoning under Persistent Meta-Strategic Supervision
LogicSR: A Unified Benchmark for Logical Discovery from Data
Learning to Commit: Next-Commit Prediction via Online Supervised Contrastive Reflection
OxyGen: Unified KV Cache Management for VLA Inference under Multi-Task Parallelism
LDPCache: Locally Differentially Private Multi-Query Processing with Cache Optimization for Large Language Models
How Private is Private? A Comparative Study for Face De-Identification
EIHMR: Collaborative Human-Camera Estimation for Global Human Mesh Recovery
Don't Lose Focus: Activation Steering via Key-Orthogonal Projections
Emergent Misalignment as Data-Mediated Transfer
Language Models Demand New Computer Science
From Contexts to Conditionals: Statistical Self-Consistency of Persona Prompting
Reconciling Operational Energy Trilemma: A Heterogeneous Risk-Constrained MDP Framework with Residual Policy Learning
SAFE-DRIFT: Data Selection for Supervised Fine-tuning with Controllable Off-Target Drifts
The FACTS Leaderboard: A Comprehensive Benchmark for Large Language Model Factuality
Generative Scenario Rollouts for End-to-End Autonomous Driving
MAPLE: Latent Multi-Agent Play for End-to-End Autonomous Driving
SPECS: Faster Test-Time Scaling through Speculative Drafts and Dynamic Switching
Learning Collision‑Free Dispatch Policies for Route‑Wise Decision‑Dependent Anomaly Detection
Bayes-Optimal BER and AUC: Estimation and Evaluation of Estimators
SchemaPose: RGB-Based Category-Level Pose Estimation with Parametric Category Schema
Provable Selective Auto-labeling with Reliability Guarantees
Mechanistic Interpretability Needs Philosophy
Dynamic Latent Routing
On approximation and estimation of Schrödinger potentials without the curse of dimensionality
Spectral Identifiability for World Models: Polynomial Projectors, Resolvent Stability, and a Krylov Bottleneck
UniFlow-Audio: Unified Flow Matching for Audio Generation from Omni-Modalities
Cross-User Poisoning: User-Task Boundary Failures in Multi-User Collaborative Language Agents
EditDistill: Is It Possible to Guide Video Editing with Image Editing
CoANeRV: Coordinate-Aware Token-Space Neural Video Representation
Don't Pay Attention, PLANT It: Pretraining Attention via Learning-to-Rank
HyperSkill: Training-Free Omnimodal GRPO via Hypergraph-Indexed Skill-Library Evolution
LL-Bench: Rethinking Low-Level Vision Evaluation in the Era of Large-Scale Generative Models
M-plicits: Neural Implicit Surfaces via Nested Multiscale Residuals
AutoManifold: Agentic Design of Data Visualisation Algorithms via Manifold Embedding
NS-VLA: Towards Neuro-Symbolic Vision-Language-Action Models
LiSA: Lifelong Safety Adaptation via Conservative Policy Induction
Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse
Stability-Aware Self-Training for CLIP under Cross-Modal Anchoring Mismatch
Orthogonal Sparse Subgraph Alignment for Structure-Function Coupling in Brain Networks
RISE: Red-teaming via Iterative Strategy Evolution for Modern Text-to-Image Models
Darwin-7B: A Multi-Omic Foundation Model for the Human Gut Microbiome via Sparsified Quality-Aware Tokenization
Multiobjective Submodular Maximization with Concave Aggregation
SphMind: Towards Robust, Training-Free VLM-based Spatial Reasoning with a 360 Camera
Constructive Neural Policies for the Quadratic Assignment Problem via Multi-Expert Imitation
UnlearningSoup: Is Repeated Tuning Necessary for Large Language Model Unlearning?
From Facts to Personas: Interpretable Role Unlearning in LLMs via Mixture-of-Experts
Dynamics-Informed Adaptive Offline RL for Real-Time Tokamak Plasma Control
DT-PBO: an Interpretable Tree-based Surrogate Model for Preferential Bayesian Optimization
Does Your Neural Network Extrapolate? Feature Engineering as Identifiability Bias for OOD Generalization
Few Contrastive Attention Heads Enable Visual Grounding in Large Vision-Language Models
Rethinking Dataset Distillation for Classification: Do Distilled Sets Outperform Coresets?
When Copying Is Hard: Copy-Constrained Decoding for Exact Span Reproduction
VersaCamVLA: Camera-Configurable VLA Policies for Robotic Manipulation
GeoMemory: Geometry-Indexed Memory for Long-Horizon Interactive Video Generation
Global linear convergence of entropy-regularized softmax policy gradient beyond tabular MDPs
Unveiling the Value of Motion for Cinematic Camera Trajectories
Provably Efficient Regularized Online RLHF with Generalized Bilinear Preferences
Beyond Clipping: Signed Logarithmic Smoothing for Policy Optimization
Neural‑Visual Decoding via Cognitive‑guided Adaptive Blurring and Information‑Constrained Alignment
Heads That Write, Not Just Point: Image Retrieval Heads in Vision-Language Models
DecompDreamer: A Composition-Aware Curriculum for Structured 3D Asset Generation
GARDO: Reinforcing Diffusion Models without Reward Hacking
Adaptive Stepsizes for Eligibility Traces in Deep Reinforcement Learning
Edit-R2: Context-Aware Reinforcement Learning for Multi-Turn Image Editing
A Unifying Perspective on Language Model Interpretability
Learning with Enumeration: Neural-Guided SAT Framework for Cryptographic Key Recovery
How Much is Left? LLMs Linearly Encode Their Remaining Output Length
RoboExo: Structure-Guided Wrist-to-Exocentric Video Generation for Scalable Robot Learning
RIGOR: Risk-Gated Topology Adaptation for Robust LLM Multi-Agent Reasoning
Quasi-Linear ICA for Motor Unit Decomposition during Dynamic Contractions
Scaffold3D: SfM-Conditioned Pointmap Prediction for Multi-View 3D Reconstruction
ManifoldCache: Training-Free Diffusion Acceleration via Constraint Manifold Caching
Spikes as Detectors: Phase-Conditioned Spiking Dynamics for Time-Series Anomaly Detection
MoRSE: Task-Oriented Multi-Agent System with Mixture of Role-Subtask Experts
Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks
When Does Flow Matching Help Deterministic Multimodal Prediction: A Spatial Transcriptomics Study
Displacement Geometry Captures Platonic Shared Reality Across Models and Modalities
A Minimal Interpretable Architecture for Zero-Shot Reconstruction of Dynamical Systems
Holistic EvoLution via Intrinsic eXchange for Unified Multimodal Models
From Weak Data to Strong Policy: Q-Targets Enable Provable In-Context Reinforcement Learning
CM-EVS: Sparse Panoramic RGB-D-Pose Data for Complete Scene Coverage
Example-Based Spatial Guidance for Training-Free Concept Erasure in Diffusion Models
VTBench: Disentangled and Human-Aligned Evaluation for Image-Based Virtual Try-on
Decomposing SGD Dynamics in Neural Networks: Teacher-Induced Spikes and Variance Inflation
Overcoming Catastrophic Forgetting in Visual Continual Learning with Reinforcement Fine-Tuning
Neural Structural Reasoner: A Brain-inspired Architecture for Reasoning over Structured Knowledge
Preserving Geometric Symmetry in Uncertainty Estimation for Molecular Forces
Learning When to Stop: Selective Imitation Learning Under Arbitrary Dynamics Shift
CrossID: Cross-Supervised Spatio-Temporal Gated Fusion for Personalized Portrait Generation
Risk Horizons: Structured Hypothesis Spaces for Longitudinal Clinical Prediction
Values as Style: Disentangling Values from Semantics with One-Way Mixing for Low-Damage LLM Steering
Representation Rigidity in Face Embeddings: Orthogonal Identifiability and Backfill-Free Compatibility
Continuously-Augmented Hybrid Masked Diffusion Model for Data Imputation
Learning Informative Invariant Representations via Hierarchical Latent Decomposition
Risk-Aware Action Repetition via Expected Skip Evaluation
Sparsely-Supervised Data Assimilation via Physics-Informed Schrödinger Bridge
Shared-Noise Mechanisms for Verifiable Differentially Private Counting
From Static Geometry to Dynamical Singularity: Detecting Memorization in Diffusion Models via Score Evolution
PaperLens: How Predictable Is Paper Acceptance?
EDITORS Know Your Style! Editing LoRA Subspaces for Stylistic Attribution and Imitation
Scaling Laws for Synthetic Pretraining in Radio-Map Prediction
HeterSEED: Semantics–Structure Decoupling for Heterogeneous Graph Learning under Heterophily
Beyond Coordinates: Encoding Graph Structure via Contextual Distribution and Relational Similarity
A Structure-Aware Higher-Order Message Passing Framework on Walk States for Graph Classification
BeamWitness: Rooted Subgraph Beam Search for Selective Graph Representation Learning
CSCN: The Crossed Subtree Convolutional Network
VGB for Masked Diffusion Model: Efficient Test-time Scaling for Reward Satisfaction and Sample Editing
HyperGen: Learning Structure-Aware Spectral Flows for Hypergraph Generation
BA-T: An Iterative Transformer for Two-View Bundle Adjustment
Cross-order Consensus Graph Matching
Learning the Context of Errors: Black-Box Online Adaptation of Time Series Foundation Models
TwinRouterBench: Fast Static and Live Dynamic Evaluation for Realistic Agentic LLM Routing
Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents
Reflection Anchors for Propagation-Aware Visual Retention in Long-Chain Multimodal Reasoning
Ordered Policy Optimization
Localized Dynamics-Aware Domain Adaption for Off-Dynamics Offline Reinforcement Learning
REACT: Physically and Chemically Consistent Reconstruction of Marine Active Tracers
CanvasMAR: Improving Masked Autoregressive Video Prediction With Canvas
DSSA: Dynamic Sparse Semantic Anchoring for Purifying Protective Perturbations against Diffusion Models
TaskGround: Structured Executable Task Inference for Full-Scene Household Reasoning
Beyond Encoder Accumulation: Measuring Encoder Roles in Multi-Encoder VLMs
Heterogeneous Judge-Aware Ranking with Sensitivity, Disagreement, and Confidence
Feed-Forward 3D Gaussian Splatting for High-Fidelity Animatable Hand Avatar Reconstruction from a Single Image
Learn from the Gap: Differential-Aware Advantage Pruning with Adaptive Rollout Sampling for GRPO
Empowering Time Series Analysis with Large-Scale Multimodal Pretraining
Chebyshev Differential Flows for Shape Matching and Interpolation with Endpoint Guidance
Multi-Oracle Agreement Reveals the Limits of Self-Consistency Evaluation in RNA Design
When a Window Is Not an Action: Selective Phase-Script Deliberation for Sliding-Window Human Activity Recognition
Complexity-guided Regularization for Generalizable Human Gaussian Splatting
SetCon: Towards Open-Ended Referring Segmentation via Set-Level Concept Prediction
Does Cross-Panel Pretraining Transfer Under Marker Heterogeneity? A Large-Scale Empirical Study in Clinical Flow Cytometry
Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models
Seeing or Rationalizing? Scene-Evidence-Guided Chain-of-Thought for Faithful 3D Multimodal Reasoning
TrackTok: Object-Centric Video Tokenization with Semantically Persistent Tokens
Verigrad: Verification-Driven Multi-Agent GPU Kernel Generation for High-Order MLIP Derivatives
OmniMemBench: Towards Scalable Evaluation of Long-Term Omni-Modal Agent Memory
Phantom Transfer: Data Poisoning can Survive Data-Level Defences
Closed-Form Implicit Neural Representations
Constrained Graph Clustering: A Spectral Algorithm with Generalized Eigenvectors
ST-Bridge: Bridging Sketch and Text with Large Language Models for Coarse-to-Fine Image Retrieval
V1-Inspired Dynamic Vision System: A Bio-Plausible Video Embedding Framework with Decoupled Shape–Color Pathways and Long-Range Spatiotemporal Perception
S$^2$-RL: Sample-Set Dual Reinforcement Learning for Generative Semantic Segmentation Dataset Distillation
Conditional independence and graphical models for rankings
TIC-GRPO: Provable and Efficient Optimization for Reinforcement Learning from Human Feedback
MCPHallu: Benchmarking Reasoning, Execution, and Memory Hallucinations in MCP Agents
Chain of Dual Structures in Transformer Attention
HaM-World: Soft-Hamiltonian World Models with Selective Memory for Planning
Top-$k$ Identification with Correlated Biased LLM Judges via Anchor Leverage
How Does Pruning Change Decisions in Large Language Models?
MindLoom: Composing Thought Modes for Frontier-Level Reasoning Data Synthesis
ScopeSAE: Model-Scope Feature Discovery with Interpretable Layer Selection
What to Perturb, How to Propagate: A Graph-Guided Transferable Attack on VLP Models
HierRR: Enhancing Instruction Alignment in Open-Vocabulary Indoor Scene Synthesis via Agentic Hierarchical Reasoning and Reflection
Geometry-Regularized Collapse Resistance via Consensus Enhancement for Federated Learning
Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory
RewardFlow: Topology-Aware Reward Propagation on State Graphs for Agentic RL with LLMs
Transition-Aware Credit Assignment in Agentic Learning for LLM Reasoning
Constrained Goal-directed Planar Graph Generation with Grammar-based Reinforcement Learning
LAFP: Preserving Latent Action Structure in Latent Policy Learning via Flow Matching
Process-Aware LNS for Large-Scale MILP via Context-Enhanced Fine-Tuned LLM-driven Selector
First-Order Trajectory Matching: Fast Ensemble Predictions of Chaotic, Turbulent, Stochastic Systems
Beyond Pairwise Supervision: Spectral Characteristic Matching for Data-Efficient Multimodal Alignment
WorldPrism: 3D Consistency for Video World Models via Bidirectional Cross-Space Verification
HomeFlow: A Data Flywheel for Smart Home Agent Training with Verifiable Simulation
NADS: Navigator-Guided Data Selection for Mitigating Catastrophic Forgetting in Fine-Tuning
TriSpec: Ternary Speculative Decoding via Lightweight Proxy Verification
UniSHARP: Universal Sharp Monocular View Synthesis
Diff-Aid: Inference-time Adaptive Interaction Denoising for Rectified Text-to-Image Generation
When Debate Helps: Proposal Supply and Verification-Aware Readout in Multi-Agent Reasoning
GlyphAnchor: Enhancing Visual Text Rendering via Position-Anchored Glyph Priors
Political Neutrality as Balanced Approval: A Large-Scale Human Evaluation of AI Responses
Reward Modeling for Multi-Agent Orchestration
Program-as-Weights: A Programming Paradigm for Fuzzy Functions
AudioCALM: Continuous Autoregressive Language Modeling for Universal Audio Generation
Drift-React: One-step Generation of Reaction Pathways via SE(3) Drifting Fields
GEOPHYS: The Geometry of Physical Plausibility
SkiP: When to Skip and When to Refine for Efficient Robot Manipulation
Adaptive-Margin Masking and Restoration for Balanced Multimodal Learning
RankVQ: Low-Rank Parameterized Commutative Vector Quantization for KV Cache Compression
What, Where, and Boundary: Hierarchical Cognitive Decomposition for Echocardiography Video Segmentation
When and What to Prune? Stage-Aware Visual Token Pruning for Efficient VLA
Analyzing and Guiding Zero-Shot Posterior Sampling in Diffusion Models
SynerVLA: Exploiting Embodied Execution Phases for On-Device Dual-System VLA Acceleration
AuxGeoAgent: Synthesizing Challenging Geometry Proving Data via Planning and Symbolic Deduction
Learn from Your Mistakes: Self-Correcting Masked Diffusion Models
ChildPose: Foundation for Children Pose Modeling
Subspace-Guided Continual Learning: Hessian Based Stable–Plastic Decomposition for Exemplar-Free Class-Incremental Learning
Mixture of Activations: Token-Adaptive Mixing for Expressive Feedforward Layers
LessMimic: Versatile Humanoid-Object Interaction with Unified Distance Field Representations
Multi-Part Object Representations via Graph Structures and Co-Part Discovery
SWE-Crafter: Scaling Executable Multilingual Software Engineering Data with Meta-Skill Agents
Membrane Sensitivity and Deployment Fragility of Learnable Time Constants in Spiking Neural Networks
When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon
Beyond Bit Matching: Orthogonal Watermarks for Collusion-Resistant Image Fingerprinting
PathView-Bench: Can Multimodal Large Language Models Achieve Fine-grained Multiscale Understanding of Pathology Images?
Distance-Dependent Connectivity Shapes Continual Learning by Synaptic-Resource-Delimited Separation of Neural Dynamics
BioMicroAgents: A Co-evolutionary Multi-Agent Framework for High-Fidelity Biomicroscopy Imaging
Why Transformers Struggle with Distribution-Independent In-Context Learning
SF-DST: Adapting Vision-Language Models for Anomaly Detection via Asymmetric Modulation and A-LoRA
Tropical Boundary Complexity of Deep ReLU Networks
Spherical Flows for Sampling Categorical Data
Rethinking Parallel Multi-Agent Systems: A Cost-Aware Framework for Efficient Coordination
Flow Matching for Count Data
From Intent to Evidence: A Categorical Approach for Structural Evaluation of Deep Research Agents
Exploiting Negative Multi-Cluster Structure in Class-Wise Embeddings for Weakly Supervised Multi-Label Learning
LoCo: Selective Local Competition for Discriminative Open-Vocabulary Multi-Label Recognition
Trading Sensing for Structure: Sparse IMU-EMG Fingertip Force Estimation via Neuro-inspired Structured Modeling
Simple Test-Time Refinement for Plot-to-Code Generation via Visual-Code Diagnostics
Nonparametric In-Context Learning under Growing Geometric Complexity: Minimax Optimality and Local Geometry-Adaptivity of Transformers
WASD: Wasserstein-based Knowledge Distillation for Large Language Models
Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs
Efficient algorithms for linear regression with heteroskedastic errors
PhysElite: How Far Are LLMs from Solving Olympiad-Level Physics Problems?
ClusterSplat: Semantic Cluster Selection for 3D Visual Grounding in Gaussian Splatting
Flow Equivariant State Space Model
Seeing Beyond the Next Step: World-Model-Guided Human-Like Navigation in Multi-Agent Scenes
PercepCap: Video Captioner with Structured Spatio-Temporal Perception
OmniSE: Support-Faithful Optimization for Evidence-Centric Audio-Video Reasoning
Statistical Complexity of Soft Bellman Residual Minimization
Asymmetric Hierarchical Anchoring for Robust Audio–Visual Cross-Modal Generalization
Rethinking Incompleteness: Formalizing Protocol Divergence and Train-Once Learning for Robust IMVC
One Unified Representation: Resolving the Appearance-Semantics Dilemma via Structural Regularization
OASIS: Observation-Action Space Alignment via SE(3) Trajectory Prediction for Robotic Manipulation
Rethinking Infrared Small Target Detection: A Foundation Driven Efficient Paradigm
Gen-Searcher: Reinforcing Agentic Search for Image Generation
A unified pairwise distribution matching framework for graph domain adaptation under structure shift
Local Manifold Identification with Latent Linear Models and OT Flows
Seed-Your-Motion: Householder Orthogonal Noise for Motion-Controllable Video Diffusion Models
Sparse Fine-Tuning for Parameter-Efficient Adversarial Training
Fast-dLLM++: Fr\'{e}chet Profile Decoding for Faster Diffusion LLM Inference
Uncertainty-Aware Probabilistic Constrained Clustering from Entangled Pairwise Supervision
On the Complexity of Discounted Robust MDPs with $L_p$ Uncertainty Sets
Beyond Accuracy: A Diagnostic Benchmark for Hypothesis-Driven Experiment Planning in LLM Agents
Cross-Layer Evolution Graph Learning for Fine-grained VLM Hallucination Detection
Beyond Flat Walks: Compositional Abstraction for Autoregressive Graph Generation
Bridging Image Restoration and Recognition via Causal Mediated Unrolling
Bits Beat Tokens: A Regret Rate Distortion Theory for Large Language Model Agents
BayesJudge: Uncertainty-Aware Bayesian Meta-Evaluation of Human and LLM Judgments
Online Min-Max Optimization: From Individual Regrets to Cumulative Saddle Points
A Sparse Low-Rank Biclique Decomposition for Graphs
The Graph Concept Bottleneck: Decoding Combinatorial Reasoning in GNNs for Interpretability
SemGeo-Gen: Unsupervised Generation of Approximate Cross-Instance Semantic-Geometric Correspondences
MACRO: Training-free Multi-plane Attention for Closeup Render Optimization
Video Stitching from Multiple Moving Cameras
Efficient Variational Inference for Log-Gaussian Cox Processes via Voronoi Tessellation
Prompt-Conditioned Semantic Bottleneck for Cross-Domain Face Attack Detection
How Does Personalized Memory Shape LLM Behavior? Benchmarking Rational Preference Utilization in Personalized Assistants
High-Dimensional Conditional Independence Testing via Random Projection Aggregation
3D Molecule Generation from Rigid Motifs via $\mathrm{SE}(3)$ Flows
PULSE: A Synchronized Five-Modality Dataset for Sensorimotor Coordination in Long-Horizon Daily Activities
Defining Operational Conditions for Safety-Critical AI-Based Systems from Data
Scaling Neural Motor Decoding via Decoupled Behavioral Pretraining
CASAM: Consistency-Anchored Sharpness-Aware Minimization for Improved Model Generalization
MetaKE: Meta-Learning for Knowledge Editing Toward a Better Accuracy-Editability Trade-off
SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
Ask, Answer, and Detect: Role-Playing LLMs for Personality Detection with Question-Conditioned Mixture-of-Experts
Improving the Efficiency of Language Agent Teams with Adaptive Task Graphs
MIND-DDI: Multi-Omics Interpretable Drug-Drug Interaction Prediction with Joint Optimization of Graph Structure, Neural Architecture, and Symbolic Rules
Cross-Channel Agreement Beats Consensus: Compositional Verification for Geometry Reasoning
Compositional Training-Free Diffusion Planning for Long-Horizon Multiple Reach-Avoid Tasks
MM-DyGraph: A Dataset, Benchmark, and Model for Multimodal Dynamic Graphs
Graph-Based Stochastic-Power-UCT: Monte-Carlo Graph Search with Power Mean Estimation
What Gets Measured Gets Managed: Sign-aware Recommendation Needs Sign-aware Evaluation
Bayesian Causal Experimental Design for CATE Estimation under Noncompliance
Spike-SFT: Selective Parameter Enhancement and Fusion for Efficient Spiking Neural Networks
RoutingBench: Can Agentic Routing Analysis Scale to Production Datacenter Networks?
Stealth Apart, Harm Together: Skill Cascading Attacks on Skill-Based Agent Systems
Random Neural Network Expressivity for Non-Linear Partial Differential Equations
NeuroInk: Retinomorphic Spiking Sequence Modeling for Handwritten Text Recognition
Aligning Flow Map Policies with Optimal $Q$-Guidance
TabClustPFN: A Prior-Fitted Network for Tabular Data Clustering
InTAct: Interval-based Task Activation Consolidation for Continual Learning
ALAM: Algebraically Consistent Latent Transitions for Vision-Language-Action Models
MemoryFusion: Cross-Temporal Memory Learning for Multimodal Video Fusion
Few-Step Cofolding with All-Atom Flow Maps
Smart Picks in the Dark: Towards Efficient RLVR for Reasoning via Tracing Metacognitive Pivots
Depth-Recurrent Attention Mixtures: Giving Latent Reasoning the Attention it Deserves
FocusVLA: Hijacking Attention to Break Visual Token Pruning in Vision-Language-Action Models
Algorithm for Contextual Queueing Bandits with Rate-Optimal Queue Length Regret
Hide to See: Reasoning-prefix Masking for Visual-anchored Thinking in VLM Distillation
Logistic Bandits with $\tilde{O}(\sqrt{dT})$ Regret without Context Diversity Assumptions
Efficient Retrosynthesis Prediction with Integral Flow Matching and Latent Inversion
Reward-Estimated Hypergradient for Bilevel Reinforcement Learning with Black-Box Follower
LLM-enabled Applications Require Systematic Threat Monitoring
Structure, Subspace and System: Push the Real Limit of Extremely Low-Bit Quantization for MoE-LLMs
The Butterfly Effect in Reasoning: Branch-Structured Distributional Memory for Stochastic Agents
Strengthening LLMs for Tabular Prediction with Structural Priors
Scalable Token-Level Hallucination Detection in Large Language Models
Alignment Dynamics in LLM Fine-Tuning
Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models
SocialDirector: Training-Free Social Interaction Control for Multi-Person Video Generation
Learning Pseudo-Riemannian Manifolds for Heterophilic Graphs via Graph Signature
Inference-Time Vulnerability Beyond Shallow Safety: Alignment Along Generation Trajectories
Training Optimal Large Diffusion Language Models
SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking
A Simple Class-Agnostic Approach to Enhance Fair Adversarial Training
Robust Domain Generalization under Divergent Marginal and Conditional Distributions
Chess-World-Model: A 10M-Game Benchmark for Exact State Tracking from Chess Move Sequences
AgentGrad: Intervention-guided Prompt Optimization for Multi Agent Systems
Faithful Embeddings of Irregular and Asynchronous Data for Online Log-NCDEs
Hide to Guide: Learning via Semantic Masking
Large Language Models as Graph Computational Solvers via Topology-aware Residual Attention
PRISM: Phenotype-Resolved Inference in Single-Cell Mixed Models via Latent Disease States and Contextualized Differential Expression
MIRAGE: Hierarchical MI-Surrogate Regulation for Graph Contrastive Learning
Progressive Layer-wise Supervision: Deep-to-Shallow Supervision Annealing for Efficient and Robust Speech Deepfake Detection
Atomic Trajectory Modeling with State Space Models for Biomolecular Dynamics
DUDS: Dual-stage Data Selection for Efficient Reinforcement Learning with Verifiable Rewards
OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents
LLM Is a Good Conditioner: End-to-End Sign Language Video Generation with VQ-Diffusion
Image Matting without Matting-Specific Annotations via Eikonal Fields
Tackling the Data-Parallel Load Balancing Bottleneck in LLM Serving: Practical Online Routing at Scale
Asymmetric Invertible Threat: Learning Reversible Privacy Defense for Face Recognition
PriFT: Prior-Support Guided Token Reweighting for Supervised Fine-Tuning
Beyond the Prompt: Leveraging Pre-Decoding States for Jailbreak Detection in dLLMs
Group Perspective Matters: Regulating Debate Relationships Can Mitigate Blind Conformity in Multi-Agent Debate
OASIS: Online Adaptive Steering for In-Training Safety of LLMs
Revisiting On-policy Adversarial Black-Box Distillation: Calibrating Groupwise Reward Geometry for Effective Advantage Construction
Two Layers of Attention Stability: A Koopman-Operator Analysis of Linear and Softmax Attention
Learning in Causal Markov Games
CRAFT: Causal Responsibility and Failure Tracing in Medical Vision Language Models
Can Agents Price a Reaction? Evaluating LLMs on Chemical Cost Reasoning
StructBridge: Structure-Grounded 3D Indoor Object Generation via 3D Latent Diffusion Bridge and Normal Refinement
Where Do We (Not) Need Temporal Context in Low-Resource Video Task Adaptation?
Spectral Estimation with Deformed Decompression
Free Decompression with Algebraic Spectral Curves
CoE-Agent: Co-Evolving Patient-Doctor Agents via Interactive Policy Graph Optimization for Clinical Decision Making
Decoupling Direction and Magnitude: Language-Steered Flow Matching for Super-Resolution in the Dark
Memory Inception: Latent-Space KV Cache Manipulation for Steering LLMs
Who Wrote This Paper? Autonomous Scientific Discovery for 3DGS Research
Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformation
LAMP: Look-Ahead Mixed-Precision Inference of Large Language Models
Preserving Exploration for LLM Reasoning via Mean Order-Statistic Alignment
FLASH: Efficient Visuomotor Policy via Sparse Sampling
WsiSSM: A Weakly Supervised Subset-Matching Framework for Unified Classification and Segmentation of Histopathology Whole Slide Images
Pygmalion Effect in Vision: Image-to-Clay Translation for Reflective Geometry Reconstruction
Topology-Aware Representation Alignment for Semi-Supervised Vision-Language Learning
AesGI-Bench: Benchmarking and Evaluating the Aesthetic Quality of AI-Generated Images via Large Multimodal Models
Estimating Model-Level Membership Inference Vulnerability Without Reference Models
DynT2I-Eval: A Dynamic Evaluation Framework for Text-to-Image Models
Value-Priced Uncertainty: A Family of PPO-Compatible Exploration Bonuses
Why Learning Rediscovers the Closed-Form Diagonal Regularizer
VideoOdyssey: A Benchmark for Ultra-Long-Context and Omni-Modal Video Understanding
Boosting Off-Policy RLVR with Data-Centric Replay
Reducing Credit Assignment Variance via Counterfactual Reasoning Paths
Information Loss and Disparate Effects in Network Embeddings
Towards Optimism-Pessimism Trade-off in Model-based Offline-to-Online Reinforcement Learning
Few-Step Boltzmann Generators via Scalable Likelihood Flow Maps
Learning to Synergize Textual and Visual Prompts for Fine-Grained Traffic Element Detection in HD Maps
SIGMA: A Sigmoid-Gated Sampler for Test-Time Scaling in Diffusion Language Models
MCPHunt: An Evaluation Framework for Cross-Boundary Data Propagation in Multi-Server MCP Agents
Temperature-Regulated Stochastic Sampling for Diffusion-Based High-Quality Molecular Generation
On-Policy Distillation with Open Property-Equivalence Reward for LLM-Based NL-to-SVA Generation
Is Agentic AI Ready for Real-World Hardware Engineering? A Deep Dive with Phoenix-bench
Efficient Decoder Scaling Strategy for Constructive Neural Routing Solvers
VDE: Verifiable Dynamic Evaluation of Mathematical Reasoning via Typed Bipartite Graphs
VEX-Bench: Benchmarking Verification Complexity of LLM-Generated Misinformation
HDL-RepoBench: Multi-Paradigm Repository-Level Code Completion for Hardware Design Languages
Logarithmic Depth Suffices for In-Context Gradient Descent
Finetuning with Sampling: Make SFT Generalize, Not Forget
Thinking with Imagination: Agentic Visual Spatial Reasoning with World Simulators
Toward Efficient Reasoning of Large Language Models via Latent Concept-Pyramid Modeling
Cross-Architecture Transferability is Width-Confounded:Diagnosis and Subspace Correction
SIRAS: Sibling-Relative Advantage Shaping for Reinforcement Learning from Verifiable Rewards
Learning Cost-Efficient Autoscaling for Latency-Constrained Disaggregated LLM Serving
Spatial-IQ: Deconstructing Spatial Intelligence via Hierarchical Capability Tests
Reinforcement Learning for View-Adaptive Distillation in 3D Gaussian Compression
Insight-Driven Search: A Framework for Multi-objective Automated Heuristic Design with Large Language Models
TSB-SEG: A Systematic Time-Series Segmentation Benchmark
LiBrA-Net: Lie-Algebraic Bilateral Affine Fields for Real-Time 4K Video Dehazing
Feeling of Knowing in Large Language Models
GeLVR: Geometry-Consistent Latent Visual Reasoning in Multimodal LLMs
Effectiveness of Curriculum Learning Depends on Reward Sparsity and Competing Optima
ASQ: Agent-guided Semantic-aware Quantization for Large Language Models
AtomWorld-Mem: Memory-Restored World States for Long-Horizon Atomistic Evolution
When Alignment Fails: Stabilizing Cross-Dynamics RL with Prototype Trust Regions
HiFloat4 Format for End-To-End Reinforcement Learning Post-Training of Large Language Models
Verifying Agents in Rubric-Graded Environments
BankerToolBench: Evaluating AI Agents in End-to-End Investment Banking Workflows
SteerCast: Retrieval-Based Latent Steering for Decoder-Only Time Series Forecasting
AlphaPROBE: Alpha Mining via principled retriveval and on-graph biased evolution
mRNABench: A curated benchmark for mature mRNA property and function prediction
HiFloat4 Format for Language Model Pre-training on Ascend NPUs
Beyond MNIST: Limitations of Amplitude Encoding on Quantum Classification
DiReCL: Learning Differentiable Reward Code with Inverse Reinforcement Learning
Guided Data Generation for Understanding Model Behavior
ProxyPose: 6-DoF Pose Tracking via Video-to-Video Translation
Reasoning Under 1 Billion: Memory-Augmented Reinforcement Learning for Large Language Models
Model Guides You How to Draw: Adaptive Visual Gating for Unified Multimodal Reasoning
HoTS: Homophily-Aware Temperature Scaling for Graph Neural Network Calibration
StainNFT: Curriculum-Gated Multi-Reward Post-Training for Pathology-Faithful Virtual Staining
ReFPO: Reflow Regularization for Flow Matching Policy Gradients
Rare Disease Diagnosis Agent with Decoupled Workflows and Knowledge-Driven Self-Evaluation
SPIRAL: Self-Evolving Action-Conditioned Video Generation via Reflective Planning Agents
Geometry is an Operator: Lie-Algebraic Space Routing for View-Robust 3D MLLMs
HoloCode: A Code-Centric Multi-Agent Framework for Image-to-3D Scene Generation
PathNavigate: A Training-Free Pathology Agent with Surprise-Guided Scan and Shared Slide Memory for Whole-Slide VQA
P$^3$-VLM: A Point-based Alternative for Grounded 3D Vision-Language Models
WorldVLN: Autoregressive World Action Model for Aerial Vision-Language Navigation
Source-Causal Control of Historical Context in Longitudinal Radiology Report Generation
CHARM+: Cross-Hardware Attention with Re-Merge Multistream Mechanism
Stability-Weighted Direction Regularization Disentangles Generator Shortcuts from Detection Signal
SAGE: Semantic-Agnostic Image Embedding for Generalized AI-Generated Image Detection
Revealing Epistemic Uncertainty in MLLMs via Causal-Invariant Masking
VC-OPD: Visual Counterfactual On-Policy Distillation for Grounded Vision-Language Reasoning
CycleSpectra: Cyclic Motion Spectra for Phase-Queryable 4D Cardiac Reconstruction
Metropolis-Scale Road Network Datasets for Fine-Grained Urban Traffic Modeling
ProGraf: Profile-Guided Planning for Step-by-Step Generation of Structured Non-Natural Images
Correspondence Pruning by Iterative Structural Rectification
In STeP: Speculative Tensor Parallelism for Concurrent Heterogeneous Inference of LLMs
Blocked Gibbs meets Diffusion Transformers: Unsupervised Learning for Constraint Optimization
Minimizing Modality Gap from the Input Side: Your Speech LLM Can Be a Prosody-Aware Text LLM
Benchmarking Graph Self-Supervised Learning for Node-Level Tasks: Insights and Strong Baseline
Preference-Guided Adaptation for Open-Vocabulary Semantic Segmentation via Prompt Disagreement
Achieving Directional-Stationarity from a Single Random Direction Step
Best-of-$N$ Guidance for Test-time Diffusion Alignment
AOT-POT: Adaptive Operator Transformation for Large-Scale PDE Pre-training
Predicting Nothing Beats SAM 3: Revisiting Evaluation in Video Object Segmentation
DUET: Optimize Token-Budget Allocation for Reinforcement Learning with Verifiable Rewards
CrossWeave: Emergent Cross-Modal Scene and Instance Retrieval from Sparse 2D-3D Alignment
Learn where to Click from Yourself: On-Policy Self-Distillation for GUI Grounding
VidUEU-Agent: A Data-Curation Agent for Multimodal Understanding, Editing, and Unified Tasks
Dodge-It: Learning Collision-Aware VLA Models for Robotic Manipulation
To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents
FlowMAS: Learning Multi-Agent Workflow Topology via Information-guided Generative Flow Network
Multiscale Supervised Unbalanced Optimal Transport Flow Matching
From Chats to Markets: AgenticPay for LLM-Powered Negotiation in Multi-Agent Commerce
Skill-Adaptive Noise Scheduling for Diffusion Policies
Autonomous Scientific Discovery via Iterative Meta-Reflection
Disentangling Optimization Geometry via Hierarchical Polar Adapters for Class-Incremental Learning
Hyperagents
FeatCal: Feature Calibration for Post-Merging Models
NPCBench: A Clinical Apprenticeship Benchmark for Guideline-Constrained Care-Pathway Reasoning in Nasopharyngeal Carcinoma
Ground False: Uncovering Errors in Formal Mathematics Benchmarks
Boosting Multiagent Reinforcement Learning at High Replay Ratios with Ensemble Reset
Does Your Large Language Model Have An Intuitive Sense of The Difficulty of A Question?
In-Context Benign Overfitting: A Feature-Selection Model in Linear Regression ICL
Dynamic Delayed Tree Expansion For Improved Multi-Path Speculative Decoding
Utility-Constrained Policy Optimization
DiffRatio: Training One-Step Diffusion Models Without Teacher Supervision
UniCustom: Unified Visual Conditioning for Multi-reference Image Generation
Beyond Adjacent Layers: Graph-Guided Layer Fusion for Compressing Large Language Models
Answering At Any Cost: Frontier LLMs Are Consequence-Insensitive
Adaptive Multi-Frame Learning for Expressive and Stable Atomic Representations
Decoupling Time and Risk: Risk-Sensitive Reinforcement Learning with General Discounting
Characterizing the Aesthetic Defaults of Generative Image Models
Predicting the Needle in a Petabyte Scale Haystack: Open-Vocabulary Event Anticipation in Satellite Imagery
Overcoming Kernel Redundancy for Scaling Logic Gate Networks
UniForm: Segment-Aware GRPO for Joint Punctuation Restoration and Inverse Text Normalization
Pose6DAug: Physically Plausible Multi-View Object Swapping for Robot Data Augmentation
SRA: Spatial Reasoning Adapter via Evolving Social Interaction Graphs for Trajectory Prediction
SICAF: Time-Varying Focus Bottleneck for Self-Supervised Event-Based Optical Flow with Spiking Neural Network
GeoWorld: A Geometry-First World Model for Reconstruction and Imagination
Multimodal AI Detection In Two Words
Learning under Localized Minority Imbalance
No Model Required: Text Entropy Rate Filtering Prevents Iterative Fine-Tuning Collapse
Prompt Ensemble Image Purification for Test-time Adversarial Robustness of CLIP
Efficient Scaling of LLM Training with Flexible Context Parallelism
CoDMD: Copula-aware Distribution Matching Distillation for Fast Video Generation
The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning
Reformulate LLM Reinforcement Learning for Stable Training under Black-box Discrepancy
XTraj: A Coarse-to-Fine Autoregressive Framework for Transferable Trajectory Generation
Planning as Dynamics Relaxation: Hippocampal Recurrent Network Realizes Optimal Goal-Directed Navigation
Beyond Correctness: Robustness-Driven Evolutionary Self-Training for Large Language Models
GMO-E²DIT: Grounded Multi-Operation Editing for E-Commerce Images
Too Aligned to be Real: Detecting AI-Generated Images via Cross-modal Alignment Shift
FrequencyBooster: Advancing Pixel Diffusion for High-Fidelity Image Generation
SynGS: Synergistic Continual Learning and Change Detection with Gaussian Splatting
PhysFormer: Learning to Simulate Mechanics in World Space
ClothTransformer: Unified Latent-Space Transformers for Scalable Cloth Simulation
NORMA: Norm-Guided Explanation Subgraph Discovery
The road reaches every place, the short cut only one: Self-Adversarial Shortcut Mitigation for AI-Generated Image Detection
Touch-R1: Reinforcing Touch Reasoning in MLLMs
Making Open-Source Text LLM Watermarks Durable Against Merging
Local–Global Sparse Autoencoders for Multiscale Interpretability in Vision Models
PiCA: Pivot-Based Credit Assignment For Search Agentic Reinforcement Learning
Implicit Drifting Policy: One-Step Action Generation via Conditional Expert Geometry
SGD in Multiclass Logistic Regression: Sequential Learning and Scaling Laws
Functional Gradient Descent with Adaptive Representations
Discovering Programmatic Policies from Reinforcement Learning-Based Traffic Signal Controllers
Principled Design of Diffusion-based Optimizers for Inverse Problems
Why Latent Actions Fail, and How to Prevent It
Multiform Attack for Transferable Cross-Modal Person Re-Identification
Closing the Loop with Fixed-Point Self-Attention
Geometry-Constrained Kolmogorov–Arnold Networks: Learning Edge Geometry via Banach Duality
BrainEM: A Large-Scale and Diverse Benchmark for EM Neuron Segmentation in Connectomics
Temperature Guidance For Robust Reward Conditioning In Diffusion Planning
HandXFM: Semantic-Structural Distillation for Hand Radiograph Foundation Models
Disentangled Representation Learning via Flow Matching
Temporal Selective Exploration for Reinforcement Learning-Guided Continuous-Discrete Flow Matching in 3D Molecular Design
SageSched: Efficient LLM Scheduling Confronting Demand Uncertainty and Hybridity
Drift Q-Learning
WURI: Watching Unfolding Risk in Agent Interactions
Self-Supervised Reconstruction Knockoffs for Calibrated Unsupervised Feature Selection
Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation
Look Before You Reason: Implicit Visual Thinking for Efficient Multimodal Reasoning
OTROPE: Optimal Transport-based Robust Off-policy Evaluation for Large Language Models
SpreadsheetBench 2: Evaluating Agents on End-to-End Business Spreadsheet Workflows
Beyond the Readout: Reservoir State Statistics for Model-Space Learning under Sparse Observations
NarrativeBench: Benchmarking Multi-trait Automated Scoring and Feedback Efficacy of Large Language Models for Chinese Narrative Essays
PickMoment: Continuous-Time Single-Image-to-Video via Learning Deblurring and Blur-to-Video
ReGDiff: Guided Diffusion in Regulated Latent Space for Exploring Metamaterial Voxel Geometry
ODDR: One-Step Deshadow Diffusion via Reward Guidance
ABHBench: Evaluating Moral Decision-Making of Foundation Models from an Agentic Perspective
PerQ: Inverse Generative Modeling for Neural Image Compression via Quantization Error Compensation
CoupledFlow: One-Step Neural Operators for Coupled Multi-Physics PDEs
StructLens: A Structural Lens for Language Models via Maximum Spanning Trees
PolyTopoBench: A Benchmark for Complex Vector Polygon Generation from Remote Sensing Imagery
FlowLeak: Coverage-Guided Extraction of Dynamic Workflows in LLM-Based Multi-Agent Systems
Survive or Collapse: The Asymmetric Roles of Data Gating and Reward Grounding in Self-Play RL
Resilience Matters for Embodied Agents System: New Metrics, Systematic Evaluation, and Optimization
Fine-tuning Does Not Reach All: Uneven Safety and Knowledge Dynamics in Language Models
Auditing Single-Query Recoverability in Self-Supervised Representations
Evaluating Spatiotemporal Reasoning of Vision-Language Models in Atari Gameplay
Salvation Lies Within: Proactive Prefix Re-forming for LLM-based Tagging
Patch Hierarchical Attention Transformers for Efficient Particle Jet Tagging
What Does a Sparse Autoencoder Feature Do? A Weight-Based Account
INEUS: Iterative Neural Solver for High-Dimensional PIDEs
AlloSpatial: Agentic Harness Framework for Spatial Reasoning in Foundation Models
VLRS-Bench: A Vision-Language Reasoning Benchmark for Remote Sensing
Stage-Aware Dual Alignment for Covariate Shift in Graph Domain Adaptation
Structural Blindness in Latent Data Assimilation: Representation Geometry Misleads Sensor Design
ANCHOR: Audio-Visually Grounded Chain-of-Thought Reasoning Benchmark
G-PAC: Constructing Cohesive Pseudo-Features for Generalizable Physical Adversarial Camouflage
GGQR: Gaussian-Grounded Query Refinement for Feed-Forward 4D Gaussian Splatting
Certification-Enhanced Generalization Bounds
Unlocking Accurate Geometry in 3DGS via Spatially Varying Affine Rectification
Don't Pause! Every prediction matters in a streaming video
They Can See It but not Say It: Iterative Self Knowledge Re-expression in Visual Reasoning Relative Pose Identification
Position: Semantic Uncertainty Measures Disagreement, Not Reliability
Verifiable LLM-Guided Focal SMT Solving for Quantified Arrays
SpecLoR: Spectral Lookahead Rectification for Motion-Coherent Text-to-Video Generation
Dynamic Resolution Routing for Efficient Egocentric Grounding
Asymptotically Log-Optimal Bayes-Assisted Confidence Sequences for Bounded Means
Block Sphere Vector Quantization
ONE-SHOT: Compositional Human-Environment Video Synthesis via Spatial-Decoupled Motion Injection and Hybrid Context Integration
Skipping Domain Shifts: Domain Memory Retention Enhanced Hyperspectral Single-Source Domain Generalization
EP-Flow: Disordered Crystal Structure Prediction without Site-level Annotation
DC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion Convergence
Semantic-level Exploration for Multi-Agent Reinforcement Learning
LongSpike: Fractional Order Spiking State Space Models for Efficient Long Sequence Learning
Optimal Representation Size: High-Dimensional Analysis of Pretraining and Linear Probing
Distinguishing Performance From Competence in Evaluations of Humanlike Abstract Reasoning
T3-S2S: Training-free Triplet Tuning for Sketch to Scene Generation
GIVLA: Deep Geometry Internalization for A Lightweight VLA via Geometry Instruction and Gradient-Informed Training
An Efficient Cross-modal Feature Reconstruction Model for Multimodal Multi-class Anomaly Detection
ControlFlow3D: Distilling Multi-View Knowledge into Latent Flow Matching for Point Cloud Upsampling
COCOTree: A Dataset and Benchmark for Open Tree-Structured Visual Decomposition
Beyond Eigenfunctions: Divergence Principal Functions for Representation Learning
Hessian-Dependent Sample Complexity in Zeroth-Order Stochastic Optimization: Suboptimality of Convex-Support Sampling and Optimal Sample Complexity
Reliable Federated Multi-View Learning via Conflict-Aware Evidence Calibration
Extending Pretrained 10-Second ECG Foundation Models to Longer Horizons
Latent-space Attacks for Refusal Evasion in Language Models
Evaluating AI-based Scientific Knowledge Synthesis with Epidemiological Systematic Reviews
MonoChunk3D: Monocular Online 3D Instance Segmentation with Persistent Instance States
AETDICE: Unified Framework and Offline Optimization for Nonlinear Multi-Objective RL
StableHand: Quality-Aware Flow Matching for World-Space Dual-Hand Motion Estimation from Egocentric Video
Coordination Connectivity: Shared Initialization Shapes the Joint-Policy Landscape in MARL
Posterior Inference in Latent Space for Scalable Constrained Black-box Optimization
FlowHOI: Flow-based Semantics-Grounded Generation of Hand-Object Interactions for Dexterous Robot Manipulation
RiboC2F: Pose-First Coarse-to-Fine Flow Matching for Protein-Conditioned RNA Co-Design
Hitting Time Isomorphism for Multi-Stage Planning with Foundation Policies
ManiTaskGen: A Comprehensive Task Generator for Benchmarking and Improving Vision-Language Agents on Embodied Decision-Making
Seeing but Not Detecting: Privacy-Preserving Scene Text Attack via Hybrid Adversarial Policy Learning
Interpretable Relational Inference with LLM-Guided Symbolic Dynamics Modeling
Teach-to-Reason: Competition-Guided Reasoning with a Self-Improving Teacher
Learning Motion-Appearance Coupling Priors for Solving Video Inverse Problems
AnalogToBi: Device-Level Analog Circuit Topology Generation via Bipartite Graph and Grammar Guided Decoding
DN-Flow: Driver–Navigator Structured Flow Matching for Mixed-Type Tabular Data Generation
When Parallelism Pays Off: Cohesion-Aware Task Partitioning for Multi-Agent Coding
Reconstructing the Vocal Tract with Differentiable Acoustic Simulation
Manifold Random Features
SemISP: Semantic-Consistent Diffusion for Cross-Camera RAW-to-sRGB Generation
VeriVul: A Verification-Guided Framework for Generating Realistic Vulnerability Benchmarks
BitDance: Scaling Autoregressive Generative Models with Binary Tokens
DySurface: Consistent 4D Surface Reconstruction via Bridging Explicit Gaussians and Implicit Functions
RelationVGGT : Visual Geometry Transformers for 3D Spatial Relation Segmentation
SaaS-Bench: Can Computer-Use Agents Leverage Real-World SaaS to Solve Professional Workflows?
RoadmapBench: Evaluating Long-Horizon Agentic Software Development Across Version Upgrades
Step-wise Rubric Rewards for LLM Reasoning
Efficient Brain-to-Speech Decoding with Fixed-Delay Spiking Neural Networks
Neural Signals Generate Clinical Notes in the Wild
Evaluating Physical Reasoning in LLM Agents Requires Construction Benchmarks
Irreducible Supervision Enables Compositional Generalization in Post-Training
Multi-view Relational Distillation for Spatial Reasoning with Vision-Language Models
Knowing When to Ask: Segment-Level Credit Assignment for LLM Tool Use
Benchmarks Design under Data Scarcity: From Coarse Labels to Diagnostic Evaluation of Biosynthetic Gene Cluster Models
ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Driving
SIMBAD: Spatio-Temporal Traffic Forecasting Robust to Aperiodicity
Majority-of-Three is an Optimal PAC Learner
MUX: Continuous Reasoning via Multiplexed Tokens
SeoulMMOD: A Large-Scale Multimodal Origin-Destination Flow Benchmark
FlexMoE: One-for-All Nested Intra-Expert Pruning for MoE Language Models
Querying Counterfactuals on Tissue Graphs with Supervised Disentanglement
BALTO: Balanced Token-Level Policy Optimization for Hallucination Mitigation
DAGent: Evaluate-then-Grow Planning for Deep Research Agents
Keep or Preempt? Termination-Aware Scheduling for LLM Serving with Speculative Decoding
Towards Effective and Transferable Physical Camouflage against Multi-View BEV-based 3D Perception in Autonomous Driving
VAANI: Capturing the language landscape for an inclusive digital India
METAFORGET: Audit-Driven Update-Policy Learning for Reliable Language Model Unlearning
Enhancing Speech Large Language Models through Reinforced Behavior Alignment
Beyond Average Flatness: Domain-wise Flatness for Domain Generalization
Nash Social Welfare for Multi Armed Bandits: Trajectory-wise Expected and High Probability Regret
QUTCC: Quantile Uncertainty Training and Conformal Calibration for Imaging Inverse Problems
MindAlign: Bridging EEG, Vision, and Language for Zero-Shot Visual Decoding
Social Choice Foundations for Simulation-Augmented Generation
Neural Refraction Fields for Image Verification
MotionCFG: Boosting Motion Dynamics via Semantic Motion Sharpening
Mesh BDF: Barycentric Dominance Field for 3D Native Mesh Generation
Not Only Where, But When: Temporal Scheduling for RLVR
Weisfeiler-Leman Is Incomplete on Simple Spectrum Graphs, so Canonicalize Them
What Drives Test-Time Adaptation for CLIP? A Controlled Empirical Study from an Update Perspective
CLEAR: Complementary Tripartite Play with Bayesian Calibration for Semi-Supervised Edge Classification
Complementary Cache Guidance with Gradient Disentanglement for Continuous Test-Time Adaptation
A Systematic Evaluation of Co-folding Model Representations for Small-Molecule Learning
Fast KVzip: Efficient and Accurate LLM Inference with Gated KV Eviction
Robust PAC Learning of Concurrent Stochastic Games
Mark, Don't Erase: Token Inoculation for Dual-Use Knowledge in LLMs
OperatorSHAP: Fast and Accurate Shapley Value Estimation for Neural Operators
MySign: A High-Fidelity Motion-Capture Dataset for 3D Sign Generation in Bahasa Isyarat Malaysia
Concept-Based Mechanistic Interpretability Needs a Concrete Evaluation Paradigm
Pairwise AUC Optimization Needs Corrective Power: A Unified View
Improved Sample Complexity for Markov Games via Variance-Aware Bandit Learning
Orlicz–Sobolev with Musielak: An Efficient Regularization Approach for Graph-based IPM
When Does Structure Help? Statistical Tradeoffs for Structured Reverse Processes in Diffusion Large Language Models
FOAM: Factored One-sided Adam-Moment for Practical and Scalable SOAP
Training-Free Entangler Selection for Quantum Neural Networks via Hilbert–Schmidt Geometry
On the Necessity of Guidance Decay: From Three-Phase Analysis in Gaussian Mixture Models to Dynamic Optimization
Exact power indices for plurality-voting ensembles
No Free Best-of-Both-Worlds Learning in Repeated Bilateral Trade
Known By Their Actions: Fingerprinting LLM Browser Agents via UI Traces
Learning Robust Reasoning through Guided Adversarial Self-Play
MissPath-FM: Flow Matching with Structured Priors for Partially Observed Time Series
Spectral Adaptive Repositioning for Flow-Based Single-Cell Perturbation Modeling
From Ideas to Code: Tree-structured Policy Optimization for Automated Algorithm Design with LLMs
Conditioning Gaussian Processes on Almost Anything
Efficient Pre-Training with Token Superposition
Hierarchical Adaptive Frame Sampling For Video Understanding
The Curse of Multiple Mediators: Hidden Interaction Effects in Activation Patching
Beyond Unidirectional: Unsupervised Trajectory Learning for Omnidirectional Controllable Underwater Image Enhancement
Fed-AGA: An Anchor Graph Alignment Framework for Federated Unaligned Multi-view Clustering
Bayesian Optimization with Fisher Information Geometry: Gradient Bounds and Trust-Region Methods
FoldAbS: Repurposing the Protein Folding Model as a Foundation Encoder for Antibody Screening
Network Intervention by Polling Strategic Agents
Test-Time Sequential Steering of Diffusion Models via Preconditioned Crank-Nicolson
Collective Supervision for Unified Biomolecular Conformation and Dynamics Modeling with CoDyna
TrajLift: Encoding Verbal Memory Dynamics via Heat Diffusion on Semantic Hierarchies
PhGPO: Pheromone-Guided Policy Optimization for Long-Horizon Tool Planning
NavOCR: A Dataset Generator for Navigation-Relevant Text Detection in Mobile Robots
Transductive Generalization for GNNs via Optimal Transport
RepoMirage: Probing Repository Context Reasoning in Code Agents with Perturbations
Stress Testing Chain-of-Thought Monitoring Against Covert Misalignment
Bet Imaginatively, not Historically in Independent-Data Sequential Testing
Fine-Grained Benchmark Generation for Comprehensive Evaluation of Foundation Models
VicEdit: Learning to Edit Videos from Visual In-Context Examples
Second-Order Complexity Theory for Neural Networks
SurGe: Improved Surface Geometry in Point Maps
Towards Scalable Data Diversification for Language Model Pretraining via Leverage Score Sampling
Seeing Together, Acting Apart: Shared Environmental Understanding for Multi-Robot Navigation
A Benchmark for Omni-Modal Reasoning in Long Videos
When Poison Meets Structure: Topology-based Defense against Poisoning Attack on Graph-based Retrieval-Augmented Generation
Fed-SB: A Silver Bullet for Extreme Communication Efficiency and Performance in (Private) Federated LoRA Fine-Tuning
EgoTac: In-the-wild Tactile Prediction from Egocentric Vision
DexOPE: 6D Object Pose Estimation in Dexterous Manipulation
Discovering dynamical parameters of synthetic multicellular systems from image sequences
FourierMoE: Fourier Mixture-of-Experts Adaptation of Large Language Models
MedIGen: Reliable Medical Illustration Generation via Interleaved Introspective Reasoning
Bilinear Matching Bandits
GPA: Generative Population Annealing for Test-Time Sequence Design with Pretrained Generative Models
Verification-Aware Training for Speculative Decoding
Iterative Nonlinear Computation Underlying Abstract Reasoning
Text-Vision Co-Instructed Image Editing
Jointly Reinforcing Diversity and Quality in Language Model Generations
The Laplacian Keyboard: Beyond the Linear Span
Anchoring Physiological Invariance, Expanding Domain Plasticity: Prior-Stabilized Dynamic Adaptation for Continual rPPG Measurement
Phase-wise Velocity Distillation: Towards Effective Image Generation with A Single NFE
Rethinking Bayesian Optimization for Co-Optimizing LLM Training Configurations
Rethinking CT Synthesis through Semantics-Structure Alignment
$\texttt{RNAGenScape}$: property-guided, optimized generation of mRNA sequences with manifold Langevin dynamics
What Do Audio Models Really Hear? Layer Selection and Mechanistic Structure in Sound Representations
EnvTrap: Revealing the Environment-Only Attack Surface in Embodied AI via Consequence-Blind Action Execution
Understanding the Effects of Hyper-Connections on Self-Attention Dynamics: A Bifurcation Analysis
Aggregation Dispersion: An Information-Geometric Diagnostic of Oversmoothing in Graph Neural Networks
More Than Meets the Eye? Uncovering the Reasoning-Planning Disconnect in Training Vision-Language Driving Models
Meta-TTRL: A Metacognitive Framework for Self-Improving Test-Time Reinforcement Learning for T2I Generation in Unified Multimodal Models
L-FAME: Longitudinal Focused Attention Meditation EEG Dataset and Benchmark
MindGuard: Guardrail Classifiers for Multi-Turn Mental Health Support
Pretraining Data Statistics Shape the Phases of Learning Entity Comparison in Language Models
Self-EvolveRec: Self-Evolving Recommender Systems with LLM-based Directional Feedback
PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization
Clustering-Free End-to-End Spoof Diarization with Encoder-Decoder Attractors
Personalize-then-Store: Benchmarking and Learning Personalized Memory for Long-Horizon Agents
Beyond DSA: Conjugacy-based Comparison of Dynamical Systems
WirelessMathBench-XL: A Contamination-Audited Benchmark for Wireless Mathematical Reasoning
Sparse Biological Features Reveal Early Functional Commitment in Diffusion Protein Language Models
Measuring Collapse and Correction in Homogeneous-Panel LLM Debate
TailCon: Mitigating Tail Signal Erosion through Memory Consolidation for Long-Tailed Recognition
Narrative Paradoxes in LLM Inference: Shaping Reasoning Trajectories toward Misalignment
Conformal Agent Error Attribution
GUARD: Scalable Gradient-based Unlearning with Adversarial Robustness Defense
LibEvoBench: Probing Temporal Knowledge Stratification in Code Generation Models
Improved Robust Verifiable Federated Learning Based on Packed Secret Sharing
BBOWP-Bench: Evaluating LLMs on Black-Box Optimization Word Problems
Robust Statistical Estimators with Bounded Empirical Sensitivity
Reference-Guided Training: Adaptive Gradient Scaling via Per-Sample Loss Comparisons
Long-term Embodied Visual Tracking with Lightweight Vision-Language-Action Models
Provable Robustness against Backdoor Attacks via the Primal-Dual Perspective on Differential Privacy
Early Semantic Grounding in Image Editing Models for Zero-Shot Referring Image Segmentation
Post-Training Quantization with Gradient-Projected Fisher Approximation for Vision Transformers
Simple Extensions of Single-Objective Acquisition Functions and Hedge Strategies for Multi-Objective Bayesian Optimization
Stop or Restart? Principled Inference Control for Large Reasoning Models via the Pandora's Box
Sparse Repair in Reasoning Traces: A Structural View of Test-Time Inference
PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping
Learning-Augmented Online Portfolio Selection: Optimal Robustness-Consistency Tradeoffs
High-Dimensional Learning Dynamics of Attention-Indexed Models
Parabolic Position Encoding: Vision-Centric, Principled, Extrapolatable, General
MapPFN: Learning Causal Perturbation Maps in Context
Newton-PINet: A fast physics-informed neural network with Newton linearization for meta-learning nonlinear PDEs
Verification-Guided Abstraction Generation with Large Language Models for Generalized Planning
CyberDualEval: Measuring Dual-Use Cyber Risks in Frontier Language Models
Neural Quantum Spectral Operator Learning for Solving Partial Differential Equations
Unveiling Implicit Advantage Symmetry: Why GRPO Struggles with Exploration and Difficulty Adaptation
Co-Evolving Policy Distillation
SPA-Q: Structure-Preserving Adaptive Post-Training Quantization for Monocular Depth Estimation
Online Directional Regression for Streaming Sufficient Dimension Reduction
Self-Distilled RLVR
What Survival Benchmarks Don’t Tell You: Impact of Model Selection and Dataset Regimes
VINCIE-NExT: Unlocking Video Editing from Images via In-Context Modeling
Harnessing Streaming Video in the Wild
The Price of Choosing Examples: Context Overfitting in Adaptive In-Context Learning
Anytime-Valid PAC-Bayes Certificates for Adaptive Test-Time Scaling
ProQuant: Progressive Quantization-aware Training for Edge MLLMs
Sparse Planning in Visual World Models via Cost Gradients
Selective Answering for Medical VQA via Parallel Independent Claim Verification
Rich Insights from Cheap Signals: Efficient Evaluations via Tensor Factorization
Offline Inverse Reinforcement Learning with Unified Diffusion Planning
PRISMIC: Reconstructing User Preference via Intent Decomposition and Consolidation
Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds
Attention Sinks Induce Gradient Sinks: Massive Activations as Gradient Regulators in Transformers
What do EEG Foundation Models Capture from Human Brain Signals?
GCD: GCM-consistent Diffusion for Zero-shot Downscaling across Heterogeneous GCMs
Structure-Guided Masked Autoencoders for Ultra-High Resolution Scientific Image Understanding
Microstructure Descriptor Fields as Supervision for Scientific Images
Deep Research as Rubric
Expanding Flow Maps
TALES: Text-Adventure Learning Environment Suite
Causal discovery needs explicit epistemic standards
ADA: Resolving Attribution Ambiguity in End-to-End Power System Dispatch via Two-Time-Scale Stochastic Approximation
SynDORBench: Evaluating LVLM Perceptual Robustness Under Physically Constrained Visibility Conditions
Prospective Hindsight: Self-Calibrating Reinforcement Learning via Prediction–Reality Gaps
DynaCell: an Evaluation Framework for Dynamic 3D Virtual Staining of Live Cells
Fine-Detail Monocular Geometry Estimation with Self-Guided Sparse Volumetric Refinement
Multilingual Safety Alignment via Self-Distillation
Bridging the Gap Between Harmfulness Belief and Refusal Behavior for Safety Alignment
Sandboxed Coding Agents are Competitive Omni-modal Task Solvers
MSAR: Next-Scale Autoregressive Forecasting for Time Series via Modular Multi-Scale Decoupling
Nuwa: Evaluation-Grounded Agentic Construction of Time Series Forecasting Systems
What Claims Do LLM Benchmark Scores Support?
Adaptive Residual Quantization for Memory-Efficient Temporal Action Segmentation
When LLMs Know but Fail to Reason: Injecting Memory for Reasoning Enhancement
CounterFlowNet: From Minimal Changes to Meaningful Counterfactual Explanations
Where Are MLLMs Looking When They Hallucinate? Mitigating Visual Hallucination via Gaze Steering
FLINT: Coupling Proximal Initialization and Bounded Stochasticity for Flow-Matching Inverse Problems
Understanding and Defending VLM Jailbreaks via Jailbreak-Related Representation Shift
Bidirectional Sparse Attention for Faster Video Diffusion Training
Interaction-Aligned Robot Learning from Human Videos with Structured Graph Modeling
PhysTacGen: Physics-Aware Visual-Tactile Sensor Image Generation
Noise-Regularized Training for Learned Image Compression
Aligning MLLMs with the Latent Structure of Human Cognition via Behavior-Derived Semantic Dimensions
Learning to Discriminate Scene Structures Makes Self-Supervised Depth Learning Scalable
Multi-Step Likelihood-Ratio Correction for Reinforcement Learning with Verifiable Rewards
Capricorn: Highly Efficient and Secure Mixture of Experts Inference Framework
Conformal Prediction for Time-Dependent PDEs
Forced Orders: What LLM Leaderboards Hide About Model Comparisons
Breaking Noise Shortcuts in Self-Supervised Learning via Noise-Aligned View Generation
ShadowFPT: Backdooring Federated Prompt Tuning via Shadow Triggers
$\mathcal{P}$Torch: Narrowing the Gap Between Projection and Gradient-Based Learning
UpSafe℃: Upcycling for Controllable Safety in Large Language Models
Nexus: Same Pretraining Loss, Better Downstream Generalization via Common Minima
InduceKV: Fixed-Footprint Continual Adaptation of Multimodal LLMs via Inducing KV Memories
Value-Rectified Distillation for Flow-based Offline Reinforcement Learning
Kernel-Gradient Drifting Models
TailAdapt: Heavy-Tailed Sparse Variational Adaptation for Long-Tailed Class Incremental Learning
FRInGe: Distribution-Space Integrated Gradients with Fisher–Rao Geometry
Block-OBS-GS: Exact Per-Block Joint Brain Surgery with Gauss–Seidel Refinement for LLM Pruning
TwinPrune: Density-Aware Two-Phase Token Pruning for Vision-Language Models
Canopy: Tree-Aware Rollout Scheduling for Agent Reinforcement Learning
Active Learning as Nullspace Regulation: A Spectral Representation Perspective
LaST-R1: Reinforcing Robotic Manipulation via Adaptive Physical Latent Reasoning
Static-to-Dynamic: Animating Still Mattes via Generative Motion for Video Matting
Can We Trust Item Response Theory for AI Evaluation?
Rethinking Personalized Generation: Test-time Alignment via Factorized Ranking Models
SC$^3$: A Multi-Solvent Solubility Challenge and Benchmark
MASTA: A Feedback-Scheduled Multi-Agent System for End-to-End Tamarin Protocol Modeling and Analysis
Verified-Source Authority Is Not Generic Sycophancy: Cue-Family Decomposition of LLM Compliance
VideoMDM: Towards 3D Human Motion Generation From 2D Supervision
NP-LoRA: Null Space Projection for Subject-Style LoRA Fusion
GraphUAT: Uncertainty Attribution in Graph Neural Networks
Gradient-Free Editing for Attribute Invariance in Graph Neural Networks
Why DiT Models Underperform as Representation Learners without Long Skip Connections
SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation
Self-Improving World Modelling with Latent Actions
HOGWARTS: Mitigating Perspective Distortion for 6DoF Head Pose Estimation via Virtual Camera Space
SANEval: Open-Vocabulary Compositional Benchmarks with Failure-mode Diagnosis
When Should Agents Remember? Falsification-Gated Self-Evolution for LLM Agents
Higher-Order Cell Tracking Transformer
LITHE: Lattice-Indexed Twin Hadamard Encoding for Diffusion Personalization
Why Jailbreaks Succeed in Diffusion Language Models: An Energy Landscape Analysis
CausalAffect: Causally Guided Learning of Psychology-Aligned Facial Affect Relations
Improving the Diffusability of Motion Tokenizer
Even Sailors Need Calm Seas: Taming the Geometry of VLMs for Fast Adversarial Fine-Tuning
FairMT: Fairness for Heterogeneous Multi-Task Learning
Beyond Outcome Rewards: Process-Aware Optimization for Search Agents
Tool-Integrated Reasoning via Hierarchical Multi-Agent Reinforcement Learning
Adam under Generalized Smoothness with Second-Moment-Type Stochastic Gradients
Negative-Only Policy Optimization for One-Sided Verifiable Rewards
Backtracking with Linear-in-Depth Search-Space Growth: Width-Limited Tree Search for Large Language Models
B[FM]$^2$: Brain Foundation Model via Flow Matching with SplitUNet
CompJudge: Fine-Grained Comparative Evaluation using Multimodal LLM for Subject-Driven Generation
Exploring Starts Are Not Enough: Counterexamples and a Fix for Monte Carlo Exploring Starts
InfoFlow: A Framework for Multi-Layer Transformer Analysis
GUIGuard-Bench: Toward a General Evaluation for Privacy-Preserving GUI Agents
Black-Box Uncertainty Quantification for Large Language Models via Ensemble-of-Ensembles
PATH: A Dual Perspective for High-quality Text-attributed Graph Learning
When Edge Independence Fails: Joint Graph Diffusion with Latent Sociability Priors
Adaptive Random Forests from Online Learning and Testing by Betting
DPIAgent: Divide, Protocol, Isolate for Agentic Reproduction Test Generation
Human-AI Teaming Through the Lens of Calibration
Constrained Factorization with Diagonal Scaling: Rank-Revealing Training and Pruning
State of Thought Enables Endogenous Reasoning
Intent2CAD: How Semantic-Parametric Supervision Shapes Text-to-CAD Generation
SceneShifter: Training-free Multi-Scene Temporal Control for Audio-driven Human Animation
Rank-Constrained Adaptation for Reliable Real-World Performance
MemCoRe: Recovering Evidence from Progressively Compressed Factual Knowledge for Agent Memory
Reproducibility study of "Bilinear MLPs enable weight-based mechanistic interpretability"
VocalCoachBench: Benchmarking Audio-Language Models on Expert Feedback for Singing
SETA: Scaling Environments for Terminal Agents
Ensuring Deployment-Time Safety of Neural Network Controlled Systems via Localized Certificate Repair
Do We Really Need Diffusion for Generative Object Detection? A Minimal Prototype Perspective
Iterative Scarcity-Guided Exploration: Bootstrapping Generative Auto-bidding from Narrow Support
IGGT4D: Streaming 4D Instance-Grounded Geometry Transformer
Ask KG Agent: A Multi-Agent Framework for Code Localization Using Code and Knowledge Graphs
PipeFSDP: Efficient Pipeline Parallel under Fully Sharded Data Parallel for Large Language Model Training
CLaW: Codec-Guided Adaptive Latent Watermarking for Traceable Diffusion Image Generation
FusionNeXt: Sequence-First 3D Multi-Modal Fusion in the Era of LLMs
Forgery Evidence Peaks Mid-Stack: Forensic Evidence Relay for Multimodal Forgery Detection
Values Are Not Single Labels: Distributional Value Profiling Across Groups and Contexts
Block-R1: Rethinking the Role of Block Size in Multi-domain Reinforcement Learning for Diffusion Large Language Models
Grasp-Then-Plan with Failure Attribution: A Closed Two-Stage Framework for Precise and Generalizable Robotic Manipulation
M3-HNTM: Hyperspherical Multimodal Topic Modeling with Symbolic and Contextual Evidence
From Generic to Dedicated: A Novel Optimizer for Online Continual Learning
Attention Heads are Complementary Visual Units: Mitigating Hallucinations in LVLMs via Adaptive Visual Cues Focusing
Breaking the $\sqrt{d}$ Communication Barrier in Federated Sampling with Adaptive Hamiltonian Monte Carlo
Minimax Rates and Spectral Distillation for Tree Ensembles
DiffCool: Label-Free Synthesis of Chip-Tailored Heat Sinks via Thermal-Aware Diffusion
SpikingGamma: Temporally Precise Online SNN Training Through Smoothed Temporal Delays
IDEA: Unwrapping Visual Black-box Models by Interaction Decomposition
Collapse Hunter: Tackling the Dimensional Degeneration in Generative Ranking
TeMPO: Frame-Causal Token Compression for Efficient Video Large Language Model
Uncovering Semantic Hierarchies in Text-Attributed Graphs via Variational EM-based LLM–GNN Synergy
ATI-VLA: Action-Centric Predictive Vision–Language–Action Models via Actionable Alignment Then Adaptive Injection
Towards Financial World Modeling
PROLA: Principal-Orthogonal Low-rank Adaptation for Predictive Spatiotemporal Weather Downscaling
Systematic Hazard Sampling: Minimal-Variance Inference for Discrete Diffusion and Flow Models
Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?
DexMirror: Real-to-Sim Scene Mirroring for Sim-to-Real Dexterous Manipulation
AssayBench: An Assay-Level Virtual Cell Benchmark for LLMs and Agents
Articulation in Prime: Primitive-Based Articulated Object Understanding from a Single Casual Video
TPO: Tri-level Distributionally Robust Learning for OOD Direct Preference Optimization
PlasticMem: Adding Temporal Reasoning to Diffusions for Consistent Long Video Generation
Progressive Residual Warmup for Language Model Pretraining
Improving Consistency in Retrieval Augmented Systems With Group Similarity Rewards
Normalized Friedkin–Johnsen Opinion Dynamics
Angular Networks: Low-Bit Learning from Randomized Similarity Estimators
Mitigating Knowledge Conflicts in Retrieval-Augmented Generation via Inference-Time Representation Editing
Beyond Parameter Arithmetic: Sparse Complementary Fusion for Distribution-Aware Model Merging
Feedback World Model Enables Precise Guidance of Diffusion Policy
Not All Layers Are Equal in Image-to-Video Transfer
ProCLIP: Progressive Vision-Language Alignment via LLM-based Embedder
Amortizing Generative Guidance for Model-Based Reinforcement Learning
Unifying Contrastive and Generative Objectives for Visual Understanding and Text-to-Image Generation
Learning from Disagreement: Multi-Teacher Distillation for Chinese Spelling Correction
MoEZip: Routing-Aware KV Cache Compression for Sparse Mixture-of-Experts LLMs
Interleaved Head Attention
Learning Discrete Riemannian Metrics for Physical Fields with Cochain-Frame Equivariance
DGRAF: Observation-Quality-Aware Reinforcement Learning for Dynamic Reconfigurable Batteries
AVIS: Adaptive Test-Time Scaling for Vision–Language Models
Prism Attention: Proposal-Refined Index Sharing Mechanism for Efficient LLMs Inference
StaDy: Factorizing the World into Static and Dynamic via Likelihood Matching
Mixture-of-Experts for Online Matrix Completion on a Drifting Union of Subspaces
Bridging Scene Generation and Planning: Driving with World Model via Unifying Vision and Motion Representation
Attribution-Guided Shared-Private Decoupling for Noise-Reduced Audio-Visual Representation Learning
Deep Barycentric Regression for Optimal Transport Map Estimation and its Statistical Optimality
Beyond the Grid: Continuous Dictionary Pursuit for Interpretable Signal Decomposition
Multimodal LLMs Outperform Pathology Foundation Models in Cross-Domain Histological Similarity
On the Information Loss of Multi-Token Prediction: Origin and Solution
ASTRA: ADMM-Accelerated Topology Reconfiguration for Dynamic Satellite Constellations
Senses Wide Shut: A Representation-Action Gap in Omnimodal LLMs
Simple yet Effective Semi-supervised Knowledge Distillation from Vision-Language Models via Dual-Head Optimization
ControlJEPA: Principled Trajectory Regularization via Lyapunov Tube Loss
TasteBench: multimodal benchmark for sensory prediction, from molecules to sustainable foods
Recovering Evolving User Preference State via Adaptive Interaction-aware Representation Correction
Memorize When Needed: Decoupled Memory Control for Spatially Consistent Long-Horizon Video Generation
DocAtlas: Long-Document Understanding as Mutable-State Interaction
Learning to Audit ML Models with Theory of Mind
Propagation of Chaos in Contextual Flow Maps
XL-DocBench: Benchmarking Evidence-Grounded Extra-Long Document Understanding
Evolutionary System Prompt Learning for Reinforcement Learning in LLMs
Biological Graph Priors Enable Representation Learning for Cellular Microscopy
VLM$^3$: Vision Language Models Are Native 3D Learners
Learning From Failures: Efficient Reinforcement Learning Control with Episodic Memory
TReDS: Trajectory-Grounded Requirement-Capability Modeling for Training Distribution Shaping in Tool-Interactive Tasks
AffordSim: A Scalable Data Generator and Benchmark for Affordance-Aware Robotic Manipulation
Learning Planning Budgets in Real-Time RL
End-to-End Neural Modeling of EM Response and Design Performance for Free-Form RFIC Passives
SkillOpt: Executive Strategy for Self-Evolving Agent Skills
From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills
Sample Size Design for Bounds on Discrete Probabilities of Causation
Tracing Persona Vectors Through LLM Pretraining
Distributional Alignment as a Criterion for Designing Task Vectors in In-Context Learning
Same Concept, Different Directions: Cross-Modal Feature Heterogeneity in Sparse Autoencoders
Nonlinear Direct Feedback Alignment for Scalable Backpropagation-Free Training
Frank-LoRA: Federated Rank-Aware LoRA for Fine-Tuning Large Models
Visual Harness: Grounding Multimodal Reasoning in Physics Engines
DISCOVER: Online Variance-Guided Data Discovery for Budgeted Multimodal GRPO
Learning Human-Intention Priors from Large-Scale Human Demonstrations for Robotic Manipulation
Flow+Diff: Unifying Flow and Diffusion Representations for Multivariate Time Series Anomaly Detection
Improving Flexible Image Tokenizers for Autoregressive Image Generation
Addressable Memory for Video World Models
Entangled Schrödinger Bridge Matching
When Attention Closes: How LLMs Lose the Thread in Multi-Turn Interaction
Permit: Permission-Aware Representation Intervention for Controlled Generation in Large Language Models
Hybrid Neural World Models for Physical Dynamics
Structured State-Space Regularization for Generation-Friendly Image Tokenization
ReCon: Toward Balanced Learning under Inter-Context and Context-Memory Conflicts
Distillation of Foundation Models for Time-dependent PDEs
A Unifying View of Anchoring via Operator-Side Tikhonov Regularization
IDEAL: In-DEpth ALignment Makes A Discrete Representation AutoEncoder
Selective Rollout: Mid-Trajectory Termination for Multi-Sample Agent RL
Natural-Language-Guided Protein Generation for Ligand-Binding Design
Oversmoothing as Representation Degeneracy in Neural Sheaf Diffusion
Ego-HMB: Human Motion Bridging from Egocentric Images via Motion Bridge Diffusion Model
Early Failure Detection and Intervention in Video Diffusion Models
TED: Text-Axis Evidence Decomposition for Prompted Anomaly Localization
DecQ: Detail-Condensing Queries for Enhanced Reconstruction and Generation in Representation Autoencoders
Statistical Limits of Affine Equivariant Estimation
HyperSkill: Multi-Modal Skill Learning on the Unit Hypersphere
Mind the Parameters: Lightweight and Efficient Brain Visual Decoding with Shared Tensor Cores
Channel-wise Vector Quantization
Reusable Conditional Resampling via Flow Matching for Constraint-Based Causal Discovery
Fault Tolerance in Transformers Favors Output Alignment over Hidden-State Consistency
Extraneous Cognitive Load in Large Language Models
Optimal Risk Bounds of Stochastic Gradient Descent for Shallow ReLU Networks
MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping
Large Language Models Develop Belief State Geometry In-Context
ReSAM: Representation-Level Safety Margin Alignment for Vision–Language Models
FEAD: Fine-Grained Epipolar Attention Diffusion for Large-Disparity Light Field Spatial Super-Resolution
The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation
InvestigationWorlds: An Agentic Environment for Legal Investigation
Binary Regression: Universal Ising Model, Binary Expansion and Beyond
A2Eval: Agentic and Automated Evaluation for Embodied Brain
Factorized Gradients for Scalable Highly-expressive Parametric Diffeomorphisms
AEGIS: Adaptive Efficient Generative Inference Scheduling for Structured Latent Models
Uncertainty Quantification for Multimodal Large Language Models with Incoherence-adjusted Semantic Volume
Improved State Mixing in Higher-order and Block Diagonal Linear Recurrent Networks
PhyMo: Learning Physical Dynamics with Accurate and Continuous Motion from Multi-View Videos
Target-Aware Nuisance Shaping for Object Detection
Editing Large Language Models with Geometry-Aware Regularization
Selectivity Makes State-Space Models Universal Sequence Approximators
Rethinking Sequential Locate-Then-Edit: Optimality and Stability
Pretext Reasoning: Scaling the Building Blocks of Interleaved Multimodal Reasoning
VidVec: Unlocking Video MLLM Embeddings for Video-Text Retrieval
WebSpatial: A Benchmarking Framework of Spatial Intelligence via Web-based Runtime Environments
Beyond Outcome Rewards: Step-Level Self-Distilled Policy Optimization for Deep Search Agents
WAREX: Web Agent Reliability Evaluation on Existing Benchmarks
DyCoRM: Dynamic Criterion-Aware Reward Modeling for Text-to-Image Generation
Relative Energy Barriers for Copyright-Aware Language Model Adaptation
Inductive Deductive Synthesis: Enabling AI to Generate Formally Verified Systems
RCSTAT: A Statistical Framework of Relative Contextualization in Transformers
VI-Bench: Benchmarking Prompt Inversion from AIGC Videos
Beyond difficulties: Insights for provably efficient design of autocurriculum in RLVR
Communication-Efficient Federated Learning of Latent Patient Representations from Multi-Institutional EHRs
Continuous Open-ended Discovery and Evolution of Skills as Hierarchical Reward Programs
Avoiding Obfuscation with Prover-Estimator Debate
Circuit-Level Knowledge Distillation for Large Language Models
Query-Limited Community Recovery in Stochastic Block Models
PREPING: Building Agent Memory without Tasks
U-MVP: Encode Locally, Decode Globally for Feed-Forward 3D Gaussian Splatting
TIMA: Test-Time Internalization for Agentic Memory
ThinkSafe: Self-Generated Safety Alignment for Reasoning Models
A Near-optimal SQ Lower Bound for Smoothed Agnostic Learning of Boolean Halfspaces
Soft geometric inductive bias for object centric dynamics
BlendCast: Teaching Vision-Language Model to Anticipate Member Skill in Weather Ensembles
High-arity Sample Compression
Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models
A Local Geometric Analysis of Maximal Coding Rate Reduction via Error Bounds
Asymmetric Generalization in Deep CTR Models: A Block-wise Diagnosis
Approximate Memory Suffices for Universal Approximation with State Space Models
TrackFish3D: Self-Supervised 3D Tracking of Schooling Fish from Multi-view Videos
Training Deliberative Monitors for Black-Box Scheming Detection
ProtGlycanDock: Towards Accurate Protein-Glycan Docking with Tailored Dataset, Benchmark and Model
AKTD: FDR Control for LLM Training Data Detection under Approximate Exchangeability
EAT: Eviction-Aware Training for Long-Context LLM Inference on Edge Devices
STRIDE: Automated Evaluation of Text-to-Trajectory Alignment across Diverse Contexts
Minimax Optimization without Spurious Solutions in Optimal Transport Learning
NEXUS: Neural Energy Fields for Physically Consistent Contact-Rich 3D Object Dynamics
EMO: Pretraining Mixture of Experts for Emergent Modularity
VisGym: Diverse, Customizable, Scalable Environments for Multimodal Agents
From Solver Trajectories to Teaching Trajectories: Cognition-Aligned Reasoning Distillation
Beyond IID: How General Are Tabular Foundation Models, Really?
HuPER: A Human-Inspired Framework for Phonetic Perception
Efficient One-Step Diffusion Restoration Model with Compact Token Compression and Linear Attention
MT-CC: Multi-Group Temperature Scaling for Asymmetric Calibration Behavior in Class-Incremental Learning
GRINQH: Graded Input-based Quantization Hierarchy for Efficient LLM Generation
BASIL-DCM: Biophysical Amortized Scalable Inference for Latent Dynamic Causal Modeling
Ripple in Still Water: Zero-Shot Clustering in Heterogeneous Federated Learning with Wavelet Scattering Transform
SamaDICE: Safe Multi-Agent Reinforcement Learning with Stationary Distribution Correction Estimation
How Diffusion Models Memorize
Precision-Aware Hopfield Retrieval: Unifying Population Codes and Memory Retrieval with Information Optimization
AdaMAP: Learning Adaptive Multi-Action Prediction with Grounded Dreaming Guidance
Unified Loss-Aware Density Control for 3D Gaussian Splatting
Low-Dimensional Adaptation of Rectified Flow: A Diffusion and Stochastic Localization Perspective
Towards Anytime-Valid Statistical Watermarking
Not Just Oversmoothing: Detecting Echo Chamber Effect in Graph Neural Networks
Inferring how internal brain state shapes neural responses with state-dependent diffusion models
CHAIN: Complementary Signed Graph Propagation for Uncertainty Quantification in Large Language Models
Tail-Risk-Aware Stackelberg Learning
Physics-Informed Functional Tucker Method with RKHS Factors for Sparse Spatiotemporal Reconstruction
RepoScope: Bridging Physical Structure and Logical Flow for Intent-Driven Repository Documentation
Chance-constrained Flow Matching for High-Fidelity Constraint-aware Generation
Improving LLM Final Representations with Inter-Layer Geometry
Nearly Optimal Bounds for Orthogonal Trace-Sum Maximization
MOSAIC: Concept Bottlenecks via Text-Anchored Optimal Transport
DeFlow: Decoupling Behavior-Prior Modeling and Value Maximization for Offline Policy Extraction
SPEXT: A Decoupled Multi-Spectral Foundation Model for Earth Observation and Vision-Language Grounding
LINE: LLM-based Iterative Neuron Explanations for Vision Models
Argument Graph Uncertainty: Quantifying Uncertainty from the Logical Structure of Reasoning Chains
Fast and Accurate Probing of In-Training LLMs' Downstream Performances
Extracting Training Data from Diffusion Language Models via Infilling
Exploration via Exploitation: The Blessing of Reward Diversity in Personalized Federated RL
Disen-Forcing: Disentangling Semantic Anchoring from Motion for Autoregressive Video Diffusion
Log-Averaged Mirror Prox for Fast, Large-Scale Optimal Transport in Linear Space
RSRCC: A Remote Sensing Regional Change Comprehension Benchmark Constructed via Retrieval-Augmented Best-of-𝑁 Ranking
Directional Confusions Reveal Divergent Inductive Biases Through Rate-Distortion Geometry in Human and Machine Vision
FM-ChangeNet: Learning Change through Pathwise Feature Transport
Listening to the Wise Few: Query–Key Alignment Unlocks Latent Correct Answers in Large Language Models
Spectral Insights from the Unconstrained Feature Model for Neural Multi-Output Regression
Memory Determines Learning Direction: A Theory of Gradient-Based Optimization in State Space Models
Beyond Flat Frames: Hierarchical Graph Reasoning for Long Video Understanding
REVERSE: Reinforcing Evidence Verification and Search for Agentic Image Geolocation
Sequential Solution Concepts in Cooperative Games with Generalized Characteristic Functions
Deep Minds and Shallow Probes
Class-Incremental Learning via LoRA-based Elastic Ensemble of Experts
Visual Expert Skipping for MoE-MLLMs via K-Armed Bandit based Expert Estimation
ValuSpec: Plug-and-Play Candidate Valuation before Target Verification for Tree-Based Speculative Decoding
Anchoring Adversarial Trajectories to Data Manifolds: A Bilevel Transfer Optimization Framework
Simple yet Effective Budget-Feasible Procurement Auctions for Submodular Welfare Maximization
GauGal: Gaussian-Galerkin Electromagnetic Inverse Scattering Imaging
Affine-Image Propagation for Tight and Scalable $\ell_{2}$ Neural Network Verification
To Think or Not to Think: Pre-Decisional Reasoning Budgets for Referring Audio-Visual Segmentation
Seeing the Unseen: Unified Visible–Invisible Motion for Physically Consistent Video Generation
FRESCO: A Novel Consistency Control for Asynchronous Pipeline Parallel Training
From Senses to Decisions: The Information Flow of Auditory and Visual Perception in Multimodal LLMs
RedVLA: Physical Red Teaming for Vision-Language-Action Models
ViCoR: Estimating Visual Necessity via Counterfactual Residuals for Multimodal Medical Data Selection
PISA: Piecewise Sparse Attention Is Wiser for Efficient Diffusion Transformers
Practical Adversarial Attacks on Stochastic Bandits via Fake Data Injection
Matryoshka Transcoders and Hierarchy Misalignment: When SAE Absorption Protection Does Not Transfer
Best Arm Identification in Generalized Linear Bandits via Hybrid Feedback
Verifier-Backed Hard Problem Generation for Mathematical Reasoning
Generalization Error Bounds for Picard-Type Operator Learning in Nonlinear Parabolic PDEs
Behavior Pack Optimization for Video MLLM Post-Training
Winning Lottery Tickets in Neural Networks via a Quantum-Inspired Classical Algorithm
iDETR: Implicit DETR for Tiny Object Detection
Solver-as-Teacher: Solver-Guided On-Policy Post-Training Framework for PDE Foundation Models
Energy-Based Operator Learning in Function Space
Hybrid Reinforcement Learning for One-step Degraded Infrared and Visible Image Fusion
Nereus: A Large-Scale Underwater Dataset for Fine-Grained Attribute Understanding and Grounded Counting Perception
Cyclic Discrete Diffusion: A Novel Multi-Class Segmentation Refinement Technique
Total Variation Distance Estimation in Autoregressive Models
SMART: Scalable Multi-Agent Role-conditioned Teaming via LLM-free Tree Search
Agentic Multi-Turn Reasoning: A Fairness Approach
Smooth Partial Lotteries for Stable Randomized Selection
Brain2voice 2.0: High-performance voice synthesis brain-computer interface
Can LLM Agents Respond to Disasters? Benchmarking Heterogeneous Geospatial Reasoning in Emergency Operations
Decision Path Tracing for Causal Analysis in Transformers
Mental Health AI Must Move Beyond Diagnostic Prediction and Chat-Based Support: Toward Perspective-Aware, Multisensory Co-Experience
A Latent World-Action Model with Jointly Aligned Reasoning
Augmented Equivariant Mesh Networks for Anatomical Segmentation
Towards Precise Knowledge Distillation for Large Language Models via Knowledge Probing
TurboVGGT: Fast Visual Geometry Reconstruction with Adaptive Alternating Attention
Norm Anchors Make Model Edits Last
OPSRL-SSP: Optimistic Posterior Sampling for Stochastic Shortest Path with Minimax-Optimal Regret
DinoComplete: 3D Shape Completion with Distilled Semantic Priors and State Space Models
Reward Inflation: A Healthy Stimulus for Reinforcement Learning
Follow-Bench 2.0: An End-to-End 3D Benchmark for Socially-Aware Robot Person Following
MindShape: Superquadric-Constrained High-Fidelity 3D Reconstruction from fMRI
The Geometric Wall: Manifold Structure Predicts Layerwise Sparse Autoencoder Scaling Laws
Robust Conditional Conformal Prediction via Branched Normalizing Flow
Graph-Regularized Sparse Autoencoders for LLM Safety Steering
The Geometry of Noise: Why Diffusion Models Don't Need Noise Conditioning
Behavioral Probes for Information Flow in LLM Swarms
Latent Spatial Reasoning: Building Innate 3D Awareness via Latent-Space Distillation
Learning the Committor Function using Weighted Ensemble Simulations
PRISM: Programming Interactive Scenes from Monocular Images for Embodied Simulation
Language Model Memory and Memory Models for Language
Multi-Marginal Couplings for Metropolis--Hastings
M$^2$RNN: Non-Linear RNNs with Matrix-Valued States for Scalable Language Modeling
Unified Panoramic Geometry Estimation via Multi-View Foundation Models
An Information-theoretic Framework for Auditing Unfairness in Training Data
SOAR: Regression-based LiDAR Relocalization for UAVs
Internalize External Competence for Visual Instruction Editing
Geometry-Aware Similarity Metrics for Neural Representations on Riemannian and Statistical Manifolds
Explainability matters: The effect of liability rules on the healthcare sector
Chain-of-Correction: Progress-Aware Policy Steering via Anchor-Grounded Predictive Reasoning
DeformMaster: An Interactive Physics-Neural World Model for Deformable Objects from Videos
Optimize Once, Execute Fast: Latency-Aware Multi-Agent Workflow Learning for Recurrent Queries
InformedXRD: Reproducible Benchmarks and Physics-Informed Evaluation for Powder Diffraction Symmetry Classification
PGID: Progressive Guided Inversion and Denoising for Robust Watermark Detection
Train at the Moving Edge: Rollout-Efficient RL for Large Reasoning Models
Quantum Speedups for Stochastic Optimization with Heavy-Tailed Noise
FML-bench: A Controlled Study of AI Research Agent Strategies from the Perspective of Search Dynamics
DECEIVE-AFC: Adversarial Claim Attacks against Search-Enabled LLM-based Fact-Checking Systems
TTVidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining
DiagEval: Trajectory-Conditioned Diagnosis for Reliable Software Evaluation with GUI Agents
Face Deepfake-aware Recovery via Semantic-driven Facial Representation-based Watermarking
Recursive Semantic Divergence for LLM Agent Consistency
Estimation of the Label-Noise Transition Matrix with Performance Guarantees via Selective Classification
Taming CoT Obfuscation in VLMs: From Mechanistic Evidence to Activation-Level Enforcement
Flow-Guided Target-Space Alignment via Path Consistency
ShopGym: An Integrated Framework for Realistic Simulation and Scalable Benchmarking of E-Commerce Web Agents
OrchestraRL: Learning to Orchestrate LLM Agent Swarms with Entropy-Aware Communication Control
Addressing Sparse-Rewards in RL with Scalable Hierarchical Novel Eigen Options
DSAQuant: Denoising-Stage-Aligned Quantization-Aware Training for Video Generation
Equilibrium Forcing: Adaptive Video Generation Without Noise Conditioning
Overcoming State Inertia in Full-Duplex Spoken Language Models via Activation Steering
Post-Processing Guarantees for Classification under Linear-Fractional Performance Metrics
Efficient Memory Crystallization for Graph Learning under Non-Stationary Distribution Shifts
Change-Robust Online Topological Memory for Long-Term Relocalization and Semantic Navigation
Seeing Together: Multi-Robot Cooperative Egocentric Spatial Reasoning with Multimodal Large Language Models
From Generation to Restoration: Residual Diffusion for Neural Channel Decoding
STDec: Spatio-Temporal Stability Guided Decoding for dLLMs
DIBench: Benchmarking Decision Integrity of GUI-based Mobile Agents Under Deceptive Injections
SkillOS: Learning Skill Curation for Self-Evolving Agents
FloatDoor: Platform triggered Backdoors in LLMs
Explaining Cross-Modal Model Behavior with Gradient-Estimation-Based Feature Interaction
Re-evaluating Continual Learning with Few-Shot Adaptation
A Solver-Efficient Neural Adversarial Attack on Subgraph Matching Models
Adversarial Corpus Selection to Attack Subgraph Matching based Graph Retrieval
XFeat Revisited: Reproducibility and Evaluation of a Lightweight Image Matcher
PhysGuard: Fisher-Guided Gradient Projection for Sim-to-Real Neural PDE Surrogates
SteadyThought: Mitigating LLM Under-Thinking via Thought-Level Preference Optimization
SpikeSSL: A Universal Spike Inference Framework with Dynamics-Informed State-Space Layers
Local FDR Membership Inference Attacks: Multiple Testing and the Role of Ridge Regularization
SaMA: Morpho Adaptation via Asymmetric Expansion of Kronecker Product
Revisiting Value Iteration: Unified Analysis of Discounted and Average-Reward Cases
Disentangled Sparse Representations for Concept-Separated Diffusion Unlearning
AI for Drug Discovery Models Often Do Not Learn as Expected and How to Diagnose These Failure Modes
Manifold-Aligned Adversarial Perturbation for Anti-Customization under Diffusion-based Purification
A2I: Adjacency-to-Image Structural Encodings for Graph Learning
Robust Stream Classification using Time Neutralising Decision Trees
GraphMemRL: Action-Native Reinforcement Learning for Persistent Graph Memory Construction
FastDSAC: Unlocking the Potential of Maximum Entropy RL in High-Dimensional Humanoid Control
Veri-Sure: Multi-Agent RTL Code Generation with Temporal Tracing, Slicing and Formal Verification
Origami as a Real-Image Benchmark for Procedural State-Transition Reasoning
Contrastive Thinking Decoding: Steering Answer Generation in Reasoning Models
Grounding 3D Affordance from Human-Object-Interaction Videos via Multimodal Large Language Model
How to Interpret Agent Behavior
NoTVLA: Semantics-Preserving Robot Adaptation via Narrative Action Interfaces
The Spectral Amplitude Principle for Dynamics of Quantum Neural Networks
Dialectics of Alignment: Harnessing Unsafe Knowledge for Dynamic Safety Routing
OmniJigsaw: Enhancing Omni-Modal Reasoning via Modality-Orchestrated Reordering
A Differentiable 3D Scene Graph Metric via Contextual Hellinger Triplet Geometry
Practical Non-Stationary Graph Gaussian Processes
Decoupling Label Shift and Surrogate Gradient Errors for Robust Federated Spiking Neural Networks
How Does Cutout Benefit Out-of-Distribution Generalization?
Prior-Anchored Local Statistical Representation Rectification for Low-Light Image Enhancement
EVIDENT: Routing MLLM Adaptation through Entity-Grounded Visual Evidence for Cross-Domain Video Temporal Grounding
Efficient SAM 3 Adaptation for Multi-Class Semantic Segmentation via Dense Competitive Representations
CRAFT: Counterfactual-to-Interactive Reinforcement Fine-Tuning for Driving Policies
Submodular Benchmark Selection
Self-Evolution Reasoner: Continuous Optimization via Policy-Intrinsic Exploration and Exploitation
The Pok\'emon Theorem and other Fairness Impossibility Results
ProactBench: Beyond What The User Asked For
Thinking in Pictures: A Systematic Benchmark for Reasoning-driven Image Generation
StreamOV: Streaming Omni-Video Understanding via Evidence-Guided Memory and Response Triggering
Test-time Multi-agent Coordination by Decomposed Value Gradient Flow
Conformal Cache: Reliable Proxy-Discrepancy Caching for Fast Generative Inference
ICAT: Incident-Case–Grounded Adaptive Testing for Physical-Risk Prediction in Embodied World Models
TALK: One-Shot Batch Design for Protein Variant Effect Prediction
Conservative Pareto Set Amortization for Offline Multi-Objective Optimization
Small Model Portfolios for Many Deployment Profiles: Submodular Coverage under Bundled Constraints
Exploring the Epipolar Consistency for Light Field Deraining
ADKV: A Low-Overhead Adaptive Delta Quantization for KV Cache in LLM Inference
Hydra-DP3: Frequency-Aware Right-Sizing of 3D Diffusion Policies for Visuomotor Control
SynMQG: Disentanglement and Mutual-Information Optimization for Synergistic Multi-modal Question Generation
Bridging CLIP with DINO: Cross-Modal Information Maximization for Online Test-Time Adaptation
HAMSTAR: Hamiltonian Structured Inter-Period Refinement for Long-Term Time Series Forecasting
Dialect ASR based on Multi-View Pseudo-Parallel Augmentation and Noise-Robust Contrastive Learning
TGRL: Temperature-Grouped Reinforcement Learning for Efficient Exploration in LLMs
MicroWorld: Empowering Multimodal Large Language Models to Bridge the Microscopic Domain Gap with Multimodal Attribute Graph
Every Measurement, Every Direction, All at Once: Multimodal Flow Matching for Molecules and Spectra
Entropy Polarity in Reinforcement Fine-Tuning: Direction, Asymmetry, and Control
TTCS: Test-Time Curriculum Synthesis for Self-Evolving
All-Addition Spiking Diffusion Models with Attention Enhancement
Hitting a Moving Target: Test-Time Adaptation for AI Text Detection under Continual Distribution Shift
The Reciprocity Gradient
Dynamic Representation Modeling for Federated Medical Image Domain Generalization
CRESiST: Self-Enhancing Exploritive Policy Learning for Simultaneous Speech Translation
DetailAnywhere: Fashion Detail Generation via Cross-Modal Feature Alignment Distillation
No Detail Left Behind: Revisiting Self-Retrieval for Fine-Grained Image Captioning
Reformulating KV Cache Eviction Problem for Long-Context LLM Inference
Architecture-Embedded Physics Priors for Mitigating Spectral Bias in Physics-Informed Neural Networks
Confidence Estimation via Decoupled Smoothing for Dynamic LLM Routing and Aggregation
LiteNav: Lightweight Map-free Outdoor Visual Navigation
Dirichlet-Guided Group Forecasting for Alleviating Over-smoothing in Time Series Forecasting
The Missing Corpus: Infinite Ground Truth for File-Grounded LLM Evaluation
Disentangled Multimodal Learning for Scalable Dynamic IR-Drop Analysis
Multilateral Resistance-Guided Graph Message Passing for Trade Flow Prediction
HiddenPathQA: A Benchmark for Knowledge Graph Question Answering When Questions Hide Their Paths
PIS: Pose-Interpolation Smoothness for Skinning Weight Refinement
Working with AI: Measuring the Applicability of Generative AI to Occupations
Self-Organized Conformal Prediction: Reducing Regional Coverage Gaps with Unsupervised Group Discovery
Taming Generative Co-Folding Prior for Molecular Docking with Diffusion Bridge
Variational Consequence-Driven Offline Reinforcement Learning
DC-Ocean: Deep Latent Compression for Global High-Resolution Ocean Forecasting
MCGI: Manifold-Consistent Graph Indexing for Billion-Scale Disk-Resident Vector Search
Cross Flow: One-Step Generation Across Latent and Pixel Spaces
Federated Unlearning with Gradient Adaptive Shaping
On Data Engineering for Scaling LLM Terminal Capabilities
Polestar: Drift-Aware Cache Calibration and Token Commitment for Efficient Inference of Diffusion LLMs
ORCA: Orthogonal Residual Consensus Alignment for Multi-View Clustering
Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models
CUDABench: Benchmarking LLMs for Text-to-CUDA Generation
Sharper Guarantees for Misspecified Kernelized Bandit Optimization
Revisiting Subgradient Dominance in Robust MDPs: Counterexamples, Hardness, and Sufficient Conditions
On the Effect of Token Correlations on Semantic Transfer in Transformers
AdapMatch: Adaptive Bias Decoupling for Semi-Supervised Partial Label Learning under Unknown Class Distributions
EnterpriseBench: Evaluating LLM Agents on End-to-End Spreadsheet Tasks in Finance
The Weight Gram Matrix Captures Sequential Feature Linearization in Deep Networks
Efficient Label Distribution Inference Attack and Defense on Classifier Weights in Federated Learning
SOLAR: AI-Powered Speed-of-Light Performance Analysis
Epiplexity Guided Data Selection and Generation for Out-of-Distribution Generalization
First-Token Attraction in Mamba Dynamics
Deconstructing Multi-Task Active Learning: The Paradox of Gradient Conflict and Orthogonal Decomposition
Objective-Aligned Amortized Inference for Offline Bayes-Adaptive MDP Model Learning
Mitigating Retaliatory Algorithmic Collusion in Repeated Games
Quantum Composite Hypothesis Testing with Small Error
From Local to Global: Progressive Consensus via Hierarchical Communication in Multi-Agent Reinforcement Learning
Diffusion Guidance Is a Controllable Policy Improvement Operator
FedLoVA: Value-Only Aggregation for Federated LoRA Fine-Tuning of Large Language Models
Efficient bias mitigation in T2I diffusion models using Concept Graphs
Learning Dynamic Evidence Routes for Vision Transformer Probing
DASS: A Solver-Agnostic Dynamic Auxiliary Search Strategy for Symbolic Regression
Artificial Aphasias in Lesioned Language Models
Morpho-Temporal Decoupling: How Primate Neurons Expand Dendrites Without Losing Speed
MGMem: An Efficient, Deterministic, and Provenance-Preserving Framework for Long-Horizon Agent Memory
S-EDL: Eliciting Self-Evidence from Sequence Likelihoods for Semantic Calibration of LLMs
SPRM: From Cooperative Games to Marginal-Contribution Process Reward Modeling
Tyche: One Step Flow for Efficient Probabilistic Weather Forecasting
RoboAlign-R1: Distilled Multimodal Reward Alignment for Robot Video World Models
Adversary-Robust Learning from Fully Asynchronous Directional Derivative Estimates
Dynamical Adapter Fusion: Constructing A Global Adapter for Pre-Trained Model-based Class-Incremental Learning
Adversarial Attack and Defense for Machine Learning in Statistical Physics
Feature Recovery for Object Understanding Under Physical Transformation
POP: Online Structural Pruning Enables Efficient Inference of Large Foundation Models
Rigel3D: Rig-aware Latents for Animation-Ready 3D Asset Generation
Conformal Prediction for Distribution-to-Distribution Regression
The Subjectivity of Monoculture
Time series analysis with Gumbel dynamics
SuperSycophantic: Stress-Testing Frontier LLMs from Single- to Multi-Turn Sycophancy
CompactAttention: Accelerating Chunked Prefill with Block-Union KV Selection
BEAST3D: animal behavioral analysis and neural encoding from multi-view video via Gaussian splatting
FaithSieve: Fine-Grained Evaluation of Math Proofs with Faithful Formal Evidence
Alignment Imprint: Zero-Shot AI-Generated Text Detection via Provable Preference Discrepancy
On Generalization in Bilevel Optimization with Overparameterized Models
RipBench: A Unified Benchmark for Multi-Level Rip Current Detection, Classification and Segmentation
Cross-Modal Prior-Guided Training with Visual Foundation Models for Unsupervised LiDAR Point Cloud Registration
A Surrogate Perspective on Convergence of Fixed-Target DQN
Controllable Multi-label Video Safety Detection via Adaptive Tversky Policy Optimization
MoT3DVG: A Benchmark for Outdoor 3D Visual Grounding with Motion-Aware Descriptions and Temporal Cues
Chain-of-Thought Oversight Should Not Treat Faithfulness as Monitorability
Trust Region Q Adjoint Matching
RePO-VLA: Recovery-Driven Policy Optimization for Vision-Language-Action Models
Reinforcement Learning with Multi-Step Lookahead Information Via Adaptive Batching
Attention-Based Sampler for Diffusion Language Models
MAGE: Multi-Agent Self-Evolution with Co-Evolutionary Knowledge Graphs
Introspective Coupling: LMs Learn to Explain Themselves Better Than Their Training Targets
PACE: Partial-state Amortized Constraint Editing for Neural Combinatorial Optimization
Training Language Models to Explain Their Own Computations
DETS: An Interval-Censored Evidential Sampling Framework for Cross-Domain Scientific Discovery
SLOPE: Optimistic Potential Landscape Shaping for Model-based Reinforcement Learning
LP-RAG: Learning to Retrieve with Link Predictors
AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent Systems
Relaxation-Aligned State Control for Test-Time Scaling in Generative Combinatorial Optimization
MobTA: Bus-Conditioned Zero-Shot Trajectory Generation via Task Arithmetic
Robust and Efficient Backdoor Mitigation for ML Models via Tolerant Property Testing
Static-Dynamic Disentanglement for Efficient Multi-Frame Vision-Language-Action Models
Visual Grounding First, Multimodal In-context Learning Follows
Done, But Not Sure: Disentangling World Completion from Self-Termination in Embodied Agents
DEDCA: Test-Time Adaptation for Generalized AI-Generated Image Detection
SierpinskiCam: Camera-Controlled Video Retaking with Sierpinski Triangle Pattern Cues
VSRo-200: A Romanian Visual Speech Recognition Dataset for Studying Supervision and Multimodal Robustness
ENGINE: Endogenous Variational MultiScale Optimization for Zeroth-Order LLM Fine-Tuning
Deferred Aggregation in Hierarchical Bayesian Optimization
Positional LSH: Binary Block Matrix Approximation for Attention with Linear Biases
Seeing Across Skies and Streets: Feedforward 3D Reconstruction from Satellite, Drone, and Ground Images
Uncertainty Quantification of Least Squares Estimator for Generalized Orthogonal Procrustes Problems
Scaling Laws for SAE Training Data
APIVOT: Adaptive Planning with Interleaved Vision-Language Thoughts
AsdaKV: Attention-Overlap Driven Semantic KV Retrieval for Long-Context LLMs
Not All Tokens Should Be Treated Equally: Context Credits Reassignment
Can Folding Models Tell Binders from Bluffers? Evidence from POISK: The Patent-Derived Antibody Dataset
An Assessment of Human vs. Model Uncertainty in Soft-Label Learning and Calibration
Geometry-Calibrated Conformal Abstention for Language Models
From Static Policies to Adaptive Priors in Offline Reinforcement Learning
A Unified Image and Video Encoder for Multimodal LLMs
Representation Learning Enables Scalable Multitask Deep Reinforcement Learning
InfCoiL: Coordinated Planner-Controller Learning for Closed-Loop Physics-Based Human-Object Interaction
Rethinking LLM Fine-Tuning via Weight Space Reparameterization: Preserving Safety during Downstream Adaptation
SurvCancel: A Longitudinal Dataset and Benchmark for Dynamic Order Cancellation Prediction in On-Demand Ride-Sharing Systems
Calibrating Scientific Foundation Models with Inference-Time Stochastic Attention
Reading the Unreadable: Text-Aware Image Super-Resolution Needs Reasoning
Sketching the Readout of Large Language Models for Scalable Data Attribution and Valuation
The PokeAgent Challenge: Competitive and Long-Context Learning at Scale
Can LLMs Reliably Grade Olympiad Proofs? A Controlled Study of Mathematical Verification with LLMs
OverLay++: Dense-Overlap Layout-to-Image Generation Dataset
On the Overscaling Curse of Parallel Thinking: System Efficacy Contradicts Sample Efficiency
CausalSpatial: A Benchmark for Object-Centric Causal Spatial Reasoning
EA-WM: Event-Aware Generative World Model with Structured Kinematic-to-Visual Action Fields
AVID: A 5T fMRI Dataset for Benchmarking Auditory-induced Visual Mental Imagery Decoding
Phase Transitions in Attention: A Bayesian Theory of Copy Head Emergence
Breaking $\textit{Winner-Takes-All}$: Cooperative Policy Optimization Improves Diverse LLM Reasoning
Benchmarking Membership Privacy Risks in Preference-Based LLM Post-Training
PixelART: Image-to-Layer Decomposition without Latents or Text-to-Image Pretraining
SKIM: Pruning Large Language Model Agents via Selective Knowledge Informed Masking
RADIUM: RadioActive Decay of Image-Underlaid Marks
Coarsening Linear Non-Gaussian Causal Models with Cycles
VLMGuard: Bootstrapping Malicious Prompt Detectors from Unlabeled Vision-Language Prompts in the Wild
MoTo: Mixture of Tokenizers Towards Fair Multilingual Language Modeling
Prompting Diffusion Models for Zero-Shot Instance Segmentation
ByteDistill: Cross-Tokenizer Distillation via Chunk-wise Byte-Level Distribution Alignment
PreDiff: Sequential Recommendation by Denoising Preference Distributions
RAIL: Representation-Aligned Imitation Learning for Student-Compatible Teacher Policies
PRECISE: SDE-Consistent Stochastic Sampling for RL Post-Training of Flow-Matching Models
The Fault in Our Metrics: Revisiting Generative Model Evaluation with Chamfer Distance
TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning
Pareto Preference Optimization for Structure- and Stability-Aware RNA Inverse Folding
Matching2Matching: Zero-Shot Light Field Image Denoising with Matching View Construction
Probe-Guided Gradient Balancing for Multimodal Learning
Selective Disk Bispectrum: A Complete and Rotation Invariant Image Descriptor
$\texttt{bispectrum}$: Selective $G$-Bispectra Made Practical
OrbitLoRA: Learning Rotation-Aware Low-Data Adaptation of Vision Foundation Models
FoMo: Forking Moment in Generative Trajectory as a Perceptual Distance
A Theory of Training Profit-Optimal LLMs
OrangeTree: A Linear and Tree-based Time Series Forecasting Model Supporting Multiple Input and Output Lengths
Distributed-Order Fractional Spiking Neural Network
Policy-Level Exploration for Coordinated Multi-Agent Reinforcement Learning
From Click Imitation to Transition Equivalence: Rethinking Supervision for GUI Agents
Power Distribution Bridges Sampling, Self-Reward RL, and Self-Distillation
GLACIER: Rethinking Mass Spectrum Prediction as an Object Detection Problem
DeformGen: Dynamics-Based Topology Augmentation for Deformable Manipulation Policy Learning
S2D: Sparse-To-Dense Keymask Distillation for Unsupervised Video Instance Segmentation
Dynamic Dual-Feedback Conformal Inference for Time Series Forecasting
Beyond Fixed Benchmarks and Worst-Case Attacks: Dynamic Boundary Evaluation for Language Models
CofactVLA: Deconfounding Vision-Language-Action Models via Counterfactual Intervention
Sparse blind deconvolution via thresholded Wirtinger flow
Beyond Spatial-Domain Supervision: A Relation Constrained Space for Multi-Modal Image Fusion
When Integral Meets Decomposition: A Signal-Level Self-Supervised Feature Decompose Paradigm for Multi-Modal Image Fusion
Bandits via Additive Quantized Representations
FineVLA: Fine-Grained Instruction Alignment for Steerable Vision-Language-Action Policies
SpatialFlow-GRPO: Where Spatial Credit Drives Image Editing
Breaking the Group Size Barrier: Parameter-Efficient Group Dance Generation with Chain-of-Dancers
AdaPreLoRA: Adafactor Preconditioned Low-Rank Adaptation
AdaCodec: A Predictive Visual Code for Video MLLMs
Imitation Dominates Reinforcement: Direct In-Context RL Is Closer to ICL Than RL
Co-PiLOT: Constrained Physics-Informed Latent Optimization for Target-Driven Inverse Design
Stable3R: Streaming 3D Reconstruction with Stable Geometric References
Confidence-Calibrated Inference Expansion for Evaluator-Guided Test-Time Reasoning
Posterior Contraction Rates for sparse Kolmogorov-Arnold Networks in Anisotropic Besov Spaces
TimeTraveler: Temporal Strategy Planning with Time Dictionary for Streaming Video Understanding
AMUSE: Anytime Muon with Stable Gradient Evaluation
Memorize Theorems, Not Instances: Probing SFT Generalization through Mathematical Reasoning
Unlocking Fine-Grained Perception in CLIP via Structurally-Aware Latent Masked Modeling
SPERA: Spherical Prior EEG Foundation Model with Geometry- and Frequency-Aware Latent Prediction
PEIRA: Learning Predictive Encoders through Inter-View Regressor Alignment
The Cost of Symmetry: Universality and Hardness for Permutation-Invariant Neural Networks
Mean Testing under Truncation beyond Gaussian
Frequency-Structured Hamiltonian Neural Network for Multi-Timescale Dynamics
3D Consistency Tokens
HaNDF: Object-Conditioned Geometric Neural Hand Distance Fields
Tree-Sliced Orlicz Integral Probability Metric
Controllable Generative Sandbox for Causal Inference
Hindsight Relabeling is All You Need for Reach-Avoid Learning
TopoCurve: Geometry-Aware Topology Reasoning via Bézier Curves in Autonomous Driving
MedVIGOR: Visual Evidence Internalization for Observation-Driven Reasoning in Medical VLMs
Empirical Bayes Rebiasing
Scaling Storm-Resolving Atmospheric AI Simulation to the Entire Planet
HyFAD: Hybrid Time-Frequency Diffusion with Frequency-Aware Embedding for Time Series Imputation
AC/DC on a Budget -- Alternating Sparse Phases
Layer Precision Reduction for Deep Anomaly Detection
Efficient Streaming Audio-Visual Target Speaker Extraction for Real-World Acoustic Scenes
TPRL: Adaptive Visual Token Pruning in LVLMs via Language-Guided Reinforcement Learning
History-Aware Conformal Prediction Sets for Censored Time-to-Event Outcomes
VALOR: Vector-Aware Low-Rank Restructuring of Neural Networks for RISC-V Inference
Radial-Angular Geometry for Reliable Update Diagnosis in Noisy-Label Learning
FlashMask-3: Efficient and Expressive Mask-Aware Distributed Attention
M$^2$E-UAV: A Benchmark and Analysis for Onboard Motion-on-Motion Event-Based Tiny UAV Detection
Where and When Identity Forms: Identity-Vital Attention Redistribution for Training-Free Subject-Driven Generation
Distilling Graph Geometry: Knowledge Gap from GNNs to MLPs
LoRAtorio: An intrinsic approach to LoRA Skill Composition
BasicLT: Basic-Level Abstraction and Selective Differentiation for Long-Tailed Recognition
U-MOF: Uncertainty-Guided Parameter-Efficient Multi-Objective Fine-Tuning for Long-Tailed Recognition
Weakly Supervised Concept Learning for Interpreting and Attributing LVLM Predictions
Language-Assisted Image Clustering Guided by Discriminative Relational Signals and Adaptive Semantic Centers
SimReg: Achieving Higher Performance in the Pretraining via Embedding Similarity Regularization
Virtual Head Attention
SynBench: A Benchmark for Differentially Private Text Generation
You CAN Teach an Old Model New Tricks: Domain Adaptation via Complementary Subspace Expansion
SAMAT: A Stereotype-Aware Multimodal Transformer for Interpretable Misogynistic Meme Detection
Backdoor Attacks Rerouted: BatchNorm as a Sink for Adversarial Signals
Prysma: Efficient Modality Adaptation for SLO-aware LLM-based Video Question Answering
What to Remember, What to Reveal: Privacy-Aware Memory for Conversational Agents
M2A: Synergizing Mathematical and Agentic Reasoning in Large Language Models
Where Does Warm-Up Come From? Adaptive Scheduling for Norm-Constrained Optimizers
Roll2Depth: Zero-Shot Metric Depth Estimation Exploiting Camera's Rolling Shutter Effect
CryptanalysisBench: Can LLMs do cryptanalysis?
AgentLens: Revealing The Lucky Pass Problem in SWE-Agent Evaluation
Efficient Algorithms for Distributed Saddle Problems
D$^2$Quant: Accurate Low-bit Post-Training Weight Quantization for LLMs
Algorithms for Linear Equations with Min and Max Operators Under (Absolutely) Halting Condition
EDISCO: Equivariant Discrete Diffusion for Euclidean Combinatorial Optimization
Tool-IQA: Augmenting Image Quality Assessment with Simple Tools
Coarse-to-Refine: Trajectory Self-Refinement in Single Autoregressive Pass for Driving VLA
HandEdit: A Unified Benchmark for Egocentric Human-to-Robot Dexterous Hand Image Editing
Ballad: Bandit-Based LLM Routing for Automated Heuristic Discovery
Local Gaussian Processes on Compact Lie Groups
PaxBench: A Multimodal Sequence Benchmark for Protein Abundance Prediction
Auction-Based Online Policy Adaptation for Evolving Objectives
EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience
GReFEM: Multimodal LLMs as Zero-Shot Semantic Assistants for Physics-Guided 3D Mesh Refinement
PARE: Pruning and Adaptive Routing for Efficient Video Generation
Efficient and Accurate Zero Shot Generation of Symmetric Protein Complexes
AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling
Higher-Order Action Supervision Makes A Strong Policy Class
Beyond Generation: Unlocking Discriminative Representations from Diffusion Models
OHATP: Graph Anomaly Detection with Orthogonal-Hyperspherical Augmentation and Topology Perception
SynTeX-FL: Cross-Modal Text Transfer in Federated Learning for Medical Visual Question Answering
Dynamic Query as Budgeting for Tiny Object Detection
Bridging Academia and Industry: A Comprehensive Benchmark for Attributed Graph Clustering
Learning Pareto Stationary Fronts via Single-Pass Backpropagation
Full-Sequence Masked Diffusion for Generative Recommendation
Position: Next-Generation Game Engines Should Be Built on Interactive Generative Video
$\mathbf{\mathtt{MAD\text{-}Bench}}$: How Do Multimodal Agents Deceive You?
GeoRad-3D: Factorized Geometry Transport and Residual Radiometry for 3D Radar Nowcasting
Trajectory-Consistent Diffusion Policies for Offline Reinforcement Learning
Decentralized Coupled Representation Learning
AbsoluteDegradation: A Physics-Inspired Synthetic Film-Degradation Pipeline and Archival Film Restoration Benchmark
Knowledge-Graph Paths as Intermediate Supervision for Self-Evolving Search Agents
Resilient Latent Readouts for Long-Context Question Answering
FiRe: Fine-grained Multimodal Reasoning for Enhanced Image Generation
MinMax Recurrent Neural Cascades
Robust Satisficing Ensemble: Scalable Model Aggregation Under Distribution Shifts
Training for the Model You Return: Improving Optimization for Iterate-Averaged Language Models
P$^{3}$: Joint Program-and-Proof Planning\\ for Verified Code Generation
Exact Instance Compression for Convex Empirical Risk Minimization via Color Refinement
Can LLMs explain themselves truthfully with code?
The Locality Cost of Semantic Patch Self-Distillation
Efficient Tree Draft for Long-Context Speculative Decoding
FrameScout: Scouting Query-Relevant Frames for Long Video Understanding
Achieving Better Local Regret Bound for Online Non-Convex Bilevel Optimization
Fully First-Order Algorithms for Online Non-Convex Bilevel Optimization
GLOVE: Global Verifier for LLM Memory-Environment Realignment
Pessimistic Latent Task-aware Optimization for Robust Offline Meta-Reinforcement Learning
SAFE-SVD: Sensitivity-Aware Fidelity-Enforcing SVD for Physics Foundation Models
Meow-Omni 1: A Multimodal Large Language Model for Feline Ethology
Remote Photoplethysmography Based on a Skin Reflection Exponential Model
Phase Kernel Lifts Capacity of Dense Associative Memory
MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization
Beyond Raw Observations: Distilling and Storing Invariant Driving Memories for Generalizable Autonomous Driving
ViLo: LiDAR Localization with Vision-Language Priors
Cite What You Explore: Budget-Aware LLM Reasoning over Medical KGs with Verifiable Evidence
What Should Remain After Forgetting? Rethinking LLM Unlearning as Predictive Posterior Correction
LADDERS: Length-Aware Data Distribution and Existing-Response Speculation for Fast RL Rollout Generation
SPLICE: Structured Prompt Local Iterative Combinatorial Evolution
Joint Sequence--Vocabulary Selection for Efficient LLM Distillation
MaPP: A Unified Marginalized Posterior-Predictive Framework for Data-Efficient RLVR
Multi-bit LLM Watermarking with Certified Semantic Distortion
Reinforcement Learning with Verifiable Physics: Post-training LLMs for PDE Solver Generation
Efficient Agentic GPU Kernel Optimization with a Compact Domain-Specific Language and Speed-of-Light Guidance
The Platonic Defense: Backdoor Defense for Self-Supervised Encoders in the Era of Large Scale Pre-training
COMET: Codebook-based Online-adaptive Multi-scale Embedding for Time-series Anomaly Detection
Learning Where to Look: Observation Policy Optimization for Thinking with Images
TanGCE: Manifold-Aware Concept Erasure
What Kind of Diffusion Models Do We Need in Online Reinforcement Learning?
HABIT: Human-Aware Behavior and Interaction Training Dataset for Robot Manipulation
Do Speech BCIs Need Larger Models? Rethinking Neural Decoding beyond Scaling
Decoupling Action from Egocentric Observation for World Simulation
AdaWM: Few-Shot Adaptation of World Models to Unseen Dynamical Regimes
Generalised Linear Models in Deep Bayesian RL with Learnable Basis Functions
DCVD: Dual-Channel Cross-Modal Fusion for Joint Vulnerability Detection and Localization
Neural-DISCO: Source-Conditioned Counterfactual Editing of Neural Population Activity
Direct Estimation of Schrödinger Bridge Time-Series Drifts: Finite-Sample, Asymptotic, and Adaptive Guarantees
A Composite Activation Function for Learning Stable Binary Representations
FRUC: Feedforward Dynamic Scene Reconstruction from Uncalibrated Collaborative Driving Views
Mobility Helps Learning: Unsupervised Model Adaptation for Object Recognition via Movement
vExpert: Virtualizing Expert Storage for Adaptive Load Balancing in Distributed MoE Inference
PRISM: Human Point Cloud Reconstruction via Skeleton-Guided Diffusion from MmWave Radar
RRL-HOI: Reflective Reinforcement Learning for Open-Vocabulary HOI Detection
Cross-Model Transfer Attacks against Large Vision-Language Models via Model Diversity Enrichment and Stochastic Parameter Sampling
Persistent Planar Memory for Video World Models
PATCH: Learnable Tile-Level Hybrid Sparsity for LLMs
Accelerating the Inference Era with AI-Driven, Globally Optimized HW/SW Co-Design
RADAR: Routing Agents via Difficulty-Aware Recovery
CasePlay: Self-Play Reinforcement Learning from Case Reports for Medical Reasoning
FedCAG: Federated Causality-Aware Graph Learning for Multi-Cloud Workload Forecasting
OliO: ODE-based Linear Transition Operator for Self-Supervised Time Series Forecasting
AdKnob: Ad Intensity Control and Labeling for LLM-Native Advertising
XDecomposer: Learning Prior-Free Set Decomposition for Multiphase X-ray Diffraction
Explaining and Preventing Alignment Collapse in Iterative RLHF
Don’t Let Gains FADE: Breaking Down Policy Gradient Weights in RL
Norm Enforcement for AI Agents: Robustly Shaping Behavior in Multi-Agent Systems
Rethinking Softmax Attention: Polynomial Activations for Transformers
Mitigating Asymmetric Boundary Encroachment in Continual Learning of Vision-Language Models
TOM-Pruning: Target-aware Output Manifold for LLM Pruning
NDPP-Grasp: Non-Differentiable Physical Plausibility Constraint-Guided Task-Oriented Dexterous Grasp Generation
FreeSpec: Training-Free Long Video Generation via Singular-Spectrum Reconstruction
Stable and Granular Policy Optimization for Generative Recommendation
BayesAT: Bayes-Guided Progressive Distillation for Semi-Supervised Adversarial Training
REAL-MED: Benchmarking LLM Agents on Real-World Medical Tasks
SAX: Advancing Video Diffusion Models for Sequential Action Execution
Energy-Adaptive Equivariant State Space Models for Noise-Robust Protein Structure Representation
WorldSR: Harnessing World Knowledge Search for Grounded Image Super-Resolution
Self-Cleaning Diffusion Models
BECON: Belief-Conditioned Constrained Multi-Objective Reinforcement Learning under Drifting Preferences and Budgets
Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents
Large-Scale Pretraining unlocks Few-Shot Prediction for Relational Data
COMPASS: Composable Policy-Amortized Structured Search for LLM-Based Optimization Modeling
Temporal Slice Learning for AI-Generated Video Detection with 400× Fewer FLOPs
Spectral Degeneration of Softmax Attention under Isotropic Score Geometry
PermaVid: Consistent Video Generation Across Edits via Disentangled Context Memory
Component-Based Out-of-Distribution Detection
POST: Progressive Object-Slot Tokenization for Multimodal Large Language Models
Intend, Reflect, Refine: An Adaptive Multimodal Reflection Framework for Autonomous Driving
KVFocus: A Perturbation-Theoretic Token-Risk Score for Selective KV Cache Reuse in RAG
Balanced Multi-Task Learning from an Optimality-Gap Perspective
Z-AXIS: From Deterministic Ground to Agentic Depth for Enterprise Evaluation
Joint Learning of Hierarchical Neural Options and Abstract World Model
Better Source, Better Flow: Learning Condition-Dependent Source Distribution for Flow Matching
L$^2$EAP: Supercharging LLMs for Formal Mathematics with Agentic Frameworks
Fast-Slow Evolutionary Occupancy Prediction via Controlled Dynamics
PARI: Policy-Driven Active Residual Intervention for Weakly Supervised Point Cloud Segmentation
NeuroRVQ: Multi-Scale Biosignal Tokenization for Generative Foundation Models
The Minimax Rate of Online Isotonic Regression on Product Orders
Preconditioned Implicit Midpoint Langevin Sampling for Non-Smooth Bayesian Imaging
IMTS-Tokenizer: Time-Aware Tokenization for Irregular Multivariate Time Series Forecasting
OGPO: Offline Goal-conditioned Policy Optimization for Recoverable Vision-Language-Action Models
Right Results, Wrong Reasons: Auditing Behavioral Reliance in Motion Forecasting
Long-Term Composition of Human-Object Interactions
Exploring Multi-Order Self-Similarity for Motion Understanding
VidHalluDoctor: Learning Video Differences to Mitigate Hallucinations in Vision-Language Models
PI-EDG: Physics-Informed Full-Space Electron Density Generation from Molecular Geometry
InfoNav: A Unified Value Framework Integrating Semantic Relevance and Information Gain for Zero-Shot Object Goal Navigation
EgoBench: An Interactive Egocentric Multimodal Benchmark for Tool-Using Agents
Principled Policy Optimization for LLMs via Self-Normalized Importance Sampling
Diffusion LLMs are Natural Adversaries for any LLM
Horizon-Stream: Long-Horizon Attention for Streaming 3D Reconstruction
ToolSearcher: Optimizing Tool Selection at Scale via Reinforcement Learning
Learnable Spectral Activations
Complete or Sparse: A Tale of Two Identifiabilities
Masked Diffusion Language Agents for Tool-Integrated Chemical Reasoning
BitShift-RoPE: Zero-FLOP Relative Positional Encoding for Spiking Neural Network Transformers
Identifying and Mitigating Diversity Collapse in Zero-Shot Personalization with I2I Editing Models
Identifiable Feedback-Controlled Latent Flow for Unpaired Single-cell Spatio-Temporal Dynamics
FedVaccine: Knowledge Recall after Spatial-Temporal Catastrophic Forgetting in Federated Continual Learning via Gradient-Based Vaccine
Multi-Variable Conformal Prediction: Optimizing Prediction Sets without Data Splitting
Temporal Concentration from Rollout Errors: Implicit Preference Optimization For Text-to-Video Diffusion
TGPO: Trace-Guided Policy Optimization for Robot Task Planning via Verifiable Subgoal Generation
Tango3D: Towards Alignment for Global and Local 2D-3D Correspondence
Aligning Inductive Bias for Data-Efficient Generalization in State Space Models
CuBic: Curvature-Driven Dynamic Inference Caching for Fast, High-Fidelity Flow Matching
MeshFIM: Local Low-Poly Mesh Editing via Fill-in-the-Middle Autoregressive Generation
MoCA: Mixture-of-Components Attention for Scalable Compositional 3D Generation
Search at the Cost of Sampling: Nearly-Instant Latent Space Bayesian Optimization
Falcon-X: A Time Series Foundation Model for Heterogeneous Multivariate Modeling
Hi-Q: Hierarchical Evidence-guided Query Refinement for Multi-Hop Question Answering
Treat Bias as Noise: Training Bias-Robust LLM Reasoning via Reinforcement Learning
Can Linguistic Reasoning Vectors Enhance Multimodal Reasoning Ability?
PGSB: Pretrained-Guided Shared Basis for LoRA Model Merging
WorldVLA: A Unified Vision-Language-Action and World Model
Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion
Existence Precedes Value: Joint Modeling of Observational Existence and Evolving States in Time Series Forecasting
Mitigating Compounding Errors in Online Reinforcement Learning via Optimal Transport Regularized Flow Matching
The Geometry of Agent Skills: Non-Commutative Composition in Representation Space
Text-side fragility in contrastive vision-language retrieval
MorphoGen: Free-Form XML Evolution for Robot Morphology Design
SGEvolve: Semantic Gradient Guidance for LLM-Driven Evolutionary Search
Masked Visual Actions for Unified World Modeling
Despa: Resolving Spatial Collapse in VLMs via Depth-Grounded Geometry
SpectralKV: Redundancy-Aware KV Cache Compression via Spectral Coreset Selection
Universal Byte-Level Encoding: UTF-8/UTF-16 Routing to Reduce Cross-Script Token-Budget Disparities
Synaptic Strength Controls Trainability and Structural Stability in Rank-Deficient RNNs
Object Hallucination Mitigation in Large Vision-Language Models via Self-Vision Dual Masking and Uncertainty-Triggered Assembly
SCHOLARPEER: A Multi-Agent Framework for Automated Peer Review
Agent$^2$ RL-Bench: Can LLM Agents Engineer Agentic RL Post-Training?
TraceGuard: Defending Multi-Turn Jailbreak Attacks via Prompt-Response Risk Signal Tracking
LLMs Keep Thinking When Told Not To
Co-evolution: A "One-to-many" LLM Fine-Tuning Paradigm
How Fine-Tuning Objectives Shape Layer-Wise Information in LLM Hallucination Detection
Glance Before You Tell: Anomaly-Guided 3D Radiology Report Generation with Heat-Conduction Slice Encoders
Reasoning Warm-up: Scaling Label-free RL via Verifiable Surrogate Rewards
UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling
Welfare, Improvability, and Variance: A Principal-Agent Approach to Optimal Benchmark Item Aggregation
Frontier-Eng: Benchmarking Self-Evolving Agents on Real-World Engineering with Generative Optimization
Learning Event-to-Field Operators Without Interpolation
Disentangling Dual Image References in Frequency Aware Diffusion Models for Personalized Generation
TokenRouter: Efficient Serving System for Token-Level LLM Routing
PAI-Actor: Cinematic Multi-Actor Character Replacement in Dynamic Scenes
Diffusion Path Samplers via Sequential Monte Carlo
Efficient evaluation and error pattern discovery for blackbox AI systems
OS-Pruner: Pruning Chains-of-Thought of Reasoning Models via Optimal Stopping
SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining
Reinforcement World Model Learning for LLM-based Agents
The Value of Covariance Matching in Gaussian DDPMs and the Lanczos Sampler
CPA: Efficient and Stable FP4 RL Training via Cross-Precision Alignment
Bricker to BRACE: A Bracket Exposure RAW Dataset and Restoration Model for Flicker-Banding
Biomedical Acquisition-induced Style Shifts as Mixture Shifts: Style-aware Mixture-of-Experts Multimodal Prompt Learning
What Makes Two States the Same? Value-Aware State Matching for Multi-Turn Agent Credit Assignment
Provably Accurate Shapley Value Estimation in High Dimensions via Sparse Leverage Sampling
Stochastic Heat Diffusion Models
Generalized Priority-Aware Shapley Value
Flexformer: Flexible Linear Transformer with Learnable Attention Kernel
RIFLE: Removal of Image Flicker-Banding via Latent Diffusion Enhancement
FlareReal: A Real-Captured Paired Dataset for Nighttime Lens Flare Removal
Dynamic Spectral Federated Graph-Level Clustering
Frequency-Synchronized Boundary Coupling for Training-Free Multi-Prompt Long Video Generation
TACO: Towards Task-Consistent Open-Vocabulary Adaptation in Video Recognition
A Batched Hartigan's $k$-Means Clustering
NorSA: Accelerating LLM Decoding via Normalized Sparse Activation
KNN Implementation Details Can Dramatically Change Performance: An Example from Cover Trees
Online Minimum Description Length Passive-Aggressive Algorithms
Paloma: Phase-Conditioned Residual Modulation for Time Series Forecasting
Module Specialization in Transformer Factual Recall under Correlated Fact Distributions
Weather-Robust Cross-View Geo-Localization via Prototype-Based Semantic Part Discovery
Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models
AMGenC: Generating Charge Balanced Amorphous Materials
DualSAT: A Dual-Branch GNN-Transformer Framework for SAT Solving
Randomized Kriging Believer For Parallel Bayesian Optimization With Regret Bounds
Good Token Hunting: A Hitchhiker's Guide to Token Selection for Visual Geometry Transformers
Consolidating Rewarded Perturbations for LLM Post-Training
Towards Principled Fine-Grained MoE Expert Pruning via Pseudo-Boolean Approximation
OmniCapBench: A Deep-Structured Evaluation Framework for Fine-Grained Audio-Visual Captioning
TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation
UniFlowDock: Flexible Docking with Complete Equivariant Velocity Fields
MIST: Reliable Streaming Decision Trees for Online Class-Incremental Learning via McDiarmid Bound
Fractal-G: Topology-Aware Heterogeneous Graphs for Medical Image Segmentation
Beyond SFT-to-RL: Pre-alignment via Black-box On-policy Distillation for Multimodal RL
Unlocking Compositional Generalization in Continual Few-Shot Learning
TRACE: Data-Free Text Reconstruction Attacks against Approximate Unlearning in LLMs
What does a Bayes-filtered transformer believe? A predictive Monte Carlo approach
Self-Programmed Execution for Language-Model Agents
Learning a Task-Adaptive Low-Dimensional Semantic Space for Improved Visual Classification
GHOST: Geometry-Hierarchical Online Streaming Token Eviction for Efficient 3D Reconstruction
Clapping: Removing Per-sample Storage for Pipeline Parallel Learning with Communication Compression
Training-Free Cultural Alignment of Large Language Models via Persona Disagreement
The Narrative Gap: Can LLMs help us Navigate Diverse Narratives Across Languages?
Horizon Adaptive Offline Policy Learning via Value Stitching
Encoding RNA Topology into Synthetic Alignments for 3D Structure Prediction
From Seeing to Foreseeing: Unleashing LVLM Thinking in Dynamic Latent Space
PISG: Constraint-Aligned Signal Amplification for Diffusion-Based Combinatorial Optimization
GEAR: Bridging the Planner-Actor Gap via Gradient-Aligned Policy Extraction
The Illusion of Multi-Agent Advantage
MapPolicy: Structure-Aware Imitation Learning for Robot Manipulation via Physically Constrained Scene Map
Aligned Delta-Triplane Transformers as Occupancy World Models
Repurposing Video Diffusion Transformers for Cross-View Temporal Object Correspondence
Adaptive LLM Routing for Multi-Turn Conversations with Continuously Evolving User Queries
Correpondence Alignment For Improved Virtual Try-On
Detect What You Need: Chain-of-Causal Reasoning for 3D Intent Grounding
Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation
Progressive Pseudo-label Self-balancing Towards Unsupervised Vision-Language Models Adaptation
FA-LAM: Focus-Aware Large Avatar Model for One-Shot 4D Animatable Gaussian Head
WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors
Hyperbolic Language Models: From Zipf to Compute-Optimal Scaling
ManipulationRAG: Retrieval-Augmented Fine-Grained Manipulation of Object Functional Parts
PRISM: Priority-Guided Scanning in the Wavelet Domain for UAV Maritime Small Object Detection
ProCARE: Real-World Study Automation via Profile-Grounded Evidence Contracts
Dynamic Cross-Modal Prompt Generation for Multimodal Continual Instruction Tuning
Logit-Gap Steering: A Forward-Pass Diagnostic for Alignment Robustness
Towards Optimal Pre-training Data Mixtures for Empowering Reinforcement Learning in LLMs
Breaking feature collapse in self-supervised time series encoder
AdvJudge-Zero: Binary Decision Flips in LLM-as-a-Judge via Adversarial Control Tokens
Decomposing how prompting steers behavior
MiniPIC: Flexible Position-Independent Caching in <100LOC
QuantDemoire: Quantization with Outlier Aware for Image Demoiréing
SPHQuant: Efficient extreme low bit weight quantization for Vision-Language Models
Bayesian Causal Stress Testing: Posterior Fragility of Treatment-Effect Conclusions
PRISM: Prior Rectification and Uncertainty-Aware Structure Modeling for Diffusion-Based Text Image Super-Resolution
RePiD: Efficient Recursive Pixel-Space Diffusion via Hierarchical Patch Denoising
Positional Encoding and Prompt-Order Sensitivity in In-Context Learning
RESIST: Resilient Decentralized Learning Using Consensus Gradient Descent
Where, What, Why, and Importance: Structured Defect Grounding for Text-to-Image Feedback
dRAE: Representation Autoencoder with Hyper-Spherical Codes
SearchV: Evolutionary Fine-Grained Visual-Token Skipping for Efficient Vision-Language Models
Contextual Flow Matching for High-quality Visual Content Generation
LongBanana: An Expert-Verified Benchmark for Long-Context Multi-Reference Image Synthesis
SAVeR$^2$: Reasoning-based Safety Alignment for Large Reasoning Models via Verifiable Rewards
ToLD: Efficient Time Series Forecasting via Tokenized Truncated Latent Diffusion
Robust and Efficient Continual Model Merging via Global Singular Subspace Separation and Restoration
The Multiscale Single-Index Model: A Toy Model for Hierarchical Feature Learning
Geometry Conflict: Explaining and Controlling Forgetting in LLM Continual Post-Training
KG-Guard: Graph-Based Hallucination Detection for Knowledge Base Question Answering
Gaussian Density Splatting Network
Seirênes: Adversarial Self-Play with Evolving Distractions for LLM Reasoning
SAGE: Scalable Automated Robustness Augmentation for LLM Knowledge Evaluation
HyperVQ: Enabling Hyperprior Entropy Modeling for VQ-Based Generative Image Compression
Scene-Adaptive VLA: Efficient Autonomous Driving via Dynamic Layer Routing
Simulation-Ready Compositional 3D Scene Reconstruction from a Single Image
Modeling the Vividness of Imagined Natural Scenes Reveals a Model-Common Image-Level Component in Vision Models
Computational Depth Predicts Quantization Sensitivity in Multimodal Models
Certified Robust Interpretability via Concept-Space Stability under Interventional Proxies
EvoCodeBench: Evaluating Coding Agents in Multi-Turn Iterative Interactions
DPA: Decentralized Primal Averaging with Quasi-Global Momentum for Highly Heterogeneous Data
Scaling Laws and Tradeoffs in Recurrent Networks of Expressive Neurons
CARD: Internalizing Expert Critique into Reinforcement Learning for Deep Search
Rethinking Credit Assignment in Cooperative MARL via Interventional Reward Response
EnvFaultBench: Benchmarking LLM Agents on Software Environment-Fault Troubleshooting
FIND: Frequency Invariance Disentanglement for Test-Time Adaptation in LiDAR 3D Detection
CA-Judge: Teach Large Models to Judge Anomalies via Comparison for Video Anomaly Detection
Continual Learning in Modern Hopfield Networks with an Application to Diffusion Models
Characterizing the Generalization Error of Random Feature Regression with Arbitrary Data-Augmentation
Beyond Data Scaling: Representation-Centric Pre-training for Vision-Language-Action Models
Reflection with Action-Induced Visual Differences for Desktop GUI Agents
PrivacySIM: Evaluating LLM Simulation of User Privacy Behavior
CURE: Coupled User-Grouped Reinforcement Learning for Cross-Domain Recommendation with Non-Overlapping Users
DSBTR: A Diffusion Schrödinger Bridge Trajectory Refiner for Multi-Agent Trajectory Prediction
Fast and slow gradient descent dynamics of logistic regression through weak alignment
FASTER: Rethinking Real-Time Flow VLAs
StreamPI: Streaming Multimodal Temporal Modeling for Vision-Language-Action Models
Beyond Semantics: The Unreasonable Effectiveness of Reasonless Intermediate Tokens
RxDiff: Discrete Diffusion for Medication Recommendation with Inference-Time Safety Control
PosePlaner: Denoising Any Feedforward Pose Predictor from Pairwise Planar Geometry
Action-On-Item Preference Flow: A Shared Event Schema for Predictive and Generative Personalization
EventLens: Event-Structure Reinforcement Learning for Video Understanding
Normalized SGD in the Convex Regime: First High-Probability Guarantees and Momentum Extension
BridgeTwist: Twisting Schrödinger Bridges for Training-Free Conditional Sampling
EvoOptiGraph: Weakness-Driven Coevolution via Graph-Based Structural Generation for Optimization Modeling
ELF: Embedded Language Flows
From Expert Knowledge to Optimization Modeling: Prototype-Based Data Synthesis and Logical Reinforcement Learning
Why Struggle with Continuous Latents? Interpretable Discrete Latent Reasoning via Rendered Compression
From Label Priors to Task Evidence: Long-Video Frame Selection via Bayesian GRPO
GenZ: Hybrid statistical–foundational models for knowledge discovery from real-valued multidimensional targets
LIME: Link-based User-item Interaction Modeling with Decoupled XOR Attention for Efficient Test Time Scaling
SPDEBench: An Extensive Benchmark for Learning Stochastic PDEs
Debiasing Random Oblique Projections for Subsampled OLS and Fast CUR in High Dimensions
Coverage-Verified Sparse Attention: Closed-Loop Quality Control for Long-Context LLM Decoding
Think Before You Generate: Active Panoramic Exploration for Text-to-3D Scenes
Seeing Is Not Screening: Multimodal Hidden Instruction Attacks on Agent Skill Scanners
Neuronal Identity as an Organizational Basis for Analyzing Neural Population Dynamics
Auditing Closed-Loop Learning in Recurrent Neural Networks: Reproduction, Robustness, and Generalization
PosterDuet: Co-Evolving Design Generation and Reward Optimization for Product Poster Synthesis
RiSE: Residual Subspace Expert for Generalizable Text-Centric Image Forgery Localization
DegBins: Degradation-Driven Binning for Depth Super-Resolution
Mimicking the Physicist's Eye: A VLM-centric Approach for Physics Formula Discovery
AgentVista: Evaluating Multimodal Agent in Ultra-Challenging Realistic Visual Scenarios
Brittlebench: Quantifying LLM robustness via prompt sensitivity
SatNav: A Scalable Benchmark for Long-Horizon UAV Vision-Language Navigation from Satellite Imagery
Stabilizing Off-policy LLM Optimization with Prefix Importance Ratio
Reweighted Flow Matching via Unbalanced Optimal Transport for Label-free Long-tailed Generation
SDFlow: Similarity-Driven Flow Matching for Time Series Generation
DressWild: Feed-Forward Pose-Agnostic Garment Sewing Pattern Generation from In-the-Wild Images
Multi-Agent Coordination via Support-Preserving Distillation
PROACT-Agent: Progressive Runtime Oversight and Active Circuit-breaking for Real-Time Safety
Renoise Consistency: Unlocking Efficient Self-Correction for Diffusion Large Language Models
Beyond Suspicious Steps: Ontological Trust in Long-Horizon Agents
Compact SO(3) Equivariant Atomistic Foundation Models via Structural Pruning
The Alternation Depth Principle for Neural Operator Design
MapShift: Controlled Post-Intervention Evaluation for Embodied World Models
PhaseDance: Capturing Rhythm and Expressivity in Dance Modeling
State Evolution Awareness for Category-agnostic 3D Point Cloud Tracking
RaPD: Resolution-Agnostic Pixel Diffusion via Semantics-Enriched Implicit Representations
PolyVision: Conditional Visual Scaling Via Dynamic Expert Routing For Vision-Centric MLLMs
Spectral Rank Calibration for Continual LoRA Merging in Multimodal Large Language Models
Joint EM Image Super-Resolution and Segmentation with Semantic and Structural Priors
The Alignment Illusion in Multimodal Large Language Models
TopoRefine: Topology-Aware Correspondence and Residual Refinement for Training-Free Subject-Consistent Generation
Accelerating Rectified Flow Models via Trajectory-Aware Caching
Stranger Things: When Objects Appear Without Their Typical Neighbours
HeatKV: Head-tuned KV-cache Compression for Visual Autoregressive Modeling
L2P: Unlocking Latent Potential for Pixel Generation
PoEM: Predicting New RL Outcomes from Existing Policies
Bridging Compute- and Data-Optimal Pretraining
Probabilistic Signature Inversion: Learning Conditional Distributions from Truncated Signatures
TopoRefine: Plug-and-Play Topology-Aware Contour Refinement for Building Segmentation
Noise-Started One-Step Image Super-Resolution via LR-Conditioned SplitMeanFlow and GAN Refinement
EntiRE: Invariant Learning for Robust Concept Erasure in Text-to-Image Generative Models
LiFT: Likelihood-Free Tree-Structured Policy Optimization for Flow-Based VLAs
MemTailor: Hierarchical Memory-Augmented Multi-Expert Learning for Long-Tailed Recognition
Learning Survival Models with Right-Censored Reporting Delays
HALO: Heterogeneous-Aware LoRA Optimization via Rank Allocation and Client-Aware Projection
Monroe: A Molecular Foundation Model for In-context Probabilistic Inference
An Efficient Algorithm for Thresholding Monte Carlo Tree Search
3D Gaussian Splatting within Self-Learned Neural View-Dependent Color Fields
Rethinking "RL Generalizes, SFT Memorizes": The Role of SFT Data
UGM: Unified Multi-scale Genomic Event Modeling with Site-level Joint Prediction
Joint protein, mRNA, DNA sequence design and optimization with nucleotide-level Potts models
Aligning LLMs with Biomedical Knowledge using Balanced Fine-Tuning
Flux: Online, Fine-Grained Data Scheduling for Training Machine Learning Interatomic Potentials
Before It Fades: Reinforcing Temporal Representations at Inference Time in VideoLLMs
PP-Mark: Provable and Publicly Verifiable Watermarking for Generative AI
Advancing Narrative Long Video Generation via Training-Free Identity-Aware Memory
A Unified Audio Language Model with Text-Aligned Factorized Audio Tokenization
TreeGraft: Adaptive Multi-Drafter Grafting for Tree-Based Speculative Decoding
Rethinking Memorization–Generalization Trade-Off in Generative Models
OBJECT-UNI: A Unified Model for Object-Centric Spatial Understanding and Controllable Generation
ControlSVG: Exploring Controllable SVG Generation with Autoregressive Models
JailBound: A FOL-Guided Jailbreak Evaluation Framework for Revealing Safety Boundaries of LLMs
Distance Marching for Generative Modeling
DriveStreamBench: Evaluating User-Conditioned Watch-and-Notify in Streaming Driving Video
CompactSplat: Spatially Adaptive Gaussian Distribution for Feedforward Scene Reconstruction
BMAttn: Block-Aligned Mixed-Precision Attention Quantization for LLM Inference
Sophon: A Procedural Diagnostic for Spatial Reasoning in Vision-Language Models
IRIS: Interpolative Rényi Iterative Self-play for Large Language Model Fine-Tuning
Code2World: A GUI World Model via Renderable Code Generation
ChronosAlign: A Large-Scale, Updatable Benchmark for Decomposing Temporal Alignment in LLMs
FocusBranch: Combinatorial Branch-and-Bound for $\ell_0$ Neural Network Robustness Verification
Symmetric Interventions for Eliciting Model Intent
Test-Time Prompt-Agnostic Decomposition
dMoE: dLLMs with Learnable Block Experts
Toward Minimal-dimensional Convex Calibrated Surrogate Losses for Classification with Rejection
RVCBench: Benchmarking Robustness of Voice Cloning Across Modern Audio Generation Models
Trajectory Evaluation via Rollout-Free World Model for End-to-end Autonomous Driving
Beyond Real or Fake: A Dual-Channel Authenticity and Reasoning Protocol for Photographic Assessment
Urbex: Agentic Spatial Grounding for City-Scale 3D Scenes
GEAR: Generator-Adaptive State Space Models for Associative Recall
Routeability Before Routing: Routeability Audit Protocol (RAP) and RouteabilityBench for Audited LLM Model Selection
PanoHK360: A Large-Scale 8K Urban Panoramic Dataset and Benchmark for Depth Estimation
xHC: Expanded Hyper-Connections
Masked Generative Pretraining Improves Cross-Dataset Transfer in Pixel-Space Diffusion
Compose Your Oracles: Off Policy Improvement with Aggregated Guidance
Discrete Diffusion Playground: A 2D Benchmark for Discrete Generative Models
FreshMem: Brain-Inspired Frequency-Space Hybrid Memory for Streaming Video Understanding
Efficient Serving for Dynamic Agent Workflows with Prediction-based KV-Cache Management
Causal-Geo: Neuro-Symbolic Spatial Grounding for Situated Agent Planning
Distributionally Robust Black Box Optimization-based Bidding Strategy in Auction-based Federated Learning
FELPS: Fair and Efficient Scheduling for Multi-LoRA Serving System
VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systems
Anymotion: A Dataset, Benchmark, and Baseline for Controllable Human Motion Editing
Simulation-free Unbalanced Dynamic Optimal Transport with General Growth Penalty
Hierarchical Concept Geometry in Language Representations Emerges from Word Co-occurrence
When Metropolis and Hastings Meet Bradley and Terry: Exact MCMC From Preference Voting
Extracting Search Trees from LLM Reasoning Traces Reveals Myopic Planning
Transformers Can Learn Multiclass Classification In-Context: Isotropy Governs Generalization
Learning Agentic World Vision-Language-Action Models for Autonomous Driving
CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating
ApertureAttn: Native 4K Video Generation with Image-Only Supervision
MDK-MoE: Multi-view Decomposed Kalman Mixture of Experts Framework for Non-stationary Time Series Forecasting
Gym-Anything: Turn Any Software into an Agent Environment
Approximation of Maximally Monotone Operators : A Graph Convergence Perspective
ReCoG: Relational Concept Graph for Training-Free Personalization
VSearcher: Long-Horizon Multimodal Search Agent via Reinforcement Learning
CoreQ: Learning-Free Mismatch Correction and Successive Rounding for Quantization
AdaM-Rec: Adaptive Modality Routing for Multimodal Recommendation
RealICU: Do LLM Agents Understand Long-Context ICU Data? A Benchmark Beyond Behavior Imitation
Robust Approximate Nearest Neighbor Search for Any Dataset
MedFlowBench: Auditing Medical Agents in Full-Study Workflows
Cooperative Multi-Agent Reinforcement Learning via Epigraph-Form Guided Exploration
Rethinking Visual Reasoning in Text-to-Image Reward Modeling
Position: AI Development Should Prioritize Cognitive Security
Learning to See Through Language: An Exploration of Language Modeling's Effect on Visual Representations
Diffusion Masked Pretraining for Dynamic Point Cloud
Tikhonov-Stabilized Bezier Representation Forecasting for Training-free Diffusion Acceleration
Decoupled Safety Control: A Safety-Control Algorithm for Training-Free Safety Guidance
Implicit Neural Representations for Variational Problems on Graphons
STEER: Route-Aware Adaptive Reasoning for Autonomous Driving
RA-CFGCache: From Branch-Level Criteria to Guided-Risk Control under Classifier-Free Guidance
LEGO: Sizing Rules for Budget-Aware Dense-to-MoE Conversion of Vision-Language Models
CI4A: Semantic Component Interfaces for Agents Empowering Web Automation
Hermes: A Multi-Scale Spatial-Temporal Hypergraph Network for Stock Time Series Forecasting
FLAME: Flow Enhanced Legendre Memory Models for General Time Series Forecasting
REFLEX: Reflective Evolution from LLM Experience
Adaptive Internal Readout for Native Multimodal Models
Exposing and Mitigating Temporal Attack in Deepfake Video Detection
WavNAF: Learning Wave Propagation Priors for Neural Acoustic Fields
Safeguarding Mutual Correction in Source-Free Domain Adaptation via Cut Statistics
Localizing Input Uncertainty Quantification for Large Language Models via Shapley Values
Instance-Dependent Bandit Convex Optimization in One Dimension
Balancing Image Compression and Generation with Bootstrapped Tokenization
TimeTok: Granularity-Controllable Time-Series Generation via Hierarchical Tokenization
Beyond Appearance Shifts: Task-Semantic Action Calibration for VLA Models
Prism: Harmonizing Missing Modalities via Implicit Structural Alignment on Lightweight Pulse RWKV for Multimodal Crack Segmentation
A Unified Approach for Computing Wasserstein Barycenters of Discrete and Continuous Measures
Attention Transfer Is Not Universally Effective for Vision Transformers
Beyond Token Representations: Explicit Visual Object Grounding for Video Reasoning Segmentation
Safe Active Learning with Future Viability Guarantees in Time-Series Models
Training Quality Determines Efficiency Boundaries in Test-Time Reasoning
SUGAR: A Scalable Human-Video-Driven Generalizable Humanoid Loco-Manipulation Learning Framework
FETTUCCINE: Fast and efficient brain-to-text decoding on mobile devices
FoundSurface: Feedforward Ray-Based 3D Scene Surface Reconstruction from Unposed Images
Revisiting Activation Steering Through an Optimization Lens
OFBD: Object-Focused Background Debiasing for Long-Tailed Learning
ARROW: Augmented Replay for RObust World models
DepthMaster: Unified Monocular Depth Estimation for Perspective and Panoramic Images
Subliminal Learning Is Steering Vector Distillation
Speculative Self-Distillation enables Efficient Knowledge Internalization
Direct Product Flow Matching: Decoupling Radial and Angular Dynamics for Few-Shot Adaptation
One Loss to Rule Them All: Marked Time-to-Event for Structured EHR Foundation Models
Rethinking Causal Action Tokenization with Conditional Annealing in Flow Matching
Contribution-Aware Structured Sparsity for Model Merging
DMax: Aggressive Parallel Decoding for dLLMs
Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex
Rethinking Molecular Graph Backdoors under Chemistry-aware Admission
PrivateSeal: Low-Sensitivity Latent Directions for Diffusion-Resilient User-Specific Watermarking
MoME: Mixture-of-Memory Embeddings for Context-Aware Sparse Lookup
Deadline-Constrained Dynamic Workflow Scheduling Can be Cast as a Representation Learning Problem
Efficient Hybrid Distillation: Synergizing Score and Adversarial Objectives for One-Step Diffusion
Beyond Feature Disruption: Boundary-Diverting Unlearnable Examples against Linear Probing
PACE-dLLM: Elastic Block Decoding via Confidence Cliff Estimation for Diffusion Language Models
UniDBO: A Unified Dual-Branch One-Step Denoising Framework for Autonomous Driving Scenario Generation
The Foundation Model Transparency Index
MMCompass: Diagnosing Position Bias in Generative Multimodal Reward Models
Environment-Robust Representation Learning with Empirical Bayes
BrainWhisperer: Leveraging Whisper for Speech Decoding in Neuroprosthetics
Model-Agnostic FDR Control via Group Gaussian Mirror and Permutation SHAP
MFlowAudio: Efficient Text-to-Audio Synthesis via Mamba-based Stateful Flow Matching
CLeaR: A Unified Framework for Resolving the Leakage–Degradation Dilemma in Style Transfer
PO-PDDL: Learning Symbolic POMDPs from Visual Demonstrations for Robot Planning Under Uncertainty
Calibration without Ground Truth
Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems
Masked Diffusion Vision-Language Models for Temporal Action Localization
LongSCOP: Semantically Consistent Long Video Outpainting
See to Believe: Segmentation by Reasoning with Visual Evidence
Training with Harnesses: On-Policy Harness Self-Distillation for Complex Reasoning
Social Interaction Breaks Replicate Independence in Controlled-Clone LLM Agents
Learning Generalizable Hand-Object Tracking Control without Human Demonstrations
DataFlex: A Unified Benchmark and Evaluation Platform for Data-Centric Training of Large Language Models
LLM Rheology: Auditing Refusal Geometry in Aligned Language Models
UniRank: Unified List-wise Reranking via Confidence-Ordered Denoising
TRIDENT: Post-Selection Evidence Accountability for Token-Efficient RAG
On JEPA Isotropy
GeoRouter: Dynamic Paradigm Routing for Worldwide Image Geolocalization
Memory Type Varies: Empowering LLM Agents for Long-Term Memory with Diverse Strategies
TrajEvolve: Trajectory Evolution for Reinforcement Learning with Hindsight Credit Assignment
Resolving Time-Frequency Ridge Crossings via Frequency-Rate Lifting
Amortized Optimal Transport from Sliced Potentials
Moment-Constrained Latent Steering for Flow Policy
Foveal-Mamba: Inside-Out Ring Scanning with Recurrent Offset Prediction for Visual State Space Models
Counting without Scale: Scale-Consistent Error Correction for Crowd Counting
Online Quantile Omniprediction for Proper Losses
CoQuant: Covariance-Aware Rotation for 2-bit KV Cache Quantization
When does LeJEPA learn a World Model?
The Hidden Ratio in Adam: Stable Structure, Compression, and Sign Dynamics
Know Where You Stand: Memory-Source Choice in Long-Context Dialogue Agents
MILES: Modular Instruction Memory with Learnable Selection for Self-Improving LLM Reasoning
Opponent Modeling in Incomplete-Information Continuous Colonel Blotto
$\mathbf{D^{3}S^{2}}$: Diffusion-Guided Dataset Distillation for Semantic Segmentation
Ask in the Crowd: Differentially Private LLM Inference via Dummy-Augmented Shuffling
SenseBench: A Benchmark for Remote Sensing Low-Level Visual Perception and Description in Large Vision-Language Models
TrAction: Action Recognition with Sparse Trajectories
One-Shot Federated Graph Learning via High-Fidelity Proxies and Transferability-Guided Collaboration
Compute-optimal data scaling for neural surrogates via multi-fidelity training
Distributionally Robust Listwise Preference Optimization
Measuring Coherence in Predictive Models
The Reward Was in Your Data All Along: Correcting Flow Matching with Discriminator-Guided RL.
REDACTED-Tunes: An Open 1.4M-Track Dataset and Perceptual Benchmark for AI-Generated Music
CLIFT: Conformal Self-Verification for Web Agent Training and Test-Time Scaling
Neural networks are more modular than single neurons suggest
Sparse All-Layer Connector for Domain Generalised Semantic Segmentation
PRIME: Poincaré return induced measure for learning partially observed dynamical systems
Temporal Prototype Alignment for Frozen-Feature Dataset Distillation
AVENUE: Audio-Video Editing Understanding and Evaluation
AgentTailor: Dual-Gate LLM-Assisted Re-ranking for Personalized Long-Tail Recommendation
Fast and Consistent Structure Learning in Graphical Models via Approximate Cross-Validation
Ultra Flash: Scaling Real-Time Streaming Video Generation to High Resolutions
On the Faithfulness of Visual Thinking: Measurement and Enhancement
Reproducibility study of FACTER: Fairness-Aware Conformal Thresholding and Prompt Engineering
Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models
D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models
Visual-Advantage On-Policy Distillation for Vision-Language Models
DiT4DiT: Jointly Modeling Video Dynamics and Actions for Generalizable Robot Control
Learning Reusable Motor Motifs for Continuous Animal Behavior Modeling
From Document Layout to Causal Topology: An End-to-End Architecture for Temporal Causal Reasoning
STAR: Boosting Time Series Foundation Models for Anomaly Detection Through State-Aware Adapter
SitCom: Scaling Egocentric Multi-Party Spoken Dialogue for Situated Communication Assistance
A Hebbian Recurrent Neural Network Explains the Hierarchical Geometry of Sequence Memory
NeuroHorizon: Long-Horizon Forward Prediction of Neural Population Activity via Autoregressive Decoding with Hierarchical Memory
Near-Linear Time Generalized Sinkhorn Algorithms for Bounded Genus Graphs
Counterfactual Estimation under Composite Treatments via Progressive Distribution Alignment
Implicit Bias in State Space Models and Linear Autoregressive Training
ReSET: Accurate Latency-Critical NVFP4 Reasoning via Step-Aware Temperature Scaling
Search, Edit, and Fold: LLM-Guided MSA Optimization for Protein Conformation Prediction
Can In-Context Learning Support Intrinsic Curiosity?
The Quantization Benefits of Residual-Free Transformers
Reasoning-Aware IRT: Explainable Evaluation of Test-Time Scaling in Reasoning Models
Towards Realistic Conversational Multimodal Instruction Following
CoRE-RL: Co-evolving Reasoning Trajectories and Evidence Subgraphs with Learned Evidence Projection
AdaTree: Serving-Aware Adaptive Tree Construction for Speculative Decoding
Efficient Training of Deep Spiking Neural Networks with Input-Driven Derivative-Free Updates
Inadvertent Context Leakage in Language Models
ChartArena: A Unified Benchmark with Atomic-Primitive Reasoning for Chart Parsing
Bias-Variance Optimized Preference Optimization for Large Reasoning Models
Prefix-Tuning for Arbitrary Output Sequences on Pretrained Transformers
Attention Drift: What Auto-Regressive Speculative Decoding Models Learn
Fine-tuning language encoding models on slow fMRI improves prediction for fast ECoG
SAMoR: Motion Modelling for Articulated Objects of Any Skeleton and Topology
DiffScore: Text Evaluation Beyond Autoregressive Likelihood
Kairos: Toward Adaptive and Parameter-Efficient Time Series Foundation Models
Invaria: Learning Scale and Density Invariance in Point Clouds via Next-Resolution Prediction
Cross-Domain Knowledge Separation and Positive Transmission for Noisy Domain Incremental Learning
MaskSense: Confronting the Visual Exploration Trap in Masked Image Generation
Trustworthy and Efficient Map-free LiDAR Localization via Scan-Pose Alignment and Flow Matching
BiLi: Bridging the Last Mile in LiDAR Localization
Understanding Generalization Requires Universal Induction
Blind-Window Forecasting: Real-Time Benchmarking and Multimodal Reconstruction for Tropical Cyclones
Understanding and Mitigating Under-Confidence in GNNs from the Final Layer
Hawkeye: Hardware-Aware GPU Kernel Optimization with Minimal Supervision
From Retrieval to Recognition: Knowledge-Enhanced Foundation Models for Time Series Classification
KL for a KL: On-Policy Distillation with Control Variate Baseline
Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor’s Internal States
Look Before You Leap: Self-Evolving Clinical Reasoning with Psychometric Preference Optimization for Radiology Report Generation
Controllable Dynamic 3D Shape Generation via 3D Trajectories and Text
Pathway-Aligned Regulator Tokens for Interpretable Spatial Gene Expression Prediction from Histologyatial Transcriptomics Prediction from Histology
The Compliance Trap: Diagnosing How AI Agents Consume Conflicting Memory
Linear approximations to HMM filtering
Grounding Agent Reasoning with Structured Process Supervision for Multi-turn Reinforcement Learning
KaliBench: A Fine-Grained Benchmark for Cybersecurity Tool Use on Kali Linux with Runtime-Free Verifiable Rewards
Learning Multimodal One-step Flow Policy via Value-weighted Optimal Transport
MOCHA: Discovering Multi-Order Dynamic Causal Structure in Temporal Point Processes
Rank-Aware Differentially Private Release of Listwise Preferences for LLM Alignment
Meta-Reinforcement Learning with Zero-Shot Reinforcement Learning
Align Before Aggregation: Basis-Consistent Federated LoRA under Heterogeneous Ranks
Dataset Distillation via Drifting
Improved Weakly Supervised Semantic Segmentation with A Relationally Optimized Prototype Memory Bank Framework
Are Well-Trained Surrogates Optimal? Rethinking the Surrogate Role with Instability for Unlearnable Examples
Post-Selection Distributional Model Evaluation
A Closer Look at Dynamic Scene Graph Generation in the Era of Multimodal Large Language Models
A Stability Analysis of AdamW: Unstable Equilibria and Non-Convergence
Muon Does Not Converge on Convex Lipschitz Functions
Time to Pay Attention! Understanding High Complexity Corpus Reasoning Tasks
Can Language Models Actually Retrieve In-Context? Drowning in Documents at Million Token Scale
The Reflexivity Threshold: A Phase Transition for Multi-Agent Performative Prediction
Structural Causal Bottleneck Models
Imagine, Don't Narrate: The Generative Bottleneck in World Models of Interaction Dynamics
Why Speculative Decoding Works Better Than Predicted on Sparse MoE Models
Leveraging unlabelled data for generalizable neural population decoding
Where to Look Is Not How to Fix: Pre-Denoising Diagnostics and Modality-Dependent Control in Diffusion Composition
Unlocking Any-Order Generation in Pretrained Autoregressive Image Models
Behavioral Foundation Models for Quality Diversity
STILL: Selecting Tokens for Intra-Layer Hybrid Attention to Linearize LLMs
Leveraging Error Diversity in Group Rollouts for Reinforcement Learning
Differentiable Learning of Lifted Action Schemas for Classical Planning
ParetoM$^3$: Learning on the Pareto Set under Preference Guidance via Min-Max-Min Optimization
Cognitive Firewalls: A Synthetic Account of Cross-Lingual Reasoning Collapse
Last-Iterate Convergence of Single-Loop Stochastic Methods for Constrained Convex-Concave Minimax Problems
Region-Normalized DPO for Medical Image Segmentation
TRACE: Tourism Recommendation with Accountable Citation Evidence
Multi-step Consistency Models: A Complete Error Theory and Optimal Step Selection
PhaseLoRA: Control-Regime-Conditioned Low-Rank Adaptation for Continuous-Action Vision-Language-Action Policies
Learning Joint Semantic-Geometric Uncertainty for Structured Prediction with Closed-Loop Calibration
DualDrift: Combining Forward and Reverse Drifts for One-Step Generative Modeling
ReflectMT: Internalizing Reflection for Efficient and High-Quality Machine Translation
RAWild: Toward Sensor-Agnostic RAW Object Detection via Physics-Guided Curve and Grid Modeling
MolHIT: Advancing Molecular-Graph Generation with Hierarchical Discrete Diffusion Models
DisCoMBO: Steering Expert-in-the-Loop Black Box Optimization via Distributional Conformance
Temporal Alignment Guidance: On-manifold Sampling in Diffusion Models
AdaOcc: Adaptive 3D Occupancy Prediction for Embodied Tasks
FluxFlow: Conservative Flow-Matching for Astronomical Image Super-Resolution
Beyond Flat Gossip: Tiered Gossip Learning for Scalable Collaborative AI
VideoSleuth: A Narrative-Centric Agentic System with Video-Audio Native MLLM for Long-Form Video Understanding
SENTINEL: A Multi-Level Formal Framework for Safety Evaluation of Foundation Model-based Embodied Agents
Path-Guided Flow Matching for Dataset Distillation
StateTree: Enhancing Long-term Dialogue Reasoning via Reinforcement Learning
The Many Senses of Visual Similarity: A Text-Prompted Image Perceptual Metric
AGiR: Mitigating Gift Over-Reliance in Mixed-Motive Games
TracingFlow: A Simulation-Free Trajectory Inference Framework Based on Second-Order Dynamics
Revisiting Gradient Ascent: Machine Unlearning from a Geometric Perspective for Source-Free Scenarios
Truth as a Compression Artifact in Language Model Training
Reporting Practice Matters: The Impact of Reference Choice on Chest X-ray Report Evaluation
Market Incentives for AI Safety Investment
Scaling Laws for Multimodal Data Mixtures
TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking
Neural Compression of Long ADMM Trajectory for Multiparametric Quadratic Program
Comparing Linear Regions in ReLU-Type Networks: Theory and Monte Carlo Methods
A Unified Merge Calculus for Learning-Rate Scaling on Neural Computation Graphs
DART: Zero-Shot Dual-Side Alignment Routing for LLM Performance-Cost Tradeoffs
RelAgent: LLM Agents as Data Scientists for Relational Learning
Iterative Chow Filtering for Learning with Distribution Shift
IntentLens: Grounding Underspecified Multimodal Queries for Recommendation via Tool-Augmented Reasoning
UTOPI: Efficient Egocentric Long-Video Understanding in AR via User-Guided Token Pre-Compression
BRIDGE: Brain-Vision Representation Integration through Depth and Granularity Encoding
AnyEdit: A Unified Framework for Speech and Singing Voice Editing with Real-World Environmental Consistency
SFT-then-RL Outperforms Mixed-Policy Methods for LLM Reasoning
VideoMaMa++: Temporally Consistent Video Matting via Preserve-and-Refine Tokens
BrickFlow: Connectivity-Guided Brick Reconstruction
Test-Time Graph Recalibration: Enhancing Robust Zero-Shot Inference for Graph Foundation Models
My Video Stays Mine: Temporally Consistent Universal Adversarial Perturbations against Video Customization
Why Deterministic PRM Guidance Underperforms in Discrete Diffusion Reasoning
Video Generation Research Needs a Legally Sustainable Data Infrastructure
StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction
VUM: Visual Unified Models for Image Generation and Perception
A Generative Model of Contextual Integrity: Appropriate vs. Inappropriate Information Sharing
How Much of a Model Do We Need? Redundancy and Slimmability in Remote Sensing Foundation Models
CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes
I2V-DETACH: Source Grounding Detachment for Unauthorized Image-to-Video Generation
Get a GRIP, this will be a long TRIP: A Quantifiable Long-Range Framework for Verifying Over-squashing
Semantic Concept Steering Breaks the Explanation Drift Loop in Continual Learning
FraudBench: A Legal Evaluation of AI Deception on Realistic Tasks
Who&When Pro: Can LLMs Really Attribute Failures in AI Agents?
RAO-Nav: Probing Omni-Language Models for Zero-shot Semantic Audio-Visual Navigation
DiffCap-RL: Differential QA Rewards for Dense Image and Video Captioning
Learning Where It Matters: Geometric Anchoring for Robust Preference Alignment
Support Before Frequency in Discrete Diffusion
PULSE: Probabilistic Uncertainty-Aware Longitudinal Simulation for EHR Trajectories
Rescaled Asynchronous SGD: Optimal Distributed Optimization under Data and System Heterogeneity
Autonomous Continual Learning for Environment Adaptation of Computer-Use Agents
Generative Modeling by Value-Driven Transport
Aligning Few-Step Generative Model via Amortizing Sample-Based Variational Inference
Selected-Tail Reliability in Verifier-Guided Best-of-$N$ Inference
Deep Probabilistic Supervision for Image Classification
Lumberjack: Better Differentially Private Random Forests through Heavy Hitter Detection in Trees
Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation
Why Do DiT Editors Drift? Plug-and-Play Low Frequency Alignment in VAE Latent Space
Perception, Not Reasoning, Limits Visual Theory of Mind
SciHazard: A Benchmark for Measuring Scientific Safety Risks with Decomposed Harm Scoring
Manifold-Guided Stereo-Monocular Refinement for Endoscopic Stereo Disparity Estimation
Reading Between the Dots: Decoding Hidden Computation across Filler Tokens
When Does Non-Uniform Replay Matter in Reinforcement Learning?
Every Bit, Everywhere, All At Once: A Binomial Multibit LLM Watermark
Tracing the Cascade: A Topology-Aware Evaluation Framework for Scientific Agent Hallucinations
Active Flow Expansion for Out-of-Distribution Discovery: from Theory to Molecules
Fast Organic Crystal Structure Prediction with Unit Cell Flow Matching
What Is Worth Representing? Representational Empowerment for Continual Model Construction
Defense-as-Skill: Evolving Runtime Guard Skill for Skill-Augmented Agents
In-context learning to predict critical transitions in dynamical systems
MLLM Makes Strong Backbone for Multi-Modal Object Detection
Federated Logic Gate Networks via Boolean Feature Selection
Ensembling Language Models with Sequential Monte Carlo
From Link Prediction to Linear Community Detection: A Finite-Sample Guarantee for Graph Pretraining
FlatClip: Reusing Image Foundation Models for fMRI Representation Learning via Cortical Flatmaps
BrainWorld: A Structural-Prior-Conditioned Generative Model for Whole-Brain 4D fMRI Dynamics
Asymmetric Flow Models
Structured Coupling for Flow Matching
RIVET: Regex-to-Indexable Keys via Neural Translation for Interactive LIMIT-k Retrieval
Generative Molecular Morphing for Flexible-Size Design via Unbalanced Optimal Transport
How Complete Should a Reference Be? A Benchmark Audit for Fluorescence Spot Detection
LOSCAR-SGD: Local SGD with Communication-Computation Overlap and Delay-Corrected Sparse Model Averaging
The Symmetries of Three-Layer ReLU Networks
Cascaded Sparse Autoencoders LearnMulti-Level Visual Concepts in Multimodal LLMs
BAT3R: Robust Online 3D Reconstruction with Bayesian Adaptive State Updates
Learning to Solve Generative ODEs Beyond the Linear Span
Multistage Defer Trees for Hybrid Interpretability: If at First You Can't Succeed, Tree Again
LLMs Show No Signs Of Individuated Metacognition
PointZero: 3D Point Track Completion for Learning Transferable 3D Dynamics
In search of a definition of importance: Do attributions capture it?
Simple Baselines are Competitive with Code Evolution
BenchRep-T: A Systematic Evaluation of T-Cell Repertoire-Based Disease Diagnostics
HALO-VGGT: Heterogeneity-Aware Lightweight Online Compression Allocator for Efficient VGGT
PhysFlow: Physics-Intrinsic Velocity Regularization for Motion-Intensive Video Generation
Improving Neural Processes in the Low-Data Regime via Context-Subset Training and Self-Distillation
Q-ViK: Question-Guided Visual KV Cache Eviction for Large Vision-Language Models
PriSM: Prior-guided Shared-basis Mixture Personalization for LLMs under Sparse User Histories
Regret-Based $(\epsilon,\delta)$-optimal Stopping Criteria for Bayesian Optimization
From Noise to Diversity: Random Embedding Injection in LLM Reasoning
Hallucination as Commitment Failure: Larger LLMs Misfire Despite Knowing the Answer
UniMoE-World: A Unified Mixture-of-Experts Architecture for Scalable Multi-Control Video Generation World Modeling
Occupancy-based Quantile Risk Control
MMDiff: Multimodal Model Diffing for Feature Discovery and Control
Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks
Vortex: Efficient and Programmable Sparse Attention Serving
Stable Continuous-Time Consistency Distillation: An Empirical Study with a Multistep Extension
A latent control model for realistic rodent motion
Hypergraph Generation with Latent Diffusion
Information Discernment in Large Language Models
Automated Causal Effect Estimation through Self-Evolving AI
Learning to Explore with Parameter-Space Noise: A Deep Dive into Parameter-Space Noise for Reinforcement Learning with Verifiable Rewards
Controllable User Simulation
Estimating Implicit Regularization in Deep Learning
Persona Generators: Generating Diverse Synthetic Personas for Arbitrary Contexts
Beyond Langevin: Sampling Multimodal Densities using the Witten Laplacian on 1-forms
LensVLM: Selective Context Expansion for Compressed Visual Representation of Text
Invisible Ink, Visible Lies: How Production Watermarking Causes LLMs to Hallucinate
On Making $SE(2)$-Invariant Networks Optimal
Route-Consistent Adaptation for Stable Quantization of Mixture-of-Experts Models with Theoretical Guarantees
Diffusion Transformers with Residual Adaptive Layer Normalization
STREAM: Stochastic Riemannian Flow Matching with Anisotropic Decoder for Digital Histopathology Image Generation
From Denoising to Refining: A Corrective Framework for Vision-Language Diffusion Model
Kinetic-Optimal Scheduling with Moment Correction for Metric-Induced Discrete Flow Matching in Zero-Shot Text-to-Speech
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation
Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments
LaSA-Net: A Language-Guided Network for Outdoor Generalized 3D Referring Expression Segmentation
The Dormant Spiking Neuron: A State-Driven Mechanism for Efficient Spiking Neural Networks
IFDECORATOR: Wrapping Instruction Following Reinforcement Learning with Verifiable Rewards
Analyzing Learning-Dynamics Across Loss and Prediction Choices for Diffusion Models
Failing to Falsify: Evaluating and Mitigating Confirmation Bias in Language Models
Neural Neural Scaling Laws
Serialization Tax in Shared-Latent Exchangeable Decisions
Hit Expansion via Localized Exploration of Synthesizable Chemical Space
Boundary Mass in Feature Space as a Label-Budget Diagnostic for Representations
Robust Noisy Inductive Matrix Completion with Local Linear Convergence
PHIONet: Port Hamiltonian Inertial Odometry Network
On-Policy Consistency Training Improves LLM Safety with Minimal Capability Degradation
Learning Modular Addition with Auxiliary Modulus
From Finding to Linking: Benchmarking and Advancing Cross-Long-Video Reasoning for Multimodal LLMs
Low-Rank Adaptation for Critic Learning in Off-Policy Reinforcement Learning
TraceSim: A Generative Simulator and Benchmark for Joint scRNA-seq and Lineage Tracing
Guaranteed Jailbreaking Defense via Disrupt-and-Rectify Smoothing
Invariant Hyperbolic Unfolding: Radial Canonicalization for Label-Free Cross-Graph Link Prediction
Uncertainty Estimation for Pretrained Medical Image Registration Models via Transformation Equivariance
Pooling Versus Ensembling for Ridge Regression Under Covariate Shift
Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models
Ad-Hoc Teamwork from Human Demonstrations
Hidden Measurement Error in LLM Pipelines Distorts Annotation, Evaluation, and Benchmarking
ForceFlow: Learning to Feel and Act via Contact-Driven Flow Matching
PACE: Progress Actively-internalized Conditioning Execution for Long-horizon Manipulation
Robust Importance Sampling for Rare Events via Constrained Gaussian Mixtures
fxBench: Evaluating and Understanding Formula Suggestions in Spreadsheets
Characterizing Learning in Deep Neural Networks using a Tractable Algorithmic Complexity Estimator
From Clips to Streams: A Unified Framework for Streaming Sign Language Translation
Free Lunch for Pass@$k$? Low Cost Diverse Sampling for Diffusion Language Models
Learning POMDP World Models from Observations with Language-Model Priors
On the Relaxation of Conditional Independence Assumption for Image Segmentation
HyperVAttention: Efficient Sparse Attention with Spatio-Temporal Clustering for Video Diffusion
Asymmetric Scaling Laws from Sparse Features
Humanoid Horizon: Extending Task Horizon in Whole-Body Loco-Manipulation via Parallel Training, Dynamic Starting, and Reward Gating
Deceptive Grounding: Entity Attribution Failure in Clinical Retrieval-Augmented Generation
Understanding the Convergence of Direct Training of SNNs with Surrogate Gradients
Rethinking Gradient Approximation in Quantization: A Zeroth-Order Expectation Perspective
Fair Range k-Supplier Clustering in Offline and Streaming Models
dStructAD: Domain-Level Structured Normality Representation with Variation Calibration for Time Series Anomaly Detection
Block-Wise Differentiable Sinkhorn Attention: Tail-Refinement Gradients with a Gap-Aware Dustbin Bridge
SkillMaster: Toward Autonomous Skill Mastery in LLM Agents
SignalBench: Comparing Dense Feedback Methods for Long-Horizon Agents
Structuring Open-Ended NAS: Semi-Automated Design Knowledge Structuring with LLMs for Efficient Neural Architecture Search
Matrix-Free Natural Gradient via Stochastic Truncated Metrics
GRAPE: Graph-Augmented Prototype Explanations for Interactive Medical Image Diagnosis
Time-Frequency Decoupled Cross-Scale Partial Optimal Transport for Time Series Domain Adaptation
Exact Channel Decoupling via Joint Diagonalization and Uniform Splicing for Diffusion Transformer Quantization
ResKV: Residual-based Channel-wise Unstructured Pruning for KV Cache Compression
When Do Learned State Representations Break Sensitivity Analysis?
SoccerNarrate: Event-Grounded Streaming Soccer Commentary with Macro-Window Preference Alignment
Reflective Prompted Policy Optimization: Trajectory-Grounded Revision and Salience Bias
MSP: Modality Self-Play for Training Multimodal LLMs Without Paired Cross-Modal Data
Is Complex Training Necessary for Long-Tailed OOD Detection? A Re-think from Feature Geometry
Risk-guided Estimation-aware Acceptance for Learning with Synthetic Data
DDx-TRACE: A Benchmark for Medical Diagnostic Trajectories in VLMs
Epigenomics-Guided Flow Matching for 3D Genome Super-Resolution
Sharpness, Stability, and Step-Size Scaling in Deep Polynomial Networks
Consistent Bayesian Spatial Domain Partitioning Using Predictive Spanning Tree Methods
Statistical field theory for Markov decision processes under uncertainty
Minimax Optimal Two-Sample Testing under Local Differential Privacy
"What is Different Between These Datasets?" A Framework for Explaining Data Distribution Shifts
Towards Principled Task Grouping for Multi-Task Learning
Emergent Biological Capabilities in a Foundation Model for Molecular Interactions
Focus on Where You Aggregate: Restricted SAM for Non-IID Federated Learning
RSQ: Learning from Important Tokens Leads to Better Quantized LLMs
Rethinking the Mixture of Vision Encoders Paradigm for Enhanced Visual Understanding in Multimodal LLMs
Random features for Grassmannian kernel approximation with bounded rank-one projections
OTIS: Learning High-Quality Time Series Features With Tiny Encoders
Mollifier Layers: Enabling Efficient High-Order Derivatives in Inverse PDE Learning
In-context Learning in Presence of Spurious Correlations
Knowing What is Missing: Efficient Conversational Memory via Explicit Evidence-Gap Tracking
BioXArena: Benchmarking LLM Agents on Multi-Modal Biomedical Machine Learning Tasks
GeoReason: Bridging Logical Reasoning and Spatial Fidelity in Remote Sensing Segmentation
Below the Reliability Floor: Recovering True Success from Judge-Gated Loops
Learning-Augmented Streaming Algorithms for Approximating Boolean Max-CSPs
Toward Interactive Understanding of Code APIs
ReLoop: Structured Modeling and Behavioral Verification for Reliable LLM-Based Optimization
M*: A Modular, Extensible, Serving System for Multimodal Models
A Statistical Framework for Algorithmic Collective Action with Multiple Collectives
Neural population tuning statistics as priors for multitask generalization
Speculative Decoding Is Per-Token, Not Path
Non-Expanding Gated Continued Fraction Architecture for Feedforward Layers in Language Models
Automated Reformulation of Robust Optimization via Memory-Augmented Large Language Models
X-AVDD: Cross-Attentive Audio-Visual Dataset Distillation
Block Optimism for Nonstationary Bandits with Latent Linear Dynamics
Linear Ensemble Sampling with Fewer Ensembles
AnchorRep: Defending LLMs Against Cross-Model Adversarial Transfer via Representation Repulsion
Topic-Aware Contextual Cascading Bandits
Hierarchical Variational Policies for Reward-Guided Diffusion
Static Recovery Is Not Dynamic Stability: Dynamics-Aware Benchmarking of Protein Motif Scaffolding
SWE-Pro: A Benchmark for Evaluating LLMs on Performance-Oriented Repository-Level Optimization
Beyond Downstream Scores: Controlled Diagnostics for Point-Cloud Self-Supervised Learning Evaluation
BoardGameArena: A Multi-Dimensional Benchmark for Strategic Reasoning of LLMs in Board Games
Cracks in the Foundation: A Civil Infrastructure Dataset to Challenge Vision Foundation Models
TokenRepel: Generating Diverse Image Sets Without Sacrificing Quality
ASPI: Seeking Ambiguity Clarification Amplifies Prompt Injection Vulnerability in LLM Agents
NestedVLA: Learning to Consolidate and Generate Skills for Vision-Language-Action Model
Dynamic Model Merging Made Slim
Probing the Trajectories of Reasoning Traces in Large Language Models
Learning Generative Dynamics for 3D Molecule Generation via Sequential Neuro-Symbolic Constraints
Learning to Ask: Metacognitive Action Policy for Large and Small Language Model Collaboration
When to Inject the Target: Stage-Decoupled Guidance for Diffusion-Based Targeted Adversarial Attacks
ReasoningShield: Safety Moderation over Reasoning Traces of Large Reasoning Models
Beyond High and Low: Evaluating Graded Cognitive Diversity in LLM Persona Simulations
Attributions All the Way Down? The Metagame of Interpretability
Reward Hacking in Rubric-Based Reinforcement Learning
Same Words, Different Judgments: How Preferences Vary Across Modalities
GAPS: Gradient-Aware Adaptation-Gap Scoring for Time-Series Anomaly Detection with Foundation Models
CogArena: Benchmarking Multimodal Agents on Interactive Behavioral Experiments
MOOD: Benchmarking Post-Hoc OOD Detection for Materials Property Prediction
Behavior Cloning is Not All You Need: The Optimality of On-Policy Distillation for Noisy Expert Feedback
COOP$^2$: Defining, Observing, and Repairing Cooperation in LLM Multi-Agent Systems
WorldSpeech: A Multilingual Speech Corpus from Around the World
Flowette: Flow Matching with Graphette Priors for Graph Generation
Variational Active Flow Matching for Discrete Online Black-Box Optimization
Learning through Internalization
How to Instruct Your Robot: Dense Language Annotations Power Robot Policy Learning
TENET: Time-point Encoding Network for Multivariate Time Series Anomaly Detection
Unlocking LLM Creativity in Science through Analogical Reasoning
WiREBench: Evaluating AI Agents' Capabilities in Reverse-Engineering Black-Box Applications in the Real World
Distilling Multi-Teacher Scoring Principles for Unsupervised Time Series Anomaly Detection
Prefix Executability: Evaluating Tool-Using Agents Beyond Final Success
Align $\&$ Invert: Solving Inverse Problems with Diffusion and Flow-based Models via Representation Alignment
Internal Evaluation of Unsupervised Anomaly Detection Algorithms with Explanation
Before Words, Beyond Speech: Evaluating Nonverbal Social Reasoning in Early Childhood
Rethinking Knowledge Distillation for Diffusion Language Models
RESBev: Making BEV Perception More Robust
MoBayes: A Modular Bayesian Framework for Separating Reasoning from Language in Conversational Clinical Decision Support
FACETS: Cross-Granularity Vision--Language Modeling for 3D Anomaly Detection
Rethinking Projector Training in Multimodal LLMs
Reversing the Roles of Signal and Noise: Modeling Noise in Astronomical Images without Paired Data
EgoBabyVLM: Benchmarking cross-modal learning from naturalistic egocentric video data
Evaluating Uncertainty Calibration in Probabilistic Time Series Foundation Models
The Unreasonable Effectiveness of Text Embedding Interpolation for Continuous Image Steering
Structural Self-Teaching for Compositional Generation in Unified Multimodal Models
SUPERVISE: A Unified Framework for Standardized and Reproducible Superpixel Evaluation
Data Diversity Drives the Emergence of Symbolic Mechanisms Supporting Abstract Reasoning
CutAttn: Discovering Cognitive Transition Layers for Efficient Long-Context Prefilling
Towards Identifiable Latent Additive Noise Models
CausalCompass: Evaluating the Robustness of Time-Series Causal Discovery in Misspecified Scenarios
E-GEO: A Testbed for Generative Engine Optimization in E-Commerce
Revisiting the Adam–SGD Gap Beyond Single Factors
Reinforce Adjoint Matching: Scaling RL Post-Training of Diffusion and Flow Models
Reset Dependence Is Embodied: Training Protocol Changes Which Morphologies Appear Optimal
OfficeInstruct: A Dataset for Tool-Augmented Office Agents on Long-Trajectory Generative Tasks
DROGO: Default Representation Objective via Graph Optimization in Reinforcement Learning
On the fundamentals of gradient-based SAT solvers
Shaping Useful Noise: Energy Distributions Predict Visual Pretraining Quality
A Stratified Multi-Rater Evaluation of LLM-Based Virtual Standardized Patients with a Deployed Data-Generation Platform
Winning the Symmetry Lottery: Learning Invariance from Data Augmentations with Transformers
InSpect: A Curated Natural History Collection Dataset for Insect Specimen Understanding
CTE-Bench: Audited Counterfactual Trace Evaluation for Stateful Software Simulators
Off-policy Learning with Excursion Policies
Hidden Forgetting in Continual Multimodal Learning: When Accuracy Survives but Grounding Fails
MotionHalluc: Diagnosing Kinematic Hallucinations in Fine-Grained Motion Reasoning
VideoSailor: Navigating Video Deep Research via Trajectory-to-Policy Flywheel
FlexCover: Flexible Cover Song Generation via Symbolic Lead Sheet Control
Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth
On Reparameterizing the Score Function
Formal Conjectures: An Open and Evolving Benchmark for Verified Discovery in Mathematics
Greedy Alignment Principle for Optimizer Selection
Ask-E: An Environment for Calibrated Question Generation
MoCAR: Motion-code Coordinate-aware AutoRegression for Continuous Trajectory Forecasting
Noisy2Latent: Nonparametric Deconvolution and Denoising via Maximum Mean Discrepancy
Don't Match the Noise: Distribution Matching under Unknown Measurement Error with an Audit Sample
When Policy Entropy Constraint Fails: Preserving Diversity in Flow-based RLHF via Perceptual Entropy
StaminaBench: Stress-Testing Coding Agents over 100 Interaction Turns
LAION-BVD: A 10-Million-Hour Open Video Dataset for Multimodal Pre-training
V2VFusion: Text-Controlled Video-to-Video Diffusion for Degradation-Aware Video Fusion
Incorporating Neural Network Structure in the Bayesian Learning Rule
Representation Forcing for Bottleneck-Free Unified Multimodal Models
SREGym: A Live Benchmark for AI SRE Agents with High-Fidelity Failure Scenarios
MetaLoop: Benchmarking the Full Metacognitive Loop in LLMs
Testable and Actionable Calibration for Full Swap Regret
SOAP-Bubbles: Effective and Scalable Variational Learning with Structured Covariances
ELMA: Benchmarking Anaphoric Compositions for Long-Term Text-to-Motion Generation
Watermarking Should Be Treated as a Monitoring Primitive
Nature3D-AD: Geometry-Aware Feature Learning for Natural-Growth 3D Anomaly Detection
Tatemae: Detecting Alignment Faking via Tool Selection in LLMs
MindGames:A Multi-Agent Benchmark and Trajectory Dataset for Evaluating Social and Strategic Reasoning in LLMs
The Surprising Effectiveness of Deleting Weights in LLM Reasoning and Adaptation
Sample-Grained Approximate Unlearning with Provable Per-Sample Bounds
Disambiguating 2D-3D Correspondences in Gaussian Splatting-based Feature Fields for Visual Localization
CIPHERGRID Benchmark: From Multimodal Rule Inference to Sequential Action
GenAI Evaluation Results are Largely Artifacts of Evaluation Design Choices: Evidence from Audit Studies of Resume Screening
LatentRAG: Latent Reasoning and Retrieval for Efficient Agentic RAG
LEAF: Language-EEG Aligned Foundation Model for Brain-Computer Interfaces
Process-conditioned Pretraining with Topographic Spatial Retrieval for Large EEG Models
A Theoretical Analysis of Test-Driven Code Generation
V2M-Zero: Zero-Pair Time-Aligned Video-to-Music Generation
WorldForge: Forging Unified World Modeling into Video Generation
Auditing Conformal Prediction for Language Models Under Inference-Time Model Shift
Flash PD-SSM: Memory-Optimized Structured Sparse State-Space Models
CircuitSeer: Mining High-Quality Data by Probing Mathematical Reasoning Circuits in LLMs
Efficient Benchmarking Is Just Feature Selection and Multiple Regression
Selective Off-Policy Reference Tuning with Plan Guidance
Rationale-Guided Policy Optimization: Learning to Reason with Adaptive Rationale Scaffolding
Two-Level Softmax Sampling Done Right: Correcting Bias from Size Imbalance and Dispersion
Zeroth-Order Stackelberg Control in Combinatorial Congestion Games
Signature-Kernel Evaluation Metrics for Robust Probabilistic and Tail-Event Forecasting
Training-Free Task Vectors for LLM Behavioral Control
Matching-while-Decoding: Enhancing Template-Free Retrosynthesis via Explicit Structural Alignment
Hidden Tails: Certifying Tail-Risk Claims under Selective Labels
PixFoundation 2.0: Do Video Multi-Modal LLMs Use Motion in Visual Grounding?
Fisher-Glass: Tail Sample Complexity from Nuisance-Projected Fisher Information
Stabilizing RL+Search for Imperfect-Information Extensive-Form Games
SurgReasoner: Surgical Reasoning Segmentation with Dynamic Difficulty-Aware Reinforcement Learning
Gradient Descent’s Last Iterate is Often (slightly) Suboptimal
MINT: Meeting-time INdicators for Truncation in Multi-Step Off-Policy RL
When Guessing is Rewarded: Rethinking Language Model Evaluation with Distributional Uncertainty Scoring
PIU-CR: Physics-Informed Deep Unfolding Network with SAR-Optical Image Fusion for Cloud Removal
Crossing the Validation crisis: Cross-validation reduces benchmarking variance surprisingly well
S2T-RLHF: Hierarchical Credit Assignment for Stable Preference-Based RLHF
MURPHY: Feedback-Aware GRPO with Retrospective Credit Assignment for Multi-Turn Code Generation
ZeoBench: A Benchmark for Self-Supervised Learning on 3D Zeolite Representations
ObsConDA: Observability-Constrained Data Assimilation with Control-Space Inference
Fisher information and the geometry of memorization in neural networks
AsyncMesh: Fully Asynchronous Optimization for Data and Pipeline Parallelism
ChainForge: Tool-Chain Hijacking Attacks against LLM Agents via Execution-Grounded Tool Synthesis
DualSteer: Dual-Space Steering for Robust Jailbreak Mitigation of Large Vision Language Models
Beyond Node Sequences: Relational Diffusion for Unified Graph Learning
T2V-AttnDisrupt: Inducing Hallucinations in LVLMs via Misrouting Visual Evidence Retrieval
ConforFlux: Particle-Guided Trunk Repulsion for Diverse Protein Conformations
AERO: Adaptive Ensemble-Disagreement Routing for Oracle Feedback in Sample-Efficient Online RLHF
Synsema: Syntax-Guided Learning of Semantically Valid Programs
Spectral Transformer Neural Processes
SEAR: Sample Efficient Action Chunking Reinforcement Learning
Scalable Maximum Entropy Reinforcement Learning for Diffusion Policies via Adjoint Matching
Drifting Fields are not Conservative
LoopPrune: Evolutionary Module Selection with Iterative Execution for Efficient Large Language Model Compression
Multigroup Fairness and Omniprediction: Separations and Equivalences
Latent Introspection: Models Can Detect Prior Concept Injections
Provable Joint Decontamination for Benchmarking Multiple Large Language Models
Problem-Dependent Dynamic Regret over a Predictor Class with One-Gradient Feedback
IADR: Interface-Augmented Neural Operator for Phase-Field Mean-Curvature Flow
LDD-RFM: Learnable Domain Decomposition for Random Feature Models via Variable Projection
Locally-Additive Regret for Delayed Non-stationary Bandit Convex Optimization
Sample Efficient Generative Molecular Optimization with Joint Self-Improvement
Tail Competition Explains Scaling in Best-of-N Sampling for Verifiable Problems
Real-World Dual-Pixel Raindrop Removal: A New Benchmark and Degradation-Adaptive RWKV Baseline
Conclusions from Circuit Extraction Depend on the Level of Description: A Controlled Comparison
Visual Enhanced Depth Scaling for Multimodal Latent Reasoning
Discretizing Continuous Time Series for Imputation with Masked Diffusion Training
A Locally Tokenized Generative Model for Robust Time-Series Watermarking
Code Review Bench: An Automated Benchmark for Evaluating the Software Factory
Efficient Forecasting of Task Failures in LLM Agents through Adaptive Fault Injection
Test-Time Scaling in the Wild: Why Exploitation, Not Exploration, Is the Bottleneck
Uncovering Hidden Propensities in Language Models via Limited-Parameter Finetuning
SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning
KernelDNA: Cross-Layer Kernel Sharing via Decoupled Neural Adapters
Learned Lagrangian Models of PDEs via Euler–Lagrange Residual Minimization
MC^2: Monte Carlo Correction for Fast Elliptic PDE Solving
When All Paths Lead to Dead End: Deadlock-Depth-guided Monte Carlo Tree Search for Reentrant Blocking Hybrid Flow Shops
TRACE: Structure-Aware Character Encoding for Robust and Generalizable Document Watermarking
Causal Discovery with False Positive Error Control
Surface Recovery Is Not State Recovery: Pressure–Recovery–Relapse in Multi-turn LLMs
Gradient Boosted Trees for Retrieval-Augmented Generation
Graph Topology Augmentation for Prioritized Sweeping in Non-stationary Reinforcement Learning
Label-Efficient Dataset Pruning via Semi-Supervised Pseudo-Labeling
Uniform Spectral Growth under Factor-wise Muon Orthogonalization in Matrix Factorization and LoRA
CAST: Certifiable Aggregation of Smoothed Teachers for Robust Policy Adaptation
Agnostic Language Identification and Generation
Beyond Exemplar Selection: Value-Aware Memory Allocation in Replay-Based Continual Learning
On-Policy Counterfactual Influence
AdaptFlow: State-Anchored Goal Conditioning with Flow Matching for Offline Goal-Conditioned RL
Unified Approach for Weakly Supervised Multicalibration
NoTA: Normalized Tensor Adaptation for Parameter-Efficient Continual Learning
Emergent Steering Beyond Endpoint Alignment in Chemical Reaction Models
Efficient Diffusion Policy Fine Tuning with Latent Noise Representation Bridging
Quantile Geometry Regularization for Distributional Reinforcement Learning
NASDAQ: Normalized Observation Space Dynamics-Augmented Q-Learning
PEEK: One-Step Look-Ahead Exposure Bias Correction for Diffusion Sampling
MODULE: A Mutual-Promoting Deep Unfolding Framework Towards Degradation-Robust Multi-modal Image Fusion
Sparse Delta Memory: Scaling the State of Linear RNNs through Sparsity
Leaderboard Hacking: Preference-Based Model Evaluations are Vulnerable to Manipulation
CoLVR: Enhancing Exploratory Latent Visual Reasoning via Contrastive Optimization
G2Fusion: Geometric-to-Generative Image Fusion via Registration-Restoration Evolution
CoVisIT: Cross-modal Prior Guided Diffusion Model for Visible-to-Infrared Image Translation
Pruning and Distilling Mixture-of-Experts into Dense Language Models
AQBENCH: Benchmarking Neural Surrogates for Air Quality Forecasting
Is the Importance Ratio Necessary for Stable Reinforcement Learning in LLMs?
ZNO: Stable Rational Neural Operators in the Z-Domain for Discrete-Time Dynamics
Heuresis: Evaluating Search Strategies for Autonomous Machine Learning Research Agents
PolySplat: Workload-Regime-Aware Rasterization for 3D Gaussian Splatting
When Are Predictions Enough? An Evaluation Protocol for Frozen Expert Composition
Manifold-weighted neural networks
Tail Cues, Principal Corrections: Plug-and-Play Rectification for Open-Set Test-Time Adaptation
RPC-GS: Gaussian Splatting with native RPC Rendering for Satellite Imagery
Don't Discard Your Rollouts: Reusing Teacher RL Traces for Student Distillation
Beyond Global Alignment: Structured Compositional Reasoning for Vision-Language Models
Do You CARE to Generalize? Extracting Robust Concept Directions from LLMs
CORA: Per-Slice Coherent Orthogonal Rotation for SVD-based Low-Rank Adaptation
Flow-Corrected Shape Optimization: Taming Manifold Drift in High-Dimensional 3D Models
Interpretable Multiway-Split Trees
ASVQ: What Reparameterization Is Just Enough for Efficient Codebook Learning?
Assign and Add: A Mechanistic Study of Compositional Arithmetic
Speak Early: Speculative Speech Generation for Low-Latency SpeechLLMs
Adversarially Attacking Symbolic Vocabulary Vulnerabilities In LLM Planners
How do Small Transformer Models Learn Hard Math Tasks?
High Performance Differentially Private Fine-Tuning using Dataset Distillation
SWE-Marathon: Can AI Agents Autonomously Complete Ultra-Long-Horizon Software Work?
Harbor Adapters and Harbor-Mix: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation
PhysAgentGym: Free Physical-Law Verifiers for Training Small Code-Reasoning Agents
On the Importance of Gating: Memorization vs. In-Context Learning in State Space Models
Attention-based Routing for Interpretable Multimodal Brain Encoding
N-vium: Mixture-of-Exits Transformer for Accelerated Exact Generation
Vendi Anomaly Scores for Efficient and Accurate Anomaly Detection
MedVTok: A General-Purpose Medical Visual Tokenizer
Reasoning-Aware Relational Representation Learning for Open-Vocabulary Scene Graph Generation
Behavioral Geometric Supervision Aligns Video Foundation Models with Human Social Perception
VIGOR: Zero-Shot Visual Generalization via Latent-Space Consistency in Model-Based Reinforcement Learning
Prediction-Augmented Trees for Reliable Statistical Inference
Understanding the Challenges in Iterative Generative Optimization with LLMs
Christoffel-DPS: Optimal sensor placement in diffusion posterior sampling for arbitrary distributions
Tuning the Tuner
Stable Resolution-Invariant Emulation in Entropically Controlled Kinetic Methods
Perturb, Repair, Verify: Self-Play Vision-Language Verifiers for Compositional Understanding
Uncovering the latent structure of interwoven population and temporal codes
Training ML Models with Predictable Failures
MixNLQ: An Effective Post-Training Nonlinear Low-Bit Quantization Method for Large Language Models
Distilling Conditional Image Generators into Spatial Effect Maps
Drift-Aware Multimodal User Representation Learning via Multi-Scale Temporal Modeling and Sparse Mixture-of-Experts
Fine-Tuning Language Models to Know What They Know
Reasoning with Undecoded Tokens in Diffusion Language Models
Compressing Collections of Trees with Decision Equivalence
Towards Generalizable Data Valuation: Learning an End-to-end Deep Model to Compute Shapley Values
Deep Gaussian Processes on Directed Acyclic Graphs
Sample Transform Cost-Based Training-Free Hallucination Detector for Large Language Models
Bridging Graph Worlds: Neural Approximation of Gromov-Wasserstein Distances
Grounded or Fabricated? Unsupervised Detection of LLM Hallucinations via Contextualized Influence on Response Embeddings
Stochastic Reconfiguration as Statistical Filtering for Overparameterized Neural Quantum States
I-Perceive: A Foundation Model for Vision-Language Active Perception
A meshfree exterior calculus for generalizable and data-efficient learning of physics from point clouds
ARCANA: A Benchmark for Abstraction and Analogical Reasoning
EviSAM3: Evidence-Driven SAM3 for Referring Remote Sensing Image Segmentation
The Denoising Wrapper: A Modular Post-Processing Framework for Noisy First-Order Optimizers
Flexible Routing via Uncertainty Decomposition
FLARE: Verifying MILP Reformulations with LLM-Based Formal Proof Synthesis
Toward a theory of Evaluability
CASL-VAE: Learning Structured Latent Variables from Unpaired Data for Semi-supervised Clustering and Paired Sample Generation
Random Attention Pattern Learning Enables Emergent Capabilities
Predictive Representation Learning for Partially Observed Neural Dynamics
ATLAS: Agentic or Latent Visual Reasoning? One Word is Enough for Both
ECG Dataset with Multi-Expert Annotations and Delineations
Full Fine-Tuning Is Not the Problem: Why Adam Fails and SGD Succeeds in Few-Shot CLIP Adaptation
Learnable Diffusion-based Positional Encodings for Link Prediction
Pandora's AI Model Routing Box: Efficient Allocation with Costly Value Estimation
Mesh-Free Convolution: Learned Spectral Attenuation and Transport
LLMs Optimizing LLMs: Automated MegaKernel Generation for Inference Acceleration
CRUMB: Efficient Prior Fitted Network Inference via Distributionally Matched Context Batching
Tapes Together Strong: The Co-evolution of Computation and Cooperation
Hierarchical Regime-Conditioned Dynamics for Spatiotemporal Graphs
Quantile-Coupled Flow Matching for Distributional Reinforcement Learning
Causal Bias Detection in Generative Artifical Intelligence
Online Allocation with Unknown Shared Supply
StepCAD: Mesh-to-CAD Code Generation via LLM Policy and Geometry-Guided Search
FTerViT: Fully Ternary Vision Transformer
On the Convergence of Success Conditioning for Policy Optimization
Visual-Redundancy-Controlled Parallel Decoding for Diffusion-Based Multimodal Large Language Models
A Little Robustness Is All You Need: Leveraging Predictions for Contextual Optimization
SVG-3D: Mining Decision Boundaries with Generative Splatting Priors for Zero-Shot 3D Classification
Provably Safe, Yet Performant Reinforcement Learning
Risk-Controlled Post-Processing of Decision Policies
Geometry Matters in Packed 3D Attention
Trust What Matters: Language-Conditioned Evidence Routing for Video-IMU Action Question Answering
Boule or Baguette? A Study on Task Topology, Length Generalization, and the Benefit of Reasoning Trace
Learning When to Collaborate: Selective Multi-Agent Medical Reasoning via Uncertainty-Aware Routing
CAVE: A Structured Credit Assignment Approach for Fragmented Visual Evidence Reasoning
User Embeddings are Superpositions of Interpretable Behavioral Modes
DiRecT: Safe Diffusion-Based Planning via Receding-Horizon Denoising
Test Time Search Requires Training for Diversity
Compute Allocation Under Model-Provider Competition
Characterizing Trainability of Instantaneous Quantum Polynomial Circuit Born Machine
Stability Regimes for Framing-Sensitive Fine-Tuning in Language Models
Deep Learning-based Algebraic Reynolds Stress Closures for RANS simulations of Turbulent Flows
ReGuidance: Diffusion Steering with Strong Latent Initializations Solves Hard Inverse Problems
CLEF: EEG Foundation Models for Learning Clinical Semantics
CineMME: Benchmarking Fine-Grained Perception and Plot Reasoning in Multimodal Large Language Models
CoilStellaration: A Dataset and Benchmark for Engineering-Aware Stellarator Coilset Generation
Dexterous Skill Discovery via Topology-Aware Wasserstein Dependency
Beyond Low-Pass Dynamics: Frequency-Selective Spiking Reservoirs with Resonant Neurons
SCALECUA : Scaling Computer Use Agents with Verifiable Task Synthesis and Efficient Online RL
Beyond Proxy Metrics: MLLM-Based Human Surrogate Evaluation for Explainable AI
Manifold Embedding of Deep Image Features for Image Matching via Neural Adjoint Maps
Beyond ICA: Identifiability by Symmetry Breaking
Optimal Rates for Differentially Private Hypothesis Testing with E-values
CardioLens: Revealing the Clinical Reality Gap of MLLMs via Multi-Sequence Cardiac MRI Evaluations
SCION: Scene Composition via Instanced Neural Primitives
Structural Support Certificates for Mechanistic Hypothesis Selection
Hierarchical Cross-Class Part Alignment for Prototypical Part Networks via Hyperbolic Entailment
RABBiT: Rapidly adaptive BOLD foundation model via brain-tuning for accurate zero-shot and few-shot prediction of speech-elicited responses in the brain
Retrieval-Centric Deep Learning in Growing Nonparametric Neural Networks
Ask Early, Ask Late, Ask Right: When Does Clarification Timing Matter for Long-Horizon Agents?
Characterizing Universal Object Representations Across Vision Models
DrPO: Drifting Preference Optimization for One-Step Generative Models
Fractional State Space Transition for Long Sequence Modeling
SelfCritic-VLA: Language as Intrinsic Critic for Vision Language Action Models in Autonomous Driving
LaST-VLA: Thinking in Latent Spatio-Temporal Space for Vision-Language-Action in Autonomous Driving
DriveFuture: Future-Aware Latent World Models for Autonomous Driving
OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation
Detection and Classification in Latent Spaces: High-Dimensional Analysis and Validation
Diagonalizing the Softmax: Hadamard Initialization for Tractable Cross-Entropy Dynamics
Improving Audit Realism with Inference-Time Compute and Deployment Scaffolds
Machine Learning-Driven RAG System Design
BiHashFormer: Hash-Driven Dual-Branch Transformer for Efficient Object Detection in HRW Shots
CoTs as Probabilistic Programs: A Programmatic View of Thinking Step-by-Step in Language Models
AWP: Activation-based Window Pruning for Gigapixel Object Detection
SpanFormer: Multi-Level Adaptive Sparsity for Object Detection in High-Resolution Wide Shots
MobileWan: Closing the Quality Gap for Mobile Video Diffusion
Sequence-to-Sequence Modeling with Camera-Induced Priors for Multi-View Stereo
Native Multi-Dimensional Subquadratic Operators via Input Dependent Long Convolutions
Online Fair Division Meets Reordering Buffers
A Unified Graph Language Model for Multi-Domain Multi-Task Graph Alignment Instruction Tuning
Sup-Norm Error under Proportional Asymptotics: Phase Transitions under Linear Regression
Loop-Free Inverse Reinforcement Learning via Sequential Value Recovery
GeoPair: Geometry-Preserving Cross-Layer Factorization for Training-Free Transformer Compression
COMPOT: Calibration-Optimized Matrix Procrustes Orthogonalization for Transformers Compression
Cross-Foundation Complementary Learning Systems for Continual Test-Time Adaptation in Open-Vocabulary Semantic Segmentation
Hodge Laplacian Quasi-Harmonic Flows for Option Discovery
ROCKET: Rapid Optimization via Calibration-guided Knapsack-Enhanced Truncation for Efficient Model Compression
DynamicRad: Content-Adaptive Sparse Attention for Long Video Diffusion
How Useful Is Cross-Domain Generalization for Training LLM Monitors?
Voice "Cloning" Is Actually Style Transfer
Indications of Belief-Guided Agency and Meta-Cognitive Monitoring in Large Language Models
Grid Games: The Power Of Multiple Grids for Quantizing Large Language Models
Intrinsically Interpretable Attention via Sparse Post-Training
COMPOSE: Composing Future Theorems from Citations and Formal Structure
On the Sparsity of Direct Preference Optimization: Weight Disentanglement in the NTK Regime
Beyond Single Expert: Harmonizing Diverse Visual Priors in MLLMs for Spatial Understanding
TStruct: Learning Shared Temporal Structures for Long-Term Time-Series Forecasting
Reinforcement Learning-Guided Symbolic Execution for Efficient and Exploitable Smart Contract Analysis
ExoC2T: An exogenous-driven spatio-temporal learning framework for cross-city transfer
Beyond Linear Decoders: Dynamic Expert-Coupled Optimal Decoding for Time Series Forecasting
A Dual-Domain Vision Transformer with Spectral Positional Bias
ExtrapAir: Air Quality Inference at Unmonitored Locations via Weather-Bridged Spatial Attention
Effect-Level Validation for Causal Discovery in Interactive Telemetry
Where Root Cause Analysis Fails: A Retrieval-Reranking Decomposition
RealityTest: How People Probe AI Identity and Whether Models Disclose It
Federated Graph Learning with Local Message Compensation
Closed Loop Dynamic Driving Data Mixture for Real-Synthetic Co-Training
AEM: Adaptive Entropy Modulation for Multi-Turn Agentic Reinforcement Learning
Fair Bubble Sort: Provably Optimal Fair Ranking with Continuous Sensitive Attributes
Bridging Sequence and Structure with Unified Domain Adaptation for Drug-Target Interaction Prediction
SCG-HF: Semantic Consistency Grouping for Hierarchical Fusion in Video Emotion Recognition
LAPLEX: The FFT of Learnable Laplace Kernels
PRISM: Spectral Pruning and Reconstruction for Parameter-Efficient Model Merging of MLLMs
Black-box model classification under the discriminative factorization
FLoRA-Chef: Making A Good LoRA Recipe in Federated Generalization
Prototype Topology Consistency for Visible-Infrared Lifelong Person Re-Identification
D-GAP: Improving Out-of-Domain Robustness via Dataset-Agnostic and Gradient-Guided Augmentation in Amplitude and Pixel Spaces
When and Why Does Multi-Agent Debate Fail and Does It Really Underperform?
VVTRec: Radio Interferometric Reconstruction through Visual and Textual Modality Enrichment
Rollout Pass-Rate Control: Steering Binary-Reward RL Toward Its Most Informative Regime
Control Charts for Multi-Agent Systems
Idempotency Exposes Consistency Problems in Sparse Autoencoders
SplineFlow: Flow Matching for Dynamical Systems with B-Spline Interpolants
Online Control with Multiple Sensors
Phase Transitions in Heavy-Tailed Mean Estimation under $\ell_p$ Norms
TreemapMix: Dirichlet-Controlled Multi-Image Augmentation for Probability and Ordinal Supervision
ChiP-STAR: Spatial-Topological Attention for Pre-trained Generative Chip Routing
Universal Approximation Theorems for Dynamical Systems with Infinite-Time Horizon Guarantees
A Mechanistic Analysis of Looped Reasoning Language Models
Coupled Guidance for Flow Matching
Learning a Trajectory-Geometric Condition from Reasoning for VLA Planning
From Representational Complementarity to Dual Systems: Synergizing VLM and Vision-Only Backbones for End-to-End Driving
When a Zero-Shooter Cheats: Improving Age Estimation via Activation Steering
MCAS: Signal-Processing-Based Multi-View Contrastive Learning for Acoustic Sensing
Progressive Memory Transformer: Memory-Aware Attention for Time-Series
SMoA: Spectrum Modulation Adapter for Parameter-Efficient Fine-Tuning
HIMMEL: Hierarchical Interleaved Multi-stream Motion Encoding for Long Video Understanding
Rethinking Rubric Generation for Improving LLM Judge and Reward Modeling for Open-ended Tasks
ChunkFT: Byte-Streamed Optimization for Memory-Efficient Full Fine-Tuning
gfnx: Fast and Scalable Library for Generative Flow Networks in JAX
Anytime-Valid Conformal Risk Control
HOMIE: Human-object Centric Video Personalization via Multimodal Intelligent Enhancement
AdDirector: Anchored Guidance for Generating Camera-Controllable Advertisement Videos
On the Convergence of Multicalibration Gradient Boosting
Synthetic Anchor-Assisted Prototype Alignment for Heterogeneous Federated Learning
Kernel Token Contradiction: a Fast and Principled Approach for LLM Claim Uncertainty Quantification
Safe Linear Bandits with Unknown Safety Gaps
Near-Optimal Learning in Parametric Bandits with Action-Dependent Coarsened Feedback
Asking the Right Questions: Improving Reasoning with Generated Stepping Stones
VisionCreator-S1: Evolving Visual-Generation Agents via Skill-GRPO Optimization
VisionCreator-R1: A Reflection-Enhanced Native Visual-Generation Agentic Model
Neuro-KE: Knowledge-Guided Interfaces for Semantically Grounded EEG Foundation Models
Orthogonal Origin Parking: Decoupling Lorentz Manifolds for Robust OOD Generalization
DRAMA: Dissecting Attention Redundancy for Accelerating Multimodal Diffusion Large Language Models
On Concentration Inequalities for Sampling without Replacement
What Sketches Tell Us about LVLMs: Conventions, Grounding, and Localisation
EvoMM: Reinforced Self-Evolving Multimodal Agentic Memory
When Sanitization Becomes the Trigger: Defense-Triggered Backdoor Attacks
fmxcoders: Factorized Masked Crosscoders for Cross-Layer Feature Discovery
Approximation in Contrastive Representation Learning
CAM: Question Answering on Entity-Centric Videos with Continuous Extraction and Adaptive Querying
Tight Gap-Dependent Regret Bounds and Problem-Independent Bounds for Cost-aware Cascading Bandits
RSPReg: Reliability-aware Structural Prototype Learning for Point Cloud Registration
Regret-Optimal Wasserstein-Robust Regression
The Dynamics of Policy Gradient in Social Dilemmas with Partner Selection
Valid Best-Model Identification for LLM Evaluation via Low-Rank Factorization
Federated Concept-Based Models: Interpretable models with distributed supervision
Conditional misalignment: common interventions can hide emergent misalignment behind contextual triggers
ERIS: Enhancing Privacy and Scalability in Federated Learning via Federated Shard Aggregation
Rectifying Categorical Flows on Statistical Manifolds for One-Step Generation
DaCe-DT: Data-Centric Offline Multi-Task Reinforcement Learning via Adaptive Prompts and Trajectory Correction for Heterogeneous Tasks
Stability-Enhanced Federated Learning with Accelerated Gradient
Revisiting Decentralized Online Convex Optimization with Compressed Communication
Retrieve-then-Steer: Online Success Memory for Test-Time Adaptation of Generative VLAs
HIST3R: Rectified State Decomposition from History for Streaming 3D Reconstruction
Beyond World-Frame Action Heads: Motion-Centric Action Frames for Vision-Language-Action Models
StereoSplat: Metric-Scale Novel View Synthesis via Stereo-Grounded Gaussian Splatting
How Deep Are Deep GPs, Really? A Sharp Threshold and a Non-Gaussian Limit for Compositional GPs
Locking Pretrained Weights via Deep Low-Rank Residual Distillation
Facts Don't Speak Louder than Words: The Behavioral Essence of Long-CoT Distillation
ECHO-2: A Large-Scale Distributed Rollout Framework for Cost-Efficient Reinforcement Learning
StreamPhy: Streaming Inference of High-Dimensional Physical Dynamics via State Space Models
Training on Documents About Monitoring Leads to CoT Obfuscation
On the Limits of Latent Reuse in Diffusion Models
Motif-Mamba: network motif improved mamba for long-range sequence modeling
SQUEEZE: Preserving Homeomorphism and Smooth in Higher-Dimensional Flows
Improving Generative Adversarial Networks with Self-Distillation
Unveiling Memorization–Generalization Coexistence: A Case Study on Arithmetic Tasks with Label Noise
ACD-GS: Asymmetric Curvature-aware Densification for 3D Gaussian Splatting
Recovering the Apresjan Hierarchy Using Linkage-Based Clustering
MSCR: Jointly Balancing Modality Utilization and Discovering Synergistic Information
HRIL: Isolating Multimodal Synergy via Higher-Order Dependence
B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data
Matching-Based Few-Shot Semantic Segmentation Models Are Interpretable by Design
Verifier Choice is a Benchmark Design Variable: Auditing Structural Counting Evaluation in Text-to-Image Models
When Language Overrules: Revealing Text Dominance in Multimodal Large Language Models
A Structured LLM Framework for Inorganic Material Synthesis Planning
Plan2Sense: Open-World Task Planning in Epistemic States via Interleaved Ontic and Sensing Actions
The Scaling Paradox of Tool-Calling LLM Agents Under Realistic MCP Faults
Leech Lattice Vector Quantization for Efficient LLM Compression
Reasoning as Compression: Unifying Budget Forcing via the Conditional Information Bottleneck
Contact Geometry for Generative Models: An Unbalanced Optimal Transport Formulation
LARGO: Low-Rank Hypernetwork for Handling Missing Modalities
Distributionally Robust Domain Randomization with Learned Risk-Sensitive Dynamics Samplers
Learning Agentic Policy from Action Guidance
Why Routers Freeze: Infinite Width Learning Dynamics for Mixture of Experts
Attention-Discounted Adaptive Sampler for Masked Diffusion Language Models
When Does Interaction Help? Representational Tradeoffs in Value-Based Imitation Learning
Publishing Below-Threshold Triangle Counts under Local Weight Differential Privacy
Optimistic Dual Averaging Unifies Modern Optimizers
Raven: High-Recall Sequence Modeling via Sparse Memory Routing
AcceleGrad#: Adaptive Geometry-Aware Acceleration
Constrained Stochastic Spectral Preconditioning Converges for Nonconvex Objectives
Equivariant Reinforcement Learning for Clifford Quantum Circuit Synthesis
Cache the Future: Training-Free Self-Revision for Diffusion Transformer Acceleration
Finding Koopman Invariant Subspaces via Personalized PageRank
VLA-Pro: Cross-Task Procedural Memory Transfer for Vision-Language-Action Models
Patch Rebirth: Fast and Transferable Model Inversion of Vision Transformers
Phase Space Attention: A Hairer Lift Resolves the Single-Layer Induction Obstruction
CoDeRNet: Selective Cross-Task Routing under Heterogeneous Supervision for Change Detection and Captioning
GPU Hierarchy Meets Structured Matrices: Fast Algorithms for State-Space Models
Calibrating Generative Models to Feature Distributions with MMD Finetuning
Long-Horizon Q-Learning: Accurate Value Learning via n-Step Inequalities
Reasoning over Coupled Receptive Fields: Eliminating Subgraph Redundancy at Scale
Workspace-Bench 1.0: Benchmarking AI Agents on Workspace Tasks with Large-Scale File Dependencies
Communication-Efficient LLM Adaptation over Decentralized GPU Meshes
AIRA-Compose: Agentic Discovery of Neural Architectures
LongScape: Advancing Long-Horizon Embodied World Models with Context-Aware MoE
Bridging Diffusion and Autoregression for Flexible Time Series Synthesis
Order-Marginalized Scoring for Masked Diffusion Models
Measuring Weak-to-Strong Legibility of Reasoning Models
WordEval: Evaluating Word-Native Operation Fidelity in Document Editing
SIEVES: Selective Prediction Generalizes through Visual Evidence Scoring
On the Depth of Monotone ReLU Neural Networks and ICNNs
Measuring AI Agents' Progress on Multi-Step Cyber Attack Scenarios
EmbodiedObject: All-in-One Object Understanding with SLAT
End-to-End Identifiable and Consistent Recurrent Switching Dynamical Systems
Aligning LLMs Toward Multi-Turn Conversational Outcomes Using Iterative RLHF
Adapting Vision Transformers to Organoid Imaging
Prediction Under Imperfect Compression: A Theory of Approximate MDL
StiCAS: Compositional Activation Steering via Stiefel Manifold Coordinate Transport
LLM-WikiRace: A Benchmark for Planning and Reasoning over Real-World Knowledge Graphs
TopoScope: A Graph-Scoped LLM Agent for Printed Circuit Board Schematic Design
ScrapeBench: Evaluating Legal Compliance of AI Agents in Website Scraping
Negation Neglect: When models fail to learn negations in training
Global PIQA: Evaluating Commonsense Reasoning Across 100+ Languages and Cultures
Platonic Representations in the Human Brain: Unsupervised Recovery of Universal Geometry
The Marauder’s Map: Bézier Manifolds Reveal Hidden Surfaces for Model Merging and Ensembling
A Trust Region Approach for Learning Schrödinger Bridges
GAMMA: Scalable 4D Gaussian Reconstruction Model for Novel View Synthesis of Monocular Videos
TESLA: Native 4D Gaussian Splatting Generation with Temporally Structured Latents
BiLoCo: Binary Low-Rank Corrections for LLM FP4 Decode
PatchScout: Thematic Web Data Collection via Information Foraging
Neural Garbage Collection: Learning to Forget while Learning to Reason
EnerGNN: Learning Optimization-Compatible Energy Functions for Exact Constrained Combinatorial Inference
An Empirical Study on Noisy Data and LLM Pretraining Loss Divergence
KroQuant: Kronecker-Structured Block Transforms for Efficient Post-Training Quantization of Diffusion Transformers
Dynamic Convolutions Improve Transformers
Agnostic Online Learning with Reliable Abstention
Efficient Prediction of Pass@k Scaling in Large Language Models
GIST: Gauge-Invariant Spectral Transformers for Scalable Graph Neural Operators
AdaptNC: Adaptive Nonconformity Scores for Conformal Prediction under Distribution Shift
Weird Generalization from Narrow Finetuning: Persona Shifts and Inductive Backdoors
Intrinsic-dimension empirical Bernstein inequalities for bounded self-adjoint operators
Extracting Governing Equations from Latent Dynamics via Multi-View Contrastive Learning
Sequential Membership Inference Attacks
Refactoring Code Through Library Design
MaxSketch: Robust Distinct Counting in Streams via Random Projections
How are linear representations learned? Exact solutions to the dynamics of abstraction
Tempered Guided Diffusion
Block Sparse Flash Attention
Collaborative Reasoning Distillation via Cross-Feedback and Coherent Curation
Decomposing Conformal Uncertainty: Calibration- and Instance-Driven Feature Attribution
MorphGen: Controllable Cell-Image Generation with Biological Representation Alignment
Learning Options for Compositional Motor Control with Adapter Banks
MahaVar: OOD Detection via Class-wise Mahalanobis Distance Variance under Neural Collapse
Predictive Concept Decoders: Training Scalable End-to-End Interpretability Assistants
Zero-Shot Coordination among LLM Agents
SOLE-R1: Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning
ASH: Agents that Self-Hone via Embodied Learning
CIG: Exploration via Conditional Information Gain
Hallucination-Guided Unlearning: Using Hallucination Traces to Reveal Overfitted Memories
Fast 4D Mesh Generation by Spatio-Temporal Attention Chains
Enhancing Novel View Synthesis via Geometry Grounded Set Diffusion
Don’t Learn What You Can Compute: Arithmetic Residual Blocks for Exact Arithmetic in Transformers
DC-ViT: Modulating Spatial and Channel Interactions for Multi-Channel Images
TIDE: Trajectory-Aware Watermark Propagation for Text-to-Image Diffusion Models
FedVSSAM: Mitigating Flatness Incompatibility in Sharpness-Aware Federated Learning
Compatible Likelihoods for Flow Matching on Manifolds
Causal Discovery over Clusters of Variables in Non-Markovian Systems
Spatial Representation Distillation and Knowledge Routing for Vision-Language-Action Models
Sparsity for Free: A Budget-Induced Equilibrium in Joint Topology–Parameter Search
Rethinking Vector Field Learning for Generative Segmentation
Guiding Visual Autoregressive Models through Spectrum Weakening
Understanding Randomization in Greedy Model Search
Predicting Human-Gain Curves under Local Proxy Optimization from Repeated Ratings
Visual Reinforcement Fine-Tuning via Bootstrapped Medical Reasoning
Seeking the Unfamiliar but Memorable: Conceptual Creativity as Meta-Learning
Disentanglement as Identifiable Pushforward Factorisation
The Shape of Events: Edge-Based Inductive Biases via Cross-Domain Distillation
Path Dependence under Adaptive AI Delegation
On the Recall Scaling Laws in Mamba: A Theoretical and Mechanistic Study via Hashing
Closed-Loop Alignment: Socially Coupled In-Context Learning and Relational Posterior Collapse
Towards Real-Time Full-Waveform LiDAR Transformers via Intensity-Guided Token Reduction and Physics-Aware Augmentation
Text as Partial Constraint: Core–Residual Alignment for Robust Vision–Language Learning
Augmented Lagrangian Predictive Coding
Step-by-Step Optimization-like Reasoning in LLMs over Expanding Search Spaces
Malicious Node Injection: A Transferable Adversarial Attack on GNN Fairness
Prompt Optimization Makes Misalignment Legible
Backdoor Attacks under Lossy Compression: From Failure to Reactivation and Adaptation
Neural Reconstruction of LiDAR Point Clouds under Jamming Attacks via Full-Waveform Representation and Simultaneous Laser Sensing
Overcoming the Resolution Limit: Significance-Aware Regularization for Intersectional Fairness
Watermarking Game-Playing Agents in Perfect-Information Extensive-Form Games
Filtered Conformal Ellipsoids for Graph-Native Time Series
LocalAgent: Collaborative Agentic Verification for Fine-Grained Instance-Level Consistency
Two Stages of Folding: Convergent Mechanisms in AI Protein Folding Trunks
A Measure-Theoretic Analysis of Reasoning: Structural Generalization and Approximation Limits
Fast Algorithms for the Label Propagation Operator on Signed Graphs
Auxiliary Clues Aware’s Geometry Problem Solving
WATERFALL: Workflow for Adaptive Training with Evolutionary Reward Formulation and Automated Learning Loops
RotVLA: Rotational Latent Action for Vision-Language-Action Model
Toward Multimodal Sheet Music Recognition and Understanding
Hadamard Representation: Scaffolding Performance Across Model-free RL
Splatting the Invisible: Geometry and Appearance Scene Completion from Sparse Views
A Theory of Time-Sensitive Language Generation: Sparse Hallucination Beats Mode Collapse
Subdata Selection: A Unified Framework for Optimal Selection and Statistical Efficiency Assessment
Stable Max Coverage Under a Cardinality Constraint
Breaking the Synthesis Barrier for AI-Designed DNA Libraries
Reconciling Causality and Non-Equilibrium Thermodynamics with Hamiltonian Causal Models
Breaking the Exactness Barrier: Interleaved DeepSeek Sparse Attention for Efficient Long Context Reasoning
Learning to Continually Learn via Meta-learning Agentic Memory Designs
Deep Double Q-learning
Cross-Question Reliable Reinforcement Learning
How Likely Are Voting Rules Equitable?
Iterative ILP with Update-Size Control for Reducing Surrogate-Task Mismatch in Bit-Width Selection
Colour me shocked: Exact Molecular Hessians from MLIPs in O(N) time using sparse differentiation!
EDMA: Entropy-Driven Multimodal Answering
Efficient Adaptive Data Analysis over Dense Data Distributions
Georeferenced Cross-View 3D Reconstruction from Ground and Satellite Images
Exploring Lifelong Adaptation: In-Context Reinforcement Learning in Non-Stationary Environments
Sound Verification of Deployed Neural Networks
Advanced Routing as Regularization Allocation for Efficient Diffusion Transformer Training
Closing the Approximation Gap in Simulation-free Latent SDEs
Autoregressive Learning in Joint KL: Sharp Oracle Bounds and Lower Bounds
Does Synthetic Data Help? Empirical Evidence from Deep Learning Time Series Forecasters
Towards Closing the Autoregressive Gap in Language Modeling via Entropy-Gated Continuous Bitstream Diffusion
Coarse-to-Real: Generative Rendering for Populated Dynamic Scenes
ESENSC: A Polynomial-Time Axiomatic Alternative to SHAP
Sampling-Free Privacy Accounting for Matrix Mechanisms under Random Allocation
Model-Aware Tokenizer Transfer
Root-Selecting Fixed-Point Inversion for Rectified Flows via Trajectory Straightness
The Attacker in the Mirror: Breaking Self-Consistency in Safety via Anchored Bipolicy Self-Play
CMI-Trans: Cross Modal Inconsistency-aware Transport for HSI-LiDAR Classification
Not Too Generative, Not Too Discriminative: The Human Alignment Sweet Spot
On the Sparsity-Storage-Accuracy Tradeoff in Parsimoniously Activated Dictionary Learning
Rotation-Invariant Vector Normalization for Molecular Force Learning
Render Structure Uncertainty for HTML Repair in MLLM-based UI-to-Code Generation
Towards Generalizable Partially Relevant Video Retrieval
Embeddings for Preferences, Not Semantics
Reduced Cost Influence Functions for Predict-then-Optimize under Noisy Data
Preserving DEG Rankings for Gene Discovery in Histology-Based Spatial Gene Expression Prediction
Perturb and Correct: Post-Hoc Ensembles using Affine Redundancy
Short-Context Dominance: How Much Local Context Natural Language Actually Needs?
Generating in the Limit with Infinitely Many Hallucinations
Variance Reduction for Expectations with Diffusion Teachers
Contractive Restoring Flows: Robust Reasoning Distillation via Orbital Stability
Equilibrium Matching: Generative Modeling with Implicit Energy-Based Models
The Minimax Rate of Second-Order Calibration
LoRAcles: Self-Supervised Weight-Space Interpretability at Scale
Optimal Hidden-Target Learning for Online Inventory Optimization on General Convex Sets
Point Cloud Sequence Encoding for Material-conditioned Graph Network Simulators
Zero-Shot Instruction Following in RL via Structured LTL Representations
LOCU: Löwdin-Orthogonalized Constraint Updates for Multi-Constraint Policy Optimization
Sink vs. diagonal patterns as mechanisms for attention switch and oversmoothing prevention
A Differentiable Interior-Point Method in Single Precision
Anatomy-aware Spatio-Temporal Modeling for Echocardiography Segmentation
Adaptive Fine-Tuning Scheduler for Multi-Tenant Edge LLM via Convergence-Aware Bandits
Understanding Sample Efficiency in Predictive Coding
Safe Evolution with Circuit Anchors
Never Stop Learning: Test-Time Reinforcement Learning for Vision-Language-Action Models
Time-Sensitive Anytime-Valid Testing
Semiparametric Efficient Tests for Interpretable Distributional Treatment Effects
Non-Asymptotic Best Policy Identification Guarantees in Online Reinforcement Learning
Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM Systems
Less Language, More Latents: Annotation-Efficient VLAs for Driving
The Design Space of Tri-Modal Masked Diffusion Models
Causal Effect Identification with a Single Agnostic Proxy
HyperFlow: Gradient-Free Test-Time Adaptation for Cross-Domain Few-Shot Classification
Steering Optimisation Trajectories in Diffusion Representation Learning
Assistive Dueling Bandits: No-Regret Algorithms for Assisting No-Regret Users
BAPM: Boundary-Aware Prompt Mining for Training-Free Few-Shot Medical Image Segmentation
FlashSSM-3D: A Distilled State Space Model for Lightning-Fast Dense 3D Reconstruction
From I/O to Code with Discovery Agent
Wayfinder: Adaptive Resource Routing from Agent Citations
Gradient-Mine Units: Scorched-Earth Strategy for Model Protection against Unauthorized Fine-Tuning
NOFE – Neural Operator Function Embedding
Certification from Examples is Hard for Circuits and Transformers under Minimal Overparametrization
ReorgGS: Equivalent Distribution Reorganization for 3D Gaussian Splatting
WaveSem: Frequency-Adaptive Tokenization for Disentangling Semantics and Noise in Genomics
Exactness Matters for Physical Rule Enforcement
Steer2Edit: From Activation Steering to Component-Level Editing
DiM$^3$: Bridging Multilingual and Multimodal Models via Direction- and Magnitude-Aware Merging
Generalized Intention Modeling in Multi-Agent Reinforcement Learning
LLM Agents Already Know When to Call Tools - Even Without Reasoning
LightMoE: Reducing Mixture-of-Experts Redundancy through Expert Replacing
Post-ADC Inference: Valid Inference After Active Data Collection
The $1/\mathcal{W}$ Law: Context Length is the Dominant Energy Lever in LLM Inference Fleets
CLIOPATRA: Extracting Private Information from LLM Insights
Don't Waste Population: Post-Anneal Refinement for Combinatorial Optimization
Online Data Selection for Instruction Tuning via Gaussian Processes
StableAvatar: Ultra-Long Audio-Driven Avatar Video Generation
Contrastive Identification and Generation in the Limit
Intelligence per Watt: Measuring Intelligence Efficiency of Local AI
FlashPlanner: Real-Time Goal-Conditioned Flow-Matching Planning for Autonomous Driving with Online RL Fine-Tuning
RANSAC Scoring Done Right
Why Invariance is Not Enough for Biomedical Domain Generalization and How to Fix It
SIEVE: Overcoming Topological Obstruction in Equivariant Self-Supervised Learning
MEME: Lightweight Hierarchical Mixture-of-Experts for Unified Affective Computing
Contour Monte Carlo: Sampling via Energy Level Sets
When Transcriptomic Foundation Models Scale: Domain-Focused Pretraining for Drug Development in Immunology and Inflammation
SpecBridge: Learning Natural-Language Formalization Plans for the Formal Specification Synthesis Task
Two-Clustering Regime of Token Dynamics in Causal Attention
NeuralBES: A Differentiable, Control-Aware Emulator for Scalable Building Energy Modeling
Adaptive auditing of AI systems with anytime-valid guarantees
Per-Loss Adapters for Gradient Conflict in Physics-Informed Neural Networks
On the Tightness and Computational Tractability of Higher-Dimensional Confidence Sequences
Intern-Atlas: A Methodological Evolution Graph as Research Infrastructure for AI Scientists
Symmetry Guarantees Statistic Recovery in Variational Inference
PAGER: Bridging the Semantic-Execution Gap in Point-Precise Geometric GUI Control
Concept frustration: Aligning human concepts and machine representations
A mathematical theory of balancing relational generalization and memorization
Behaving Better, Thinking Worse: Sycophancy Across Post-Training Stages
A Computational Perspective to Data Ablation Experiments
Layout Before Pixels: Topology-Anchored Transcriptome-to-Histology Generation
Interactive Combinatorial Reinforcement Learning for Knowledge Graph Reasoning
Mixture-of-Top-$k$ Attention: Efficient Attention as Scalable Fast Weights
Causal learning with the invariance principle
On the Burden of Achieving Fairness in Conformal Prediction
Combating Data Laundering in LLM Training
Sharp Capacity Scaling of Spectral Optimizers in Learning Associative Memory
Distribution-First Framework for Learning Risk-Sensitive Individualized Treatment Rules
Euler-Mamba: Learning Resolution-Invariant State Evolution on Polar Manifolds for Asymmetric Pansharpening
Discovering Phase Space Structure in Learned Hamiltonian Systems
Stability and Generalization in Looped Transformers
Point Clustering Encoders
Parallel Computation Algorithms and Convergence Guarantees for Mean-Field Langevin Dynamics
Zeroth-Order Sharpness-Aware Learning with Exponential Tilting
When to Trust a PFN: Detecting Harmful Shift in Tabular Foundation Models
Distributionally-Robust Policy Learning from Observational Data
Looped Diffusion Language Models
Structural Entropy Optimized Communication for Multi-Agent Reinforcement Learning
Offline Materials Optimization with CliqueFlowmer
Neuron Populations Exhibit Divergent Selectivity with Scale
PACO: Partial-order-Augmented Continuous Optimization for Differentiable Causal Discovery
Bridging the Simulation-to-Experiment Gap with Adversarial Distribution Alignment
Beyond the Training Distribution: Evaluating Predictions Under Distribution Shift and Selection Bias
Disentangling Continuous-Time Latent Dynamics: Identifiability of Latent SDEs via Diffusion Shifts
Beyond Uniform Detection: Adaptive Hallucination Detection for RAG Across Response Regimes
Integrated Imputation-Classification for Supervised Learning with Missing Data
RadarFlowPose: Vision-Inspired Coarse-to-Fine Skeleton Refinement with Flow Matching
SolvMix: Learning Formulation-State Landscapes for Liquid Electrolyte Conductivity Prediction
Semantics-to-Contact: A Stagewise Framework for Robust Contact-Rich Manipulation
Accelerating Safe Reinforcement Learning with Massive Parallelism
CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narratives
Baton: Explicit Semantic Blueprints for Joint Video-Audio Generation
Coupling-Aware Reinforcement Learning for Co-Evolving Graph Games
Position Without Positional Embeddings: A Directional Mechanism in NoPE Transformers
State Augmented Flows
Concepts in Motion: Temporal Concept Bottleneck Model for Interpretable Video Classification
Sponsored Questions and How to Auction Them
Sliced Wasserstein Meets Quantum Optics: Provable Wavefunctions Tomography with Scarce Noisy Measurements
Visual-ERM: Reward Modeling for Visual Equivalence
Directional Noise Conditioning for Diffusion Models
Do Diffusion Models Learn to Generalize Basic Visual Skills?
Are we really tilting? The mechanics of reward guidance in flow and diffusion models
OCTOPUS: Optimized KV Cache for Transformers via Octahedral Parametrization Under optimal Squared error quantization
Differentiable Exact Learning of Algorithms
Ensemble Modeling for Time Series Forecasting: an Adaptive Robust Optimization Approach
Distributionally Robust Algorithmic Recourse for Tree Ensembles
Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Sampling
Spatially-Grounded Long Video Generation with Self Geometry Forcing
Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context
AEON: Unifying Video and 3D World Models
ReGen: Agentic Video World Modeling with Synergized Reasoning and Generation
All Roads Lead to Rome: Flow-driven Multi-Anchor Exploration for Open-Environment Active 3D Mapping
CHORD: Cross-Model Hallucination Detection via Relational Graph Discrimination
Bentkus-type asymptotic e-values
Manifold Prior Guided Deep Unfolding for Hyperspectral Image Reconstruction
Archimedean Copula Inference via Taylor-Mode AD
Shifting the Gradient: Understanding How Defensive Training Methods Protect Language Model Integrity
Local Intrinsic Dimension Unveils Hallucinations in Diffusion Models
DyRA: Dynamic Residual Approximation for Efficient Matrix Multiplication in DNNs
PCDFusion: Proposal-Context-Detail Bayesian Rendering for Infrared-Visible Image Fusion
On the Price of Privacy for Language Identification and Generation
PR-Smoother: Simulator-Preserving Non-Gaussian Smoothing for Data Assimilation
Confounding-Aware Client Selection in Federated Learning via Causal Mediation Analysis
Training Vision Transformers to Focus: Emergence of Attention Head Specialization
When do Prophets Profit in Prediction Markets?
From Jumps to Signatures: a Generative Method for Temporal Point Processes
Why Heavy-Tailed Weights Predict Model Quality
ASAP: Attention Sink Anchored Pruning
Partially Performative Prediction
Spectral Representations for Provably Robust Offline Meta-Reinforcement Learning from Bagged Rewards
Does Inference-Time Reasoning Really Improve Video Understanding?
ProDG: Prototypes for Data-Free Generative Post-Hoc Explainability
Sequential Probability Assignment against Smoothed Adversaries with Unknown Base Measure
Is Dimensionality a Barrier for Retrieval Models?
Sharpness-Aware Hybrid Model Learning for Architecture-Agnostic Parameter Estimation
Make Each Token Count: Towards Improving Long-Context Performance with KV Cache Eviction
Reinforcement Learning from Rich Feedback with Distributional DAgger
Inference-time Alignment via Sparse Junction Steering
GRASP: Learning to Ground Social Reasoning in Multi-Person Non-Verbal Interactions
Causal Inference for Sequential Settings under Interference and Latent Confounding
Regularization Paths for Continuous DAG Learning
Efficient Fine-Tuning for Structured Sparsity Under Group Repartitioning
Diffusion Thinking for Fast Long-Form Spatial Reasoning in Vision--Language Models
Test-Time Learning with an Evolving Library
SAFE-Hair: Scalp-Anchored Fields for Exportable Single-View Hair Reconstruction
PRISM: Principal Subspace Alignment for Parameter-Efficient Fine-Tuning
Refining Compositional Diffusion for Reliable Long-Horizon Planning
Surprises in Proper Positive-Only Learning
GeoMamba: Geometry-Aware State Space Modeling for Image Restoration
Continuous Audio Thinking for Large Audio Language Models
Growing a Neural Network in Breadth, Depth, and Time
Adaptive Prior Selection in Gaussian Process Bandits with Thompson Sampling
Looped Transformers with Layer Normalization Provably Learn the Power Method
Pygmalion: Bridging Reconstruction and Generation in Sparse Voxel-based 3D Modeling
Nearly-Optimal Algorithm for Adversarial Kernelized Bandits
Robust Offline Reinforcement Learning against Out-of-Distribution Dynamics in Autonomous Driving
When to Trust Memory: Retrieval-Guided Probabilistic Spatiotemporal Forecasting under Distribution Shift
DegradeQuery: Counterfactual Tuple Pretraining for Context-Aware PROTAC Degradation Prediction
GaitLingo: Self-Supervised Gait Representation Learning with Language Priors
Temporal Smoothness Constraints on Efficient Neurobiological Codes Imply Temporal Specialization
Pixels over Symbols: Sensory Realism Improves Behavioral Alignment in Models of Cognition
Self-Calibrated GUI Reward Model via Inverse Dynamic Modeling
HypMoE-ReID: Hyperspherical Mixture-of-Experts for Large Scale Person Re-Identification
Few-Shot Truly Benign DPO Attack for Jailbreaking LLMs
High dimensional theory of two-phase optimizers
GlycoGen: Crystallizing Flows for De Novo Glycan Structure Prediction
Decentralized Q-Learning in Markov Potential Games
Laplacian Heads Improve Transformers by Smoothing Token Representations
Do Glimpse Policies See Like Humans? A Behavioral Audit Reveals Dissociated Viewing Priors in Classification-Trained Active Vision
Sample-Efficient Optimization over Generative Priors via Coarse Learnability
Mechanism-Aware Ensemble Conditioning for Data-Limited Emulation of Extreme Events
Cross-Model Circuit Discovery
BLARM: Animating 3D Objects from Video via Blending LAtent Rigid Motion Primitives
Forgetting to Improve: Principled Data Removal in Active Learning
VIGOR: Visual Gain Ordering for Hallucination Mitigation in Multimodal Discrete Diffusion Language Models
Concentrated Gradients Amplify Forgetting: Dominant-direction Projection for Continual Multimodal Learning
Transferable SCF-Acceleration through Solver-Aligned Initialization Learning
Test-time Scaling for Diffusion Language Models with Frequency-Aware Remasking
AeroMosaic:Transport-Aware Multimodal Evidence Fusion for Atmospheric Pollution Risk Inference
Query Lower Bounds for Approximating the Top Eigenvector of Asymmetric Matrices
Conservative neural posterior estimation via distributionally robust training
Benchmark for Assessing Olfactory Perception of Large Language Models
xVGAE: A Hierarchical Variational Graph Autoencoder for Exchangeable Graphs
Replicability is Asymptotically Free in Multi-armed Bandits
Classification of high-dimensional data with spiked covariance matrix structure
Bigger Isn't Always Memorizing: Early Stopping Overparameterized Diffusion Models
Chain-of-Thought Is Not Explainability
AutoDataBench: How Far Are LLM Agents from Autonomously Engineering Post-Training Data Pipelines?
MAEB: Massive Audio Embedding Benchmark
FOGO: Forgetting-aware Orthogonalization Optimizer
Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs
Announced Breaks Separate Conformal Reliability from Frequency Calibration
Parallel Broyden methods for efficiently evaluating nonlinear state space models
ConnectomeBench2: A Unified Benchmark for Automated Connectomic Proofreading
AudioAgentBench: Evaluating Multi-Turn Voice Agents on Real-World Tasks
PhysEval: Quantifying the Gap Between Video Generation and World Physical Laws
Emergent representations of graphical structure in mechanistic neural models of causal judgment
NuMuon: Nuclear-Norm-Constrained Muon for Compressible LLM Training
VeriScope: Measuring Verification-Ready Verilog Artifacts
MMA-SafetyBench: A Benchmark for Multimodal Agent Safety Evaluation
Extending ROC Analysis to Uncertainty-Aware Risk Prediction with an Interval-Based AUC (iAUC)
FinMTM: A Multi-Turn Multimodal Benchmark for Financial Reasoning and Agent Evaluation
RISE-Video: Can Video Generators Decode Implicit World Rules?
When Stored Evidence Stops Being Usable: Scale-Conditioned Evaluation of Agent Memory
Stroke-Audited Quadratic Bezier Splatting with Structural Initialization for Efficient Painting Rendering
Self-Supervised On-Policy Reinforcement Learning via Contrastive Proximal Policy Optimisation
Beyond [SEG] Tokens: Training-Free Video Reasoning Segmentation via Counterfactual Inference and Contrastive Concept
LeanSearch v2: Global Premise Retrieval for Lean 4 Theorem Proving
Verifiable Environments Are LEGO Bricks: Recursive Composition for Reasoning Generalization
Benchmarking and Optimizing Multimodal Structured Generation: The OracleGraph Dataset and PRISM Framework
Conditional Evaluation of Language Models with Cheap Auxiliary Signals
Optimizing Analytic Constants via AI-Guided Lean Proof Refinement
Cost-Aware Best-LLM Identification using Dueling Feedback
FiLoRA: Focus-and-Ignore LoRA for Controllable Feature Reliance
Why Copy Others? Insights into Social Learning from Multi-Agent Reinforcement Learning
TILT: Target-induced loss tilting under covariate shift
Richer or More Gates? Fan-In Trade-offs in Learnable Logic Circuits
Implicit Goal Conditioning via Value Disaggregation
Fast-WAM: Do World Action Models Need Test-time Future Imagination?
Mechanism-Level Chemical Reaction Simulation with Electron Bookkeeping Transformer
Inferring learning rules in deep neural network architectures from animal learning data
CAPO: A Primal-Dual Framework for Constraint-Aware Prompt Optimization
Epitope-Conditioned Nanobody CDR Design via Retrieval-Augmented Protein Language Models
Freshness-Gated Imagination: Step-Level Trust for Latent World Models
LoRaQ: Optimized Low Rank Approximation for 4-bit Quantization
Compressible Representations: Functional Spines in Deep Neural Networks
Visual Instruction Tuning Aligns Modalities through Abstraction
Information-Theoretic Generalization Bounds for Sequential Decision Making
Dual-Contrastive Sparse Autoencoders Reveal Features of Musical Interpretation
Adaptive Entropy-Sparing for Efficient Reasoning
Attention Sinks as Spectral Spikes: A Mechanism Analysis of Gated Attention
DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop Reasoning
InfCLIP: Unified Data Valuation for CLIP Pretraining via Influence-Inspired Scoring
Effect-Driven Skill Abstractions for Offline Reinforcement Learning
Beyond MSE: Differentiable Complexity Priors for Structure-Preserving Neural Denoising
MulCLIP: A Multi-level Alignment Framework for Enhancing Fine-grained Long-context CLIP
SLDR: Defending Against Malicious Fine-tuning via Selective Layers Recovery and Dynamic Routing
Model Collapse is a Singular Complexity Trajectory
Bounds on Extrapolation across Phase Transitions with Generalized Regression
The Block Catastrophe of Marginal Calibration in Certified Requirements Traceability
Transcoder Adapters for Reasoning-Model Diffing
Information-Theoretic Generalization for Set-Input Optimization-Valued Objectives
Gluing Local Contexts into Global Meaning: A Sheaf-Theoretic Decomposition of Transformer Representations
The Rate-Distortion-Polysemanticity Tradeoff in SAEs
Basis-Mediated Bilinear Attention: A New Method for Greatly Reducing Query--Key Pathway Parameters
Mask-Conditioned Gradient Masking for Fine-Tuning Mixture-of-Experts Diffusion Language Models
Emotion-Trained Vision Models Do Not Necessarily Learn EEG-Aligned Facial Dynamics
VoluCore: Spanning Teacher Representations with Volumetric Coresets for Data-Efficient LLM Distillation
Gradient Routing Localizes and Removes Unintended Behaviors in RL
Model Incrimination: Investigating Whether Concerning Behavior Reflects Misalignment
How Much Information is Needed for Accurate Kalman Filtering?
Knocking-Heads Attention: Drop-in Shared Projections for Cross-Head Coordination
Self-Supervised Goal-Reaching Results in Multi-Agent Cooperation and Exploration
Dependency-Guided Parallel Decoding in Discrete Diffusion Language Models
Reliable Clustering and Quantization via Distortion-Constrained Optimal Transport
DASM: Dynamic Autoregressive Subgraph Mining via Two-Stage Policy Alignment
Scalable Supervised Optimal Transport of Gaussian Mixture Models
Enhancing Agentic Code Localization with Traceability Recovered from Repository Evolution
Survival Transformers for Longitudinal Data Analysis: Application to Atrial Fibrillation Risk from ECG
LAMP: Language-Modulated Geometric Preservation for Multi-Modal Object Re-Identification
Nearly Optimal Robust Covariance and Scatter Matrix Estimation Beyond Gaussians
Understanding Goal Generalisation in Sequential Reinforcement Learning
On the Instability and Stabilization of Blockwise Muon
Decomposing Earth Embeddings with Sparse Autoencoders
Token-Conditional Expert Dropout: Implicit Regularization for Stable MoE Pretraining
Specificity-Aware Diffusion Steering via Variance-Reduced Sequential Monte Carlo
LINC: Decoupling Local Consequence Scoring from Hidden Matching in Constructive Neural Routing
Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples
PPO in the Fisher-Rao geometry
Agent Meltdowns: The Road to Hell Is Paved with Helpful Agents
Agent2World: Learning to Generate Symbolic World Models via Adaptive Multi-Agent Feedback
PROBE: Learning to Audit Policy Compliance in Tool-Using LLM Agents
Designing Effective Monitor-Based Interventions for Mitigating Reward Hacking During RL
Optimizing Agent Tool-Use via Trajectory-based Insight Evolution
How Much Evidence Should Retrieval-Augmented In-Context Learning Use Under Distribution Shift?
On the Origin of Algorithmic Progress in AI: Evidence from Language Model Pre-Training
Full-Atom Cyclic Peptide Design via Test-Time Scaled Autoregressive Flow Matching
What Arranges Features in Activation Space? Non-Classical Predictive Geometry in Next-Token Predictors
Requential Coding: Measuring Model Compressibility by Coding Data Instead of Parameters
LITE: A Lightweight Lazy Sampler for Efficient SGD
TokenSwap: Benchmarking and Reducing the Modality Gap in Multimodal LLMs
Log-Likelihood, Simpson’s Paradox, and the Detection of Machine-Generated Text
Expanding LLM Agent Boundaries with Strategy-Guided Exploration
Rebellious Student: Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVR
Test-time Scaling of Diffusions with Flow Maps
Strategist: Designing Agentic Reasoning at Scale
Scaling Limits of Long-Context Transformers
Universal and Efficient Computation with 2D Attention
Dimension Bounds for Contractive Reservoir Computing from Input Entropy
Statistical Mixing Guarantees for Contractive Echo State Networks
Point-to-Manifold Geometry: Flexibly Overcoming the Curse of Dimensionality in Neural Computational Units
Lower-Level Agnostic Bilevel Optimization
Causally Structured Differential Network Modeling for Single-Cell Perturbation Prediction
Decoupled Complementary Fields on 3D Gaussian Maps for Embodied Navigation and Reasoning
Agents as Neuro-Symbolic Reasoners: Path Feasibility Reasoning for Precise Static Bug Detection
Incentivizing Agentic Retrieval for Disease-Centric Clinical Case Search via Trajectory Memory
Adaptive Attribute Completion with Representation Space for Incomplete Graph Domain Adaptation
Open-Ended Scientific Discovery and the Social Dynamics of Evolving Agent Networks
Tokenization and Architecture Jointly Allocate Component Roles in Time Series Transformers
Learning Continuously Evolving Spatio-Temporal Explanations for Traffic Flow Forecasting
Halt Fast! Early Stopping for Certified Robustness
scMAF: Single-Cell Multi-Omics Clustering via Adaptive Modality Fusion
The Scaling Laws of Skills in LLM Agent Systems
SkillOrchestra: Learning to Route Agents via Skill Transfer
StylePlan: Style-Conditioned Intent Planning for Zero-Shot Coordination
Not Every Image Teaches Vision: Visual-Necessity-Gated Continual Learning for Multimodal Large Language Models
Generalizable Physics Simulation through Compositional Energy Minimization
Catch Your Breath: Adaptive Computation for Self-Paced Sequence Production
Your Teacher Can’t Help You Here: Combating Supervision Fidelity Decay in On-Policy Distillation
Single-Pass Evidence Measurement for Interpretable and Uncertainty-Aware Multimodal Face Anti-Spoofing
Adaptive Communication Range for Scalable Cooperative Multi-Agent Reinforcement Learning
Diffusion Fine-Tuning: Iterative Refinement for Advanced Grounding with Diffusion Large Language Models
Beyond Normal References: Discriminative Few-Shot Anomaly Detection
Correction Space Steering for Hallucination Mitigation in Large Vision-Language Models
How Can SignSGD Outperform SGD? A Functional Scaling Law Perspective
C2FT: Enhancing Fine-Grained Perception in MLLMs via Confuse-then-Contrast Fine-Tuning
SpaG-DiT: Enhancing Spatial Grounding for Diffusion Transformers
SceneScaffold: Active Scene-State Construction for Unified 3D Scene Understanding
Breaking the Static: Dynamic Text Conditioning for Diverse Image Generation
MilliVid: Adaptive Latents for Long-Range Consistency in Video Generation
Mean-Field Parallel Decoding for Discrete Diffusion Language Models
WorldComposer: Generative High-Fidelity Simulation with Digital Cousins for Generalizable Robot Learning and Evaluation
Spik-NeRF v2: Pushing the Limit of Spiking Neural Radiance Fields with $ \pm $I-LIF
VSPO: Vector-Steered Policy Optimization for Controllable Model Behavior
Differential Vector Erasure: Unified Training-Free Concept Erasure for Flow Matching Models
Toward Semantically-Consistent Tuning-Free Customization for Rectified Flow Transformers
A Favorable Regime Between ODE and SDE for Few-Step Diffusion Sampling
Hierarchical Semantic Tree Anchoring for CLIP-Based Class-Incremental Learning
Bellman Residual Minimization for Control: Geometry, Stationarity, and Convergence
Consilience for Verifier-Free Test-Time Scaling
Anchored Protein Engineering
STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability
Winfree Oscillatory Neural Network
Dynamics-Aware Sparse Attention for Efficient Autoregressive Video Diffusion
Revisiting Autoregressive GCNs for Vehicle Routing Problems
Query as a Resource: Activity-Cost Guided Remote Sensing Domain-Incremental Object Detection
Expert-guided Bayesian optimization for sustainable protein formulation
TriPrompt: Progressive Local Prompting for Few-shot Out-of-Distribution Detection
FC-DGCN: Deep Graph Convolutional Network for Face Clustering and Recognition
Modulating Merging Strengths via Joint Loss Estimation for LoRA-based Continual Learning
Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning
High-probability Convergence of Gradient Methods under Markovian Stochasticity
EVA-0: Test-Time Model Evolution with Only Two Forward Passes per Sample
Unaligned Image Guided Denoising via Cross-modal Conditional Flow Matching
Semantic Freedom Bottleneck for Domain-Generalized Multimodal Face Anti-Spoofing
Most ReLU Networks Admit Identifiable Parameters
Runtime Analysis of Cartesian Genetic Programming on MAX: A Proven Exponential Speedup
Mitigating Overthinking in Large Reasoning Language Models via Reasoning Path Deviation Monitoring
Knowing You before You Speak: User State Modeling for LLM-Based Personalized Dialogue
TwinFlux: One-Step Discrete-Continuous Flow for End-to-End Autonomous Driving
Optimizing the Envy Cycle Elimination Algorithm
Decoupling Exploration and Policy Optimization: Uncertainty Guided Tree Search for Hard Exploration
Memory Grafting: Scaling Language Model Pre-training via Offline Conditional Memory
Anatomy of Off-Policy Policy Gradient: Importance Sampling, KL Regularization, and Baselines
Resolvent Ellipsoid for Minty Set Inclusions
DUST: Directional Uncertainty-aware and Scale-invariant Transfer Learning
LeAct: Learning to Reason from Expert Actions
Understanding Generalization through Decision Pattern Shift
The Illusion of Diversity: Aligning LLM Exploration via Effective Entropy
$\textbf{EchMo}$: End-to-End Radar Echo Segmentation
World Motion Models: Flexible Sequence Modeling of SE(3) Trajectories
Homological Barriers to Stable Local Nash Dynamics in Quadratic Zero-Sum Games
Exact-Form Regret and Conservative Correlated Equilibria
On Minimizing Regret in Fixed-Confidence $\varepsilon$-Best Arm Identification
MEV: A Multi-Event Video Dataset for Long-Take Generation
Simplified Reversible Residual Networks
CATS: Acceptance-Oriented Critical Token Adaptive Selection for Multimodal Speculative Decoding
LG-Bench: A Graph-Structured Evaluation Benchmark for Life Science
Spherical Bayesian Experimental Design for Active View Selection in 3D Gaussian Splatting
Eliciting Secret Knowledge from Language Models
Can Ideologues Agree on Quality? From Non-identifiable Latent Factors to Collective Outcomes
Breaking the Uniformity Trap: Scaling Video Diffusion Model via SplitMoE
OpenCoF: Learning to Reason Through Video Generation
When to Adopt Model Updates
Register Anything Model for Generalizable and Robust Point Cloud Registration
Paradoxes of Game Theoretic Equilibria and Price of Anarchy
Matched-Control Tests of Partition-Source Claims in One Routed Distillation Family
RAOP: Step-Level Resource Orchestration for LLM Agents across Edge and Cloud
Complexity-Aware LoRA Aggregation for Modality-Heterogeneous Federated Person Re-identification
MARS: Multi-resolution Adaptive Routing for Sequential Recommendation
MemContract: Contract-Sensitive Evaluation for Mutable Agent Memory
Native Audio-Visual Alignment for Generation
Prevailing Bisimulation Metric Learning Is Biased: Implicit Regularization and Its Remedy
PACE: A Proxy for Agentic Capability Evaluation
A 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale
On Differential Private $\ell_1$, $\ell_2$ and $\ell_p^p$ Distance Queries
DynEdit: Dynamic Entropy-Guided Sequential Editing for Large Language Models
A Kernel Nonconformity Score for Multivariate Conformal Prediction
Inverse Modeling of Neural Recordings via Differentiable Biophysical Simulation
Learning Active Perception and Manipulation via Spatio-temporal Visual Memory
Failure-Band Authorization for Filtered Retrieval
Is Memorization Actually Necessary for Generalization
Uni-Synergy: Bridging Understanding and Generation for Personalized Reasoning
Post-Selection-Safe Pessimistic Utilities for Offline Multi-Objective Reinforcement Learning
When the Most Disruptive Messages Are Safe to Prune in Aggregate: Functional Analysis of Communication Pruning in Two-Agent LLM Systems
SVDP: Training-Free Contextual Sparsity Predictors for Fast LLM Inference
Prefix Likelihood-Ratio Control: Tail-Stable Training for Long-Horizon Language Generation
DiagnosticIQ: A Benchmark for LLM-Based Industrial Maintenance Action Recommendation from Symbolic Rules
Adaptive Feature Propagation for Attribute-Missing Graph Clustering
Adversarial Group Fairness in Contextual Bandits: When Robust is Not Fair
Natural Language Actor-Critic: Scalable Off-Policy Learning in Language Space
Resolving Representation Ambiguity in Feedforward Novel View Synthesis Transformer via Semantic-Spatial Decoupling
AlphaPareto: Formulaic Alpha Discovery with LLM-Guided Multi-Objective Reinforcement Learning
Fast-RL: Accelerating Reinforcement Learning for LongCoT Reasoning Models
Historical Relative Policy Optimization for Bootstrapping LLM Reasoning
LINK: Learning to Localize from Known to Unknown Scenes
CompilerKV: Risk-Adaptive KV Cache Compression via Offline Experience Compilation
Parallel-in-Time Variational Inference for Latent Stochastic Differential Equations
EmpathyChat: Structured Cognitive Reasoning in Empathetic Spoken Dialogue
Breaking Information Islands in Sparse Tuning via Small-World Connectivity
Bridging Risk Approximation Gaps in Model Predictive Task Sampling via In-Context Modeling
Information Bottleneck-Guided Adaptive Hypergraph Transformer for Brain Disease Diagnosis
Elicited Adaptation: Auditable Localized Fairness via Pairwise Queries
DrawingsDreamer: A Unified Multi-View Engineering Drawings Generation Model
From Density Matrices to Phase Transitions in Deep Learning: Spectral Early Warnings and Interpretability
Aligning AI Teams
Predictively-Oriented Kalman Filtering
Reward Budgeting Reduces Premature Convergence in Reinforcement Learning for LLM Reasoning
UniVLR: Unifying Text and Vision in Visual Latent Reasoning for Multimodal LLMs
Model Spec Midtraining: Improving How Alignment Training Generalizes
NGDB-Zoo: Towards Efficient and Scalable Neural Graph Databases Training
EVA: Evidence-seeking Visual Agent for Hallucination-Resistant Multimodal Reasoning
Rubric-Align: Safety Alignment through Dynamically Co-Evolving Rubrics
FedSEM: Mitigating Cross-Client Evidence Drift in Federated Multiple Instance Learning
Learning Gaussian Conditional Distributions using Neural Ratio Estimation is Hard
Personalized LLM Alignment Should Be Counterfactually Verifiable
A Frank-Wolfe Approach to Goldstein Stationarity
ClinStab: Stability-Oriented Learning for Medical Time Series via Dual-Stream Alignment
Optimistic Q-value Adaptation for Offline-to-Online Reinforcement Learning
Differentiable Cluster Discovery in Temporal Graphs
DICEQuant: Distortion-Compensated Rounding with Dual-Ended Shrinkage for LLM Quantization
Demographic parity in regression and classification within the unawareness framework
Fast and Stable Gradient Approximation for Bilinear Forms of Hermitian Matrix Functions
Physics-Constrained Generative World Model for Off-Road Terrain via Post-hoc Projection
Geometry-Aware Zeroth-Order Optimization for Fine-Tuning Quantized LLMs
Tropical Gaussian Anticoncentration: Settling Optimal Instance-Dependent Bounds for Online Learning in Extensive-Form Games
GAE Falls Short in Imperfect-Information Self-Play Reinforcement Learning
Denoising-Time Heterogeneity in VLA Action Generation: A Controlled Study via Step-Wise Expert
Understanding Gradient Orthogonalization for Deep Learning via Non-Euclidean Trust-Region Optimization
Inverting the Bellman Equation: From $Q$-Values to World Models
DiagSQL: A Diagnostic Validator for Text-to-SQL with Reward Allocation and Co-occurrence Shaping
GeoG2U-Bench: When Does Generation Help Understanding in Ultra-High-Resolution Remote Sensing?
Sketch Then Paint: Hierarchical Reinforcement Learning for Diffusion Multi-Modal Large Language Models
Neural Backward Filtering Forward Guiding
EgoStream: A Diagnostic Benchmark for Streaming Episodic Memory in Egocentric Vision
Classification Fields: Arbitrarily Fine Recursive Hierarchical Clustering From Few Examples
Bayesian Optimization on Function Spaces via Sparse RKHS Manifolds
Reasoning Poisoning: Utilizing Social-Engineering to Steer Chain-of-Thought
Jacobian Scopes: A Unified Geometric Framework for Token-Level LLM Attributions
LookWhen? Fast Video Recognition by Learning When, Where, and What to Compute
Busemannformer: Horospherical Self-Attention for Hyperbolic Graph Transformers
On Time, Within Budget: Constraint-Driven Online Resource Allocation for Agentic Workflows
Privacy-Preserving Retrieval-Augmented Generation with Plausible Deniability
Predictive–Generative Drift Decomposition for Speech Enhancement and Separation
Test-time Risk Adaptation with Mixture of Agents
Scalable Neural Safety Certification via Monotonicity
Statistical Estimation of Adversarial Risk in Large Language Models under Best-of-N Sampling
Prune, Don’t Rebuild: Efficiently Tuning $\alpha$-Reachable Graphs for Nearest Neighbor Search
3DCodeBench: Benchmarking Agentic Procedural 3D Modeling Via Code
Quotient-Categorical Representations for Bellman-Compatible Average-Reward Distributional Reinforcement Learning
Sublinear Time Quantum Sensitivity Sampling
SLOT-IR: Learning Disentangled Slot Representations for Infrared Spectral Unmixing
The Many Faces of On-Policy Distillation: Pitfalls, Mechanisms, and Fixes
Driving Video Retrieval for Complex Queries with Structured Grounding
Activation Steering of Video Generation Models via Reduced-Order Linear Optimal Control
SPATIALEPIBENCH: Benchmarking Spatial Information and Epidemic Priors in Forecasting
Likelihood-Free Generative Policy Optimization
B2P-Corr: Batch-to-Population Gradient Estimators for Non-Decomposable Correlation Losses
FILOsofer: A TEE-Shielded Model Partitioning Framework based on Fisher Information-Guided LoRA Obfuscation
Long-Lived AI Agents Age Too: They Quietly Decay After Deployment
Improving constraint-based discovery with robust propagation and LLM priors
Dynamic k-center clustering with lifetimes
Conformal Prediction with Paraphrase-Aware Scoring for LLM Uncertainty Quantification
Bifurcation Models: Learning Set-Valued Solution Maps with Weight-Tied Dynamics
PORTool: Importance-Aware Policy Optimization with Rewarded Tree for Multi-Tool-Integrated Reasoning
Beyond Domains: Reusing Web Skills via Transferable Interaction Patterns
AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMs
SARA: Step-Adaptive Rank Adjustment for Diffusion Inference Acceleration
GAIA: Geometry-Adaptive Operator Learning for Forward and Inverse Problems
Agent-Native Research Artifacts
Beyond Risky Activities: Bridging the Supervision Gap for Situational Risk Reasoning
When Expert Disagreement Hurts: Auditing Prestige-Sensitive Revision in LLM Decision Pipelines
Diffeomoprhism-Informed 3D Gaussian Splattings via Screen-Space Optimal Transport (OT)
RA$^2$: Retain-Anchored Attraction Preserves Forget-Adjacent Utility in LLM Unlearning
When Are Compositional Problems Learnable from Verifiable Rewards?
Systematic Scaling Analysis of Jailbreak Attacks in Large Language Models
Optimal Algorithms for Fixed-Graph Multi-Attribution Privacy
Reinforcement learning enhanced flow matching for reference-based tumor generation on unpaired CT images
PosteriorBench: From Point Estimates to Posterior Matching in Evaluating Generative Inverse Solvers
RSPO: Reasoning-Supervised Policy Optimization for Long-Tail Autonomous Driving
EgoSurgHands: An Egocentric 3D Hand Pose Dataset & Benchmark for Open-Surgery Training
Efficient Multi-Source Prompt Adaptation for Cross-Domain Open-Vocabulary Learning
Differential Item Functioning as an Item-Level Diagnostic for LLM Benchmarks
TRIAGE: Evaluating Prospective Metacognitive Control in LLMs under Resource Constraints
Benchmarking Multi-Modal Graph-based Social Media Popularity Prediction
DEFT: Disentanglement-Enhanced Fine-Tuning for EEG Foundation Models
RAHF: Reward-Amplified Human Feedback for Closed-Loop Policy Fine-Tuning
TabDLM: Free-Form Tabular Data Generation via Joint Numerical–Language Diffusion
An Embarrassingly Simple Graph Heuristic Reveals Shortcut-Solvable Benchmarks for Sequential Recommendation
TraceML: An Empirical Analysis of Human-Agent Planning in Machine Learning Development
VIPBench: A Human-Aligned Benchmark for Voice Identity Perception in the Age of Voice Cloning
FrontierOR: Benchmarking LLMs' Capacity for Efficient Algorithm Design in Large-Scale Optimization
A Topological Encoder Decoder Framework for Temporal Graph Learning
Stochastic Approximation Approach for Decentralized Optimization on Time Varying Random Networks
SceneFactory: GPU-Accelerated Multi-Agent Driving Simulation with Physics-Based Vehicle Dynamics
SiliconBench: Speed, Memory, and Fidelity for LLM Inference on Apple Silicon
FindStatBench: Evaluating Large Language Models on Combinatorial Code Synthesis
SOL-ExecBench: Speed-of-Light Benchmarking for Real-World GPU Kernels Against Hardware Limits
ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?
Bottleneck Benchmark: Sequence Compression Under Controlled Difficulty and Fixed Latent Size
Corrected Integrated Laplace Approximation for Bayesian Inference in Latent Gaussian Models
PBT-Bench: Benchmarking AI Agents on Property-Based Testing
FuRA: Full-Rank Parameter-Efficient Fine-Tuning with Spectral Preconditioning
DistDebug-Bench: Can LLM Agents Diagnose Bugs in Distributed Systems?
Variational Inference via Entropic Transport Descent
A Scalable Measure of Loss Landscape Curvature for Analyzing the Training Dynamics of LLMs
When Attribution Patching Lies: Diagnosis and a Second-Order Correction
MPCI-Bench: A Benchmark for Multimodal Pairwise Contextual Integrity Privacy Evaluation of Language Model Agents
HERO: Improving the Reliability and Sensitivity of Generative Model Evaluation Using Historical Data
Convex Compositional Reasoning Models
Denoising Time Matters: Diverse Generation in Diffusion Language Models
Rethinking SAE Evaluation: An Atomic Interpretable Unit Framework Reveals Hidden Polysemanticity and Redundancy
PhyMetric: Diagnosing Physical Plausibility in Text-to-Video Generation via Scene-Level QA
NINJA: A Navigator–Inspector Joint Architecture for Context-Efficient Issue Localization
Where Tabular Foundation Models Falter on Genetic Data: Datasets That Expose and Provide a Path to Address the Gap
FlyAOC: Evaluating Agentic Ontology Curation of Drosophila Scientific Knowledge Bases
VIGOR: Benchmarking Visual Rationale Correctness in Multimodal Large Language Models
ITPEval: Benchmarking Formal Translation Across Interactive Theorem Provers
TraceDx: Criticality-Weighted Atomic Facts as a Training Signal for Sequential Clinical Diagnosis
PortPy: A Benchmark for AI and Optimization in Cancer Radiotherapy Planning
Conformal Selective Acting: Anytime-Valid Risk Control for RLVR-Trained LLMs
BOOST: Power-Optimal Strong-FWER Testing for Block-Structured Multiplicity
CUDABeaver: Benchmarking LLM-Based Automated CUDA Debugging
StaRPO: Stability-Augmented Reinforcement Policy Optimization
Learning to Persuade Exposes How Easily LLMs Abandon Correct Beliefs
Theory-Scale Auto-Formalization of Logics for Computer Science
RecoverBench: A Systematic Benchmark for Error Recovery in Robotic Manipulation
FASD: Hardware Acceleration for Multi-AI-Agent Discussion
Do Joint Audio-Video Generation Models Understand Physics?
When Simulation Lies: A Sim-to-Real Benchmark and Domain-Randomized RL Recipe for Tool-Use Agents
A$^3$Bench: A Benchmark for Compositional Reasoning over Aggressive Interactions in Videos
Prompt–Activation Duality: Improving Activation Steering via Attention-Level Interventions
Informed Posterior Sampling: More Efficient Online Learning with Few Offline Demonstrations in Average-Reward MDPs
Clustering with Weak Distance Oracles
The Illusion of Forgetting: Rank Leakage in Knowledge Editing and Its Mitigation
AdERA: Adaptive Exponent Reuse for Lossless Allgather in Sharded MoE Training
CellularS2-Bench: A Staged, Evidence-Grounded Benchmark for Cellular Network Security Reasoning
TorchUMM: A Unified Multimodal Model Codebase for Evaluation, Analysis, and Post-training
Denoising Distances in Metric Measure Spaces
Physics-Conditioned Video Diffusion with Kinematic Priors for Fusion Capsule Polishing
Amplitude Decoupling in Gaussian Process Training: Exact Decomposition, Pole Cancellation, and Evaluation-Efficient Optimization
Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage?
Escaping Reasoning Basins: Basin-Aware Search for Inference-Time LLM Reasoning
MOSAIC: Module Discovery via Sparse Additive Identifiable Causal Learning for Scientific Time Series
Towards Settling the Complexity of Non-Euclidean Parallel Convex Optimization
Theory Guided and Interpretable Neural Operator Design for Partial Differential Equation Learning
The Value of Being Wrong: Self-Mined Visual In-Context Learning from Errors
Towards a Universal Causal Reasoner
FluxLite: Inference-Time Proposal Control for Discrete Diffusion Models
Constraint-Aware Influence Estimation in Deep Constrained Learning
On the Parallel Optimality of Exponentiated Gradient Descent
CC-GS: Low-Memory 3D Gaussian Splatting Training via CPU-GPU Block-Wise Context Compositing
Optimal Real-Data Allocation for Synthetic-Data-Augmented Inference
Mode-Controlled Policy Optimization: A Geometry-Aware Recipe for LLM Post-Training
SemanticDialect: Semantic-Aware Mixed-Format Quantization for Video Diffusion Transformers
Chain-of-Route: State-Aware LLM Routing for Multi-Turn Conversations
CogBench: Evaluating Cognitive-Level Control in LLM Question Generation
Towards Understanding Momentum Acceleration in River-Valley Loss Landscape
Minimax Optimal Kernel Two-sample Testing in Sub-quadratic Time
Iterative Critique-and-Routing Controller for Multi-Agent Systems with Heterogeneous LLMs
MaPPO: Maximum a Posteriori Preference Optimization with Prior Knowledge
Compositional Reasoning in Language Models under Reinforcement Learning Post-Training
Tcell: Mitigating Harmful Fine-tuning for Large Language Models via Gradient Alignment
Certified but Private: Scalable Zero-Knowledge Proofs for the Formal Verification of Neural Networks
Self-Tuning Graph Filters via State-Dependent Operator Composition
A Mechanistic Interpretability Study of an Astronomical Foundation Model
Acting without Knowing: Planning, Prediction, and Transfer Dissociate in Interactive Visual Physics
There are Levels to It: Red Teaming LLMs with Hierarchical Reinforcement Learning
Sparse Expansion Utility: Identifying and Routing to Pivotal Steps in LLM Reasoning Chains
Is $\sqrt{d}$ Separation Necessary for Gradient EM to Learn Gaussian Mixtures in High Dimensions?
Frontier Language Models Struggle to Copy: Text Can Be Better Viewed in 2D
SpecDrop: Parameter-Free Category-Conditioned Routing for Modular Specialization
On the Optimal Sample Complexity of Offline Multi-Armed Bandits with KL Regularization
Value Entanglement: Conflation Between Different Kinds of Good In (Some) Large Language Models
Efficiently Representing Algorithms With Chain-of-Thought Transformers
Cardinality-Decomposed Loss for Heterogeneous GNNs
CipherFlow: Hardware-Aware Compiler Framework for Low-Latency Hybrid Secure Inference
Optimization Dynamics Imprint Semantic Specificity in Contrastive Embedding Norms
Can Entry-Wise Clipping Give Spectral Control of Stochastic Gradients?
Temporal Gradient Inversion for Private Trajectory Reconstruction in Embodied Reinforcement Learning
HEART: Hyperspherical Embedding Alignment via Kent-Representation Traversal in Diffusion Models
How Accurately Can a Gaussian Approximate Stochastic Approximation Iterates?
A Process-Level Evaluation of LLM Discovery Agents
Sample complexity of stochastic optimization with integer variables
Semantic Optimal Transport for Sparse Autoencoder Feature Matching and Circuit Compression
Online Imitation Learning for Stabilizing Vlasov--Poisson Plasmas
LensCT: Fine-Grained AI-Involved Text Detection via Temporal-Hierarchical Tomograms of LLM Internals
Quantum Speedup of Multi-armed Bandits at Scale by Tackling Memory Decoherence
Spike-to-Field Mechanisms of Turbulence-Like Dynamics in Spatial Spiking Neural Networks
Effective Multi-sensor Conditioning for Street-view Novel-view Synthesis
Optimizer-Induced Mode Connectivity: From AdamW to Muon
SlackBench: Benchmarking Agents on Collaborative Projects Grounded in Real Code Repositories
Personalized and Collaborative Online LQR via Thompson Sampling
DiRotQ: Rotation-Aware Quantization for 4-bit Diffusion Transformers
Improved Leverage Score Sampling for Constrained Active Linear Regression
VideoMLA: Low-Rank Latent KV Cache for Minute-Scale Autoregressive Video Diffusion
Finite Time Analysis of Risk-Sensitive RL via Noisy Power Iteration
From Preference Data to Personalization: Tracing Sycophancy in Large Language Models
Not Every Rubric Teaches Equally: Policy-Aware Rubric Rewards for RLVR
Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RL
Model-Free Assessment of Simulator Fidelity via Quantile Curves
ELPAC: Endpoint-Anchored Latent Progression with Stage-Varying Multimodal Coordination
PCBSchemaGen: Reward-Guided LLM Code Synthesis for Printed Circuit Boards (PCB) Schematic Design with Structured Verification
Order-based structure learning for zero-inflated count data under data heterogeneity
Agent-ToM: Learning to Monitor Autonomous LLM Agents via Theory-of-Mind Reasoning
COMPLLLM: Fine-tuning LLMs to Discover Complementary Signals for Decision-making
FOCUS: Benchmarking Retinal Model Generalization from Foundation Vision Encoders to Multimodal LLMs
Composing Diffusion Priors with Explicit Physical Context via Generative Gibbs Sampling
AlgoPilot: Cross-Paradigm Reasoning in Language Models via Strategy Selection and Guidance
Non-Linear Pricing Restores Tractability for a Data Seller
Coupled Integral PINN for Discontinuity
Classification at the Edge of Stability: Unifying Self-Stabilization and Convergence Rates
GOLD PANNING: Strategic Context Shuffling for Needle-in-Haystack Reasoning
ScaleBITS: Scalable Bitwidth Search for Hardware-Aligned Mixed-Precision LLMs
Optimal Linear Regression Without a Variance
3D Point Splatting for mmWave Radar Novel View Synthesis
Learning Rate Decay Can Exponentially Accelerate SGD for Global Optimization of Nonconvex Functions
DARLING: Detection Augmented Reinforcement Learning with Non-Stationary Guarantees
PatternBloom: Empowering Agentic RAG with Externalized RL-Distilled Graph Patterns
Alignment Is Not Enough for Safe Medical LLM Evaluation
Ensembits: an alphabet of protein conformational ensembles
Offline Preference-Based Trajectory Evaluation
BLEND: Balancing Personalization vs. Generalization in Federated Vision–Language Models
From Zero to Hero: Training-Free Custom Concept Spawning in World Models
Policy Gradient Algorithms in Average-Reward Multichain MDPs
Transformers Provably Learn Graph Search: Training Dynamics and the Exponential Power of Depth
LARK: Learnability-Grounded Trajectory Selection for Efficient Reasoning Distillation
Runtime Monitoring of Perception-Based Autonomous Systems via Embedding Temporal Logic
Generative Control as Optimization: Time Unconditional Flow Matching for Adaptive and Robust Robotic Control
Information Templates: A New Paradigm for Intelligent Active Feature Acquisition
MCP-Atlas: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Servers
Truncated Riemannian (1+1)-ES for Black-Box Optimization with Intrinsic Dimension Guarantees
Adaptive Test Case Discovery for LLM-Assisted Decision Making in High-Stakes Domains
Attend Locally, Remember Linearly: Linear Attention as Cross-Frame Memory for Autoregressive Video Diffusion
3DSPA: A 3D Semantic Point Autoencoder for Evaluating Video Realism
Strong Teacher Not Needed? On Distillation in LLM Pretraining
Variance-Optimal State Resampling for Reinforcement Learning with Verifiable Rewards
TensorCommitments: A Lightweight Verifiable Inference for Large Language Models
UniPro: Unified Multi-Mode Medical Image Segmentation from 2D Images to 3D Volumes via Propagation
From POMDP Theory to Deep RL with Particle Filters
Escaping the Cognitive Well: Efficient Competition Math with Off-the-Shelf Models
Inference-Time Search Using Side Information for Diffusion-Based Image Reconstruction
Reinforcement Learning for Diffusion LLMs with Entropy-Guided Step Selection and Stepwise Advantages
Beyond LoRA vs. Full Fine-Tuning: Gradient-Guided Optimizer Routing for LLM Adaptation
Long-Context Language Models Require Extreme Sparsity in Context Dimension
WebNavigator: Global Web Navigation via Interaction Graph Retrieval
Perfect Parallelization in Mini-Batch SGD with Classical Momentum Acceleration
See it to Place it: Evolving Macro Placements with Vision Language Models
A Statistical Theory of Gated Attention through the Lens of Hierarchical Mixture of Experts
A Systematic Analysis of Out-of-Distribution Detection Under Representation and Training Paradigm Shifts
Revisiting the Generic Transformer: Deconstructing a Strong Baseline for Time Series Foundation Models
To discretize continually: Mean shift interacting particle systems for Bayesian inference
Prudent-Banker: No Extra Fees for Baseline Safety in Adversarial Bandits With and Without Delays
No Coin Left Behind: Maximizing Strategic Surplus Against No-Regret Dynamics
HearSayBench: Can LLMs Navigate from Abstract Human Rights to Lived Lives?
K-PWM: Control-Oriented Structured World Models under Partial Observation
Accuracy vs. Accuracy: Computational Tradeoffs Between Classification Rates and Utility
FiedlerPrune: Connectivity-Preserving Cross-Layer Pruning for Large Language Models
Severity-Controlled Prediction Sets for Medication Recommendation
Mitigating Data Heterogeneity Effect in Client-Reshuffling-Based Federated Learning
Neural Field Thermal Tomography: A Differentiable Physics Framework for Non-Destructive Evaluation
On the Fragility of Latent Knowledge: Layer-wise Influence under Unlearning in Large Language Model
Leveraging Soft Prompts for Privacy Attacks in Federated Prompt Tuning
What Does an Observability Forecasting Foundation Model Know?
UltraDiff:Transferring High-Fidelity Priors to Compressed Latent Spaces for High-resolution Image Generation
STARFlow2: Bridging Language Models and Normalizing Flows for Unified Multimodal Generation
Online Allocation with Differential Privacy
Normalizing Trajectory Models
Finite-Sample Performance of Gradient Descent in Logistic Regression with Gaussian Design
Beyond Trajectory Matching: Reflow with Marginal Distribution Alignment
SILSA: Sliding-Window Slice Latents for Topology-Preserving High-Resolution 3D Generation
Hybrid-LoRA: Bridging Full Fine-Tuning and Low-Rank Adaptation for Post-Training
Low-Rank Hierarchical Merging for Efficient Long-to-Short Reasoning
Stable GFlowNets with Probabilistic Guarantees
What Should a Streaming Video Model Remember?
A Provably Convergent and Practical Algorithm for Gromov–Wasserstein Optimal Transport
Learning How to Cube
Jet-Long: Efficient Long-Context Extension with Dynamic Bifocal RoPE
Learning What to Predict: Downstream-Guided Task Design for Continued Pretraining
Elastic Spectral State Space Models for Train-Once Budgeted Inference
Tri-Prompting: Controllable Video Generation with Scene, Subject, and Motion Prompts
Synthon Contrastive Learning for Synthesizable 3D Molecule Generation
Truthful Calibration Errors for Multi-Class Prediction
Debiasing Sketched Ridge Regression: A Functional Estimation Perspective
BACE: Behavior-Adaptive Connectivity Estimation from Multi-Region Neural Recordings
Nonconvex Decentralized Stochastic Bilevel Optimization under Heavy-Tailed Noise
AdaAlloc: Adaptive Visual Token Allocation for Long-Video Question Answering
Concept Modulation Models: A Unified Framework for Identifiability and Extrapolation
A Doubly Smoothed Decentralized Stochastic Minimax Optimization Algorithm
Spectrally Parameterized Neural Inverse Reconstruction
When Safety Becomes An Outlier: Understanding the Retention of LLM Safety Behaviors
Personal Visual Memory from Explicit and Implicit Evidence
SparDA: Sparse Decoupled Attention for Efficient Long-Context LLM Inference
Multi-Stage Planning from Single-Stage Data: Reinforcement Learning Helps Composition but Requires Anchoring
Enabling Preference-driven Unlearning in Few-step Distilled Text-to-Image Diffusion Models
Robust Surrogate Modeling for Explainable Graph Neural Networks
Query Lower Bounds for Diffusion Sampling
A Unified Spectral Theory of Multimodal Losses
Efficient Analytic Uncertainty Quantification for Multimodal Regression
State-of-art minibatches via novel DPP kernels: discretization, wavelets, and rough objectives
Submodular Clustering beyond $1-1/e$
Back to Blackwell: Closing the Loop on Intransitivity in Multi-Objective Preference Fine-Tuning
A simple model of co-emergence of grid and place fields
GraphIP–Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It?
VLS: A Vision-Language-Shape Model for Open-Vocabulary Partonomic 3D Reconstruction
OmniGF: A Dual-Branch Vision-Language Framework for Unified Gaze Following
Concurrent Image Understanding and Generation: Self-Correcting Coupled Markov Jump Process
Viverra: Text-to-Code with Guarantees
Tail Wags the Model: Generalization and Membership Privacy Trade-offs of Sharpness-Aware Minimization
Learning Biological Hierarchies in Single-Cell Foundation Models
Reinforcing Multimodal Reasoning Against Visual Degradation
SURF: Steering the Scalarization Weight to Uniformly Traverse the Pareto Front
MARS: Harmonizing Multimodal Convergence via Adaptive Rank Search
GauS: Differentiable Scheduling Optimization via Gaussian Reparameterization
Structured Masked Diffusion for Joint Multiuser Decoding
Self-Consuming Generative Models with Co-Evolving Human Preferences
Do More Modalities Always Help? A Geometric Perspective on Missing-Modality Robustness
Proper Agnostic Learning of Functions of Halfspaces
PORT: Preference Optimization via Robust Token-Level Reweighting
HESTIA: A Hessian-Guided Differentiable Quantization-Aware Training Framework for Extremely Low-Bit LLMs
Safeguarding LLMs via Model-Agnostic Latent Safety Signals from Dark Knowledge
Monotone Inclusion Approach to Weakly Monotone Discrete-Time Finite-Horizon Mean-Field Games
Mecha-nudges for Machines
Justitia: Fair and Efficient Scheduling of Task-parallel LLM Agents with Selective Pampering
Diffusion Language Models Can Approximate Optimal Infilling Lengths Implicitly
gHAWK: Structural Encoding for Scalable Training of Graph Neural Networks on Knowledge Graphs
Transformers Provably Implement In-Context Reinforcement Learning with Policy Improvement
Autoregressive Diffusion World Models for Off-Policy Evaluation of LLM Agents
OmniMem: Scalable and Adaptive Memory Retrieval for Long Video Generation
Elastic Representations via Hyperbolic Geometry
Scale-mixture Langevin sampling in the subspaces of recurrent cortical circuit dynamics
A Training-Free Video Moment Retrieval Framework via Selection from Multiple Visual Prompts
UMAS: System-Level Uncertainty Quantification for Multi-Agent LLM Systems
AnyHand: A Large-Scale Synthetic Dataset for RGB(-D) Hand Pose Estimation
Multi-Objective Causal Bandits: Minimal Intervention Space and Policy-Level Learning
CupOFMoCA: Coupled Objective-Guided Discrete Flows for Molecular Conjugate Assembly
DeepVoting: Learning and Improving Voting Rules with Fine-Tuning
Budgeted Multi-Source Counterfactual Annotation for Off-Policy Evaluation
Invertible Logits Transformation for Accuracy-Preserving Post-Hoc Uncertainty Calibration
TritonTune: LLM-Guided Multi-Agent Optimization of GPU Kernel Configurations
Distributionally Robust Token Optimization in RLHF
Debiased DPO for Diffusion Models
Residual-Autoregressive Context for 3D Gaussian Splatting Compression
Optimal Learning-Augmented Algorithm for Online Bidding
FlashBoB: I/O-Efficient Exact Backward-over-Backward for Softmax Attention
The Invisible Hand of Physics: When Video Diffusion Models Know More Than They Show
Correlating Cross-Iteration Noise for DP-SGD using Model Curvature
Bridging Modalities, Spanning Time: Structured Memory for Ultra-Long Agentic Video Reasoning
Near-Optimal Sample Complexity of Robust Reinforcement Learning with KL Uncertainty Set
SALART-VQA: Diagnosing Whether VLMs Understand Salient Artifacts in Generated Images
FlowBank: Query-Adaptive Agentic Workflows Optimization through Precompute-and-Reuse
VASR: Variance-Aware Systematic Resampling for Diffusion Models
Causal Survival Forests with Negative Controls
Decentralized Aggregation of LLM Predictions via Wagering Mechanisms
Rethinking Ratio-Based Trust Regions for Policy Optimization in Multi-Agent Reinforcement Learning
Finite-Sample and Communication-Efficient Networked Information Aggregation
Actionable Hallucination Detection: Translating Latent Uncertainty into Agentic Critique
Online Finetuning Decision Transformers with Pure RL Gradients
Policy Optimization in Hybrid Discrete-Continuous Action Spaces via Mixed Gradients
TIDE: Every Layer Knows the Token Beneath the Context
JudgmentBench: Comparing Rubric and Preference Evaluation for Quality Assessment
On the Efficiency of Structured Pruning in Small Language Model Pretraining
Data Auctions for Retrieval Augmented Generation
MAST: Label-Efficient, Robust, and Generalizable Sound Detection for Biodiversity Monitoring via Masked Audio Pretraining and Self-Training
Measuring and Strengthening Behavioral Suppression in Language Models
Towards Matrix-Parallel and Feature-Scalable 3D Gaussian Splatting Rendering on GPUs
LACE: Lattice Attention for Cross-thread Exploration
Efficient Dynamic Algorithms for Graph Neural Networks with Non-Linearity
Discovering Symbolic Differential Equations with Symmetry Invariants
Neural Expansion: A Unified Mechanism for How Deep Neural Network Generalize
The Z-Gromov-Wasserstein Distance
SarcBench: A Bilingual Benchmark for Contextual Sarcasm Understanding, Response, and Generation
Spectral Measures of Mamba Conductances Predict and Shape Effective Receptive Fields
Demystifying Numerical Errors in LLM Inference: Achieving Reproducible Inference for Mission-Critical Tasks with HEAL
PhysGraphNet: Physical-State Scene Graphs via Latent Graph Reasoning and Counterfactual Supervision
Sharpness of Minima in Deep Matrix Factorization
Evolutionary Feature Engineering for Structured Data
VeriContest: A Competitive-Programming Benchmark for Verifiable Code Generation
Constrained Code Generation with Discrete Diffusion
Optimal Recalibration of an Online Predictor
Learning to Trigger: Reinforcement Learning at the Large Hadron Collider
VolFill: Single-View Amodal 3D Scene Reconstruction with Volumetric Flow Matching
Fully Distributed Tâtonnement for Chores Markets
Structure-Adaptive Estimation of Heterogeneous Treatment Effects with Kernel Methods
DD-CAM: Minimal Sufficient Explanations for Vision Models Using Delta Debugging
Ares: Adaptive Reasoning Effort Selection for Efficient LLM Agents
Smooth Flow Matching for Synthesizing Functional Data
RoPEMover: Depth-Aware Object Relocation via Positional Embeddings
Provably Efficient Representation Learning for Low-Rank CMDPs
RefineTok: Scale-Wise Tokenization for Progressive Visual Refinement
LASER: Latent Space Adjoint Matching for Support Constrained Entropy Regularized Offline RL
SceneAligner: 3D-Grounded Floorplan Localization in the Wild
Unified Generative-Predictive Modeling for 4D Scene Understanding
Solving Max-Cut to Global Optimality via Feasibility-Preserving Graph Neural Networks
BrainTRACE: Tracing Longitudinal, Multimodal, and Volumetric Evidence in Brain MRI Clinical Reasoning
SplitZip: Ultra Fast Lossless KV Compression for Disaggregated LLM Serving
Adaptive Mass-Segmented KV Compression for Long-Context Reasoning
Lean4Agent: Formal Modeling and Verification for Agent Workflow and Trajectory
Wavefunction Flows: Efficient Quantum Simulation of Continuous Flow Models
Latent Generative Solvers for Generalizable Long-Term Physics Simulation
Inline Critic Steers Image Editing
Understanding Reasoning from Pretraining to Post-Training: Chess as a Controlled Testbed
PM1: A Multimodal Foundation Model for Genomes, Phenotypes, and Images at Biobank Scale
Generating the Unheard: Phylogeny-Guided Latent Generation for Ancestral Sound Reconstruction
TAC: Timestamped Audio Captioning
AME-TS: Anchored Mixture-of-Experts for Time Series Forecasting
Soteria: Formally Verified Planning with Runtime Enforcement for Safe LLM Agents
Linguistic Trajectory Encoding for Efficient Long-Horizon Spatial Memory in Embodied Agents
Stealthy World Model Manipulation via Data Poisoning
JODA: Composable Joint Dynamics for Articulated Objects
Missing data and cluster graphs: cluster-level missingness vs variable-level missingness
Bounding Global and Local Compression Error of Signal Parameterizations
GlucoFM: A Dual-Stream Foundation Model for Continuous Glucose Monitoring
SyncWorld: Visual Calibration Enables World Models as Zero-Shot Simulators
A Deep Learning Framework for Scalar-on-Function Models
Training Agent to Scale Inference-Time Reasoning
Does Sparse Connectivity Improve Generalization? Convolutional Networks Below the Edge of Stability
Robust Policy Optimization to Prevent Catastrophic Forgetting
Categorical Bayes filtering for computational phenotyping in adaptive learning
From Nodes to Pixels: Topological and Structural Two-View Graph Imaging
Efficient Neural Field Learning via Adaptive Coverage and Focused Sampling
Evidential Semantic Uncertainty Decomposition for Large Language Models
Simple KNN-Based Outlier Detection Achieves Robust Clustering
BioBlobs: Unsupervised Discovery of Functional Substructures for Protein Function Prediction
KV-PRM: Efficient Process Reward Modeling via KV-Cache Transfer for Multi-Agent Test-Time Scaling
Z0-Inf: Zeroth Order Approximation for Data Influence
FlashFFN: Multi-Head Decomposition Enables I/O-Aware Feed-Forward Network
ROCKET: Residual-Oriented Multi-Layer Alignment for Spatially-Aware Vision-Language-Action Models
Alleviating Hallucination with Training-Free Uncertainty-Guided Steering
Geometric Signatures of Reasoning: A Spectral Perspective on Task Hardness
Graph Label Alignment: A Diagnostic Atlas for Graph Classification
Elephant in the Fridge: Constant-Memory Frame Packing for Long Video Understanding
Total Variation Rates for Riemannian Flow Matching
When Uncertainty Is the Target: Adversarial Attacks on Uncertainty-Aware Predictors
AdaST: Adaptive Coupling for Spatial-Temporal Forecasting
SCULPT: Advancing Masked Discrete Diffusion for High-Resolution Image Synthesis.
Entropy Dynamics of Agent Reinforcement Learning
Perceive-then-Plan: Layout-as-Policy for Monocular 3D Scene Layout Estimation
InfoSFT: Learn More and Forget Less with Information-Aware Token Weighting
A Single-Sample Polylogarithmic Regret Bound for Nonstationary Online Linear Programming
POME: Post Optimization Model Edit via Muon-Style Projection
When Does Subspace Direction Matter for LoRA? Regime Analysis of the Magnitude Principle in Few-Shot Adaptation
OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents
Fine-Tuning Improves Information Conveyance in Language Models
ViT-AdaLA: Adapting Vision Transformers with Linear Attention
AI Governance Should Prioritize Control and Knowledge Boundaries Over Limiting Intelligence
Visual Robustness and Neural Alignment in a Shared Foraging Task: The Mouse vs. AI Benchmark
HiPhy: Hierarchical Alignment for Physically-Plausible Multi-Principle Video Generation
One-Bit Clustering for Two Component Sub-Gaussian Mixture Models
Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learning
Learning from Trials and Errors: Reflective Test-Time Planning for Embodied LLMs
Dynamically Structured Diffusion Language Model Decoding via Bayesian Inference
HYVE: Hybrid Views for LLM Context Engineering over Machine Data
Spectral-Sphere-Constrained Hyper-Connections
RILA: A Radar-Native Structured Interface from Sparse mmWave Point Clouds to Large Language Models
Representation Fréchet Loss for Visual Generation
On Inherent Privacy of Posterior Sampling: A Unified R\'enyi-Divergence Framework
FactorizedHMR: A Hybrid Framework for Video Human Mesh Recovery
Automatically Refining Coding Rules for AI Coding Agents
Mechanistic Critics for Sample-Efficient NPU Design-Space Exploration
DICE: Decoupling Capability from Intervention Necessity in LLM Tutoring
CineOrchestra: Unified Entity-Centric Conditioning for Cinematic Video Generation
Riemannian Ordinary Least Squares
SPIRIT: Speed-Driven Online Adaptation for Self-Speculative Decoding
Flow Matching for Offline Reinforcement Learning with Discrete Actions
LCD$^3$: Layout-Conditioned Diffusion for Dataset Distillation in Object Detection
Optimal and Efficient Contextual Combinatorial Semi-bandits with General Function Approximation
Achieving adaptivity and optimality for multi-armed bandits using Exponential-Kullback Leibler Maillard Sampling
World Tracing: Pixel-Aligned Geometry Beyond the Visible
MLLMs Fail to Refuse when Using Tools Agentically
Riemannian Bilevel Optimization under the Polyak–Łojasiewicz Condition
Scale Where It Matters: Training-Free Localized Scaling for Diffusion Models
SMASH: Probing Speech Recognition Robustness via Semantically Targeted Bit Flips
When Policies Cannot Be Retrained: A Unified Closed-Form View of Post-Training Steering in Offline Reinforcement Learning
H-Flow: Self-supervised Human Scene Flow via Physics-inspired Joint Multi-modal Learning
Offline-Online Reinforcement Learning for Linear Mixture MDPs
ACED-Bench: Evaluating How LLM Agents Acquire and Act on Causal Evidence
EMA-Nesterov: Stabilizing Nesterov's Lookahead for Accelerated Deep Learning Optimization
When and Why is Optimistic Multiplicative Weights Slow? The Geometry of Energy Dissipation
Online Learning in Stabilized Linear Dynamical Games with Adversarial Disturbances
AndroidReality: How Far Are Mobile Agents from the Real World?
ABC: Any-Subset Autoregression via Non-Markovian Diffusion Bridges in Continuous Time and Space
Revisiting Diffusion Model Predictions Through Dimensionality
Deployment-Memory LLM Test-Time Training Should Require Behavioral Evidence Beyond Perplexity
Primal Generation, Dual Judgment: Self-Training from Test-Time Scaling
The Geometry of Generative Latents: Navigability and Invertibility
Beyond Unit-Circle Eigenvalues: Invariant Bases for Stable State Space Dynamics
Fairness Failure Modes of Multimodal LLMs
Found in Conversation: LLMs Teach Themselves to Close the Multi-Turn Gap
FaceProbe: Recovering HDR Environment Map via Masked Diffusion and Physical Preference
AdpSplit: Error-Driven Adaptive Splitting for Faster Geometry Discovery in 3D Gaussian Splatting
VLA-REPLICA: A Low-Cost, Reproducible Benchmark for Real-World Evaluation of Vision-Language-Action Models
Semantic Routing: Exploring Multi-Layer LLM Feature Weighting for Diffusion Transformers
RxGS: Receiver-Generalizable 3D Gaussian Splatting for Radio-Frequency Data Synthesis
Feature learning in high-dimensions under structured covariance: Scaling laws in quadratic networks
DOME: Drift-Adaptive On-Policy Motion Erasure in Video Diffusion Transformers
Budgeted Quotient-Residual Guidance for Frozen Pocket-Conditioned Molecular Diffusion
SLIC: Reinforcement Fine-Tuning Small LMs for Multi-Turn Analog Circuit Optimization
InstructVVT: Instruction-Driven Video Virtual Try-On without Auxiliary Spatial Priors
Automated Hypothesis Discovery for Characterizing Annotation Disagreement
RAVEN-Bench: A Paired EO-IR Video QA Benchmark for Aerial Multimodal Understanding
KVBuffer: IO-aware Serving for Linear Attention
Decision Focused Scenario Learning for Contextual Stochastic Programming
Deep-Koopman-KANDy: Dictionary Discovery for Deep-Koopman Operators with Kolmogorov-Arnold Networks for Dynamics
Dense Flow from Adaptive Correspondence
Spectral Stratification of Semantic Abstraction in Vision-Language Models
Developmental Visual Experience Scaffolds Grounded Concept Acquisition in Vision-Language Models
FedRSPO+: A Heterogeneity-aware Algorithm for Decision-focused Federated Learning
Two is better than one: designing heterogeneous scales in binary rating systems
Calibrating Agentic LLMs for Clinical Prediction
Know Your Task, Learn It Right: Task-Aware Optimistic Value Learning for Multi-Task Multi-Agent Reinforcement Learning
The Complexity Kink: LLM Rubric Instruments for Causal Inference on Code Generation Reliability
Witness Overlap: Directional Provenance Inside Open-Weight Model Families
DeEscalWild: A Real-World Benchmark for Automated De-Escalation Training with SLMs
The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment
Transformers Converge to Invariant Algorithmic Cores
Layerwise Progressive Freezing: A Training Scaffold for Depth-Scalable Binary Networks
Do Graph Neural Networks Learn Generalizable Algorithms for Clustering Graphs?
Optimal sequential tests yield log-optimal e-processes
Relational Feature Distillation for Lightweight 3D Point Cloud Segmentation
Learning Digital Twins under Drift: Optimal Tracking Rates for Non-Stationary Dynamical Systems
Evaluating an Evaluation: Membership Inference Attacks as Machine Unlearning Diagnostics
LongMINT: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems
Your Hypergradient is Skewed: Antithetic Neumann Estimation for Bilevel Optimization
Explanations over Graphs: An Agent Architecture for IT Enterprise Diagnostic Tasks
RAGBoost: Robust Tabular Learning via Retrieval-Augmented and Ancillary-Guided Gradient Boosting
Beyond Incremental Beam Search for Compositional Explanations of Neurons
From Collapse to Improvement: Statistical Perspectives on the Evolutionary Dynamics of Iterative Training on Contaminated Sources
Split-RL: Local Conflict Resolution in Reinforcement Learning
Understanding Circulant Permutation to Extend the CMinHash Estimator
Reward-Conditioned Reinforcement Learning
Interpreting Latent Protein Language Model Features with Geometric Annotations
Coherent Routing in Decision Trees: Phase-Interference Learning for Interpretable Tabular Prediction
Generalizing Test-time Compute-optimal Scaling as an Optimizable Graph
On Worst-Case Guarantees for Graph-Based Nearest-Neighbor Search
Shattered Compositionality: Counterintuitive Learning Dynamics of Transformers for Arithmetic
Transfer Entropy as a Measure of Information Flow in VLMs and LLMs
Localizing Concepts in Visual Autoregressive Models
Fast Accurate Quantum Monte Carlo without Metropolis Adjustment
CM2: Reinforcement Learning with Checklist Rewards for Multi-Turn and Multi-Step Agentic Tool Use
Hyper Input Convex Neural Networks for Shape Constrained Learning and Optimal Transport
DUIL: Deep Unsupervised Inverse Learning for in situ Macromolecular Morphology Identification
The Unembedding Bottleneck: A Mechanistic Analysis of Single Digit Counting in LLMs
Hallucination in World Models is Predictable and Preventable
CCDiff: Inverse Canonical Correlation Analysis for Discovering Visual Differences in Natural Language
Speakeasy: Auditing Cheap Signals in Peer Prediction
Generalized Robust Adaptive-Bandwidth Multi-View Manifold Learning in High Dimensions with Noise
What Should Embeddings Embed? Autoregressive Models Represent Latent Generating Distributions
Rational Tuning of LLM Cascades via Probabilistic Modeling
Paradoxical noise preference in RNNs
Continual Robot Learning via Language-Guided Skill Acquisition
A Multi-Fidelity Control Variate Approach for Policy Gradient Estimation
StomataBench: Measuring Taxonomic Generalization in Stomatal Detection
Auditing Cross-Lingual Fairness in Language Model Watermarking
Be CARE-ful with Text-to-SQL Benchmarks
Attention Sinks and Outliers in Attention Residuals
AgentCollabBench: Diagnosing When Good Agents Make Bad Collaborators
Precise Debugging Benchmark: Is Your Model Debugging or Regenerating?
StarCraft Motion: A Dataset for Agent Simulation in Adversarial and Partially Observable Scenarios
Feature Learning Dynamics in Infinite-Depth Neural Networks
Auditing Evidence Framing at NeurIPS: A Decade-Scale Study of Accepted Papers
PLATO: Pointer Learner for Agent and Task Openness
Beyond Truthfulness: Evaluating Honesty in Large Language Models
Stress-Testing Neural Network Verifiers with Provably Robust Instances
Preferential dynamic modeling with forward-backward smoothing
SchemeArena: Factorized Stress Testing of Scheming in LLM Agents
OBLIQ-Bench: Exposing Overlooked Bottlenecks in Modern Retrievers with Latent and Implicit Queries
LaCache: Robust Semantic Caching for LLM Serving
VerifyThisBench: Joint Evaluation of Code, Specifications, and Proof
How New Strategies Emerge in RL Post-Training: A Controlled Study
Argus: A Cross-Regime Benchmark for the Transferability of Uncertainty Quantification in Computer-Use Agents
MT-JailBench: A Modular Benchmark for Understanding Multi-Turn Jailbreak Attacks
MITO: A Millimeter-Wave Dataset and Simulator for Non-Line-of-Sight Perception
nnTrace: Detecting and Localizing Silent Bugs in Distributed Training
Measuring and Mitigating the Distributional Gap Between Real and Simulated User Behaviors
Mini Amusement Parks (MAPs): A Testbed for Modelling Business Decisions
Benchmarks as Measurement Instruments: Quantifying Signal and Noise for More Efficient AI Evaluations Under Distribution Shift
CSI-TextBench: A Dataset and Benchmark for Language-Grounded Ambient Sensing Perception
MemLeak: Diagnosing Information Leaks in Multimodal Agent Memory
Benchmarking Fine-Grained Spatio-Temporal Awareness in Embodied Brain Models
Benchmarking Multimodal Mathematical Reasoning with Explicit Visual Dependency
DDBench: A Benchmark for Agentic Debugging on Distributed Systems
CLAMP: A Sim-to-Real Benchmark for Closed-Loop Kinematic Pose Estimation and Assembly Reasoning
Whole-Body Compliant Control via Learned Force-Regulation Modules
Conservation Laws for Diffusion Models
Cross-Dialect Generalization Without Retraining: Benchmarks and Evaluation of Schema-Derived Constrained Decoding for MLIR
Subliminal Transfer of Unsafe Behaviors in AI Agent Distillation
PhyMotion: Structured 3D Motion Reward for Physics-Grounded Human Video Generation
Geometry-Aware Score-Repellent Monte Carlo
Asymmetric Factorization for Low-Rank PSD Learning: When Is the Relaxation Exact ?
GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators
On the Design Space of Discrete Diffusion Online Adaptation for Molecular Optimization
Meta$^n$: Recursive Self-Improvement through Emergent Depth
Variational Wasserstein Model on Riemannian Manifolds for Image Segmentation
MotorSense: A Video-EMG Dataset of Motoric Representations for Action Understanding
PhysicianBench: Evaluating LLM Agents in Real-World EHR Environments
Ordinary Least Squares as an Attention Mechanism
Differentially Private Sparse Reward Estimation with Preference Feedback
ScreenSearch: Uncertainty-Aware OS Exploration
Steering Vectors as a Training Signal in LLM Post-Training
Statistical Matching via Schr\"odinger Bridge beyond Conditional Independence
Theoretical Limits of Language Model Alignment
XMNoise2Clean: Cross-Modal Denoising Under Sparse Data
Learning to Correct Geometry in Generated Videos
One-Shot Generative Flows: Existence and Obstructions
Understanding Double Descent through Universal Compression
A Theory on Flow Matching with Neural Networks
OdysSim: Building Foundation Models for Human Behavior Simulation
Sparse Multimodal Switching State-Space Models for Regime-Dependent Neural Connectivity under Partial Observations
A Bitter Lesson for Data Filtering
LIPAR: Latent Inter-Frame Pruning with Attention Recovery
Reliable Abstention under Adversarial Injections: Lower Bounds and New Upper Bounds
Stochastic Dynamic Barrier Perturbed Gradient Methods for Nonconvex Simple Bilevel Optimization
Bayesian Additive Distribution Regression
The Query Complexity of Local Search in Rounds on General Graphs
KerONet: A Single Softmax Readout Suffices for Physics-Informed Operator Learning
SLVR: Structured Latent Visual Reasoning via Human-like Reasoning Flows
GeoTransolver: Learning Physics on Irregular Domains using Multi-scale Geometry Aware Physics Attention Transformer
Wasserstein residuals: Learning Gradient Flows from Population Dynamics
Beyond Copy-Paste: How Well Do Subject-Driven Video Models Understand Their Subjects?
The Prestige: Benchmarking Cognitive Visual Reasoning using Magic Tricks
Learnable Chernoff Baselines for Provable Inference-Time Alignment
Beyond What Seems Necessary: Hidden Gains from Scaling Training-Time Reasoning Length under Outcome Supervision
LESSViT: Robust Hyperspectral Representation Learning under Spectral Configuration Shift
DiffeoMorph: Learning to Morph 3D Shapes Using Differentiable Agent-Based Simulations
Toward in Silico Strain Evaluation: A Multimodal Surrogate for Fermentation Dynamics with Metabolic Graph Pretraining
ECHO: Terminal Agents Learn World Models for Free
Projection Learning: A Principled Way to Overcome Memorization in Distribution Learning
Learning Distributions from Multiple Data Providers
Transcoda: End-to-End Zero-Shot Optical Music Recognition via Data-Centric Synthetic Training
Posterior Alternative Calibration in Ambiguous Inverse Problems
Reviving Stale Updates: Data-Free Knowledge Distillation for Asynchronous Federated Learning
A Steerable Deep Network for Model-Free Diffusion MRI Registration
Uncertainty Aware SURE Transfer Learning for Classification Problems
Absolute State-wise Constrained Policy Optimization: High-Probability State-wise Constraints Satisfaction
EgoMo3R: Joint Egocentric Motion and Scene Reconstruction
ReSCUE: Re-translation with Sentence Commitment for Unsegmented Long-Form Simultaneous Sign Language Translation
A Locality-Aware Surrogate for Natural-Gradient Descent in Quantum Optimization
B-CALM: Bias-Limited Bayesian Borrowing for RCT-Anchored Treatment Effects under Covariate Mismatch
Specialist Mediators: Causal Localization of Dense Fine-Tuning
Manifold Sampling via Entropy Maximization
Beyond Marginal Coverage: Efficient Localized Conformal Prediction via Residual Rank Calibration
TraXion: Rethinking Pre-training Frameworks for Mobility and Beyond
A Transformer-Derived Iterative Preconditioner
Mitigating Label Bias with Interpretable Rubric Embeddings
AVI-HT: Adaptive Vision-IMU Fusion for 3D Hand Tracking
Differentiable Systematic Resampling for Variational Sequential Monte Carlo
Training Transformers for KV-Cache Compressibility
SeeSE3: The Emergence of 3D Space in Vision Features
Breaking the Grid: Distance-Guided Reinforcement Learning in Large Discrete Action Spaces
PIVOT: A Unified Agentic Framework for Streaming Long-Video Understanding
Why Pass@k Optimization Can Degrade Pass@1: Prompt Interference in LLM Post-Training
Online Learning on Hidden-Convex Losses via Algorithmic Equivalence: Optimal Regret, Geometric Barrier, and Bandit Feedback
Exploring Advertising Manipulation in Diffusion Image Generation
RoMo Hands: A Large Scale Richly Organized Text to Hand Motion Dataset
Reasoning Gestures: LLM-Inferred Communicative Functions for Co-Speech Gesture Generation
From Weeks to Hours: Fast and Principled SFT Curation for LLM
Magnetic Resonance Unpaired Image Translation with Pseudometric Schrödinger Bridges
EpiPivot: Learning to Control the Simplex Method under Epistemic Uncertainty
Evolving Agent Teams
Split and Bridge: Multimodal Generation via Diffusion Bridging
SnapAudit: Active Auditing of Differentially Private In-Context Learning via Snapshot-Based Simulation
Saliency-Aware Multi-Route Thinking: Grounding and Reasoning on Vision-Language Agents
Rank Is Not Capacity: Spectral Occupancy for Latent Graph Models
BigCell: Generating Gigapixel Whole-Slide Images
Do Latent-CoT Models Think Step-by-Step? A Mechanistic Study on Sequential Reasoning Tasks
PAC Learning with Bandit Feedback: Sharp Sample Complexity in the Realizable Setting
Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning
The Stability of Online Algorithms in Performative Prediction
Adaptive Delayed-Update Cyclic Algorithm for Variational Inequalities
Transferable, Time-Parallel Graph Dynamics via Space-Time Factorization
Improving Context-Shift Robustness of Convolutional Networks via Context-Regularized Cross-Entropy
Flash-KMeans: Fast and Memory-Efficient Exact K-Means
Agentic AI-Empowered Dynamic Survey Framework
A Control-Theoretic Approximation to Predictive Coding Dynamics
Rate-Constrained Edge Metadata for Sender–Receiver Generative Video Super-Resolution
Optimizing Computational-Statistical Runtime for Wasserstein Distance Estimation
AmbientFM: A Foundation Model for Ambient Sensing
Reject, Resample, Repeat: Understanding Parallel Reasoning in Language Model Inference
Learning to Cut: Reinforcement Learning for Benders Decomposition
Algorithmic Impact Reveals the Hidden Structure of Alignment
Calibeating Prediction-Powered Inference
Inverse Reinforcement Learning with Just Classification and a Few Regressions
Learning What Evaluators Value: A Reliable Approach to Modeling Evaluator Preferences
Dynamic Expert Sharing: Decoupling Memory from Parallelism in Mixture-of-Experts Diffusion LLMs
HybridCache: Enhancing Prefix Caching for Linear–Softmax Language Models
TrajWiki: Source-Grounded Memory Trajectories for Long-Horizon Dialogue Agents
TRACER: Token ReAssignment for Concept ERasure in Generative Recommendation
SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
Exploring MLLM-Diffusion Information Transfer with MetaCanvas
Controllable and Content Based Recommendations
A Constrained Bi-level Optimization Framework for Constrained Preference-Based Reinforcement Learning
Structure-agnostic Causal Representation Learning
Who, Where, and What? Forensic Localization in LLM-Based Multi-Agent Systems
Lattice Deduction Transformers
Neural Harmonic Measure Operator
Actor-Accelerated Policy Dual Averaging for Reinforcement Learning in Continuous Action Spaces
Beyond the Full Slate: Evaluating MNL Algorithms on All Slates
When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial Reasoning
Act, Validate, Adapt: Closing the Causal Discovery-Control Loop
Learning-Augmented Online Scheduling with Parsimonious Preemption
Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction
Scalable Variational Bayesian Fine-Tuning of LLMs via Orthogonalized Low-Rank Adapters
Riemannian Lyapunov Framework: Optimization as Closed-Loop Control on Riemannian Manifolds
Corrective Diffusion Language Models
Smoothed Elicitation Complexity for Approximate $\Gamma$-calibration of Discrete Classification Tasks
Not all uncertainty is alike: volatility, stochasticity, and exploration
sMMC-22M: A Context-Aware Dataset and Benchmark for Single-Cell Spatial Transcriptomics
TargetSage: Identifying Therapeutic Target Genes with Interpretable and Robust LLM Reasoning
Beyond Pairs: Your Language Model is Secretly Optimizing a Preference Graph
Estimating the expected output of wide random MLPs more efficiently than sampling
RAVEL: Rare Concept Generation and Editing via Graph-driven Relational Guidance
Training with (Swap) Regret Loss in a Single-Layer Self-Attention Model: A Case Study on the Probability Simplex
Loyalty Capture: Reporting Relationships and Structural Sycophancy in Frontier AI Models
CASPIAN: Online Detection and Attribution of Cascade Attacks in LLM Multi-Agent Systems via Cross-Channel Causal Monitoring
Transolver-GMsFEM: A Hybrid Framework for High-Contrast Multiscale PDEs on Irregular Grids
Sparse Reward Subsystem in Large Language Models
DoFP-Aligned Lookup Tables for Real-Time Polarization Demosaicking
PLACE: Patch-Level Agnostic Concept Extraction
Two Speeds of Learning: A Representation-Readout Decomposition of Grokking and Double Descent
Decoupled Descent: Exact Test Error Tracking Via Approximate Message Passing
Complementing DINO Features with Image Structure for Part Discovery
Video Models Can Reason with Verifiable Rewards
Youdunit: Single-Call Counterfactual Necessity in Multi-Agent LLM Systems
Anchoring LLM-based Chest X-ray Report Generation via Diffusion Language Planning
ColdDDI: Evaluating Knowledge Utilization in Cold-Start Drug-Drug Interaction Prediction
HierFlow: Hierarchical Coupled Dual-Space Search for Automatic Agentic Workflow Generation
Budgeting Discretion: Theory and Evidence on Street-Level Decision-Making
Beyond Thinking: Imagining in 360$^\circ$ for Humanoid Visual Search
Speed Predictions for Online Energy-Efficient Scheduling
Not Suppressing or Purifying: Backdoor Containment via Expert Quarantine and Shutdown in LLMs
Axiomatic World Modeling for Physics Reasoning
Backdoor Purification for LoRA-Tuned LLMs via Null-Space Projection
MSConsensus: A Hundred-Million-Scale, Batch-Effect–Suppressed Dataset and Benchmark for Proteomics Machine Learning
Flow Mismatching: Unsupervised Anomaly Detection via Velocity Discrepancies in Flow Matching Models
Continuous Diffusion Scales Competitively with Discrete Diffusion for Language
The Cost of Absolute Position: A Spread-Expressivity Tradeoff for Additive Positional Encodings
Structured Human-Like Agentic Flow for RTL Design
The Score Kalman Filter
Targeted Review for AI-Assisted Biodiversity Surveys: Active Continuous-Score Occupancy Modeling
Align and Distill: Unifying and Improving Domain Adaptive Object Detection
Prediction-only distillation with optimal mixing in ridge-regularized linear and logistic regression
Guarding the Life Code: Preserving Membership Privacy in Genomic Foundation Models
Optimal Rates for Pure $\varepsilon$-Differentially Private Stochastic Convex Optimization with Heavy Tails
Pan-FM: A Pan-Organ Foundation Model with Saliency-Guided Masking for Missing Robustness
Approximation Algorithms for GPU Pricing under Finite Capacity
Embedding Security Properties into AI-Enabled Cyber-Physical Systems
Margin Dynamics for Large Language Model Alignment
TransmissiveGS: Residual-Guided Disentangled Gaussian Splatting for Transmissive Scene Reconstruction and Rendering
$\gamma$-weakly $\theta$-up-concavity: A Unified Framework for Non-Convex Optimization Beyond DR-Submodular and OSS Functions
Online Learning with Certified Unlearning over Graphs
Coarse-to-Fine 3D MRI Reconstruction via Resolution-Agnostic Neural Operators
UniVL: Unified Vision-Language Embedding for Spatially Grounded Contextual Image Generation
Rethinking Contrastive Targets in Radiology Language-Image Pretraining
Gumbo: Gumbel Optimized High-Temperature Speculative Sampling
Learning Fractional-Order Dynamics from a Single Trajectory
Guaranteed Noisy CP Tensor Recovery via Riemannian Optimization on the Segre Manifold
Post-hoc Selective Classification for Reliable Synthetic Image Detection
All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
Self-Supervised Doppler-Guided RF Odometry
Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention
DiPMInd: Distance profile based mutual independence testing for random objects
Learning in Context, Guided by Choice: A Reward-Free Paradigm for Reinforcement Learning with Transformers
Routing as a Singular Reparameterization: A Closed-Form Pushforward Prior and Exact Bayesian Complexity in a Minimal Proxy
Less Structure is More: Minimal Representations for Supervised Learning
Partition-Aware Unlearning for Removing Spurious Correlations in Large Vision-Language Models
K9-Bench: Evaluating Multimodal LLMs on Canine-Centric Videos
Two-Sided Learning in Matching Markets with Interviews
Self Driving Datasets: From 20 Million Papers to Nuanced Biomedical Knowledge at Scale
Fisher-R1: Training LLM Agents for Reliable Hypothesis Testing
CONSTRAINER: Promptable Graph-Structured Optimization via Constraint Conditioning
Fair Division of Work in Collaborative Mean Estimation via Bargaining
Global Convergence of Four-Layer Matrix Factorization under Random Initialization
Positive-Unlabeled Preference Optimization For Chest X-ray Report Generation
Towards Reconstructing Geographically Diverse Architecture with 3D Foundation Models
Multi-Turn RL Makes Small Language Model Competitive for Optimization Modeling
Reward Bias Substitution: Single-Axis Bias Mitigations Redirect Optimization Pressure
Synthetic Web: Benchmarking Language Agents under Adversarial Search Ranking
Scaling Arbitrary Architectures and Optimizers with Automatic Parameterization
Attention as In-Context Empirical Bayes: A Two-Stage View via Particle Dynamics
LoRASpace: A Pool-Wide Shared Substrate for Static and Dynamic Multi-LoRA Composition
Not All Spines Are Created Equal: How CT Segmenters Fail on Lumbosacral Transitional Vertebrae
Gradient Descent on Two ReLU Neurons: Global Landscape and Bifurcation Dynamics
Synthetic Tasks for Training AutoResearch
Computational Dynamic Mechanism Design
Learning to Persuade a Biased Receiver
RnR: a meta-solver for causal discovery in undersampled time series data
DisSparse: Pipelined Top-$p$ Sparse Attention for Long-Context LLM Serving
Generalized Smooth Stochastic Variational Inequalities: Almost Sure Convergence and Convergence Rates
Benchmark Recovery Does Not Certify a Frozen Tool-Trigger Contract After Quantization
Instance-Adaptive Online Multicalibration
Taking the Road Less Scheduled with Adaptive Polyak Steps
Safe in Its Own Words: Self-Guided Safety Alignment for Multimodal Reasoning Models
Bias, Measurement Error, and Double-Dipping: When Can GNN Convolutions Help Brain Connectome Prediction?
pCoMole: Pareto-Constrained Molecule Editing with Discrete Flows
Robust Graph Diffusion Model
Physical AI Smart Spaces: A Large-Scale Benchmark for Multi-Camera 3D Perception in Smart Spaces
Learning Preference Representations for Preference-Conditioned Image Generation
Recursive Language Models
Characterizing Underrepresentation in Generalizing Causal Survival Estimates
When Latents Forget Pixels: Restoring Fidelity in Diffusion Transformer Super-Resolution
Stein Kernelized Molecular Dynamics for Active Learning of Interatomic Potentials
Efficient LLM Adaptation with Forward-Only Passes
Bridging Simulation and Reality: Geometry and Decision Alignment for Autonomous Driving
Graph Sparse Sampling: Breaking the Curse of the Horizon in Continuous MDP Planning
Risk-Averse Online POMDP Planning via CVaR of the Immediate Cost with Performance Guarantees
Reaching a Consensus in Predictive Loops
Verifying Neural Networks with Reinforcement Learning
ContractBench: Can LLM Agents Preserve Observation Contracts?
Learning the Signature of Memorization in Autoregressive Language Models
FASTER: Value-Guided Sampling for Fast RL
Unsupervised Physics Informed Decomposition of Incomplete Time-Resolved Spectroscopy
Class Adaptive Conformal Training
Function graph transformers universally approximate operators between function spaces
Inference for Many Quantiles under Local Differential Privacy
Cost Efficient Fairness Audit Under Partial Feedback
Penalty-Based First-Order Methods for Bilevel Optimization with Minimax and Constrained Lower-Level Problems
Cognitive bias benchmarks should incorporate insights from ecological rationality
A New Framework for Quantum Reinforcement Learning
Don't Deploy Fine-Tuned Genomic Foundation Models Without Privacy Evaluation: Reconstruction Vulnerability Is Unpredictable Without Empirical Measurement
Stop Using Plausibility as the Criterion for Explainable AI
PithTrain: A Compact and Agent-Native MoE Training System
The parameters in weight-sparse transformers are interpretable
What if Agents Could Imagine? Reinforcing Open-Vocabulary HOI Comprehension through Generation
LiFT: Lifted Inter-slice Feature Trajectories for 3D Image Generation from 2D Generators
Stop Quantum Machine Learning; do AI-for-Quantum instead
Computer Science Conferences Should Require Nonrepudiable Experimental Results
No One Knows the State-of-the-Art in Geospatial Foundation Models
A second order regret bound for NormalHedge
Stop Mechanizing Reform Heuristics as Scientific Quality Filters in AI Review
Community-Centered AI is Feasible and Beneficial for Impacted Communities
Why Transformer-Based Language Models Need Explicit Mechanisms of Cognitive Control
AI Agents Push Humans Out of the Loop
Autonomous Driving Research Requires a Community-Driven Data Paradigm
Position: We Need Greater Transparency to Maintain Research Pipeline Reliability Despite GenAI
When Helpfulness Becomes Sycophancy: Sycophancy is a Boundary Failure Between Social Alignment and Epistemic Integrity in Large Language Models
Position: LLM Privacy Requires a Lifecycle-Wide Approach
Stop Calling It Reinforcement Learning in Language Models Without Clear Improvement Claims: Decision-Process Cards as a Reporting Standard
Deployment-Time Online Imitation Learning from Corrective Demonstrations
Epistemic Infrastructures of Science in AI Era Should Rebalance Costs of Generation and Verification
Factor Augmented High-Dimensional SGD
Covariate-Adjusted Deep Causal Learning for Heterogeneous Panel Data Models
Tune-Up Open-Weight CLIP: Optimization Framework for Self-Supervised Fine-tuning of CLIP
Co-Evolving Interpolants and Flows via Path-Flow Alignment
Introspection Tools Help LLMs Understand and Control Themselves
Variational Trajectory Optimization of Anisotropic Diffusion Schedules
Watermarking Without Standards Is Not AI Governance
Allocate Marginal Reviews to Borderline Papers Using LLM Comparative Ranking
Rare-Tail Statistics For Learning Biased Gaussian Halfspaces with Label Noise
G-Zero: Self-Play for Open-Ended Generation from Zero Data
Physics Unrolled Neural Operator for Wireless Field Modeling
MIRROR: Manifold Ideal Reference ReconstructOR for AI-Generated Image Detection
Rethinking the Readout: Unlocking Video Backbones for AI-Generated Video Detection
Embodied AI Cannot Scale Without Open-Source Distributed Geometric Optimization Backends for Life-Scale Egocentric Data
Composable Causality: A Toolkit for Systematic Time-Series Causal Discovery and Treatment-Effect Benchmarking
Understanding the Effects of Neuron Dominance in Deep Reinforcement Learning
Global Optimality for Constrained Exploration via Penalty Regularization
Linear Regression Under Misalignment: Algorithms and Theoretical Results
Fast Diverse Nearest Neighbor Search
Space-Optimal Streaming Algorithms via Efficient Encodings
Synthesis Through Simulation: Generating Coherent Enterprise Data via Scalable Agent-System Interaction
Cognitive constraints and thalamocortical architecture explain systematic biases and neural signatures in human hierarchical decision-making
Breakeven complexity: A new perspective on neural partial differential equation solvers
COSAC: Counterfactual Credit Assignment in Sequential Cooperative Teams
Contrast encodes inductive bias: separating slow noise from dynamics in predictive representation learning
Accelerated last-iterate convergence of Extragradient via power-law stepsizes
Finding Interpretable Prompt-Specific Circuits in Language Models
On Computing Diverse Solutions in the Earth Movers Distance
The Capability Frontier of GRPO
Verify0: Can AI Agents Build Formally Verified Software Repositories?
SCOUT: Planning under Occlusion via Object-Centric World Model Rollouts
Recreating Video Arenas via Automated Preference Scoring
Rethinking Geometric Depth in Monocular 3D Object Detection: A Projection-Consistent Reformulation
RefineAny3D: Depth Refinement as Semantic Alignment for Monocular 3D Detection
Controllable Road Marking Generation
Corrupted Plans, Clean Traces: What Planning-Execution Decoupling Reveals About CoT Monitoring
Almost Sure Convergence of Linear Temporal Difference Learning with Arbitrary Features
On the Divergence of Differential Temporal Difference Learning without Local Clocks
Latent Q-Barrier Shielding for Safe In-Context Reinforcement Learning
TherapyGym: Evaluating and Aligning Clinical Fidelity and Safety in Therapy Chatbots
Your Benchmark Is an Empirical Measure Over Difficulty
Scalable Derivative Gaussian Processes via Exact Gradient Reduction
AVSD: Adaptive-View Self-Distillation by Balancing Consensus and Teacher-Specific Privileged Signals
Shared Truth: Emergent Truth Properties in Large Language Models via Heterogeneous Injection-based Transfer
Rethinking On-Policy Self-Distillation for Thinking Models
How does RL Post-training Induce Skill Composition? A Case Study on Countdown
AI Safety Evaluations Need More Human-AI Experiments
Panoptic Scene Program Diffusion Transformer
SourceBench: Can AI Answers Reference Quality Web Sources?
MoBiQuant: Mixture-of-Bits Quantization for Token-Adaptive Any-Precision LLM
Flow Annealing Posterior Sampling for Function-Space Regression and Inverse Problems
SceneBind: Binding What and Where Across Vision, Audio, and Language
Trajectory Planning without Trajectory Data: A Manifold-Guided Approach
Conditional Multi-Event Temporal Grounding in Long-Form Video
PACEvolve++: Improving Test-time Learning for Evolutionary Search Agents
Predicting and improving test-time scaling laws via reward tail-guided search
What should post-training optimize? A test-time scaling law perspective
Precise but Uncoupled: Reviewer Precision Does Not Guarantee Critique Uptake in Multi-Agent Math Reasoning
Towards Reliable LLM Evaluation: Correcting the Winner’s Curse in Adaptive Benchmarking
\texttt{FEROM}: Frontier Endogenous Reveal-Order Marginal Policy Optimization for Masked Diffusion LMs
Talk Less, Work More: Communication-Efficient Decentralized Stochastic Approximation
Towards Fair Graph Generation Without Sensitive Attribute
MOVEBENCH: A Benchmark for Global-Scale Wildlife Movement Forecasting
Invariance and Body-Order Compose Additively: Minimax Rates on $\mathrm{SO}(3)^n$
CFC26: Building Evaluations for Deployment in Sonar-Based Fish Counting
Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA
Lang-SVG: Hierarchical Image Vectorization with Language Priors
Learning Actionable Information Landscapes for Multimodal Active Sensing in Hawkmoths
Learning Visual Feature-Based World Models via Residual Latent Action
PermuQuant: Lowering Per-Group Quantization Error by Reordering Channels for Diffusion Models
Learning Latency-Aware Orchestration for Multi-Agent Systems
HPC-Bench: A Comprehensive Benchmark for High Performance Computing Codes
Decision-Focused Learning in MDPs: An Occupancy Measure Approach
Impacts of Aggregation on Model Diversity and Consumer Utility
Adapting Actively on the Fly: Relevance-Guided Online Meta-Learning with Latent Concepts for Geospatial Discovery
StepBack: Step-Level Error-Localized Resampling for Efficient Test-Time Reasoning
Contrastive Discovery: Open-Ended Scientific Discovery over Competing Explanations
Exposing the Illusion of Erasure in Knowledge Editing for LLMs
Golden Layers and Where to Find Them: Improved Knowledge Editing for Large Language Models Via Layer Gradient Analysis
Language-Based Agent Control
Language Denoising Objectives Extend the Value of Limited Data
Conditional Optimal Bridge for Riemannian Activation Steering
Bypassing PC1 Makes SAEs More Reproducible
TaxaAdapter: Scaling Fine-grained Species Image Generation To the Tree of Life
Model-Based Online Decision Making via Generative Trajectory Planning
UniPath: Adaptive Coordination of Understanding and Generation for Unified Multimodal Reasoning
Learning Provable Neural Network Observer for Uncertain Dynamical Systems
CLUE: Correlated Latent Uncertainty for Single-Pass Deep Uncertainty Estimation
Robust Inference-Time Steering of Protein Diffusion Models via Embedding Optimization
Ergodic Trajectory Design by Learned Pushforward Maps: Provable Coverage via Conditional Flow Matching
When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited
Finite-Sample Convergence in Networked Average Reward MARL: Decentralization Pitfalls and Entropy Remedies
Training Generalizable Collaborative Agents via Strategic Risk Aversion
Sharp Convergence and Sample Complexity of Policy Mirror Descent for Average-Reward MDPs
More Is Not More: What Matters for Diversity in LLM Opinions？
When Everyone Can Submit: Designing Contests with Transparent Pre-Selection
JobBench: Aligning Agent Work With Human Will
XBRIDGE: Entity-Grounded Latent Bridge for Heterogeneous LLM Communication
Rethinking Semantic ID Construction for Generative Recommendation: SimHash with Parallel Decoding and Semantic Alignment
Harness the Memory: A Holistic Evaluation of Memory Substrates in Memory Agents
When Are Teacher Tokens Reliable? Position-Weighted On-Policy Self-Distillation for Reasoning
Agent MechSuits : Mechanistic Subspace Safety Steering for Multi-Turn CLI Agents
SCDM: Scalable Causal Discovery in Nonlinear Temporal Systems with Meta-Learning
CytoWave: Perturbation-Centric Pretraining for Single-Cell Response Prediction
Proposing Better Rollouts for On-Policy Distillation
DopplerWild: A Doppler Dataset and Benchmark for Human Kinematic Understanding in the Wild
Frontier Task Synthesis Via Solution-Centric Evolution
Context Binding and Reusable Leakage in Threshold Decryption
Leakage Thresholds for Sandwich Equilibria Under Partial Information
SMILE: Bridging Continuous Optimization and Discrete Symbolic Recovery
Private Adaptive Covariance Estimation via Gaussian Graphical Models
Projected Neural Additive Models as Universal Approximators
FLAME: Adaptive Mixture-of-Experts for Continual Multimodal Multi-Task Learning
On the Invariance and Generality of Neural Scaling Laws
SAIR: Cost-Efficient Multi-Stage ML Pipeline Autoscaling via In-Context Reinforcement Learning
Learning When Visual Context Matters for Mouse Behavior Analysis
Boosting Text-to-Image Diffusion Models via Core Token Attention-Based Seed Selection
Action Chunking Proximal Policy Optimization with Feedback Correction
CoMMa: Contribution-Aware Medical Multi-Agents for Decentralized Oncology Decision Support
MarkTune: Improving the Quality-Detectability Trade-off in Model-Embedded LLM Watermarking
FedIndex: Federated Domain Adaptation with Continuous Domain Indices
Swift Sampling: Selecting Temporal Surprises via Taylor Series
SAGE: Mitigating Long-Horizon Reasoning Biases via Topological Guidance
When Do Multi-Agent Systems Help? An Information Bottleneck Perspective
VeruSAGE-Bench: A Benchmark Suite for Rust System Verification
Do Semantic Distance Tests Actually Predict Creativity in Large Language Models?
CurveRL: Principled Distribution-Aware Context Reweighting for LLM Reasoning
Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias
From Talking Words to Sharing Thoughts: Scalable Multi-LLM Aggregation via Structured Message Passing
Structured Sparse Memory for Recurrent Reasoning
Self-Compacting Language Model Agents
Why Cancer cfDNA Models Fail on Chronic Disease: A Geometric Information-Theoretic Bound and Its Architectural Implications
CRANE: Constrained Reasoning Injection for Code Agents via Nullspace Editing
AVO: Agentic Variation Operators for Autonomous Evolutionary Search
Beyond Scalar Distances: Semantic Attribute Gradients from Frozen MLLMs for Visual Embeddings
Beyond Local Neighborhoods: Fractional Diffusion with Levy Flights on Simplicial Complexes for Link Prediction
CSO-LLM: Class Subspace Orthogonalization for Post-Training Backdoor Detection and Trigger Inversion in LLMs
MixUni: Joint Multi-Property Prediction for Chemical Mixtures with Physics-Informed Heads
Cross-Attentive Bayesian Low-Rank Adaptation for Multimodal Uncertainty Estimation
Signature Approach for Contextual Bandits with Nonlinear and Path-dependent Rewards
OmniShotCut: Holistic Relational Shot Boundary Detection with Shot-Query Transformer
TDBench: Benchmarking Vision Language Models on Top-Down Image Understanding
Learnable Low-Rank Polynomial Sketch for Effective Linear Attention
Causal Multi-Task Demand Learning
Theory on Attention Dynamics for Out-of-Distribution In-Context Learning
DARPAN: Controllability-Aware Residual Filtering for Pretrained Physical Control
Adaptive Inference for Functionals of M-Estimands
Geometry over Density: Few-Shot Cross-Domain OOD Detection
Handwriting decoding as a challenging motor task for EEG Foundation Models
Class-Mixed Diffusion Augmentation for Shortcut-Breaking in Continual Learning
CAFE: Causally-Guided Automated Feature Engineering with Multi-Agent Reinforcement Learning
Mixture of Layers: Dynamic Layer Routing for Visual Reasoning
RuleSmith: Multi-Agent LLMs for Automated Game Balancing
Gradient descent inference in empirical risk minimization
Flow Map Denoisers: Traversing the Distortion-Perception Plane for Inverse Problems
Synthetic Worlds for Temporal Evaluation and Knowledge Updating in LLMs
Early Prediction of Future Behavioral Strategy from Process Traces
Exploiting Textual Semantics for Robust Cross-View Object Correspondence
Towards Visual Query Segmentation in the Wild
TEMPO: Temporal Enforcement via Mode-Separated Policy Optimization for Trustworthy LLM Backtesting
Grounded-Exo2Ego: Structured Semantic Grounding for Robust Exocentric-to-Egocentric Video Generation
When, Where, What: Structural Guarantees for Travel Time Prediction on Temporal Graphs
On the Error Correcting Effects of Stochasticity in Discrete Diffusion
PuppetGait: Generalizing Gait Recognition via 3D Body-Aligned LVM Features
When Reasoning Meets Its Laws
CORP: Closed-Form One-shot Representation-Preserving Structured Pruning for Transformers
Benchmarking Risk Attitudes of LLMs
\$OneMillion-Bench: How Far are Language Agents from Human Experts?
Runtime Verification of Multiple Natural Language Criteria for Agent Governance
GeoFidelity-Bench: Evaluating Block-Conditioned Geographic Fidelity of Street-View Generation
StyleStream 2.0: Fast and Controllable Streaming Voice Style Conversion
Decompose the Distillation: Interpretable Single-Pass Guidance for Diffusion Models
Swarm Shepherd: Securing Multi-Agent Ecosystems Against Persistent Latent Compromise
Efficient Algorithms For Fully Dynamic Bipartite Matching In Metric Spaces
Diff-Instruct with Diffused Reward: Towards Principled One-step Generator RL
Quantum Safe Stochastic Linear Bandits
Embedding Foundation Model Predictions in Discrete-Choice Models with Structural Guarantees
Capturing In-Context Learning Dynamics with Task Operators
Rethinking Visual Attribution for Chest X-ray Reasoning in Large Vision Language Models
StereoPep: Do Molecular Models Understand Stereochemistry? A Benchmark on Synthetic Diastereomeric Peptides
CASL: Concept-Aligned Sparse Latents for Interpreting Diffusion Models
STRAND: Sequence-Conditioned Transport for Single-Cell Perturbations
NeuralFieldManifold: Reconstruction of LFP manifold with Lag Embedding
Testing and Estimation of Contextual Generalized Thurstone Models
TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models
ReToken: One Token to Improve Vision–Language Models for Visual Retrieval
Qubrio: High-Performance Quantum Compilation via Multi-Agent LLM Collaboration
Learning Sparse Compositional Functions with Norm-Constrained Neural Networks
Improving Conditional Modeling via Inter-Class Likelihood-Ratio Maximization and Unifying Classifier-Free Guidance with Alignment Objectives
SAFTAC: Simulation-Augmented Fine-Tuning of Open-Source LLMs for Analog Circuit Design
Strategic Decision Support for AI Agents
Structure Over Scale: Learning Visual Reasoning from Pedagogical Video
In-Context Optimization for Retrieval-Augmented Generation: A Gradient-Descent Perspective
ProcObject-10K: Benchmarking Object-Centric Procedural Understanding in Instructional Videos
RICE-PO: Turning Retrieval Interactions into Credit Signals for Reasoning Agents
Motion-o: Trajectory-Grounded Video Reasoning
Beyond Maximum Likelihood: Variational Inequality Estimation for Generalized Linear Models
Specialists Hold, Generalists Discount: Asymmetric Equilibrium in LLM Routing Auctions
Counterfactual Rollout Replay: Forkable Environments as Free Process Rewards for Software Engineering Agents
SWE-Protégé: Learning to Selectively Collaborate With an Expert Unlocks Small Language Models as Software Engineering Agents
Sticky Jump Diffusions: A Unifying Framework for Discrete, Continuous, and Hybrid Diffusion
Accelerating Inference of Discrete Autoregressive Normalizing Flows by Selective Jacobi Decoding
Model-Adaptive Tool Necessity Reveals the Knowing-Doing Gap in LLM Tool Use
Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning
MammoGPS: A Benchmark for Visual Grounding, Perception, and Spatial Reasoning in Mammography
Diagnosing and Repairing Citation Failures in Generative Engine Optimization
Multi-site PPG: An In-the-Wild Physiological Dataset from Emerging Multi-Site Wearables
Evaluating Depth and Breadth in Test-Time Scaling for Compositional Visual Generation
In-Context Multi-Operator Learning with DeepOSets
Stability in Multi-Step Reasoning via Jacobian-based Error Accumulation Analysis
A Large-Scale Multi-Source Dataset Linking Hacker Community Discourse to the CVE Vulnerability Lifecycle
TopoGraphRAG-Bench: Evaluating Multimodal GraphRAG on Layout-Grounded Evidence Reasoning
Calibrating LLMs with Semantic-level Reward
Efficient Collaborative LLM Fine-Tuning over Heterogeneous Mobile Devices via Many Backbones to One Side-Network Tuning
From Matrix Inversion to Constraints: Provably Tighter Confidence Regions for Importance Weights in Label Shift
FairTune Market: A Fair and Trustworthy Marketplace for Fine-Tuned LLMs via Posted-Price & Proper-Scoring Mechanisms
Learning Theory of Transformers: Local-to-Global Approximation via Softmax Partition of Unity
Beyond IPS: Reliable Counterfactual Evaluation in Multi-Stage Ad Systems without Logged Propensities
I-PTC: Interactive Programmatic Tool Calling for Stateful Tool-Augmented Agents
TimeWarp: Evaluating Web Agents by Revisiting the Past
AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent
Beyond Pessimism: Offline Learning in KL-regularized Games
Instructing LLMs to Negotiate using Reinforcement Learning with Verifiable Rewards
Predicting Plasticity in Deep Continual Learning: A Theoretical Perspective
Heavy-Tailed Flow Matching via Random Clocks
Intrinsic Riemannian Cross-covariance for Manifold-valued Random Objects
OLA-Place: Cross-Modal Place Recognition without Global Descriptors
VOID: Backdoor Injection through Knowledge Vacuity in Federated Unlearning
Hierarchical Graph Alignment for Cross-Modal 3D Scene Grounding
ForecastCompass: Guiding Agentic Forecasting with Adaptive Factor Memory
DiffATS: Diffusion in Aligned Tensor Space
Provable Quantization with Randomized Hadamard Transform
Fast Approximate $\ell_p$ Chamfer Distance via Lopsided Embeddings and Structured JL
DeepArrhythmia: Segment-Contextualized ECG Arrhythmia Classification via Selective Evidence Acquisition
Policy Regret Minimization in Partially Observable Markov Games
PAAC: Privacy-Aware Agentic Device-Cloud Collaboration
Cat-DPO: Category-Adaptive Safety Alignment
UtoMe: Observation-Uncertainty-Guided Token Merging for Weather Foundation Models
PerturbReason: A Knowledge-Grounded Benchmark and Framework for Cell-State–Conditioned Mechanistic Reasoning of Perturbation Effects
SCOT: Multi-Source Cross-City Transfer with Optimal-Transport Soft-Correspondence Objectives
A Distribution Mapping Approach to Counterfactually Fair Reinforcement Learning
TACT-KV: Tri-Axis Cosine Transform for Compressing Volumetric KV Caches in Medical VLMs
Same Signal, Opposite Meaning: Direction-Informed Adaptive Learning for LLM Agents
Opening the Black Box of Classifier-Free Guidance via Information Bottleneck
DBPS: Doob-Bridge Posterior Sampler with Balanced Endpoint-Population Control for Unpaired Neurodegenerative Pathology Transport
Bridging Textual Profiles and Latent User Embeddings for Personalization
OASES: Outcome-Aligned Search-Evaluation Co-Training for Agentic Search
Memory Retrieval for Changing Preferences
Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs
MetaPI: Constructing Prompt Injection Benchmarks from Any Agent Benchmarks
Active Learning for Conditional Generative Compressed Sensing
MaRiO: Multi-agent Collaborative Reasoning via Shared Observations in MLLMs
Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion
A$^2$IQL: Adaptive Asymmetric Implicit Q Learning for Automated Warehouse Consolidation
Optimal Contextual Pricing under Agnostic Non-Lipschitz Demand
LogicDirector: Enforcing Temporal Composition in Text-to-Video Generation
MCM-DM: Towards Better Spatio-Temporal Event Representation Learning via Discrete Morse Theory
A Method-Class Divide in Sub-4-Bit Quantization:\\Iterative vs.\ Single-Pass Sensitivity to Data Composition
Transforming Image Editors into Video Editors
Mission Impossible: Diagnosing and Fixing Non-Operative Instruction Following in Image Editing
RATS! Patches Talk Through Registers: Emergent Parts in Register Attention Transformers
Towards Mitigating Deceptive Safety Alignment in Large Reasoning Models
From Detection to Understanding — A Multi-Task Dataset for Traffic Anomaly Reasoning
Evaluating Deployable Inference-Time Error Prediction in Vision MoEs
MOSAIC-CONUS: A Multimodal, Multi-Temporally Paired dataset for Earth Sciences
Robust and Hard-to-Remove GNN Watermarking via Topological Invariant Perception
GlucoFM-Bench: Benchmarking Time-Series Foundation Models for Blood Glucose Forecasting
Stability and Diversity of Networked Self-Consuming Generative Ecosystems
Cornerstones or Stumbling Blocks? Deciphering the Rock Tokens in On-Policy Distillation
DualKV: Shared-Prompt Flash Attention for Efficient RL Training with Large Rollouts and Long Contexts
A Multimodal Benchmark for Evaluating Cause-of-Death Inference Using Child Health and Mortality Data
Optimal In-Context Learning of Autoregressive Processes under Heterogeneous Second-Order Moments of the Prompts
SimplexUQ: An Evaluation Framework and Benchmark for Conformal Uncertainty on Simplex-Valued Predictions
Iterative Gumbel Planning for Continuous Control
Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions
ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models
Normalizing Flows are Capable Trajectory Planners
Position: AI-Agent Pricing Should Become More Outcome-Dependent: An Economic Perspective
Rethink Action Chunking in VLA Through Human Motor Control
Learning to Follow In-Context Watermark Instructions via Self-Distillation
Natural Policy Gradient as Doubly Smoothed Policy Iteration: A Bellman-Operator Framework
VFIG: Vectorizing Complex Figures in SVG with Vision-Language Models
Don't Always Pick the Highest-Performing Model: An Information Theoretic View of LLM Ensemble Selection
Agentic Video Editing from Underspecified Requests
PixelDiT2: Representation-Grounded Pixel Diffusion Transformers
Contrastive Representation Shaping for LLM Unlearning
Self-Supervised Keyframe Discovery for Horizon-Invariant Behavior Cloning
Primal-Dual Flow Matching for Sample-Wise Constrained Generation
Trust the Direction, Search the Step: Zero-and-First-Order Methods for LLM Fine-Tuning
Scaling Reward Modeling without Human Supervision
Beyond Task Success: Probing Cognitive Primitives in Web Agents
Differentiable Range-Partition Entropy for Entropy-Sensitive Geometric Algorithms
High-dimensional Gaussian Graphical Model Testing for Long-Memory Time Series
Sparsifying Correlation Clustering: Edge Coresets, Triangle Witnesses, and Observation Lower Bounds
Magnitude-preserving Layers Enable Efficient GANs
Spend Only What You Need: Defect-Aware Residual Coverage for Efficient Multi-Agent Reasoning
Generative Conformal Prediction with Optimized Coverage Allocation
Learning Polyhedral Conformal Sets for Robust Optimization
Learning What Not to Impute: An Uncertainty-Aware Diffusion Framework for Meaningful Missingness
BSTabDiff: Block-Subunit Diffusion Priors for High-Dimensional Tabular Data Generation
Coverage-Based Calibration for Post-Training Quantization via Weighted Maximum Coverage over Outlier Channels
Asymmetric Phase Coding Audio Watermarking
LowRankArena: A Standardized Evaluation Platform for SVD-Based LLM Compression
DynaTokens: Teaching Dynamics to Camera-Controlled Video Models at Test Time
Beyond Linear Activation Steering: Invertible Latent Transformations for Controlling LLM Behavior
Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks
Palette: A Modular, Controllable, and Efficient Framework for On-demand Authorized Safety Alignment Relaxation in LLMs
Learning from Language Feedback via Variational Policy Distillation
Procedural Memory Distillation: Online Reflection for Self-Improving Language Models
Powering Up Zeroth-Order Training via Subspace Gradient Orthogonalization
Bayesian Preference Learning for Test-Time Steerable Reward Models
DEBATE: A Large-Scale Benchmark for Evaluating Opinion Dynamics in Role-Playing LLM Agents
Nearest-Neighbor Radii under Dependent Sampling
Inference Time Nash Alignment
GRAPHLCP: Structure-Aware Localized Conformal Prediction on Graphs
Grouped Adaptive Head Mixing for Personalized Multi-Task Federated Reinforcement Learning
Faster Rates For Federated Variational Inequalities
Progress-Aware Distillation for Mitigating Stagnation in Small Language Model Agents
SEED: Self-Speculative Decoding via Implicit Encoder–Decoder
ArcMark: Distortion-Free Multi-Byte LLM Watermark via Optimal Transport
Policy-DRIFT: Dynamic Reward-Informed Flow Trajectory Steering
You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories
The Price of Locality: Why Forward-Forward Underperforms Backpropagation?
Loop alignment: Self-organized Weight Transpose in Predictive Coding through Independent Hebbian Plasticity.
Brute-Force Jailbreaks and Codon-Aware Watermarking for DNA Foundation Models
AsymHP: Load-Balanced Sparse Attention for Video Diffusion Transformers
Robust Hopfield Decision Transformer
Approximation Guarantees for Robust Aggregation in Federated Learning
Beyond LLM-Based Reasoning: Lightweight GNNs for Agent Failure Attribution
Video Forensic Self-Descriptions: Leveraging Temporally Distributed Forensic Microstructures for Zero-Shot Detection of AI-Generated Videos
AnaDiffusion: Anatomically Compositional Latent Diffusion for Controllable 3D Brain MRI Generation
DarkVGGT: Seeing Through Darkness Using Thermal Geometry without Daylight Tax
CoScan: Multi-Scale Content-Adaptive Space-Filling Scans for Causal State-Space Image Restoration
DeltaFugue: Orchestrating Spatial and Associative Memory for Algorithmic Length Generalization
PRISM: Primitive Routing via In-context Skill Mixing for Lifelong VLA
Streaming Interventions: Can Video LLMs Correct Mistakes as They Occur?
Row-Private Symmetric Cone Programming: Scale-Efficient Algorithm and Lower Bound
S$^{2}$-PINN: Stochastic Separable Physics-Informed Neural Networks
Stochastic Interpolants via Conditional Dependent Coupling
MedExAgent: Training LLM Agents to Ask, Examine, and Diagnose in Noisy Clinical Environments
Tracing Moral Foundations in Large Language Models
Dynamic Quadtree Tokenization for Autoregressive PDE Forecasting
Flow-Based Conformal Predictive Distributions
Beyond 3 Million Tokens: A Multi-Modal Foundation Model for Full-Resolution Heliophysics
When Does Knowing the State Help? Diagnosing Process vs. Outcome Reward Design
DD-Ranking: Rethinking the Evaluation of Dataset Distillation
Diffusion Model's Generalization Can Be Characterized by Inductive Biases toward a Data-Dependent Ridge Manifold
Enabling Denoising Score Matching Type Training for Manifold Diffusion Model via Momentum and Splitting
Convergence of Near-Linear Width ReLU Networks with Unbalanced Initialization
VICO: Visual Environments Co-Evolving for Vision-Language Model Reasoning
VeriWorld: A Verifiable Visual SWE-Bench for Spatial Reasoning in 3D Environments
FLARE: Diffusion for Hybrid Language Model
Causal Effects with Unobserved Unit Types in Interacting Human–AI Systems
Almost Sure Convergence Rates of Stochastic Approximation and Reinforcement Learning via a Poisson-Moreau Drift
MathlibPR: Pull Request Merge-Readiness Benchmark for Formal Mathematical Libraries
A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training
AgentAbstain: Do LLM Agents Know When Not to Act?
Forced Deferral: Manipulating Routing Decisions in Multimodal LLM Cascades
Dynamic Tokenization via Reinforcement Patching: End-to-end Training and Zero-shot Transfer
MAdam: Metric-Aware Multi-Objective Adam
Your Embedding Model Is SMARTer Than You Think
Invariant Features in Language Models: Geometric Characterization and Model Attribution
Sequential Probabilistic Uncertainty Estimation for Parallel Multi-Agent Reasoning Systems
Toward Cognitive Supersensing in Multimodal Large Language Models
DeltaPrompts: Escaping the Zero-Delta Trap in Multimodal Distillation
Quantifying Centrality for Complex Data
Cross-Cell-Line Perturbation Prediction Needs Controls
Temporal Island Sparse Autoencoders for Interpreting Clinical Time-Series Models
Hydra: Towards Transferable Multi-Task Learning on Temporal Graphs
Inferential Theory of Learning as a Framework for Test-Time Computation in Foundation Models
Imperfect Influence, Reliable Rankings: A Theory of TRAK for Data Attribution
Do multimodal models imagine electric sheep?
Learning Large-Scale Competitive Team Behaviors with Mean-Field Interactions
Geometrically Disentangling Concept Learning from the Language Modeling Loss
MonoPhysics: Estimating Geometry, Appearance, and Physical Parameters from Monocular Videos
Cross-Fitting for Neural Posterior Estimation
Denoising Implicit Variational Inference
Trust Region Continual Learning as an Implicit Meta-Learner
Dual Dimensionality for Local and Global Attention
Crafting Reversible SFT Behaviors in Large Language Models
Towards Direct Latent-Space Synthesis for Parallel Branches in LLM-Agent Workflows
Understanding Graph Self-Supervised Pre-training under Distribution Shifts: A Scaling Law Perspective
Generalization Measures for Deep Learning Should Be Audited for Fragility
AdShot: Benchmarking Multimodal Large Language Models for Video Advertisement Clipping
ReaLM: A Unified Red-Teaming Benchmark for Physical-World VLMs
AgentKVShift: Efficient KV Cache Reuse for Agentic Memory Systems
PRO: Enabling Precise and Robust Text Watermark for Open-Source LLMs
Soft Token Alignment for Cross-Lingual Reasoning
RepoLaunch: Automating Build and Management of Code Repositories across Languages and Platforms
ShadowTransfer: A Geographic Transfer Benchmark for Overhead Shadow Detection
Free energy Estimation on Any State Space
Prompt-Driven Exploration
Aligning Forest and Trees in Images & Long Captions for Visually Grounded Understanding
RoSeViT: Role-Separated Vision Transformers for ARC Visual Reasoning
ANCRe: Adaptive Neural Connection Reassignment for Efficient Depth Scaling
PACE: Two-Timescale Self-Evolution for Small Language Model Agents
GenScale: A Benchmark for Relative Object Scale in Image Generation and Editing
GeoSPRINT: Geometric Redundancy-Aware Step Pruning for Inference in Diffusion Trajectories
MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI
Optimal Byzantine-resilient Federated Learning with User-level Differential Privacy
PolyMind: Exploring Width Scaling for Reflective Reasoning in Language Agents
CoTrek: Toward Scalable On-Policy Distillation for Long Chain-of-Thought Reasoning
C3VD-DEFCOL: A Deformable Colonoscopy Dataset with Time-Resolved 3D Ground Truth and Realistic Appearance
DnNP: Denoising Input Uncertainty in Neural Processes
Structurally Separated DAG Learning with Multi-Scale Normalized Closure
GPT-Image-Edit-1M: An Auditable Million-Scale Dataset for Instruction-Guided Image Editing
TabWorld: A World-Modeling Foundation Model for Tabular Generation
Automating ML for Science: Can Frontier Agents Climb Scientific Hills in the Wild?
Coupling Models for One-Step Discrete Generation
Vision to Geometry: 3D Spatial Memory for Sequential Embodied MLLM Reasoning and Exploration
PixelDense: Dense Prediction as Representation Alignment for Pixel Diffusion
Two-Fidelity Best-Action Identification for Stochastic Minimax Tree
On Neural Scaling Laws for Weather Emulation through Continual Training
Learning Interpretable Switching Dynamics in Shared Neural-Behavioral Latent Space
FLUX: Geometry-Aware Longitudinal Flow Matching with Mixture of Experts
ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model
Generalizing Action-Conditioned Latent World Models with Video Model Rewards
Bernini: Latent Semantic Planning for Video Diffusion
Learning What to Remember: Test-Time Training via Context Distillation
Unsupervised Concept Discovery with Dirichlet Concept Diffusion Models
MaterialsSaddles: 34 Million Transition States and a Flow-Matching Saddle-Point Predictor for Materials
Entropy Distribution as a Fingerprint for Hallucinations in Generative Models
LLMs can construct powerful representations and streamline sample-efficient supervised learning
ShadowBench: Exposing Lexical Anchoring and the Illusion of Forgetting in Large Language Models
Towards Hyperparameter Transfer for Differentially Private Optimization
SPANUQ: Span-Level Uncertainty Quantification for Large Language Model Generation
Firefly: Illuminating Verified Real-world Tool Call Data Generation
Q-MMR: Off-Policy Evaluation via Recursive Reweighting and Moment Matching
The Best-Laid SCHEMEs: Coordinated Sabotage and Monitoring in Multi-Agent Systems
Finite-Resolution Decision Sufficiency for Linear Optimization
Say the Same, Act Differently: Text-Orthogonal Action Subspaces in Reasoning Vision-Language-Action Models
Knowing Without Saying: How Contextual Evidence Survives but Fails to Surface in Transformers
A Semantic-Sampling Framework for Evaluating Calibration in Open-Ended Question Answering
Robust Instruction Compliance in Cooperative Multi-Agent Reinforcement Learning
DropKV: Decoupling Residual-Output Perturbation for Near-Optimal KV-Cache Eviction
Semantic Search over 9 Million Mathematical Theorems
Distilling Sequential Computation in Transformer Language Models
A Margin Perspective on LoRA: Robustness to Catastrophic Forgetting and Adapter Merging (MaLoRA)
Multi-Token Residual Prediction
Rethinking LoRA Initialization for Robust Asymmetric Learning Rates
Augmented Lagrangian Method for Last-Iterate Convergence for Constrained MDPs
When Scores Conflict with Preferences: Calibrated Drift Control for Heterogeneous DPO
A Latent-Load Framework for Reliability Analysis and Intervention Design in LLM Pipelines
NeuronEye: Query-Guided Visual Concept Activation for Vision-Language Reasoning
A World Model of Radiologist Reading for Medical Image Representation Learning
MedVIGIL: Evaluating Trustworthy Medical VLMs Under Broken Visual Evidence
Rep2Text: Decoding Full Text from a Single LLM Token Representation
TGPO: Temporal Grounded Policy Optimization for Signal Temporal Logic Tasks
Everything at Every Scale: Scale-Invariant Diffusion with Continuous Super-Resolution
WavFlow: Flowing Through Waveforms for Audio Generation
PRISM-Bench: A Benchmark of Puzzle-Based Visual Tasks with CoT Error Detection
A Set-Sequence Model for Time Series
Activation Functions Shape Token Synchronization in Stochastic Transformer Dynamics
Attention-Based Pretraining for Unsupervised Amortized Causal Discovery
Mixture-of-Chains: Learning Causal Graphs from Human Knowledge
Majority Bit-Aware Watermarking for Large Language Models
Model Cascades with Provable Per-Class Quality
Hierarchical Denoising For Multi-Step Visual Reasoning
Free Draft-and-Verification: Toward Lossless Parallel Decoding for Diffusion Large Language Models
Transfer Learning Through Conditional Quantile Matching
L-Flow: Longitudinal Flow Matching for Progression-Aware Speech Biomarker Modeling
LEMON-ZEST: Evolution-Informed Tokenization for Efficient Protein Language Modeling
HDCS: Hierarchy Discovery and Critic Shaping for Reinforcement Learning with Automaton Specification
A Curvature Phase Transition Governs Coherence Penalty Efficiency Against Feature Absorption in SAEs
Inside Emergence: Structure-Behaviour Gaps in Language Model Training
BuresTomFlow: Bures-Geometric Flow Matching for Posterior Quantum Tomography
A Communication-Theoretic Framework for LLM Agents: Cost-Aware Adaptive Reliability
Direct Acceleration of Stochastic Root-Finding Without Variance Reduction and Regularization
Model-based Bootstrap of Controlled Markov Chains
DRScaffold: Boosting Dense-Scene Reasoning in Lightweight Vision Language Models
Dynamic Treatment on Networks
RAD-TFM: Robust and Domain-Adapted Tabular Foundation Models
Leveraging Latent Visual Reasoning in Silence
Efficient Transferable Optimal Transport via Min-Sliced Transport Plans
TIER: Trajectory-Invariant Execution Rewards for Multi-Step Tool Composition
The Sharp Directions Are Against You: Curvature Analysis of Activation Steering
C-GRPO: Conformal Group Relative Policy Optimization
Data-Constrained Language Model Pretraining: Improved Regularization and Scaling Laws
MEMAUDIT: An Exact Package-Oracle Evaluation Protocol for Budgeted Long-Term LLM Memory Writing
Persuasive Prediction via Decision Calibration
LEAD: Length-Efficient Adaptive and Dynamic Reasoning for Large Language Models
LIBERO-PeRM: Benchmarking Personalized Robotic Manipulation
Deep Reasoning in General Purpose Agents via Structured Meta-Cognition
Relaxed On-Policy Distillation: Selective Credit Allocation for Scaling Reasoning Efficiently
RepFusion: Leveraging Multimodal Priors for Denoising in Representation Space
Structural Rationale Distillation via Reasoning Space Compression
Strategic Decision Focused Learning
Fixed-Size Active Statistical Inference
Bayes-Sufficient Compression Is Not Enough: How Communication Helps in Multi-Agent Systems?
Massively Parallel Exact Inference for Hawkes Processes
Vision-Language Models Should Commit to a Cézannian Specification
Causal Benchmarks for Multimodal AI Should Measure Categorical Difference, Not Capability Gap
Cross-Distribution Generalization in Longitudinal Behavioral Data Through Frozen Coherence Constraints
Learning When to Denoise: Optimizing Asynchronous Schedules for Latent Diffusion
One for All: A Non-Linear Transformer can enable Cross-Domain Generalization for In-Context Reinforcement Learning
L2-Bench: An Evaluation Benchmark for Measuring LLM Capabilities in Second Language Education
Learning When to Think: Adaptive Internal Computation for Reinforcement Learning
SMI: Semantic Medical ID for Hierarchy-Aware Concept Representation
MoSE3: Learning World-Space SE(3) at Every Pixel
Tokenizer Choice Shapes Generalization in State-Centric Learning for Planning
Inference and estimation with unidentifiable latent treatment effects
Signed Rectified Flow: Negativity Controlled Generation
Contrastive Nonmyopic Objective Cost-Tradeoff Acquisition for Longitudinal Data
Oracle Supervision Transfers for Hyperparameter Prediction in Model-Based Image Denoising
SGD at the Edge of Stability: The Stochastic Sharpness Gap
AdaPaD: Adaptive Parallel Deflation for PEFT with Self-Correcting Rank Discovery
Combating Catastrophic Forgetting in Continual Domain Adaptation via Knowledge Recasting
One Model, Two Roles: Emergent Specialization in a Shared Recurrent Transformer
First-Order Regret for Online Convex Optimization with Memory and Online Nonstochastic Control
Learning to Price with Persuasion
How to Have a Sensitive Debate
The Path Not Taken: RLVR Learns Off the Principals
ForceBody: Force-Paired Parametric Body Motion with Torque Uncertainty
Improved techniques for fine-tuning flow models via adjoint matching: a deterministic control pipeline
Predictive 4D Generation with Latent State Machines
Stability-Constrained Regime-Aware Forecasting for Heterogeneous Panel Time Series
Alignment Needs 'Cognitive Control': On The Role of Regularization in LLM Alignment
World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry
Learning Task-Centric World Models from Visual Foundations
ConQuR: Corner Aligned Activation Quantization via Optimized Rotations for LLMs
Factored Generative Models through Mechanism Diversity
Topology-Reinforced Swin Transformer for Medical Image Analysis
Exploiting Fine-Tuning Structures to Improve Adversarial Transferability on Downstream SAM
DriveMind: Mind-Evolving Belief Tracking for Closed-Loop Autonomous Driving
$\chi$-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?
AUTOMEM: Automated Learning of Memory as a Cognitive Skill
Teaching LLMs to Recommend and Defer in Underrepresented Epilepsy Care
Paint Anything: Toward Any-Color Controllable Image Generation and Editing
Heterogeneous Parallelism for Multimodal Large Language Model Training
Approaching Effective Merging in Model Embedding Space
To trust or not to trust: Attention-based Trust Management for LLM Multi-Agent Systems
PM-LoRA: Scalable Continual Learning via Progressive Merging of Low Rank Adapters
OpenBrain: An Auditable Generated-Label Release for Whole-Brain MRI Parcellation
Localizing and Repairing Sparse-Prompt Failure in SAM Decoders via Box-to-Point Counterfactual
Analytical Correction for Subsampling Bias in Drifting Models
Conceal, Reconstruct, Jailbreak: Exploiting the Reconstruction--Concealment Tradeoff in MLLMs
LogT: Logically Think with Images for Visual Search
She Performs Your Voice: A Unified Speech and Dance Motion Model
GEAR: A GPU-Accelerated Global Solver for Nonlinear Programs via Linear Bound Propagation
GRNAgent: A Multimodal Graph Reasoning Agent for Gene Regulatory Network Inference
REINS: Learning Inertia-Induced Geometry for Physics-Consistent Motion Representation in Clinical Gait Phenotyping
Ensemble Selective Classification
Aligning Language Models with Selective Prediction
When the Same Coefficients Reach Different Places: Asymmetric Realizability in Transplanting Tokenizers across Large Language Models
Guiding Data Allocation for Robust Subpopulation Generalization
Ultra Fast PDE Solving via Physics Guided Few-step Diffusion
Evaluating Compositional Generalization in Transformers: The Role of Composition Equivalence and Module Coverage
SimSD: Simple Speculative Decoding in Diffusion Language Models
RegimeVGGT: Layer-Wise Spatially Preserving Redundancy Removal for Visual Geometry Grounded Transformer
StreamGaze: Gaze-Guided Temporal Reasoning and Proactive Understanding in Streaming Videos
BehaviorBench: Modeling Real-World User Decisions from Behavioral Traces
Language-Induced Priors for Domain Adaptation
Breaking the Bias Barrier in Concave Multi-Objective Reinforcement Learning
Order-Optimal Sample Complexity for Distribution Learning via Flow Matching
Oracle-Robust Online Alignment for Large Language Models
Imitation from Observations with Trajectory-Level Generative Embeddings
3D-PLOT-LLM: Part-Level Object Tokens for 3D Large Language Models
Counterfactual Predictive State Representations: The Intrinsic Dimension of Partial-Information Games
Response Time Enhances Alignment with Heterogeneous Preferences
MinSteer: Minimal-Pair Steering via Two-Stage Cached Continuation
Fault Tolerant Coresets
Counterfactual Debugging the World Model Transfer Gap
Reading, Not Thinking: Bridging the Modality Gap When Text Becomes Pixels
Position: Reconciling Open Access with Owner Control in AI Model Distribution Deserves More Research Effort
Matrix-Free Stochastic Training of Low-Rank Spectral Graph Learning via Randomized Adaptive Spectral Estimation
PocketVE: Stable and Controllable Structure-Based Drug Design with Variance-Exploding Diffusion
Rethinking Long-Video Efficiency: A Joint Allocation Perspective on Frames, Pixels, and Front-End Latency
Vision-Language Grounding as Bidirectional Concept Correspondence
Markovian Experimental Design under Concept Drift
How well behaved is finite dimensional Diffusion Maps embedding?
ChanSFormer: A Channel Agnostic Vision Transformer for Multi-Channel Cell Painting Images
Agents' Last Exam
Robust and Efficient Finetuning of Vision Foundation Models via Implicit Ensembling
A Tight Hierarchy For Chain of Thought
Consumer Search and Social Learning in Agentic Markets
Minimally Invasive Steering of Language Models
Concurrence of Symmetry Breaking and Nonlocality Phase Transitions in Diffusion Models
Concorde: Geometry-Aware Link Prediction via Decoupled Energy Minimization
OmniMechanism Design for Human-AI Collaboration with Impressionable Minds
Inverting Retargeting: Humanoid Datasets Remember Their Operators
Trellis4D: Complex 4D Mesh Generation
Beyond Empirical Support: Structured Outlier Generation via Sinkhorn Optimal Transport
HorizonComposer: Spatiotemporally Consistent Driving Video Editing with Enriched Traffic Semantics
Lean Refactor: Multi-Objective Controllable Proof Optimization via Agentic Strategy Search
Joint Consistency: A Unified Test-Time Aggregation Framework via Energy Minimization
Ordinal Geometry Complements Reconstruction: Diagnosing Planning with Compressed Value Functions
You Can’t Have It Both Ways: Concept Entanglement Limits Diffusion Model Unlearning
Pacing Branch Parallelism in LLM Serving
SpecHop: Continuous Speculation for Accelerating Multi-Hop Retrieval Agents
Harder the Task, Sparser the Representation: Sparsity as a Learning Signature of Capability in LLMs
The Power of a Random Sample in Online Algorithms
Simulation-Informed Diffusion for Decentralized Multi-robot Motion Planning
Search-Augmented Masked Diffusion Models for Constrained Generation
Drift Flow Matching
Evaluating Whether LLMs Can Reliably Connect the DOTs?
Models Recall What They Violate: Constraint Adherence in Multi-Turn LLM Ideation
SapiensID 2.0: Aligning Human Recognition Foundation Models with Human Perception
Non-Colliding Biometric Identities for Digital Entities: Geometry, Capacity, and Million-Scale Virtual Identity Provisioning
Inertia-1: An Open Exploration of Wearable Motion Foundation Models
Geometry-Centered 3D Latent World Models for Growing Surfaces
Beyond the Trial-and-Error Loop: Hybrid Projection and Automated Tuning for Distributed Training
A Unified Uncertainty Representation for Graph Neural Networks via Doubly-Spectral Stochastic Expansion
Lost on Campus: Evaluating Embodied Spatial Reasoning of Vision-Language Models in the Wild
AgentOdyssey: Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning Agents
Spin-Weighted Spherical Harmonics Enable Complete and Scalable E(3)-Equivariant Networks
Improving Function Space Flow Matching with Kernel Optimal Transport
Graph Anomaly Detection as Dynamical Transport: Training-Free Scoring via Empirical Bayes
Contextualized Evaluation of Vision Language Models through Dynamic Interviews
A Principled Self-Referenced Early Stopping Approach for Deep Image Prior
On the Convergence Analysis of Muon
Learning Recoverable Neural Networks against Weight Corruption via Simple Zero-Sum Projection
ML-assisted Randomization Tests for A/B Experiments
Can Bits Seal Language?
Exact Unlearning via Quantized Sufficient Statistics
GazeFlow: From Human Gaze Behavior to Generative Egocentric Gaze Prediction
Multidimensional Observer Model and Perceptual Dimensions of Human Image Quality Assessment
MAGNET: Manifold-Aware Graph Diffusion Network for Connectome Generation
EntityBench: Towards Entity-Consistent Long-Range Multi-Shot Video Generation
RustMizan: A Compilable, Contamination-Aware Benchmarking Framework for Rust Vulnerabilities
GeoWind2Plan: Mission-Time 3D Urban Wind Prediction for Energy-Efficient UAV Planning
OATS: Online Data Augmentation for Time Series Foundation Models
Discrete Stochastic Localization for Non-autoregressive Generation
AtlasVid: Efficient Ultra-High-Resolution Long Video Generation via Decoupled Global-Local Modeling
Learning Unbiased Permutations via Flow Matching
Is Backpropagation Optimal? When Synthetic Gradients Improve Sample Efficiency
Factorized Spectral Representations for Reinforcement Learning
Extending 3D Reconstruction Models to Any Camera
Learning Orthonormal Bases for Function Spaces
Few-Step Diffusion Language Models via Trajectory Self-Distillation
COPRA: Conditional Parameter Adaptation with Reinforcement Learning for Video Anomaly Detection
Enabling approximate joint sampling in diffusion LMs
Test-Time Speculation
Token Time Continuous Diffusion for Language Modeling
NPUsper: Eliminating Redundant Computation for Real-Time Whisper on Mobile NPUs
Token Inflation: How Dishonest Providers Can Overcharge for Large Language Model Usage
(Strongly) Replicable Distribution Testers imply High Probability Distribution Testers
Sample Complexity of Linear Regression under Random-Location Coordinate Corruptions
RefDecoder: Enhancing Visual Generation with Conditional Video Decoding
IncAgg: Efficient Memory-Enhanced Graph Learning via Incremental Aggregation
RL-Inf: Tracking Non-local Training Data Influence for Online Reinforcement Learning
Adapting in the Dark: Efficient and Stable Test-Time Adaptation for Black-Box Models
CultureRed: Benchmarking Culture-Specific AI Safety Based on Global Statutes
MetaCluster: Enabling Deep Compression of Kolmogorov-Arnold Network
On-Policy Hindsight Distillation for Early Risk Prediction
Tracing Agentic Failure from the Flow of Success
Multi-Head Recurrent Memory Agents
Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime Monitoring
Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents
CMPQ: Compensatory Quantization via Input-Aware Hessian Damping
Test-Time Defense Against Adversarial Attacks via Stochastic Resonance of Latent Ensembles
MindVLM: Neural-Grounded Visual Captioning via Subject-Aware Semantic Evidence Selection
Tree Search With Predictions
The Type Theory of Stationary MDPs: Rare Events and Uncertainty Quantification
Differentiable Bit-Widths: Co-optimizing Pruning and Quantization via SVD for Ultra-Efficient LLM Compression
OpInf-LLM: Parametric PDE Solving with LLMs via Operator Inference
AMPS: Adaptive Modality Preference Steering via Functional Entropy
GRAM: Group-wise Rank-Aware Modal Merging via Subspace Alignment
HyCO: A Hybrid Neural Solver for Combinatorial Optimization
VTV-FM: Flow Matching through Variational Terminal-Velocity Closure
Reasoning Pathologies in Large Language Models: A Diagnostic Perspective
Controllable Molecular Generative Foundation Models
Rethinking Structured Generation: Can Graph-Based Reasoning Resolve Ambiguity?
VLSplat: Vision-Language Guided Object-Centric 3D Gaussian Splatting via Scene Graph
LLM-Based Multi-Agent Blackboard System for Information Discovery in Data Science
Preference Conditioned Multi-Objective Reinforcement Learning: Decomposed, Diversity-Driven Policy Optimization
DivMoE: Fine-Grained MoE Upcycling via Cross-Domain Expert Composition
CURe: Conservative Unlearning with Soft-Gating Regularization for Offline Reinforcement Learning
Unlearning Diffusion Policies via Relative Fisher Forgetting
RPP: A Certified Poisoned-Sample Detection Framework for Backdoor Attacks under Dataset Imbalance
Learning a Unified Cross-Model Semantic Dictionary via Gated Bottleneck Sparse Autoencoders
Inverted Detection and Control in Steering Vectors
Curriculum proof repair with learned counterexamples
Information-Directed Offline-to-Online Reinforcement Learning
Scaling Multi-Teacher Distillation for Digital Pathology
Revealing the Gap in Human and VLM Scene Perception through Counterfactual Semantic Saliency
Neural-Corrected Operator Learning for Homogenization and Inverse Design
Regret–Oracle Complexity Tradeoffs in Agnostic Online Learning
Less Decoder is More Encoder: Geometric Representation Learning from Novel View Synthesis
GroupMemBench: Benchmarking LLM Agent Memory in Multi-Party Conversations
Limits and Potential of Score-Based Data Valuation: Redundancy, Complementarity, and Non-Monotonicity
Sort, Partition, Randomize: Optimal Binary Hypothesis Testing under Local Differential Privacy
Rethinking Psychometric Evaluation of LLMs: When and Why Self-Reports Predict Behavior
HilbertGen-3D:Hilbert--Multifractal Conditioning for Topology-Aware 3D Generation
Dominant-Layer ZO: A Single Layer Dominates Zeroth-Order Fine-Tuning of LLMs
On the Provable Emergence of Hierarchical Concept Structure in CLIP Embeddings
RoboWits: Unexpected Challenges for Robotic Creative Problem Solving
MC$^2$Mark: Distortion-Free Multi-Bit Watermarking for Long Messages
Depth Exploration for LLM Decoding
Generation-for-Understanding with Structured Action Scripts for Embodied Multimodal Learning
Compute Aligned Training: Optimizing for Test Time Inference
CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs
Unifying Reasoning and Planning through Energy Minimization
Online Bayesian Calibration under Gradual and Abrupt System Changes
Action Images: End-to-End Policy Learning via Multiview Video Generation
$f$-GRPO & Beyond: Divergence-Based Reinforcement Learning Algorithms for General LLM Alignment
LEIA: Learned Environment for Interactive Architected Materials
Provable Test-Time Scaling for Beam Search in LLM Reasoning
Progressive Risk Estimation for Accident Anticipation
On the Meta-Design of Allocation Problems
Chain-of-Generation: Progressive Latent Diffusion for Text-Guided Molecular Design
CHoRD: Coordinating Scheduling and Data Placement for Efficient Deep Neural Network Inference on Chiplet-Based GPUs
Compositional Policy Optimization with Language Models
Uncertainty-Guided Reward Labeling for Reinforcement Learning under Limited Feedback
Latent Barrier Steering: Hierarchical Safety for Generative Planning
Reward Shaping to Improve Language Model Query Generation
Label-Free Consistency Correction for Weak-to-Strong Generalization
Tiny but Trusted: Efficient Vision-Language Reasoning for Time-Series Anomaly Detection
ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation
LLM Judge Validation Under Sparse Overlap: From Inference to Design
ActWorld: From Explorable to Interactive World Model via Action-Aware Memory
Precision As You Need: Stochastic Computing Is a Dense Adaptive Quantizer
RigidFormer: Learning Rigid Dynamics using Transformers
DSAD: Dynamic Soft Anisotropic Diagrams for Reduced-Order Video Representation
Do Reasoning LLMs Refuse What They Infer in Long Contexts?
TKCAM: Text and Keyframe to Camera Trajectory Generation
AbFlowNet: Optimizing Antibody-Antigen Binding Energy via Diffusion-GFlowNet Fusion
Scaling Whole-Body Loco-Manipulation through Compositional Data Synthesis
Demystifying Classifier-Free Guidance for Auto-Regressive Image Generation
LLM-ACES: Closed-Loop Discovery of Dynamic Systems with LLM-Guided Adaptive Search
INFUSER: Influence-Guided Self-Evolution Improves Reasoning
s2n-bignum-bench: A practical benchmark for evaluating low-level code reasoning of LLMs
Sparse Internal Control of Language Models
Computationally sufficient statistics for Ising models
B$^3$-PWL: GPU-Batched Branch-and-Bound for Piecewise-Linear Optimization with SOS2 Constraints
Toward a Unified Statistical Theory of Unsupervised Pretraining and Supervised Neural Knowledge Graph Learning
Efficient Test-time Adaptation through Candidate Verification and Divergence Shifts
UniReFP: Robust Unified Fingerprinting for Vision Models against Cross-Task Repurposing Attacks
MPQ: A Message-Passing View of Post-Training Quantization
Is Decentralized LLM Agent RL Robust to Heterogeneity? An Asymmetric Tale
The two clocks and the innovation window: When and how generative models learn rules
MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction
The Missing Positional Story in LLMs: A Case Study of Shift-Invariant Attention
Loss is Not Behavior: A Unified Output-Space Analysis of Gradient-Based Machine Unlearning
When Form Changes but Logic Doesn’t: Building Logic-invariant LLMs through Structures
Beyond Score: A Dataset for Joint Action and Score Predictions in 2v2 Sports
Verifiers in the Loop: Decoding Time Verification for Code Translation
Motion Cues from Image-based Point Tracking for LiDAR Scene Flow Estimation
CD-RCM: Generalizable Continuous-Depth Novel View Synthesis for Reflectance Confocal Microscopy
PanoWorld: Geometry-Consistent Panoramic Video World Modeling
Self-Trained Verification for Training- and Test-Time Self-Improvement
Grounding Multimodal Reasoning with Evidence-Ablated Negatives
Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization
LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling
RTEB: An Overfitting-Resistant Benchmark for Embedding Model Evaluation
On the Geometry and Latent-Space Composition of Hypernetwork-Generated LoRAs
AdaState: Self-Evolving Anchors for Streaming Video Generation
EVALUATION CARDS: An Interpretive Layer for AI Evaluation Reporting
On the Primacy Bias in RLVR Training
The Reasoning Boundary Paradox: How Reinforcement Learning Constrains Language Models
OptiWorld: Optimal Control for Video World Generation under Physical Constraints
Equivariant Force Field Calibration for Flow-based Protein Design
Neural Statistical Functions
Weighted Conformal Clustering
nuReasoning: A Reasoning-Centric Dataset and Benchmark for Long-Tail Autonomous Driving
FlashEvolve: Accelerating Agent Self-Evolution with Asynchronous Stage Orchestration
Audible World Models: Spatially Aware Sound Generation for 3D Worlds
Event-Grounded Sparse Autoencoders for Vision-Language-Action Policies
Generative Cross-Entropy: A Strictly Proper Loss for Data-Efficient Classification
Interpreting Neural Combinatorial Optimization via Evolving Programmatic Bottlenecks
Robust Diffusion Models via Divergence-Induced Weighted Denoising
A general kernel framework for non-CND distance measures using $|\mathcal{D}|$-dimensional sparse landmark embeddings
Joint Confounder Selection for Causal Mediation Analysis in High Dimensions
Persona Vectors: Monitoring and Controlling Character Traits in Language Models
Multi-Objective Reinforcement Learning Using Routed Ensembles and Trajectory Attribution
Designing Kernel Surrogate Models for Multimodal Attribution
Continuity Laws for Sequential Models
Which Tokens to Merge? Diffusion Dynamics for Efficient Image Generation
Minimax-Optimal Transformer Classification for Functional Data with Dense-Sparse Phase Transition
Multi-agent Collaboration with State Management
DORA: A Scalable Asynchronous Reinforcement Learning System for Language Model Training
Task Vector Geometry Underlies Dual Modes of Task Inference in Transformers
Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability
ClusQuant: Mitigating Outliers with Clustering-Based Representations for Low-Precision LRMs
$\epsilon$-Good Action Identification in Fixed-Budget Monte Carlo Tree Search
On the Token Value Inequality in Efficient Reasoning
Leaner transformers can easily learn to cluster
SEISMOS: A Statistical Signal Detection Framework for Semantic Chunking
Quest: Training Frontier Deep Research Agents with Fully Synthetic Tasks
Arena-T2I Hard: Benchmarking and Improving Faithfulness with Dependency-Aware Checklist Rewards
Language Model Goal Selection Differs from Humans' in a Self-Directed Learning Task
Bayes-pFCL:Bayesian Personalized Federated Continual Learning
Beyond Interpretability: When, Why, and How Sparse Autoencoders Enable Label-Free Visual Steering
Gaeta-Lie Neural SDEs: Symmetry-Regularized Learning of Stochastic Dynamics
Rank-Transformed Dissimilarity Profiles for High-Dimensional Classification
CLR-voyance : Reinforcing Open-Ended Reasoning for Inpatient Clinical Decision Support with Outcome-Aware Rubrics
Learning Evidence Highlighting for Frozen LLMs
Robust Nash Alignment under Preference Uncertainty
From History to State: Constant-Context Skill Learning for LLM Agents
MaxIM: Maximally Informative Incremental Summarization via Reinforcement Learning
Mitigating Object Hallucination in Large Vision-Language Models via False Discovery Controlled Visual Data Splitting
SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks
E4GEN: Event-level Explainable Extreme-Enhanced Time-series Generation
Dual-Granularity Learning for Regression with Continuous Noisy Labels
DictLLM: Post-training Compression of Large Language Model with Dictionary Kernels
Masked Sobolev Training for Feasibility-Reliable Optimization Proxies
Clean-Label Poisoning for Gradient-Boosted Decision Trees
ACQueReLlo: Alignment-Aware Constrained Quantization via Reinforcement Learning for Large Language Models
Near-Optimal Last-Iterate Convergence for Zero-Sum Games with Bandit Feedback and Opponent Actions
QueryStop: Dynamic Stop Signals for Efficient Streaming Inference
Representing Part-Whole Hierarchy with Nested Neuronal Coherence
Monoculture Robust Learning
Auditor-Assisted Summary-Channel Verification for Hosted LLM Identity Substitution
Towards Differentially Private Reinforcement Learning with General Function Approximation
Constrained Decoding for Diffusion Language Models via Efficient Inference over Finite Automata
A low-rank decoder bottleneck bounds reliability in foundation-model perturbation prediction
SHRED: Retain-Set-Free Unlearning via Self-Distillation with Logit Demotion
Value-Aware Stochastic KV Cache Eviction for Reasoning Models
RaZeR: Pushing the Limits of NVFP4 Quantization with Redundant Zero Remapping
ReCoVer: Resilient LLM Pre-Training System via Fault-Tolerant Collective and Versatile Workload
Learning Cultural Vectors for Cross-Cultural Generation
VAR-Q: Tuning-free KV Cache Quantization for Visual Autoregressive Image and Video Generation
Diffusion-DRF: Free, Rich, and Differentiable Reward for Video Diffusion Fine-Tuning
Safe-PG-LQR: Provably Safe, Convergent and Optimal Model-Free Linear Quadratic Regulator with Hard Constraints
Prototypes of the Mind: A Unified Framework for Probing the Visual Brain
Contrastive Pretraining Scales Agentic Exploration
Align-RAG: Alignment Is All You Need for TSFM In-Context Learning
TENG-BC: Time-Evolving Natural Gradient for High-Accuracy Neural PDE Solvers with General Boundary Conditions
ASSET: Acquisition-Sensitive Subspace Estimation for Test-Time Adaptation of Medical VLMs
Generative Modeling via Drifting
Adaptive Target-Charging with Privacy Filters and Individual Accounting
Trimming the Long-Tail of Visual World Modeling Evaluation
DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy
AI GAMESTORE: Scalable, Open-Ended Evaluation of Machine General Intelligence with Human Games
Learning a Maximum Entropy Model for Visual Textures using Diffusion
Useful Memories Become Faulty When Continuously Updated by LLMs
Flow Matching Reinforcement Learning via SDE Inference
On Lipschitz Explosion in Deep Neural Networks with Normalization: Consequences for Optimization and Robustness
Disentangling Where and When: Factored Spatio-Temporal Explanations for Video Action Recognition
Learning Chance-Constrained MDPs with Bellman Distributional Certificates
Beyond Bounded Variance: Variance-Reduced Normalized Methods for Nonconvex Optimization under Blum-Gladyshev Noise
BiMoGen: Bidirectional Motion-Text Generation via Unified Masked Discrete Diffusion
Unified High-Probability Analysis of Stochastic Variance-Reduced Estimation
Adaptive Power Iteration Method for Differentially Private PCA
Language-Conditioned World Modeling for Visual Navigation
Do Pathology Foundation Models Encode Disease Progression? A Pseudotime Analysis of Visual Representations
Action-Level Behavior Policy Optimization for Variance-Reduced Policy Gradients
SpecForge: Agent-Oriented Code Documentation Optimization via Multi-Frontier Tree Search
Learning Where and What to Restore for Composite Image Restoration
Watermarking as a Learned Intrinsic Property of Diffusion Models
Attribute-Efficient Learning of Sparse Halfspaces with Constant Malicious Noise Rate
Taming the Curses of Multiagency in Robust Markov Games with Large State Space through Linear Function Approximation
The Power of Menus in Dynamic Pricing: Near Optimal Regret and Equivalence Results
SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
Where You Backpropagate Matters: Token Hypothesis for Memory-Efficient Fine-Tuning
Learning-Augmented Mechanism Design for Facility Location under $L_p$-Norm Social Costs
Counterfactual Distillation: Internalizing Reflective Experience into LLM Agent
On the Complexity of Offline Reinforcement Learning with Q*-Approximation and Partial Coverage
SAGE: Evidence-First Biomarker Discovery through Multi-Agent Reasoning
Skill-Coupled Policy Optimization with Calibrated Group-Wise Advantage Estimation
When Think-with-Image Meets Safety: What Determines Multimodal Jailbreak Robustness?
GUI-Libra: Data-Efficient Post-Training for Reliable Reasoning-and-Acting in Native GUI Agents
Sliced Inner Product Gromov–Wasserstein Distances
Bridge Graphical Models: Coupling, Projection, and Current-Preserving Dynamics for Generative Modeling
A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language Models
SAPO: Step-Level Skill-Augmented Policy Optimization for Multi-Turn LLM Agents
To See Far, Look Close: Evolutionary Forecasting for Long-term Time Series
PIGRAM: An Interpretable Patch--Motif Interaction Grammar for Protein--Nucleic-Acid Recognition
Statistical Query Lower Bounds for Smoothed Agnostic Learning
Online Maximization of Non-Decomposable Test and Population Utilities
Mind the Gap: Information Disadvantage as a Learning Signal in Cooperative MARL
JARVIS-Bench: Benchmarking Personal Intelligence Agents on Long-Horizon Real-User Daily Traces
Pointwise Lipschitz Continuous Graph Algorithms
ScreenShot: A Foundation Model for Few-Shot Combination Drug Screening
UDT: Reconciling U-Nets and Diffusion Transformers with Data-Adaptive Token Reduction
PAIR-CI: Calibrated Conditional Independence Testing for Causal Discovery with Incomplete Data
On the Impact of Side-Information in Bandit Learning: More is Not Always Merrier
SAMPPO: Structure-Aware Mirror Proximal Policy Optimization
Fixed Universal Transformers
Lie Generator Networks for Nonlinear Partial Differential Equations
DRTriton: Large-Scale Synthetic Data Driven Reinforcement Learning for Triton Kernel Generation
Optimizing Retraining Schedules via Learning Curves
Coreset-Induced Conditional Velocity Flow Matching
Forward Shapley Scoring for Non-Myopic Active Feature Acquisition
Swimba: Switch Mamba Model Scales State Space Models
A Theory of Adversary-Directed Online Learning
High Entropy Regularization Leads to Symmetry Equivariant Policies in Dec-POMDPs
Early Signals, Strong Decisions: Prefix-Guided Sampling for Parallel Test-Time Scaling
What Fits (Into Few Tokens) Doesn't Overfit: Compression and Generalization in ML Research Agents
Proximal Difference-in-Differences for Long-Term Causal Learning under Confounding and Outcome Drift
Uniform-in-Time Weak Propagation of Chaos in Shallow Neural Networks
Generative OOD-regularized Model-based Policy Optimization
Diversity Maximization: Algorithms for Distant $k$-Subsets
ABC-Align: Prediction-Powered Alignment with Adaptive Bias Control
Spectral-Spatial Interpretation
Causal Concept Explanations for Deep Neural Models
Persistent-Transient Policy Evaluation for Markov Chains via Minimal Peripheral Quotients
Polynomial-Time Robust Multiclass Linear Classification under Gaussian Marginals
Capturing LLM Capabilities via Evidence-Calibrated Query Clustering
Causal Discovery from Unseen Environments
Testable Learning of General Halfspaces under Massart Noise
Borda-Based Fair Multi-User Dueling Bandit in Tabular and Generalized Linear Settings
Near-optimal Explainable $k$-means Clustering under $\ell_p$ Norm
Learning Orthogonal Multi-Index Models Beyond Small Initialization: Incremental Learning, Competitive Dynamics and Symmetry
Do Robust LVLMs Hallucinate More? Uncovering Robustness-Induced Hallucination in Large Vision-Language Models
Neural Modal Decomposition: Architectural Priors from Observables
Concept-Localized Generative Representations
Risk-Calibrated Context Selection for Healthcare Multi-Agent Handoff
Reasoning with Sampling: Cutting at Decision Points
Learning Rate Transfer in Normalized Transformers
Learn Locally, Recurse Globally: Neural Circuit Synthesis Beyond Training Depth
Inference and Uncertainty Quantification for Streaming $r$-PCA
Approximate Matrix–Vectors Under a Bounded $\ell_1$ Assumption and Applications to Kernel Matrices
CVTA: Cross-Variable Temporal Attention for Multivariate Irregular Time Series Prediction
Beyond Confidence: Rethinking Self-Assessments for Performance Prediction in LLMs
PEEK: Context Map as an Orientation Cache for Long-Context LLM Agents
Comparing Transformers and Hybrid Models at the Token Level
Online Change-point Detection using Foundation Probabilistic Forecasting Models
TailGuard: Subgroup Tail Coverage Theory for Safe LLM Alignment
Sparse Attention as a Range Searching Problem: Towards an Inference-Efficient Index for KV Cache
Attention Is More Than You Need: Spectral Redundancy in Multi-Head Routing
Express Language Modeling
Nearly Optimal Attention Coresets
HEED: Density-Weighted Residual Alignment for Hybrid Vision-Language Model Distillation
LatentRouter: Can We Choose the Right Multimodal Model Before Seeing Its Answer?
RECIPE: Procedural Planning via Grounding in Instructional Video
Hypothesis generation and updating in large language models
Language Models Need Sleep
Intra-Option Fitted Q-Evaluation: Evaluating Hierarchical Policies from Non-Hierarchical Data
GLOBE: Accurate Surrogates for Boundary-Driven PDEs via Domain-Inspired Architectures and Equivariance
The Stability of Data Exchange in Competitive Markets
Finite-Memory Control of POMDPs: Fundamental Limits and Efficient Design
When Are Semivalue-Based Decisions Identifiable? Robust Data Selection under Utility Ambiguity
Rethinking Language Model Scaling under Transferable Hypersphere Optimization
AI-Assisted Classification under Correlation Neglect and Trust
Safe Score Matching: Diffusion Policies with Hamilton-Jacobi Reachability for Online Safe Reinforcement Learning
Do Thinking Tokens Help with Safety?
High Probability Risk Control for Online Policy Learning
Adaptive Calibration in Non-Stationary Environments
SGD Provably Prioritizes a Shortcut Spurious Feature in the XOR Model
Foundation Models for Particle Accelerators
Understanding Private Evolution as Learning-Augmented Clustering
One-Shot Private Confidence Regions via Resampling
MoMHa: Multi-Objective Optimization of LLM Harnesses over Accuracy, Safety, and Tokens
NitroBox: Lightning-Fast Sandbox for Large-Scale RL Training
Reading Positional Coupling in Transformers with Diffusion Scores
Curvature Beyond Positivity: Greedy Guarantees for Arbitrary Submodular Functions
Even Sharper Bounds for Transductive Learning and Its Applications
Smoothed Score Queries and the Complexity of Sampling
Local linear convergence of gradient methods for overparameterized Gaussian mixtures
Train on the Sphere, Deploy on the Hill: Closed-Form-Anchored Surrogates for Real-Terrain Boundary-Integral Equations
A Refined Sample-Complexity Analysis of Robust Policy Optimization under Decaying Actor Stepsizes
CAST: Causal Anchored Simplex Transport for Distribution-Valued Time Series
Neural Dual Bounds: Valid-by-Construction JGLP Warm-Starts for MAP and Constrained MAP
TriSearch: Learning to Optimize Triangulations via Bistellar Flips
Flash-SD-KDE: Accelerating SD-KDE with Tensor Cores
Default Feature Representations of the Cognitive Map
Amortized Vine Copulas for High-Dimensional Density and Information Estimation
Move on Muon : A Hamiltonian probability gradient flow perspective of Muon optimizer
Closing the Reflection Gap: A Free Calibration Bonus for Agentic RL
Sinkhorn Based Associative Memory Retrieval Using Spherical Hellinger Kantorovich Dynamics
Base Items Overfit, New Items Underfit: Hidden Cost of Joint Training in Incremental Adaptation
Measuring Safety Alignment Effects in Autonomous Security Agents
Information-Geometric Forward Policy Training in GFlowNets
Urgency-Aware Autoregressive VLMs for Unanticipated Healthcare Occurrences
Why Muon Outperforms Adam: A Curvature Perspective
Tesserae and MoDiCo: A Billion-Fragment Dataset and Multi-Branch Architecture for File Fragment Classification
SASA: Subspace-Aware Sparse Autoencoders for Effective Mechanistic Interpretability
Emergence, Retention and Mitigation of Ill-conditioning due to Basis Lifting in KANs
ProjKAN: Model Compression via KAN Projections to Bridge the Hypothesis and Capacity Gaps
RADAR: Text-Guided Medical Image Segmentation via Residual Aggregation and Dense Alignment Representations
Leviathan: Decoupling Input and Output Representations in Language Models
From Likelihood Convergence to Parameter Convergence in POMDPs
SiliciclasticReservoirs: A Million-Reservoir Dataset and Flow-Matching Foundation Model for 3D Siliciclastic Reservoir Generation
Learning Process Rewards via Visitation Matching for Efficient RL
Calibration without labels in multiple testing
Spectral Graph Sparsification Preserves Representation Geometry in Graph Neural Networks
FedCF: Fair Federated Conformal Prediction
Shellsort as Multi-Scale Relaxation: Learning Spectrum-Matched Gap Schedules
What Sound Tells You About the Room
What Makes a Good Path? Factoring Manifold Support and Path Geometry
From Heartbeat to Cardiochoreography: A Mechanics Foundation Model for Individualized 4D Cardiac Motion Generation Conditioned on Electrophysiology
MiCo: Microstructure-Consistent Flow Matching for Diffusion MRI Angular Super-Resolution
Vibe-Spike: An Energy-Preserving EEG Foundation Model Through the Landscape of Neural Coherence
Training-Free Active Test-Time Adaptation for Vision-Language Models
CurveBench: A Benchmark for Exact Topological Reasoning over Nested Jordan Curves
Amortized Bayesian Experimental Design with In-Context Knowledge Conditioning
Control Reinforcement Learning: Token-Level Mechanistic Analysis via Learned SAE Feature Steering
Automata from Agent Traces: Failure and Next-Step Prediction
In-Context Black-Box Optimization with Unreliable Feedback
Concise and Logically Consistent Conformal Sets for Neuro-Symbolic Concept-Based Models
Concepts Worth Having: Refining VLM-Guided Concept Bottleneck Models with Minimal Annotations
Divide et Calibra: Multiclass Local Calibration via Vector Quantization
Frequency Domain Reservoir Computing
Long-Range Spatio-Temporal Graph Propagation Through Oscillations
Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning
Spherical Boltzmann machines: a solvable theory of learning and generation in energy-based models
When to Align, When to Predict: A Phase Diagram for Multimodal Learning
ADAPT: Hybrid Prompt Optimization for LLM Feature Visualization
SemanticDLM+: Improving Diffusion LLMs through Bias-variance Trade-off in Transition Kernel Design
Probabilistic Data-Driven Modelling of Astrophysical Transients: The Neural Process Family for Ultrafast and Class-Agnostic Light Curve Reconstruction
Tracing Actual Causes with Counterfactual Witness Maps
xWhy: Causal Learning from Explanations
Generating Financial Time Series by Matching Random Convolutional Features
Taking Low-Rank LLM Compression a Step Further: A Global Perspective with Fused Inference
Privacy Amplification Persists under Unlimited Synthetic Data Release
Generalizing the Geometry of Model Merging Through Fréchet Averages
RigRecon: Efficient Rig-Aware Street Reconstruction via Dual-Path Spatio-Temporal Interaction
On the Complexity of Preference-Based Bandits
On the Robustness of Watermarking for Autoregressive Image Generation
OWCE: Revealing Language Model Complementarity via Online Weakness-Conditioned Evaluation
$\delta$-Mem: : Efficient Online Memory For Large Language Models
Fast Learning Rates for Physics-Informed Kernel Methods
Decomposing One Professional-Framing Pipeline: Which Components Shift LLM Safety Boundaries?
Expected Batch Optimal Transport Plans and Consequences for Flow Matching
Decoupled Mode Connectivity for Base-to-Novel Generalization in Vision-Language Models
To Align or Not To Align: Check Your COMPASS Before You Train
CENDRe: Concept Extraction with Natural Domain Representations
AI Behavioral Evaluation Should Be Grounded in Psychophysics Across Marr’s Levels
STAC-R: Subspace-Tracked Activation Compression with Residuals
Learning to Undo: Transfer Reinforcement Learning under State Space Transformations
From Uncertain Judgments to Calibrated Rankings: Conformal Elo Estimation for LLM Evaluation
Half-Truths Break Similarity-Based Retrieval
Dynamic Video Generation: Shaping Video Generation Across Time and Space
Meta-Learning Preferences for Multilingual LLM Alignment
Consistent 3D Surface Flow Model with Global State
TIDE: Asymmetric Neural Circuits for Stabilized Temporal Inhibitory-Excitatory Dynamics
Rotations on Latent Hyperspheres: a Geometry-Aware Guiding Framework for Diffusion Models
Private Prediction via Shrinkage
An Õptimal Differentially Private PAC Learner for Concept Classes with VC Dimension 1
Routing Subspaces: Auditing Evaluation-to-Deployment Mismatch in Fine-Tuned Language Models
Stochastic Matching via Local Sparsification
Membership Inference on Synthetic Single-Cell Genomic Data
Space-Aware World Models: Spatial Persistence Through Factored Scene Representations
Outcome-Based RL Provably Leads Transformers to Reason, but Only With the Right Data
Batched Stochastic Linear Bandits with 1-Bit Communication Constraints
On Generation in Metric Spaces
Why Decoding Sharpens Without Resolving: Lock-in and Confusion in Autoregressive Reasoning
Scheming Is a Symptom: Alignment Research Should Probe Reflexive Fragility
Generative Object Detection with Co-Training
From Representation to Intervention: Using Emotion Vectors to Monitor and Guide Language Models
NOCE-Net: Representation Learning for Battery Operational Context via Nested Sequence Modelling
Auditing Attention Head Masking for Out-of-Distribution Detection: Cross-Architecture Wins, Failures, and Polarity Inversions
On Rate-Optimal Partitioning Classification from Observable and from Privatised Data
Flow-based Spectral Kernel Learning for Nonstationary Attention
AudioGS: High-Fidelity Neural Audio Compression via Continuous Gaussian Splatting
VISTA: Support-Anchored Value Targeting for Fast Flow-Based Vision-Language-Action Policies
ForesightFlow: Self-Guided Flow Matching for Improving Vision-Language-Action Models
Weight Space Learning needs to unify benchmarking! A taxonomy of evaluation practices
Itô maps for any-step SDEs
Generative Modeling under Non-Monotone MAR Missingness via Approximate Wasserstein Gradient Flows
Benchmarking sequence-to-ensemble predictors on UNICORNEdb, a UniProt-grouped database of PDB-derived conformational ensembles
Hyperparameter Transfer for Dense Associative Memories
The Sign Code: The Hidden Binary Nature of Deep Networks
Generating Symmetric Materials using Latent Flow Matching
Surjective Pseudo-Invertible Neural Networks
Coherent Hierarchical Multi-Label Learning to Defer for Medical Imaging
Replay-buffer engineering for noise-robust quantum circuit optimization
From Anti-Forgetting to Fast Adaptation: Continual Reinforcement Learning with World Models
DynaProto: Dynamic Prototypical Contrast for Temporally Consistent Object-Centric Learning
Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs
Efficient Image Synthesis with Sphere Latent Encoder
TIDES: Implicit Time-Awareness in Selective State Space Models
ConfDet: Learning Reliable Confidence for MLLM-based Detection
WORD: Diffusion-Based Posterior Inference for Online Goal Recognition
Accelerating Long-Context LLM Prefill via Layer-wise Progressive Token Pruning in Local Deployment
Propagate to Discover: Graph-Structured Propagation for Generalized Category Discovery
Beyond Worst-Case Coreset Bounds for $k$-Clustering via Determinantal Sampling
Continuous-Time Distribution Matching for Few-Step Diffusion Distillation
On the Pitfalls of Instance-Based Dynamic Curricula
Scaling Genomic Language Modeling with Unified Corpus and Evaluation in Bacteria
Rethinking Layer-wise Model Merging through Chain of Merges
Effective Context in Transformers: An Analysis of Fragmentation and Tokenization
Optimizing Social Utility in Sequential Experiments
Learning to Decide with AI Assistance under Human-Alignment
Test-Time Compute Games
Externalized CPDAG Summaries Improve LLM Causal Deduction
Models That Know How Evaluations Are Designed Score Safer
OpenWhistle: A Large-Scale Longitudinal Dataset and Benchmark of Bottlenose Dolphin Vocalizations
Plan4D: Generative Plannable 4D Worlds
Articraft: An Agentic System for Scalable Articulated 3D Asset Generation
Omni-SpikeDet: A Spiking Open-World Detector with Dynamic Text–Image Alignment
Evaluating and Understanding Scheming Propensity in LLM Agents
UniVR: Thinking in Visual Space for Unified Visual Reasoning
DP-EGGROLL: Centered Fitness-Vector Privatization for Backprop-Free Differentially Private Optimization
LLM-Enhanced Random Forests in Orthogonal Hyperbolic Subspaces for Tabular Learning
I Have a Stream: Making Self-Supervised Learning Work on Continuous Video
TropNNC: Structured Neural Network Compression Using Tropical Geometry
Robust Flow Matching under Target Corruption and Label Noise
Interpretable but Fragile? Robustness of Concept Bottlenecks under Geometric-Semantic Perturbations
Feature-Context Consistency: Unsupervised Adversarial Detection with Drift Stability on Attributed Graphs
STABLE: A Continual Learning Optimizer with Adaptive Drift Control
Few Channels Draw The Whole Picture: Revealing Massive Activations in Diffusion Transformers
The Smart Buildings Control Suite: A Diverse Open Source Benchmark to Evaluate and Scale HVAC Control Policies for Sustainability
Human-Inspired, Task-Dimension-Guided Exploration for Efficient Learning and Transfer in High Dimensions
It's All Training: A Fully Synthetic Single-Stage Recipe for LLMs
Beyond Masked Sparsity: SNACK Enables Truly Sparse Neural Networks on GPU
Heterogeneity-aware Distillation for Federated Continual Learning
Rehearsal-Free Statistical Prototype Regularization for Federated Incremental Learning
Personalized Safety in Federated Fine-Tuning of Large Language Models
FedTrace: Generated-Content-Based Watermark Verification for Traitor Tracing in Federated Learning
Avoiding Feature Collapse in Graph ODEs via Hysteretic Topology Evolution
DAG-Biased Graph Learning for Multimodal Survival on EHR
V-GIFT: Boosting Visual Instruction Tuning with Self-Supervised Guidance
Geometry-Aware Directional Alignment for Coherent Model Merging
Towards Understanding and Measuring Cognitive Atrophy in LLM Behaviour
Solaris: Building a Multiplayer Video World Model in Minecraft
UniverSat: Resolution- and Modality-Agnostic Transformers for Earth Observation
Who Needs Labels? Adapting Vision Foundation Models With the Metadata You Already Have
ORBIT: A Framework for Multi-Agent Security Evaluations
AdaCubic: An Adaptive Cubic Regularization Optimizer for Deep Learning
Target-Aligned Reinforcement Learning
Derivative-Informed Training of Neural Operators On-the-Fly via Sketched Tangent Consistency
No-Regret Caching with Delayed Hits
Improving Causal Explanations
Momentum Smooths the Path to Gradient Equilibrium
Automatic Textbook Formalization
Distilling LLM Feedback for Lean Theorem Proving
Position: AI Efficiency Gains Must Be Quantitatively Evaluated Against Rebound Effects
BLANP: Memory-Efficient Backpropagation-Free Local Training via Antithetic Node Perturbation
A Revisit of Hamiltonian Monte Carlo Efficiency on Bayesian Neural Networks
Anatomy-Activated Mixture-of-Experts for 3D Medical Vision-Language Pre-training
MID: Mask-Image Distributional Divergence for Evaluating Medical Image Segmentation
OTEdit: Entropic Transport Corrected Trajectory for Inversion-Free Flow-Based Image Editing
COVD: Continual Open-Vocabulary Object Detection with Novel Concept Injection
Geometric Inductive Biases for Semi-Supervised Equalization: The Constellation-Aware Transformer
M4Bench: Evaluating Procedural Specification for Clinical EHR Derivation Agents
When Attention Collapses: Residual Evidence Modeling for Compositional Inference
Binding Multiple Modalities via Multimodal Wasserstein Barycenter
Causal Gradient Steering: Exposing Shortcut Gradients by Destroying Causal Signal
Doomed to Re-Annotate, Forever: The ImageNet Story
FedProG: Federated Graph Learning via Server-Side LLM Semantic Bridging and Uncertainty-Aware Distillation
SyncLight: Single-Edit Multi-View Relighting
SR-GRPO: Stable Rank as an Intrinsic Geometric Reward for Large Language Model Alignment
Principia: Relational Physics Tests for Video Models
Crowded in B-Space: Calibrating Shared Directions for LoRA Merging
Thinking in Boxes: 3D Editing in Real Images Made Easy
Auditing is not Evaluating: LLM Audit Requires Dynamic, Contextual, Budget-aware and Reliable Evidence
DynaPFN: Zero-Shot Dynamical System Forecasting with Tabular Prior-Fitted Networks
EENAS: Zero-Shot Energy-Efficiency-Aware Neural Architecture Search
TabK: Amortized Bayesian Estimation of the Number of Clusters in Tabular Data
Improved Baselines with Representation Autoencoders
Restoring the RNA-Ligand Interaction Manifold via Topology-Preserving Contrastive Learning under Epistemic Uncertainty
Lost or Hidden? A Concept-Level Forgetting in Supervised Continual Learning
Learning Compositional Latent Structure with Vector Networks
DiDE: Direct Injection with Color-Texture DEcoupling for 3D Stylization
Surprisingly consistent failures of post-hoc OOD detectors reveal security concerns in open-set recognition with modern CNNs and ViTs, stemming from representation mismatch
Endowing Your Vision-Language-Action Model with a Predictive Mind
The Long-Run Distribution of Regularized Learning in Non-Concave Games: A Large Deviations Approach
Fast and Stable Triangular Inversion for Delta-Rule Linear Transformers
Self-Improvement Imitation with Biologically Guided Search for Protein Design Under Oracle Budgets
Temporal-Scale Sensitivity in Time-Series Tokenization and Scale-Robust Token Estimation by Gated Sum
THEIA: A Multimodal Dataset and Benchmark for Vision-Language Analysis of Layout
Detecting RLVR Training Data via Structural Convergence of Reasoning
From Structural Feedback to Prompt Policies: Learning Faithful Text-to-Image Prompt Editors
MAPS: Margin-Aware Priors and Verifier-Guided Search for Embodied Planning
Adaptive Robust Estimator for Policy Optimization in Reinforcement Learning
Heterogeneous Agent Collaborative Reinforcement Learning
On the Bias of Group-Based Advantage Estimation
SEGA: Spectral-Energy Guided Attention for Resolution Extrapolation in Diffusion Transformers
CRISP: Fixing Flying Pixels in Latent LiDAR Generation via Diffusion Decoding
Focused Forcing: Content-Aware Per-Frame KV Selection for Efficient Autoregressive Video Diffusion
Resource-Aware Parameter-Efficient Model Adaptation for Onboard High-Dimensional Data
Adaptive Scheduling Pipeline For Multi-Instance Asynchronous Reinforcement Learning
$\text{A}^3$-VLA: Automatic Perception-Guided Attention Alignment for Robot Manipulation
Federated Dataset Simulation: Inducing Label-Free Heterogeneity Across Tasks
StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs
MemReg: Streaming Outdoor LiDAR Point Cloud Registration with Hybrid Memory Buffers
Marginal-Nonuniform Multiclass Learning
Generalized Adaptive Boosting and the Geometry of Mistakes
Speeding up Log-Sum-Exp: Kernel Fusion at the Memory Wall, Integer Arithmetic at the Compute Wall
NAMVIS: Next-Scale Autoregressive Multi-View Image Synthesis
Topological Periodicity Test (TopPT) via Confidence Bound of Time-Delay Embeddings
Multimodal Foundation Agents Should Use Brain Data as Privileged Supervision
BESS-Bench: Benchmarking Spectral Representations for Be-Star Variability
PieArena: Ranking and Profiling Language Agents in Realistic Negotiation Scenarios
Comparing Explanations is not Enough,Explain the Change: New Standards are Needed to Explain Behavioral Shifts in Large Language Models
HumanStereo: A Benchmark for Metric Facial Depth Estimation and Its Evaluation
Position: Let’s Strengthen Verifiability if We Can’t Enforce Reproducibility
A Theoretical Bridge Between Long-Tailed Recognition and Continual Learning
OpenMedReason: Scientific Reasoning Supervision for Medical Vision–Language Models
TrialAgentBench: Evaluating AI Agents for Clinical-Trial Analysis and Long-Horizon Drug-Development Decisions
Participatory ML for Social Harm Should be Constructed, Validated and Reasoned Through First-Person Accounts
Can an LLM Reason Like a Lawyer? Benchmarking the ability of LLMs to map the facts of a case to the elements of the applicable legal rule
Liars' Bench: Evaluating Lie Detectors for Language Models
AIs with Secret Loyalties are a Serious but Addressable Threat
Gender Artifacts from Art History to Text-to-Image Generation
Seahorse: A Unified Benchmarking Framework for Spatiotemporal Event Modeling
Not Another Text Benchmark: Putting the “Visual" Back in Visual Question Answering for Large Video Models
Understanding diffusion models requires rethinking (again) generalization
We Need to Rethink Benchmarking in Anomaly Detection
Claims of AI emergence should be grounded in information decomposition
FineVision: Open Data Is All You Need
AmaraSpatial-10K: A Spatially and Semantically Aligned 3D Dataset for Spatial Computing and Embodied AI
TerraMesh-Masks: Open‑Vocabulary Segmentation for Earth Observation
TabPrep: Closing the Feature Engineering Gap in Tabular Benchmarks
Robot Demonstration Videos Should Include Transparency Disclosures
BraveATA: Benchmarking Broad and Verifiable End-to-End Automated Theoretical Analysis of Large Language Models
Approximate Envy-Free Allocations up to any k Goods
Measuring Cross-Modal Synergy: A Benchmark for VLM Explainability
SLVMBench: Skill Learning from Video Memory
LSC-Parlament: An Automatically Aligned Catalan Sign Language Dataset from Parliament Videos.
The Agentic Oversight Tax: Human Supervision of AI Agents Has a Cost that Must be Accounted For
REFORM-3D: A Representation-Centric Evaluation Framework for 3D Medical Vision Foundation Models
Position: The Road to Generalizable Neuro-Symbolic Learning Should be Paved with Foundation Models
Position: Fair Representations Cannot Hold What They Promise
Aligning Language Model Benchmarks with Pairwise Preferences
Decentralized AI Governance Must Decouple Policy Processing from Capability Enforcement
Large language models can not and should not be banned from peer review
Markov Metrical Task Systems
Position: Lottery Tickets Do Not Explain Overparameterization. How About Escape Dimensions?
Peer Review of Applied Machine Learning Papers Must Include Code Execution
StemBind: When MLLMs Get Lost Between Rules and Instances in Abstract Visual Reasoning
DriveHierarchy: A Benchmark for Diagnosing VLM Driving Capabilities from Open-Loop Understanding to Closed-Loop Execution
MINEGRID: A Multi-Modal Benchmark for LLMs Evaluation on Dynamic Modeling of Power Systems
A New Perspective on XAI: Scientific Theory Building for Auditable Artefacts
RASS: Risk-Audited Budget Selection for Compact NeRF Benchmark Subsets
Mouse Total Capture: A multi-view Dataset for 3D Motion and Expression Capture of Freely Moving Mouse
We Need to Improve Benchmarks in AI for Mathematics
Toward Embodied World Agents via Embodied-Planning Dataset and Interactive World Models
AI-Generated Content Should Be Evaluated by Its Substance, Not Its Source
Hidden Positives: Why Code Retrieval Benchmarks Underestimate Model Quality
Exploration as Constrained Policy-Space Optimization
Safe Offline Reinforcement Learning using Behavior Regularisation and Latent Feasibility-Guidance
Mesh Invaiant Infinite Dimensional Adaptive MCMC for Latent Gaussian Processes
Trust Guided Decision Transformer
Markovian Dynamics Enforcer: Feasibility Preserving Correction on Learned Dyanmics Manifolds
Progressive Signal Calibration for Medical Image Segmentation: Diagnosing and Correcting Structural Misalignment in Training Signals
Dynamics of Collective Diversity in Human–AI Co-Creation for Creative Tasks
FocusNav: Learning Task-directed Perception via Action-Aware Future Reconstruction in Vision-and-Language Navigation
Boundary-Induced Forgetting in Large Language Model Tool Chains: Measuring Field-Routing Failures
Parametric Meets Non-parametric: Bridging Dual Prediction Spaces for Semi-supervised Medical Image Segmentation
Payoff-Only Learning in Games via Best-Response Differential Inclusions
Atoms and Pivot Based Correlation Clustering
Accuracy of Noise Ceiling Estimators for Brain Scores
Contextual Flow Matching: Adaptive Step Selection in Flow Models for Efficient Visual Generation
HARP: Training-Free Dual-Profile Agentic Communication for LLM-Based Recommendation
The Constitutional Coverage Trilemma in AI Governance
SP$^3$: Spherical Priors for Plug-and-Play Restoration
A Quantitative Visual Taxonomy of Worldwide Writing Systems
SetAD: Semi-Supervised Anomaly Learning in Contextual Sets
How Should Parallel Langevin Chains Share Noise?
ContextShift: A Controlled Benchmark for Context Dependence in Object Detection
FFTSparse: Relative-Position Correlation Guided Sparse Attention for Long-Context Language Models
Retrieve-then-Rerank Inference for Vocabulary-Based End-to-End Driving
Token-to-Token Alignment of Text Embeddings for Semantic Blending
Transporting the Past: An Optimal Transport View of Backtracking Counterfactuals
Langevin-Informed Transfer Learning: Replacing the Target Samples by Black-Box Feedback
BLADE: Scalable Bi-level Adaptive Data Selection for LLM Training
GridDiffuser: Constraint-Guided Graph Diffusion for AC Optimal Power Flow
GeoCurv-TTT: Geometry-Aware Deformation Restoration for 3D Test-Time Training
Virtual Double Oracle: Faster Convergence by Leveraging Strategies That Were Watching All Along
Curriculum Multiple Shooting for Robust Training of Neural and Universal Differential Equations
The Sampling Complexity of Condorcet Winner Identification in Dueling Bandits
Implicit-Euler Value Iteration: Long-Horizon Planning via Stable Integration of the Bellman Residual Flow
FiLM-CAM: Keyed Feature Modulation for Conditional-Access Watermarking
The Sample Complexity of Multiple Change Point Identification under Bandit Feedback
Consistent One-vs-All Losses Robust to Misspecification of the Weak Label Transition Model
Adaptive Multi-view Graph Contrastive Learning via Fractional Continuous Dynamics
Feedback Forensics: A Toolkit to Measure AI Personality
Exponential Map Models as an Interpretable Framework for Generating Neural Spatial Representations
How to Train Your Latent Diffusion Language Model Jointly With the Latent Space
P-EAGLE: Parallel-Drafting EAGLE with Scalable Training
NicheIB: Targeted Spatial Bottlenecks for Predictive Microenvironment Discovery
Follow the Winners: Conservative Policy Improvement with the Cross-Entropy Method for Critic-Free RFT
Dense Cross-Tokenizer Distillation via Semantic Optimal Local Alignment
The PFAD Not Taken: Measuring Polysemanticity via Feature Affine Decomposition
Entropy-Gated Latent Recursion
On Differentially Private Mechanisms for Linear Regression
DC-DiT: Adaptive Compute and Elastic Inference for Visual Generation via Dynamic Chunking
Dynamic Optimistic Constrained OCO with Memory via Delay Equivalence
Semantic Priors Meet Statistical Evidence: Robust Forests for Few-Shot Tabular Learning
Coherence Mechanisms for Provable Self-Improvement
Performative Prediction with Selective Labels
Early Detection of Backbone Divergence via Neighborhood Structure in Learned Embeddings
Unifying Goal-Conditioned RL and Unsupervised Skill Learning via Control-Maximization
Image Generation for Automotive Lidar Open-vocabulary Semantic Segmentation
Playing Markov Games Without Observing Payoffs
Constraint Retrieval Is Not Constraint Enforcement in Large Language Models
FIVE-VLA: Fast and EffectIVE Closed-Loop Autonomous Driving with Recurrent Action Memory
LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments
Nonparametric Distribution Matching for Self-Supervised Whole-Slide Image Condensation
Factorized Self-Supervised Speech Tokenization
Multi-Environment POMDPs with Finite-Horizon Objectives
Proteus: Incremental Memory Activation for Long-Context Sequence Modeling
CoRDS: Coreset-Based Representative and Diverse Selection for Streaming Video Understanding
Skip the Hessian, Keep the Rates: Globalized Semismooth Newton with Lazy Hessian Updates
Robust and Scalable Collaborative Learning via Pull-Based Epidemic Communication
Routers Learn the Geometry of Their Experts: Geometric Coupling in Sparse Mixture-of-Experts
MIND: Monge Inception Distance for Generative Models Evaluation
Spectral Alignment in Forward–Backward Representations via Temporal Abstraction
A Unified Perturbation Framework for Analyzing Leaderboard Stability and Manipulation
GitInject: Real-World Prompt Injection Attacks in AI-Powered CI/CD Pipelines
Assessing Per-Sample Membership Inference Vulnerability without Retraining
K-prop: Deep Online Learning by Backpropagating Temporal Kernels
The limbic navigation system as a hierarchical RNN
WaveMamba: Wave-Inspired Cross-Modal Fusion for Robust event-image Semantic Segmentation
Beyond the Golden Teacher: Enhancing Graph Learning through LLM-GNN Co-teaching
PLLS-CP: Unsupervised Hallucination Detection with Layer Selection and Cross-Domain Conformal Guarantees
Joint Adaptive Neighborhood Constraint for Offline Multi-Agent Reinforcement Learning
Mechanistic Insights into LoRA: Layer Sparsity for Adaptive Fine-Tuning via Path Patching
OPERA: An Agent for Image Restoration with End-to-End Joint Planning–Execution Optimization
PRISM: Asymmetric Precision-Recall Optimization for Million-Scale Root Cause Analysis
Module-Aware Optimization for Graph Neural Networks
Annealing in variational inference mitigates mode collapse: a theoretical study on Gaussian mixtures
Neutral-atom quantum features as complementary structural encodings for graph learning
Dynamic Regret in Online Convex Optimization with Indicator Switching Costs
Conveyance: A Versatile Framework for Learning in Structured Class Spaces
Online Learning of Group-Stable Coalition Structures
Active Context Selection Improves Simple Regret in Contextual Bandits
How deep is your network? Deep vs. shallow learning of transfer operators
The Multi-Block DC Function Class: Theory, Algorithms, and Applications
Positional Encoding Is All You Need For Scalable Equivariance Constraint Relaxation
Mining Logic under Uncertainty: Probabilistic Soft Logic with Energy-Based Inference for Chain-of-Thought Verification
Fairness in limited resource prediction-driven decisions
Thinking with Visual Primitives
Uncovering Challenges of Solving the Continuous Gromov-Wasserstein Problem
Less is More: Fewer Tokens and Blocks Make AIGI Detection Faster and More Generalizable
idSCD: Identifying Training Datasets through Semantic Correlation Descriptors
Stop the Sampler! Classifier-Based Adaptive Stopping for Sampling Kernels
Unlocking Volition: Proactive Intention Decoding via Interpretable Graph Learning of Multi-Region ECoG
Length Generalization for Transformers via Compression
IDEAL: Interaction Dynamics and Force-Aware Learning for Dual-Humanoid Collaborative Manipulation
Eyes on VLM: Benchmarking Gaze Following and Social Gaze Prediction in Vision Language Models
The Geometry of Linear Program Compression: An Exact Characterization and Learning Algorithm
Hard Attention Transformers and BSS-Machines
Understanding Multi-View Transformers
The Causal Description Gap: Information-Theoretic Separations Across Pearl's Hierarchy
Gradient-Guided Smoothing for LLM Safety Defense
Learning to Search, Searching to Learn: A Closed-Loop Framework for Large-Scale Vehicle Routing
Logical Distillation of Transformer Encoders
i-DEQ: A stable inertial Deep Equilibrium model for image restoration
You Don’t Need Aligned Representations: Knowledge Distillation via Random Prototype Spaces
Discrete Diffusion Models Exploit Asymmetry to Solve Lookahead Planning Tasks
When Streaming Fails: Dynamic Algorithms for Unconstrained Submodular Maximization
Fast Gauss-Newton for Multiclass Cross-Entropy
Automatic Constraint Policy Optimization based on Continuous Constraint Interpolation Framework for Offline Reinforcement Learning
Pure Exploration Beyond Reward Feedback: The Role of Post-Action Context
Self-Evolving Agents Should Build Internal and External Models of the World
Inferotemporal Cortex Collaborates Before It Codes: Non-Serial Inter-Area Synergy in the Macaque Ventral Stream
CoLaX: Context-Aware Local Explanations for Time Series Classification
Optimal In-context Adaptivity and Distributional Robustness of Transformers
CryoGeo: Latent Pose Equivariance for Amortized Ab Initio Cryo-EM Reconstruction
HARC: Coupling Harmfulness and Refusal Capabilities for Robust Safety Alignment
MemPlan: Memory-Conditioned PDDL Planning for Partially Observable Text Environments
Towards High Semantic Fidelity: Hyperdimensional Symbolic Messages in Multi-Agent Communication
Controlling Temporal Pseudo-Label Marginals for Stable Online Test-Time Adaptation
Neuro-Inspired Inverse Learning for Planning and Control
Unlearning That Lasts: Utility-Preserving, Robust, and Almost Irreversible Forgetting in LLMs
End-to-End Verification of Neuro-symbolic Automata via Contrastive Logit-Gaps
Midpoint Generative Models
Unlocking the Duality between Flow and Field Matching
The Structural Bias of $\ell_2$-Regularized Cross-Entropy Heads in Class-Incremental Learning: Characterization, Limits, and a Gauge-Anchoring Fix
A Mahalanobis Margin \texorpdfstring{$\gamma_{\min}$}{gamma\_min} Bound on Task Confusion in Pretrained Class-Incremental Learning: From Infeasibility to Exponential Attenuation
Mitigating Saliency Collapse: Robust Saliency-Aware Long-Text Image-Text Alignment
Towards Identifying Dominant Low-Rank Subspaces in Zeroth-Order Fine-Tuning
Unifying Sparsity and Discreteness: One-Shot Pruning for Quantized LLMs via Discrete Optimization
Achieve Latency-Efficient Temporal-Coding Spiking LLMs via Discretization-Aware Conversion
ASTOR: Multi-Task Code Reinforcement Learning via Utility-Driven Coordination
Rethinking Latency Denial-of-Service: Attack the LLM Serving Framework, Not the Model
Amortized Linear-time Exact Shapley Value for Product-Kernel Methods
GT-HarmBench: Benchmarking AI Safety Risks Through the Lens of Game Theory
Safety Geometry Collapse in Multimodal LLMs and Adaptive Drift Correction
CECAR: Cache & Expert Co-Aware Routing Accelerates On-Device Inference of MoE LLMs
Dual-Pronged LoRA: Achieving Near-Zero Forgetting and High-Performance Adaptation for MLLMs
Listening to the Retriever: Perturbation-Sensitive Question Selection for Interactive Person Retrieval
Select-then-differentiate: Solving Bilevel Optimization with Manifold Lower-level Solution Sets
Direction-Aware Offline-to-Online Learning in Linear Contextual Bandits
The BatchNorm Illusion: Diagnosing Normalization Artifacts in Machine Unlearning Evaluation
Frank-Wolfe Beyond 1/t Convergence
Harnessing Accurate and Automatic Trend Detection in Data Streams via Tbps-Level Inference
BalCapRL : A Balanced Framework for RL-Based MLLM Image Captioning
Enhanced convergence guarantees of score-based generative models in $\mathcal{W}_2$-distance beyond log-concavity
Do Not Let Spikes Flip: Margin-Resculpted Learning for Robust Spiking Neural Networks
Attribution-Guided Exit Policy for Reliable Early-Exit Inference
OneSearch-V2: The Latent Reasoning Enhanced Self-distillation Generative Search Framework
SD-Search: Hindsight Self-Distillation for Search-Augmented Reasoning
ToS: Tree-of-Skill Reinforcement Learning driven by Behavior Tree for Long-Horizon Manipulation
Perception Without Engagement: Dissecting the Causal Discovery Deficit in LMMs
Mixture of Attribute-Aware Attention Experts for Fine-grained E-Commerce Composed Image Retrieval
Subset-Conditioned Boundary Compensation for Missing-Modality Multimodal Classification
Bian Que: An Agentic Framework with Flexible Skill Arrangement for Online System Operations
SP-CACW: Convergence-Aware Client Weighting for Selfish Personalized Learning
Normative Networks for Source Separation via Local Plasticity and Dendritic Computation
Complexity Aware Continuous Level of Details for Gaussian Splatting
MSR-3D: Multi-Mode Semantic Representation for Open-Vocabulary 3D Scene Understanding
Amortized Structured Stochastic Variational Inference for Gaussian Process Latent Variable Models
Geometric Alignment without Functional Equivalence: A Layer-wise Analysis of the Speech-Text Modality Gap
Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents
Rethinking Radar 3D Perception: Representation Learning from Raw Spectra
Distribution Free Fourier Sparsity Testing
Hierarchical Agglomerative Clustering via Relaxed Representatives
Ensemble Distributionally Robust Bayesian Optimisation
What are Key Factors for Updates in RL for LLM Reasoning?
UncertainGen: Scalable Uncertainty-Aware Representation Learning of DNA Sequences
Rethinking Expressivity and Efficiency in Test-Time Training
Scalable Distributed Stochastic Optimization via Bidirectional Compression: Beyond Pessimistic Limits
Overthinking as a Symptom of Knowledge Conflict: Understanding and Detecting LLM's Hallucinations in Retrieval-Augmented Question Answering
TAMEing the Open-World Personalization: Towards Open-Set Personalized MLLM Assistant
Active Learning for Gaussian Process Regression Under Self-Induced Boltzmann Weights
Uncertainty as an Underconstrained Axis in Lossy Compression
Test-Time Personalization: A Diagnostic Framework and Probabilistic Fix for Scaling Failures
Training-free Focus-Ambient Retention for Memory-Efficient Video Large Language Models
Mirror Descent Beyond Euclidean Stability: An Exponential Separation in Initialization Sensitivity
Plug-and-Play ADMM for Inverse Problems with Flow Matching Denoiser
Reviving the Discarded High-Resolution Feature for Transformer-Based Tiny Object Detection
Normalized Architectures are Natively 4-Bit
RoSA: Rotational Sparse Adaptation for Memory-Efficient Fine-Tuning
Learning Subspace-Preserving Sparse Attention Graphs from Heterogeneous Multiview Data
Geometry of Relaxed Fair Regression: A Unified Framework for Aware and Unaware Settings
Escaping the Curse of Dimensionality in One‑Step Flow-Based Generative Models
$\pi^2$: A Simple Framework for 2D-to-3D Registration
SOPO: Socratic Guided Policy Optimization for Span-Level Hallucination Detection
Towards Complementary Keypoint Detection via Mixture of Detectors
Parameterized Complexity of Stationarity Testing for Piecewise-Affine Functions and Shallow CNN Losses
Prune to Protect: Faster Training and Enhanced Privacy by Dynamic Data Pruning
Strategic PAC Learnability via Geometric Definability
Auteur: Language-Driven Cinematographic Framing for Human-Centric Video Generation
Fill the GAP: A Granular Alignment Paradigm for Visual Reasoning in Multimodal Large Language Models
World Models as Adversaries: Multi-Agent Self-Play Fine-Tuning for Robust Motion Planning
ChainSpace: A Chained-Reasoning Paradigm for Spatial Intelligence
KINDER: Kernel-based Independence for Fair Representation Learning via Prototype-space Erasure
Retrieval from Within: An Intrinsic Capability of Attention-Based Models
OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence
Geometry-Guided Semantic Reconstruction for 3D Instance Segmentation
GeoDial: A Multimodal Dialog Tutoring Dataset for Geometry Problem-Solving with Visual Tutor Turns
Referring and Reasoning Camouflaged Object Segmentation in Audio-Visual Scenes
Towards Understanding Self-Pretraining for Sequence Classification
Is Text All You Need? Text as a Universal Information Bottleneck for Speech LLMs
Beyond Pixel-wise Supervision: Local Structure Regularization for Semantic Segmentation
Predictive Geometry of Hidden Trajectories in Transformers
FacePhys: State of the Heart Learning
Where to Look Matters: Rethinking Sub-Volume Sampling in 3D Medical Self-supervised Learning
QGround: Condition-Wise Evidence Aggregation for 3D Grounding with 2D VLMs
Fast, Relaxation‑ and Hyperparameter‑Free Pairwise Worst-Case Class Separation
Exact Combinatorial Optimization for Partial Permutation Synchronization
GeoX: Mastering Geospatial Reasoning Through Self-Play and Verifiable Rewards
RayTun3R: Online Camera Adaptation in 3D Foundation Models
The Hidden Power of Scaling Factor in LoRA Optimization
PDHFormer: Progressive Dual-Head Transformer for Behavioral Choice Prediction
Harnessing Textual Refusal Directions for Multimodal Safety
Bug or Feature$^2$: Weight Drift, Activation Sparsity, and Spikes
Identifiable alignment of unpaired representations
Prior as Geometry, Not Generator: Weak-Diffusion Test-Time Reconstruction for Dynamic MRI
Market-Based Runtime Resource Allocation for LLM Multi-Agent Systems
Reflected Schrödinger Bridge Matching
Anchor PCA
AIRA 2: Overcoming Bottlenecks in AI Research Agents
Pattern-Based Matrix Analysis Under Permutations
Exact Regular-Constrained Sampling for Variable-Order Markov Generation
APM: Evaluating Style Personalization in LLMs with Arbitrary Preference Mappings
ThousandWorlds: A benchmark for climate emulation of potentially habitable exoplanets
An Open-Source Training Dataset for Foundation Models for Black-box Optimization
CompleteRXN: Toward Completing Open Chemical Reaction Databases
JAXtari: High-Throughput and Easy-to-Modify Arcade Learning Environment
Perception for Action in Latent World Models
Emergence of Distortions in High-Dimensional Guided Diffusion Models
Unrolled gradients in disguise: bridging interpolation-based and Jacobian regularization for stable neural dynamics
Training a Predictive Coding Network on ImageNet using Equilibrium Propagation
Lifting Biomolecular Data Acquisition
Mirror descent actor-critic methods for entropy regularised MDPs in general spaces: stability and convergence
GPU-Accelerated Synthesis of Mixed-Boolean Arithmetic: Beyond Caching
Macrocanonical Generator Networks: data-efficient neural surrogates for amortized physics simulation
Space Group Conditional Flow Matching
Hypernetworks for Dynamic Feature Selection
One View Is Enough: In-the-Wild Monocular Pretraining for Novel View Generation
Predicting directional flexibility in proteins
Wavelet Flow Matching for Multi-Scale Physics Emulation
Selectivity and Shape in the Design of Forward-Forward Goodness Functions
What DNA Foundation Models Learn Beyond Sequence Composition
Long-Rollout Stability in AI Weather Models: A Quantitative Benchmark and Analysis
AM-Bench: A Unified Taxonomy and Evaluation Suite for Agentic Misalignment
HelpBench: Assessing the Ability of LLMs to Provide Privacy, Safety, and Security Advice
GeoBiaset: A Counterfactual Benchmark for Demographic Bias in World-Level Geolocalization
RamanBench: A Large-Scale Benchmark for Machine Learning on Raman Spectroscopy
Fast Alignment of Embeddings: Computational Guarantees for Anisotropic Procrustes-Wasserstein
Does Seeing More Mean Knowing More? Mono-Anchored Advantage Normalization for Multi-Source Visual Reasoning
Very Fast Bayesian Additive Regression Trees on GPU
A Grid Efficient Transport Optimization Model for the Wasserstein Barycenter Problem
Towards Convergence of PPO: An Approximate Descent Approach
From sequences to schemas: low-rank recurrent dynamics underlie abstract relational representations
MAGE: Towards Generalizable Multi-timescale EEG Representations
Learning interpretable Schur forms of recurrent weight matrices
PE-SHAP: Causally Interpretable Path-Wise Shapley Explanations
The Grounding Gap: How LLMs Anchor the Meaning of Abstract Concepts Differently from Humans
The Algorithm Is Not the Behavior: Learned Priors Override Look-Ahead in a Chess-Playing Neural Network
AI Agents May Always Fall for Prompt Injections
What to Predict for Efficient Scheduling on Parallel Machines
NashDreamer: Model-Based Reinforcement Learning for Zero-Sum Imperfect-Information Games
A Unified Framework for Uniform-Price Resource Allocation Mechanisms
Primal-Dual Guided Decoding for Constrained Discrete Diffusion
Decision-Aware Proximal Bridge Learning for Optimal Treatment Selection
Causal pieces: analysing and improving spiking neural networks piece by piece
Understanding the Co-evolutionary Solution Exchange of the MOEA/D: Minimal Communication Gives Maximal Speed-Ups
Compute-Optimal Pretrain--Fine-tune in Ridge Gradient Flow
Mind the Heads: Topological Representation Alignment for Multimodal LLMs
Certified Single-Level Reformulation for Tri-Level Cyber-Physical Grid Security
NEAT: Neighborhood-Guided, Efficient, Autoregressive Set Transformer for 3D Molecular Generation
Replicable Constrained Bandits
Similarity-Constrained Reweighting for Complex Query Answering on Knowledge Graphs
A Separation Principle for Cooperative Multi-Agent Reinforcement Learning
Dimension-Uniform Discretization Analysis of Preconditioned Annealed Langevin Dynamics for Multimodal Gaussian Mixtures
Energy-Guided Transport for Projection-Free Physics-Informed Flow Matching
Monitoring Violations of Differential Privacy over Time
High-Probability Minimax Adaptive Estimation in Besov Spaces via Online-to-Batch
Learning-Augmented Coordination Mechanisms
Efficient Generative Transformer Operators for Million-Point PDEs
Neural Fractional Stochastic Differential Equations
TurtLES: A Large-Scale Benchmark for Turbulent 3D Neural PDE Surrogates
TORNADO: Adaptive Latent Stochastic Transport for Calibrated Probabilistic PDE Forecasting
Implicit Bias of Mirror Flow in Homogeneous Neural Networks: Sparse and Dense Feature Learning
Terminal Failure Is Not Computational Failure: A Pre-Collapse Readout Regime in Nonlinear Dynamical Learners
Towards instance-dependent regret optimality in Episodic MDPs with Posterior Sampling
Within-Model vs Between-Prompt Variability in Large Language Models for Creative Tasks
Optimal algorithmic complexity of inference in quantum kernel methods
Entropy Minimization without Model Collapse: Mitigating Prediction Bias in Medical Imaging
A dynamical systems theory of reward-modulated learning in linear recurrent networks
OrthoReg: Orthogonal Regularization for Hybrid Symbolic-Neural Dynamical Systems
Residual Expertise Is Not Decision Value
Fast Wasserstein rates for estimating probability distributions of probabilistic graphical models
Graph Distance Based on Cause-Effect Estimands with Latents
Conservative Continuous-Time Treatment Optimization
marc.jourdan@epfl.ch
DINOv3
Regret minimization in Linear Bandits with offline data via extended D-optimal exploration.
On the Expressive Power and Limitations of Multi-Layer SSMs
Neural Fourier Transform for Multiple Time Series Prediction
MatchEx: Model-Level GNN Explanations with Multi-Granular Insights
Many Circuits, One Mechanism: Input Variation and Evaluation Granularity in Circuit Discovery
Minimax Optimal Early-Stopped Gradient Descent for Gaussian Mixture Classification
BO-Arena: An Evolving Benchmark for High-Dimensional Bayesian Optimisation
SynthForensics: Benchmarking and Evaluating People-Centric Synthetic Video Deepfakes
Evaluating Epistemic Uncertainty: Beyond OOD Detection and Active Learning
Auditing Sabotage Bench: A Benchmark for Detecting and Fixing Research Sabotage in ML Codebases
MutQA: A Cross-Validated Q&A Dataset for Genetic Mutations
ListQA: A Benchmark for Evaluating List-Formatted Factual Knowledge Retrieval in Large Language Models
Instantiation of Human Values in Image Generation
stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation
Benchmarking Sensor-Fault Robustness in Forecasting
Smooth Piecewise Cutting for Neural Operator to Handle Discontinuities and Sharp Transitions
Chem-PerturBridge: a harmonized compendium of small molecule perturbation transcriptomic effects
SLAyiNG: A Diverse and Community-validated Dataset of Queer Slang
Redefining Instance Matching: A Unified Framework for Part-Aware Matching in Panoptic Segmentation Evaluation
ScrapeGraphAI-100k: Dataset for Schema-Constrained LLM Generation
GT-Free OCR Metrics: A Reference-Free Evaluation Framework for Document OCR Systems
Honeyval: A Comprehensive Evaluation Framework for LLM-powered HTTP Honeypots
Driving on Memory
EV-AUDIT: A Co-Evolutionary Auditing Framework for Task Hijacking in Multi-Agent Systems
Martine: Benchmarking Multi-View 3D Surface Reconstruction Across Viewpoint Coverage, Resolution, and Lighting
Fluxtrapolation: A benchmark on extrapolating ecosystem fluxes
haphazard: A unified library and benchmark for online learning under varying feature availability
Scalable Multi-Agent Contrastive Reinforcement Learning
SafePro: Generation of Safe and Functional Proteins via Cross-Task Conflict-Aware Alignment
MONET: A Massive, Open, Non-redundant and Enriched Text-to-image dataset
EditJudge-Bench: Auditing VLM Image-Edit Judges with Synthetic Ground Truth
Active Probabilistic Reasoning in Humans and LLMs
Weisfeiler and Leman Follow the Arrow of Time: Expressive Power of Message Passing in Temporal Event Graphs
Inference-Time Refinement Closes the Synthetic-Real Gap in Tabular Diffusion
QMaxCal: Path-Space Regularization for Open Quantum Control via Girsanov's Theorem
Simulation-aided Reinforcement Learning with Control Variates
Polar Transformers: $SO(2)^K$-Equivariant Angular Attention for Cryo-EM Image-Set Processing
Same Function, Different Mechanism: Implementation-Local Geometry Beyond Accuracy
Dandelions: A Spherical Flower for Neural Simulation of Planetary Dynamics
Optimized Forward-Backward Rematerialization for Memory-Efficient Pipeline Parallel Training
Velocity Ambiguity Profiles: Time-Resolved Bayes-Risk Diagnostics for Flow Matching
3D-VITAL: Visibility-aware Identity Training from Artificial Liftings of 3D Reconstruction model for Cross-View Object Re-Identification
Diffusion fine-tuning with Rewarded Moment Matching Distillation
Calibrated Safe Policy Improvement for Continuous Offline Reinforcement Learning
A Hierarchy of Entropy-Shapley Games for Multivariate Predictive Uncertainty
On objective mismatch in molecular retrieval from tandem mass spectrometry
Does Weight Decay Enhance Training Stability?
Language Models Can Coarsely Modulate Entropy Under Instruction
Black-Box Inference of LLM Architectural Properties with Restrictive API Access
Voronoi-Markov chain and spatial entropy for point pattern analysis
Hybrid Probabilistic Zonotopes for Identifiable and Refinable Predictive Uncertainty
Recovering Clean Evaluation Metrics from Contaminated Benchmarks
Spectral Annealing: Normalization-Path Exploration for Large-Scale Ising Optimization
Generalization in Neural Networks Through the Lens of Magnitude Potential
Sparse Video Generation Propels Real-World Beyond-the-View Vision-Language Navigation
Scaling Generative Foundation Models for Chest Radiography with Rectified Flow Transformers
AgentRoom: Concurrent Multi-Agent Coding in a CRDT-Backed Shared Workspace
NeuroSynTheos: Learning to accelerate counterexample-guided reactive synthesis modulo theories
$\varphi$TD: Distributional Reinforcement Learning using Characteristic Functions
Debiased Counterfactual Generation via Flow Matching from Observations
Probing for Representation Manifolds in Superposition
What’s Holding Back Latent Visual Reasoning?
Beyond MMSE: Enhancing PnP Restoration with ProxiMAP
Tight $L_\infty$ Sample Complexity for Low-Degree and Sparse Boolean Polynomials
RubiConv - Efficient Boundary-Respecting Convolutions
The risk of KV cache compression
GRASP: Guided Residual Adapters with Sample-wise Partitioning
From Persistence to Survival: Hypothesis Testing, Effect Sizes and Vectorisation for Topological Features
An Educated Guess: Deriving Statistically Aligned Gradient Estimates for Zeroth-Order Optimization
The State-Prediction Separation Hypothesis
Do Heavy Tails Help Diffusion? On the Subtle Trade-off Between Initialization and Training
Unbiased First-Order Randomized Smoothing for Differentiable Simulation
Twisted Schrödinger Bridge Matching
From Approximation to Computation: Universal Power of Deep Narrow Networks at Constant Width
Hierarchical Task Network Planning with LLM-Generated Heuristics
Shared Modular Recurrence in Contextual MDPs for Universal Morphology Control
Events as Triggers for Behavioral Diversity in Multi-Agent Reinforcement Learning
On the Convergence of First-Order Methods in Signaling Games
Beyond Single-Step Likelihood: Gibbs Variational Last Layers for Long-Horizon Dynamics Learning
Mechanistic Interpretability of EEG Foundation Models via Sparse Autoencoders
CANDO: Cooperative Agentic Network for Layout Design Optimization
Echo learning enables biologically plausible temporal credit assignment
FlowBatt: Flow Matching for Probabilistic Battery Degradation Prediction
Neural Slack Variables for Shape Constraints
Memory flows: geometry and dynamics of sequential retrieval in input-driven Hopfield networks
Tadpole: Autoencoders as Foundation Models for 3D PDEs with Online Learning
CRAFT: Conflict-Resolved Aggregation for Federated Training
GAUGECAST++: A Physics-Informed Latent Forecasting System for Localized Flood Prediction
Online Budget Allocation with Censored Semi-Bandit Feedback
No Triangulation Without Representation: Generalization in Topological Deep Learning
Efficient Matrix Product State Learning in Logarithmic Depth
Effective Biological Representation Learning by Masking Gene Expression
Diversity Curves for Graph Representation Learning
Reinforcement Learning for Long-Horizon Unordered Tasks: From Boolean to Coupled Reward Machines
Probabilistic Guarantees for Adversarial Linear Contextual Bandits
Scale-Sensitive Shattering: Learnability and Evaluability at Optimal Scale
Unrestrained Simplex Denoising for Discrete Data. A Generative Method Applied to Graphs.
X-Palm: Paired Multispectral-to-Smartphone Dataset for Cross-Domain Palmprint Authentication
PRISM: Polarimetric Road-surface Intelligent Sensing and Measurement Dataset
Min-Max Optimization Requires Exponentially Many Queries
KDASO: Knowledge-Data Dual-Driven Automated Skill Optimization for Liability Adjudication Task
Network Learning with Semi-relaxed Gromov-Wasserstein
Towards Unified Dynamic Face Landmark Detection
The sublevel Flood bifiltration: towards scalable 2-parameter persistent homology
Beyond Isotropy in JEPAs: Hamiltonian Geometry and Symplectic Prediction
Privately Estimating Monotone Statistics in Polynomial Time
The Pareto Frontier of Randomized Learning-Augmented Online Bidding
Contrastive Hypergraph Source-free Domain Adaptive Object Detection in Adverse Weathers
Mean-Field Control on Sparse Graphs: From Local Limits to GNNs via Neighborhood Distributions
Transformers Linearly Represent Highly Structured World Models
Global Convergence in Deep Networks via the Second Law of Thermodynamics
Regret Minimization in Single-Dimensional Contract-Design with Binary Actions
Near-Optimal Decentralized Stochastic Convex Optimization over Networks
Evaluation Awareness in Language Models Has Limited Effect on Behaviour
Emergent Semantic Role Understanding in Language Models
Simultaneous Gradient Learning in First-Price Auctions
Tree-Ensemble Repair through Constrained Optimization
Why Do Time Series Models Need Long Context Windows?
Mildly Overparameterized ReLU Networks on Orthogonal Data: Incremental Learning and Implicit Bias
Optimal scaling laws in learning hierarchical multi-index models
Locality-Controlled OOD Guidance for Robust Regulatory DNA Sequence Design
Kernel Granger Component Analysis for Nonlinear Directed Component Discovery
Intent Factored Generation: Unleashing the Diversity in Your Language Model
Interpretability-by-Design with Accurate Locally Additive Models and Conditional Feature Effects
JaSpec-LID: Local Intrinsic Dimension Estimation via Jacobian Spectra of ODE-based Generative Models
Spectral Geometry of Attention: From Information Routing to Uncertainty
NeuroFaith: Evaluating Mechanistic Faithfulness of LLM Free Text Self-Explanation at the Concept Level
Too Smart to Teach: The Articulability Ceiling in Language Models
Nautilus: From One Prompt to Plug-and-Play Robot Learning
Privacy by Postprocessing the Discrete Laplace Mechanism
Test-Time Conditioning with Representation-Aligned Visual Features
The Communication Bottleneck: A Round-Trip Study of Compositional Serialization in Language Models
Closed-Form Last Layer Optimization
A Dynamic Decomposition Strategy for the MOEA/D With Proven Performance Guarantees
DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention
D2D: Detector-to-Differentiable Critic for Improved Numeracy in Text-to-Image Generation
Causal-VLM: Dense Causal Captioning in Videos
Unbounded Streaming Text-To-Speech with Prefixed Sliding Window Attention
RESCAST-100K: A Comprehensive Dataset for Cross-Domain Residential Load and Indoor Temperature Forecasting
Approximate Bayesian inference with exchangeable distributions for neurosymbolic AI
Joint Treatment Effect Estimation from Incomplete Healthcare Data: Temporal Causal Normalizing Flows with LLM-driven Evolutionary MNAR Imputation
Theoretical guidelines for annealed Langevin dynamics in compositional simulation-based inference
BlockFormer: Transformer-based inference from interaction maps
SPRING: Solver-guided Process Rewards for Novel Logical Reasoning Steps Generation
PENEX: AdaBoost-Inspired Neural Network Regularization
Mini-batch kernel $k$-means
MOBO-CAPS: Multi-objective Bayesian Optimization with Cardinality-Aware Pareto Selection
SS3D: End2End Self-Supervised 3D from Web Videos
PAC-Bayesian Bounds for Learning Partially Observed Stochastic Linear Time-Invariant State-Space Systems with Inputs and Sub-Gaussian Noise
Learning Transferable Representations from Operating System Entities via Provenance Graph Distillation
Focus, Align, and Diffuse: Time-Series-Aware Keyframe Diffusion for Cardiac Dynamic Synthesis from Sparse Observations
Mapping Uncharted Symmetries: Machine Discovery in Combinatorics
Discrete Flow Matching: Convergence Guarantees Under Minimal Assumptions
Pareto DNN Verification: Fast for Most Queries
Selling Information While Being an Interested Party
Quantitative Local Convergence of Mean-Field Stein Variational Gradient Flow
Soft Forward-Backward Representations for Zero-shot Reinforcement Learning with General Utilities
Neurosymbolic Object-Centric Learning with Distant Supervision
Canonical Predictive Quotients: A Theory of Prediction under Hidden Predictive State Uncertainty with ICL Implications
TRIM: A Theory of Retrieval with Incremental Memory -- Defect, Benefit, and Critical Horizon
Recursively Trained Diffusion Models: Limiting Collapse Distribution and Spectral Characterization
Predicting Only from Selected Evidence: A Tempered Product-of-Experts Bottleneck for Auditable EEG Diagnosis
DiLaDiff: Distilled Latent-augmented Diffusion for Language Modeling
A Faster Algorithm for the Half-Trek Criterion in Structural Causal Models
Optimal Convergence Analysis of DDPM for General Distributions
Statistical Convergence of Spherical First Hitting Diffusion Models
Simplifying Transformer-Based U-Net Neural Physics Simulators
Attention-Based Soft Answer Sets
Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors
Task-Driven Bayesian Experimental Design Yields Singly Intractable Objectives for Joint Policy Training
Casper: A Projection-Based Neurosymbolic Layer for Scalable & Guaranteed Constraint Satisfaction
Beyond Success Rates: Trainability and Extractability in Offline GCRL
Theory of Optimal Learning Rate Schedules and Scaling Laws for a Random Feature Model
Toward Optimal Regret in Robust Pricing: Decoupling Corruption and Time
Bench-MFG: A Benchmark Suite for Learning in Stationary Mean Field Games
Online Resource Allocation With General Constraints
Phaedra: Learning High-Fidelity Discrete Tokenization for the Physical Sciences
DPPE: Rethinking Camera-Based Positional Encoding for Scaling Multi-View Transformers
Asymptotic Anytime-Valid Inference for U-statistics
Flexible Intensities Matter: A comprehensive re-evaluation of Classical and Neural Temporal Point Processes
Efficient Knowledge Transfer in Federated Bayesian Optimization through Neural Network Surrogates
Text-to-CAD Evaluation with CADTests
How to Scale Mixture-of-Experts: From muP to the Maximally Scale-Stable Parameterization
COMPOSE: Hypergraph Cover Optimization for Multi-view 3D Human Pose Estimation
Do Composed Image Retrieval Benchmarks Require Multimodal Composition?
Learning Better Certified Models from Empirically-Robust Teachers
Pseudo-Labeling for Unsupervised Domain Adaptation with Kernel GLMs
The Benefits of Temporal Correlations: SGD Efficiently Learns k-Juntas from Random Walks
Improving Diffusion Posterior Samplers with Lagged Temporal Corrections for Image Restoration
2-Step Agent: How a Bayesian Decision Maker Learns from AI-Decision Support
Likelihood-free inference of phylogenetic tree posterior distributions
Expressive Power of Deep Homomorphism Networks over Relational Databases
GEM: A Dual-Scale Architecture for Graph-Level Hierarchical Representation Learning
Jacobian Descent for Multi-Objective Optimization
Improved Regret bounds in Tabular Reinforcement Learning under Local Differential Privacy
NeRFix: fixing subtle mistakes in the quadrature of the NeRF volumetric integral
Muon Dynamics as a Spectral Wasserstein Flow
Factual recall in linear associative memories: sharp asymptotics and mechanistic insights
Data-Driven Covariate Selection for Nonparametric and Cycle-Agnostic Causal Effect Estimation
Jaguar: Fast Private CNN Inference with Power-of-Two Homomorphic Arithmetic
Behaviour4All: A Dependency-Aware Toolkit for in-the-wild Facial Behaviour Analysis
A Critical $\beta$-Scale for Posterior Collapse in Dirichlet $\beta$-VAEs
Diff-CA: Separating Common and Salient Factors with Diffusion Models
TextSeal: A Localized LLM Watermark for Provenance & Distillation Protection
Causal Discovery via Transformed Low-Rank Quantile Surfaces
k-th Order Deep Homomorphism Networks
A typed tensor language for federated learning
Beyond Raw Context Transfer: Representation-based Federated Retrieval-Augmented Generation
AgentCBO: Causal Belief Routing for Bayesian Optimization under Unknown Graphs
Parameter symmetries determine representational geometry in overparameterized nonlinear networks
Solving Stochastic Control under Multiplicative and Internal Noise via Constrained Optimization
Beyond the Linear Separability Ceiling: Aligning Representations in VLMs
Control Under the Wrong Model Is Better Than Under the Correct One
Explanation of Dynamic Physical Field Predictions using WassersteinGrad: Application to Autoregressive Weather Forecasting
NeuroNTP - A Generalizable Multimodal Foundation Model for Epilepsy
Surprise, Episodic Context, and Catastrophic Forgetting in LLM Fine-Tuning: An Empirical Study
Do LLMs Bind Episodes? Probing Cross-Episode Parametric Retrieval Through Shared Cues
GLUT: 3D Gaussian Lookup Table for Continuous Color Transformation
Trustworthy Retrosynthesis: Eliminating Hallucinations with a Diverse Ensemble of Reaction Scorers
General Agent Evaluation
Training Data Attribution in Diffusion Models via Mirrored Unlearning and Noise-Consistent Skew
Domination-Avoiding Learning Agents Cannot Collude
Minimax Private Estimation of Smooth Optimal-Transport Maps
DepthGraft: Structural Regularization through Hierarchical Cross-Layer KV Reconstruction
Large language models suffer from a curse of ambiguity
On the Construction and Implications of Low-Loss Valleys in LoRA-based Bayesian Inference
PhysRemover: A Unified Framework for Physically Realistic Object Removal
What’s in a Smoothness Constant? Tight Rates for Local SGD with Bounded Second-order Heterogeneity
RankAlign: Unsupervised Vision-Language Representation Alignment via Rank Transformation
Provable State Estimation with Recurrent Models
World Models as Group Actions
Maxitive Donsker-Varadhan Formulation for Possibilistic Variational Inference
Prediction-Intervention Games and Invariant Sets
Balancing Frequencies and Pixels in Flow Matching
Euclidean Score-Based Generative Modeling with Permutation Semantics
Online Bernstein-von Mises theorem
InCLAD: A Continual Learning Benchmark for Industrial Visual Anomaly Detection
CAREBench: Evaluating LLMs' Emotion Understanding by Assessing Cognitive Appraisal Reasoning
The Ruler and the Judge: Benchmark-Conditional Evaluation of LLM-as-a-Judge
Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders
Intersectional Fairness via Mixed-Integer Optimization
DART: Domain-Agnostic Residual Transfer for Generalist Anomaly Detection
Mixed-Curvature Geometric Latent Diffusion Model for Graph Generation
Sub-Gaussian Confidence Intervals for Heavy-Tailed Data: Characterizing the Limits of Inference
VeriGraph: Towards Verifiable Data-Analytic Agents
Interpretable Machine Learning Evaluates Differential Therapy Effects in Parkinsonian Gait
GISA: A Benchmark for General Information-Seeking Assistant
TabBioMed: A Large-Scale Benchmark for Biomedical Tabular Learning
C-LoRA: Continual Low-Rank Adaptation for Pre-trained Visual Models
The Panel Complexity of Sortition: Is 12 Angry Men Enough?
Weighted Sampling for Online Causal Discovery
What Can Labels Alone Audit and Edit in Frozen Representations?
DeCoRL: Decomposed Consistency Reinforcement Learning for Multi-Image Composition
DNS-Calibrated Local Stochastic Transition Closure for PDE-Free Long-Horizon Turbulence Diffusion
Adaptive Coordinate Transforms for Neural Operators
Stochastic Matching Bandits with Rare Optimization Updates
Dense Structural Compression of Transformers via Gauge-Correct Channel Removal
ReFree-S2V: Towards Realistic Co-Speech Video Generation via Reward-Free RL and Multilevel Speech Guidance
Auto-Annotation with Expert-Crafted Guidelines: A Study through 3D LiDAR Detection Benchmark
An Information-Theoretic Evaluation Framework for Benchmark and Model Diagnosis in Knowledge Tracing
Disentangling generalization and memorization in large language models using chess
Cosine is Human: The Reproducibility Ceiling of Perceptual Similarity
World-Model-Inspired Flicker State Modeling for Burst Flicker Removal
Calibrated Target Noise Recovers Curvature from the Gradients
Not All Gap Correction Helps: A Geometric View of External Information in LLM Inference
Can Hybrid-Parallel Planning Support Alternating Model–Strategy Design? Dependency-Keyed Per-Layer Primitives for Re-Planning
Bayesian Low-Rank Posteriors for Scalable Membership Inference
Sublinear Variational Optimization of Gaussian Mixture Models with Millions to Billions of Parameters
WayPOP: A Panoramic Open-Set Panoptic Tracking Benchmark
Understanding the Curse of Unrolling
Breaking BAD: Heterogeneous Byzantine-Robust Federated Learning via Gather and Scatter Scores
Ledger: A Path-Validated, Database-Grounded Benchmark for Enterprise Web Agents
One World, Dual Timeline: Decoupled Spatio-Temporal Gaussian Scene Graph for 4D Cooperative Driving Reconstruction
Filtered-Trace Online Variational Training for Probabilistic Spiking Neural Networks
Federation Is the Way Forward for AI Agents
WildBox: A Dataset and Benchmark for Aerial Monocular 3D Detection of African Savanna Wildlife
More Value per Key: Asymmetric Sparse Attention for Faster LLM Decoding
A General Filter-Enhanced Approach to Smartphone Hyperspectral Imaging
Dyna-Style Safety Augmented Reinforcement Learning: Staying Safe in the Face of Uncertainty
spora: A Unified Multimodal Dataset for Spatial Proteomics
On the Rademacher Complexity of Graph Neural Networks: Unifying Expressivity and Geometry
HalluciText: Mitigating Text Hallucinations in Diffusion-Based Image Restoration
Securing AI Agents with Information-Flow Control
AuGhostmentation: The Eyes Never Stand Still—$\textit{Why Should CNNs?}$
Dataset Collections: Challenges of Large-Scale Data Aggregation in 3D Medical Image Datasets
Too Early for AI-Assisted Peer Review: A Systematic Account of the Limits and Opportunities of Automating Human Judgment
Decoupled Prototype Contrastive Alignment Hashing for Cross-Modal Retrieval
SING-CH: Task-Scale-Agnostic Lifelong Cross-Modal Hashing on Statistical Manifolds
UGGRH: Unsupervised Generative Completion and Graph-attention Refinement for Incomplete Cross-modal Hashing
It Just Takes Two: Scaling Amortized Inference to Large Sets
Training-Free Dynamic Upcycling of Expert Language Models
Learning to Bid in Repeated Second-Price Auctions with Dynamic Values and Aggregated Feedback
DynamAuction: a reinforcement learning environment for repeated auction with dynamic value
Disentangling the Good From the Bad: Quantization-Induced Flips Are Not Random
On Observation Time for Recovering Latent Hawkes Networks
ObjView-Bench: Rethinking Difficulty and Deployment for Object-Centric View Planning
Stochastic Zeroth-Order Optimization Under Heavy-Tailed Noise
Qrita: High-performance Top-k and Top-p using Pivot-based Truncation and Selection
LayoutBridge: Anisotropic Brownian Bridges for Public Indoor Floorplan Generation
Patching Up Circuit Learning on Images
Flow-Transformed Implicit Processes for Function-Space Variational Inference
Convergence Guarantees for Federated SARSA with Local Training and Heterogeneous Agents
FrED: External Data Influence Estimation via Domain Knowledge Graph Grounding
CHASM: Cross-frequency Harmonized Axis-Separable Mixing for Spectral Token Operators
Spiking neural network initialization for scale-invariant maximization of entropy
Complexity of Classical Acceleration for $\ell_1$-Regularized PageRank
CanViT: Toward Active-Vision Foundation Models
Memory-Driven Contrastive Embedding Enhancement for Fine-Grained Open-Set Semi-Supervised Learning
On the Existence of Uniformly Optimal Policies in MDPs under Epistemic Uncertainty
Pathways of Visual Information Flow in Vision-Language Models
Efficiently Aligning Draft Models via Parameter- and Data-Efficient Adaptation
FunctionEvolve: Structure-Guided Symbolic Regression with LLMs
GNNs Meet Sequence Models Along the Shortest-Path: an Expressive Method for Link Prediction
CoPE-VideoLM: Leveraging Codec Primitives For Efficient Video Language Modelling
Certifiably Optimal Robust Angular Synchronization
CLoSeR: Closing the Loop for Long-Context Streaming Reconstruction
Quantifying Concentration Phenomena of Mean-Field Transformers in the Low-Temperature Regime
Beyond Kemeny Medians: Consensus Ranking Distributions. Definition, Properties and Statistical Learning
A Comprehensive View of Fairness through Distributional Stability
Decentralized Ranking Aggregation via Gossip: Convergence and Robustness
Cluster with Auctions for Vector Search
When Empathy Misses the Goal: A Benchmark for Goal Displacement in LLM Advice
ProgramBench: Can Language Models Rebuild Programs From Scratch?
Fixed-Point Masked Generative Modeling
ESS-Flow: training-free guidance as Bayesian inference in source space
Do Enterprise Systems Need Learned World Models? The Importance of Context to Infer Dynamics
MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image
Match the Geometry, Skip the Surrogate: Extreme Low-Budget Optimization in High Dimensions
Looking Under the Streetlight: Evaluation in Generative Molecular Dynamics
Sparse Attention as Compact Kernel Regression
Beyond the Half Approximation: Fair and Efficient Online Class Matching
A Scalable Nonparametric Continuous-Time Survival Model through Numerical Quadrature
A method to automatically discover symbolic local learning rules
FakeParts: a New Family of AI-Generated Video Forgeries
Competing Event Models: Next Event Prediction Under Interventions
ORCAID: Oblique Rule-Based Continuous-Action Interpretation for Deep RL Policies
Breaking Adversarial Transferability in Fine-Tuned Speech Recognition
Resilient Byzantine Agreement with Predictions
ReefNet: A Large-Scale Dataset and Benchmark for Fine-Grained Coral Reef Recognition
Learning Reusable Options by Decomposing Neural Policies
Tabular Foundation Model for Generative Modelling
VACE: Learning Geometrically Structured Representations for Time Series Anomaly Detection
Beyond Isolation: Neighbor-Consistent Data Pruning for Multivariate Time Series Forecasting
FusionProt: Fusing Sequence and Structural Information for Unified Protein Representation Learning
GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling
Mutable Transcripts: Mitigating Context Pollution through Editable Conversation State
IRPO: Boosting Image Restoration via Post-training GRPO
Learning from Ranking Feedback: Improved Regret Bounds via Independence Preserving Rank Breaking
Stable and Scalable Probabilistic Numerical Solvers for Stiff and High-Dimensional ODEs
Corruptions of Supervised Learning Problems: Typology and Mitigations
Adapting to Conflict: Equilibrium Structure and Adaptive Learning in Harmonic Games
State-Action Selection in General Stochastic Games under Regularized Policy Gradient Methods
BIAS-ID: A Framework for Analyzing Transformation Biases in AI-Generated Image Detectors
ProSearch: Benchmarking Multi-Constraint Protocol Retrieval in Experimental Science
Clustered Randomized Smoothing for Stochastic Prediction Functions
Spectral Quantum Memory for Implicit Neural Representations
Sparse Sum-of-Squares Layers for Certified Learning
From Claims to Context: Holistic Information Verification Requires Contextual Signals
Mosaic: A Benchmark Suite for Differentiable Physics Solvers
Characterizing the Edge of Stability in Variational Training Without Priors
FMMI: Flow Matching Mutual Information Estimation
Neuromodulated Constrained Autoencoders for Context-Dependent Manifold Learning
From Baselines to Transport Geodesics: Axiomatic Attribution via Optimal Generative Flows
In-Context Learning for Remote Sensing Vision: A Semantic-Aware Rotation-Robust Diffusion Framework
SciReason: A Controllable Benchmark for Scientific Reasoning in LLMs
Robust-by-Design Distributional Learning from Contaminated Samples
Timing Is All You Need: SpikeCore, Learnable Delays, and Gain Control for Neuromorphic Classification
LoopRPT: Reinforcement Pre-Training for Looped Language Models
WebArena-Pro: A Heterogeneous, Multimodal, Reproducible Benchmark for Web Agents
Escaping Parameter Space: Tight Generalization Bounds via Representation Quality
Hierarchical Conformal Classification
AMARIS: Merging Generalist and Specialist LLMs via Adaptive Subspace Inheritance
Enhancing Tabular Learners with Context-Aware Semantic Embeddings
Towards Fairness under Label Bias in Image Segmentation: Impact, Measurement and Mitigation
Benchmarking Attention for Tabular Foundation Models
PASSAGE: A Real-Terrain Benchmark for Trustworthy Constrained Path Planning
Depth2Pose: A Pose-Based Benchmark for Monocular Depth Estimation without Ground-Truth Depth
Random-Set Graph Neural Networks
Learning Lotteries with Minimal Violations from Membership Queries
Learning Acceptable Lotteries via Queries: Minimizing Aggregated Violation Distances
TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks
A Matter of TASTE: Improving Coverage and Difficulty of Agent Benchmarks
Rare Events, Real Signals: Functional Ensembles as Units of Computation in Deep Spiking Networks
ACDP: Architecture-aware Cross-Dataset Performance Predictor for NAS
Localize Any Object in X-Ray Security Scans without Human Annotation
Cephalonauts One: A deep fMRI dataset for decoding naturalistic speech in the human brain
(Mis)generalization of Helpful-Only Fine-Tuning
Mamba Flow Matching Neural Processes: Linear-Time Inference for Irregularly Observed Spatial Fields
The Ringelmann Effect in Multi-Agent LLM Systems: A Scaling Law for Effective Team Size
Provable Speedups From Dynamic Population Sizes in Evolutionary Algorithms for Multiobjective Optimization
Can Circuit Alignment Predict OOD Generalization?
Semantic Motion Anchors: Bridging Motion and Meaning in Co-Speech Gestures
StarWM: Self-Supervised Trained Attention Routing for Robust World Models
MedZERO: Self-Evolving Agents for Open-Ended Medical Reasoning Through Controlled Knowledge Accumulation
Reinforced Evidence-Aware Long Video Understanding
FACBench: A Benchmark for Formal-Anchor Collisions in Multilingual Mathematical Grounding
GDMD: Guiding Distribution Matching Distillation with Gradient-Based Reinforcement Learning
Learning to Evolve Scenes: Reasoning about Human Activities with Scene Graphs
A General Concept-based Decomposition for Vision–Language Embeddings
Causal Representation Learning for Generalisable Recommendation
Prediction-Powered Active Testing
Generalized Wasserstein Flow Matching: Transport Plans, Everywhere, All at Once
Stochastic Grouping Conformal Prediction for Effective Subgroup Reliability
Tight Generalization Bounds for Noiseless Inverse Optimization
KV Packet: Recomputation-Free Context-Independent KV Caching for LLMs
From Topology to Retrieval: Decoding Embedding Spaces with Unified Signatures
Foveated BagNet: Inherent Interpretability Does Not Exclude Global Context
Quantile Benchmarking Heterogeneous Web Corpora in Open LLM Pretraining
Parasite Features: Causal Abstraction Through Spurious Pathways
Submodular Multi-Agent Reinforcement Learning for Effective Online Distributed Task Allocation
Measure Less, Know More: Self-Supervised Test-Time Feature Acquisition
Affine Tracing: A New Paradigm for Probabilistic Linear Solvers
JEPAWG: Interpretable Hypernetworks for Weight-Space Physics
Robust Amortized Simulation-Based Inference via Learned Error Models
EchoKV: Efficient KV Cache Compression via Similarity-Based Reconstruction
Causal Evaluation of Membership Inference Attacks
Layer Free-Riding in Forward-Forward Networks: Real, Repairable, but Not Accuracy-Dominant
A Reproducible Evaluation Protocol for Quantum Non-Linearity in Variational Quantum Models
Tight PAC-Bayes Generalisation Guarantees for Large Language Model Safety Monitoring
The Optimal Control Foundation of Early Exits – Turnpikes and ResNets
When Must AI Training Stage Checkpoints? A Distributional Model of Durability Boundaries at Scale
Beyond Modality Fusion: Deep Ensembles for Multimodal Classification
Measuring Robustness and Efficiency in a Connectome-Constrained Fly Visual System Model on a Collision-Detection Task
One Scan is Enough: Demonstration-Free Adaptation for Language-Guided Navigation
Noisy isomorphism: Robust expressivity of GNNs under structural perturbation
Privacy Guarantees in Posterior Sampling under Contamination
EEGFaceSem: An EEG Benchmark with Paired Generative Latents for Semantic Visual Modeling
Optimal Experiments for Partial Causal Effect Identification
TempoPFN: Synthetic Pre-training of Linear RNNs for Zero-shot Time Series Forecasting
Show Me What You Don’t Know: Efficient Sampling from Invariant Sets for Model Validation
Efficient One-to-many Domain Translation via Diffusive Entropic Optimal Transport
Boosting Inference with Guided Reasoning: Stochastic Exploration for Recursive Models
Supervised Distributional Reduction via Optimal Transport and Dependence Maximization
Computationally Efficient Replicable Learning of Parities and Applications
Maximin Robust Bayesian Experimental Design
It Cancels: O(r²) Cholesky Updates for Whitened Operators
Correct but Unselectable: The Hidden Interface Tax in Multi-Candidate Reasoning
Prefill-Guided Trace Allocation for Sample-Efficient Test-Time Scaling
Neural Galerkin Normalizing Flows for Bayesian Inference of Diffusions with Inaccessible Boundaries
Lethe: Link Inference Attacks For Evaluation of Edge Unlearning Methods
When Actions Matter: Causal Affordances for Long-Horizon Credit Assignment in World Models
Are Easier or Harder Examples Better? Rethinking Data Selection for Reward Models and Preference Optimization
TS-ICL: A Flexible Time-Indexed Foundation Model for Time Series via In-Context Learning
MEMEVO: A Memory-Evolved Video Agent for Long Video Understanding
Poison-then-Hide: Finetuning-Activated Backdoor Attack on Pretrained Vision Encoders
From Experts to Sub-experts: Fine-grained Parameter-Efficient Fine-Tuning for MoE LLMs
Counterfactual Maps: What They Are and How to Find Them
Exploring the Limitations of Layer Synchronization in Spiking Neural Networks
Differentiable Nonlinear Model Predictive Control
E²Gen: Evidential Energy-Based Generation for Fair Federated Graph Learning
Consistency-Verified Backdoor Defense for Federated Graph Learning via Cross-Layer Drift
Your Neighbors Know: Leveraging Local Neighborhoods for Backdoor Detection in Decentralized Learning
Black-Box Followers, White-Box Leaders: Partial Zeroth-Order Methods for MPECs
Beyond Chamfer Distance: Granular Order-aware Evaluation Metric For Online Mapping
Measuring Black-Box Confidence via Reasoning Trajectories: Geometry, Coverage, and Verbalization
AudioSphere: Towards Self-Supervised Spatial Audio Representation Models
UniPrefill: Universal Long-Context Prefill Acceleration via Block-wise Dynamic Sparsification
Decentralized $\mu^2$-SGD: Narrowing the Parallelism Gap to Centralized Learning
DACE: Diversity-Driven Adversarial Co-Evolution for Robust LLM Safety Alignment
Quantizing With Randomized Hadamard Transforms: Efficient Heuristic Now Proven
Theoretical guarantees for Banded Approximations of Gaussian Processes
Learning Density Operator Latent Variable Models via Quantum Information Projection
Flow Matching with In-Context Priors for Out-of-Distribution Brain Dynamics
The Bayesian Origin of the Probability Weighting Function in Human Representation of Probabilities
Amortized Molecular Optimization via Group Relative Policy Optimization
Euclidean Embedding of Data Using Local Distances
Efficient Adaptive Data Acquisition via Pretrained Belief Representations
Algebraic Machine Learning: learning as computing subsets of the subdirect decomposition from Abstract Algebra
Who caused $Y$? Local identifiability for learning causal parents
𝑓-Differential Privacy Filters: Validity and Approximate Solutions
AgentKernelArena: Benchmarking Performance and Generalization of AI Coding Agents on GPU Kernels Optimization
Autofocus Retrieval: An Effective Pipeline for Multi-Hop Question Answering With Semi-Structured Knowledge
Safe Few-Step Generation via Velocity Editing
SecureClaw: Clawing Back Control of LLM Agents
Think about how AIs think about themselves
RAMA: Resistance-Aware Multi-Hop Aggregation Graph Representation Learning for Robust Ethereum Account Classification
The balance between feature learning and collapse in generative dynamical systems
AR-Edit: Training-Free Streaming Video Editing without Inversion
Sharp feature-learning transitions and Bayes-optimal neural scaling laws in extensive-width networks
ViewSAM: Learning View-aware Semantics for Weakly Supervised Cross-view Referring Multi-Object Tracking
How LLMs Distinguish Threats from Offers
Epistemic Pairwise Maximin Share
Profit Maximization in Bilateral Trade against a Smooth Adversary
DynaSub: Adaptive Subgrouping for Scalable Representation Learning
ASO Atlas 2.0: Evaluating antisense oligonucleotide prediction across the preclinical pipeline
Federated Learning by Utility-Constrained Stochastic Aggregation for Improving Rational Participation
KnowEvo: Knowledge Evolution for Protein Optimization
Integral Probability Boundaries
Virtual-Flow: Virtual Microphone-based Speech Enhancement via Unsupervised Flow Matching
Cheap Per-Component Testing for PLS, Stable Under Rotation
Understanding axial attention in TSFMs through single location regression
From Inexact Gradients to Byzantine Robustness: Acceleration and Optimization under Similarity
Finding Simple Proofs for First-Order Optimization
The SEC Filings Dataset: Reconstructing U.S. Corporate and Financial Disclosures into Layout-Faithful and Token-Efficient Pretraining Data
Know What You Need: Efficient Activation Checkpointing
High-dimensional Limit of SGD for Diagonal Linear Networks
HPE: Hallucinated Positive Entanglement for Backdoor Attacks in Federated Self-Supervised Learning
Tessellations of Semi-Discrete Flow Matching
Understanding the Interplay between Memorization and Learning in Large Language Models
Neurosymbolic Learning for Inference-Time Argumentation
CorridorLight: Cooperation as Task Negotiation with Causal Gating for Traffic Signal Control
The Window for Preventive Action Before AI Saturates Most Cognitive Benchmarks is Closing
Mitigating Over-squashing without Rewiring: A Sheaf Effective Resistance Perspective
Controlling for Omitted Variable Bias in Deep Neural Networks
Stabilizing Policy Optimization via Logits Convexity
Neural Chameleons: Language Models Can Learn to Hide Their Thoughts from Unseen Activation Monitors
Confidence-Based Decoding is Provably Efficient for Diffusion Language Models
FlexTab: A Flexible Encoder-Decoder Architecture for In-Context Learning Across Diverse Tabular Tasks
ARC-Encoder: learning compressed text representations for large language models
Learning to Discover Iterative Spectral Algorithms
One Temperature to Rule Them All?
On Length Bias in EEG-to-Text Decoding
Spatially Feasible 3D Indoor Scene Generation via Interaction-Oriented Human Proxy
Can Metadata Fix the Gauge? Calibration Turns Sparse Multi-Source Learning from Sparse PCA into Sparse Mean Recovery
Hierarchical Graph Representation Learning with Pooling-Induced Substructures
Harmonic Torsional Diffusion for Flexible Protein-Ligand Docking
How Language Models Compress and Compare: Understanding Selection with Token Covariance Maps
Observable Neural ODEs for Identifiable Causal Forecasting in Continuous Time
Consistent Geometric Deep Learning via Hilbert Bundles and Cellular Sheaves
Deep Learning as Neural Low-Degree Filtering: A Spectral Theory of Hierarchical Feature Learning
Near-Optimal Stochastic Linear Bandits with Delay
Strongly Adaptive Online Learning with Time-Varying Movement Cost
Gibbs Gradient Descent: A Langevin Approach to Optimization
Revisiting Cross-View Completion: Self-Supervised Pre-Training via Reconstruction Error Comparison
Uniform Diffusion Models revisited: Leave-One-Out Denoiser and Absorbing State Reformulation
Online Active Testing: Adaptive Importance Sampling for Unbiased Risk Estimation in Data Streams
When Prompts Override Vision: Instruction-Induced Hallucinations in LVLMs
Even More Guarantees for Variational Inference in the Presence of Symmetries
Read-Only Zero-Shot Classifier Expansion from Pairwise Semantics
OTformer: Non-Stationarity-Aware Adaptive Optimal Transport Attention for Time Series Forecasting
Structure vs. Chaos: Asymmetric Entropic Optimization for Enforcing Instruction Hierarchy
PVFormer: Proper Velocity Transformer for Stable and Scalable Hyperbolic Representation Learning
TARP: Trace-Anchored Regularization Prior for Retaining Stepwise Reasoning
A Spectral Framework for Closed-Form Relative Density Estimation
CalArena: A Large Scale Post-Hoc Calibration Benchmark
Super-Level-Set Regression: Conditional Quantiles via Volume Minimization
Frame the adversary: a structure-aware attack methodology
Difference of Convex Programming in the Wasserstein Space with Applications to MMD Optimization
SOLA: A Structured Operator Library for Attention in Pretrained Vision Transformers
CroissantMiner: Automated Extraction and Validation of Croissant Metadata for ML Datasets
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning
Integrating Local and Global Entropy for Uncertainty Quantification in LLMs
Geometry-Aware Optimal Transport: Fast Intrinsic Dimension and Wasserstein Distance Estimation
Incremental Learning in Transformers for In-Context Associative Recall
Secure Seed-Based Multi-bit Watermarking for Diffusion Models from First Principles
Evaluating Multimodal Narrative Understanding of Popular Hollywood Films
Multi-Armed Bandits With Best-Action Queries
Building Transformation Layers for Riemannian Neural Networks
Umbilic Multinomial Logistic Regression
Target-Budget Best-Function Identification for Scaling-Law-Guided Model Selection
Managing Self-Learning Experts under Per-Round Budget Constraints
Zero-Shot Quantization via Weight-Space Arithmetic
Bellman Contraction under MMD: A Unified Framework
Optimal Rates for Adaptive Private $k$-PCA
Online Set Learning from Precision and Recall Feedback
Stein Transport for Generative Modeling
The Power of Second Order Methods for Sequence Preconditioning
Shuffle and Joint Differential Privacy for Generalized Linear Contextual Bandits
Subcritical Signal Propagation at Initialization in Normalization-Free Transformers
Dancing in Fetters: Pareto-Optimal On-Device LLMs under Hardware Constraints
X2HDR: HDR Image Generation in a Perceptually Uniform Space
LLM-AutoSciLab: Closed-Loop Scientific Law Discovery via Active Experimentation with LLMs
Boosting Brain-to-Image Decoding with TRIBE v2 Data Augmentation
Consistency Regularised Gradient Flows for Inverse Problems
Learning Global Probabilistic Explanations
Adaptive Realizable Regression from Two Online Learners
Improved Algorithms for Online Classification with Surrogate Losses
Best Arm Identification for Bandits with Shifting Means
Preference-Guided Adversarial Policy Optimization for Long-Tail Robust Driving
Group-Aware Matrix Estimation and Latent Subspace Recovery
The Labeling Problem in Hallucination Detection Benchmarks: An Empirical Evaluation
Off-Policy Evaluation of Large Language Models via Learned Semantic Bottleneck Embeddings
Learning to Drive in New Cities Without Human Demonstrations
Antibody Generation via Redistributed Latent Diffusion
Position: Anthropomorphic Language in AI Discourse Can Be Constructive
Robust Task-Aware State Estimation from Pre-trained Perception
Certified Policy Optimisation for Nested Causal Bandits via PAC-Bayes Risk
TUBE: Tangent Upper Bound on Evidence for Discrete Diffusion Language Models
The Deadline Effect: Identifying and Correcting Temporal Bias in Human Evaluation
Statistical Inference in Causal Partial Identification under Smooth Densities
ViroGym: Realistic Large-Scale Benchmarks for Evaluating Viral Proteins
Tokenizer-Generator Coupling in Medical Image Generation
Backbone-Equated Diffusion OOD via Sparse Internal Snapshots
Realism VS Accuracy: Event Sequence Forecasting from a Generative Modeling Perspective
IDEAFix: Evaluation Framework for Creative Defixation Prompting in LLMs
POLAR-Bench: A Diagnostic Benchmark for Privacy-Utility Trade-offs in LLM Agents
Multiple Descent of Generalization Curve for Optimally Regularized Ridge Regression
BRACE: Bipolar Reference-Aware Calibration and Estimation for Incomplete Multimodal Learning
Principled Federated Random Forests for Heterogeneous Data
LithoBench: Benchmarking Large Multimodal Models for Remote-Sensing Lithology Interpretation
Beyond Oversquashing: Understanding Signal Propagation in GNNs Via Observables
Recon: Reconstruction-Guided Reasoning Synthesis for User Modeling
Hardware-Friendly Token-Group Activation Quantization for Low-Bit Mamba Super-Resolution
The Post-Training Dilemma: Why We Should Rethink the Sequential SFT-RL Paradigm
MSAlign: Aligning Molecular and Mass Spectra Foundation Models for Metabolite Identification
LAtte: Hyperbolic Lorentz Attention for Joint-Subject EEG Classification
The BV4 Benchmark for Unsupervised Anomaly Detection in High-Dimensional Spectral Data Streams
Linear-time rule mining under formal guarantees
DeFlowCritic: Dense Latent Reward Alignment for Text-to-Image Flow Matching Models
Can LLMs Take Retrieved Information with a Grain of Salt?
Hypergraph Generation via Structured Stochastic Diffusion
MedFlowSeg: Flow Matching for Medical Image Segmentation with Frequency-Aware Attention
Attention-based PCA
VolCo: Volumetric Contact for High-Fidelity Human Grasp Generation
AI-Mediated Communication Can Steer Collective Opinion
Robust Dreamer: Deviation-Aware Latent Gaussian Memory for Action-Controlled AR Video Generation
Unpaired Canonical Correlation Analysis
Rethinking Attention in Depth for Operator Learning
Property-Guided LLM Program Synthesis for Planning
Proxy-Based Approximation of Shapley and Banzhaf Interactions
Data-Driven Soft Labeling Scales DNA Read Classification to Whole-Body Cell-Type Deconvolution
Neural Networks With Dense Weights Are Not Universal Approximators
Optimal Dimension-Free Sampling for Regularized Classification
Learning to Complete Extremal Mathematical Structures
Validating Causal Abstraction Metrics on Simulated Complex Systems
The Dead Salmons of AI Interpretability: The Need for a Statistical Inference Perspective
PACZero: PAC-Private Fine-Tuning of Language Models via Sign Quantization
The Bayesian Learning Rule Beyond KL Geometry
FineRMoE: Dimension Expansion for Finer-Grained Expert with an Upcycling Approach
POETS: Uncertainty-Aware LLM Optimization via Compute-Efficient Policy Ensembles
ExpertNavigator: Functionally Coherent Expert Grouping and Pairwise-Ranked Routing for High-Fidelity Dense-to-MoE Conversion
The Neural Race Model
Can the Parts Fool the Test? Counterfactual Pairing Cycles for Relational OOD
Are We Making Progress in Multimodal Domain Generalization? A Comprehensive Benchmark Study
Beyond Bag-of-Words: Diagnosing Compositional Binding Failures in Vision-Language Models
Beyond Parameter Aggregation: Semantic Consensus for Federated Fine-Tuning of LLMs
GradShield: Alignment Preserving Finetuning
Zero-Shot Burst Restoration via Diffusion MAP Inference with Poisson-Gaussian Noise Likelihood
Generalization Dynamics of Linear Diffusion Models
Necessary but Not Sufficient: Spectral Tests for Value-Linear Attention Surrogates
The Horizon Threshold in Cooperative Multi-Agent Reward-Free Exploration
ToMAToMP: Robust and Multi-Parameter Topological Clustering
TopoFisher: Learning Topological Summary Statistics by Maximizing Fisher Information
LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
Physics-Informed Optimal Control by Control-Only Supervision with Error Guarantees on Value and Policy
A Generalized Tikhonov Layer for Interpretable-by-design Graph Neural Networks
RL-Guided Contraction of Symbolic Tensor Networks for Quantum Circuit Equivalence
ROAR: Benchmarking LMM Agents under Real-Time Constraints in Multiplayer Action-Shooter Games
Temporal Consistency Improves Generalization in Contextual Offline Meta Reinforcement Learning
Support-Safe Variational Hybrid Filtering for Contact-Mode and Sparse-Law Recovery
ACER: Towards Generalizable Protein-ligand Co-folding
Efficient and Robust Physical 3DGS-MPM Simulation via Interior Filling and Text-Physics Optimization
Latent Debate: A Surrogate Framework for Interpreting LLM Thinking towards Binary Decisions
What Drives Compositional Generalization? The Importance of Continuous Training Objectives in Visual Generative Models
A Hierarchical World Model for Driving
MDMR-Bench: A Multi-Dimensional Benchmark for Multi-Reference Image Generation
Gradient Span Algorithms Make Predictable Progress in High Dimension
When Graph Anomalies Learn to Hide: Test-Time Cloaking in Graph-Level Anomaly Detection
ZEBRA: Zero-shot Budgeted Resource Allocation for LLM Orchestration
Aligned LoRA Updates via Intrinsic Geometry for Federated Low-Rank Adaptation
Closing the Indexing-Decoding Gap in Multimodal Generative Retrieval via Prefix Retention Optimization
A Theory of Online Learning with Autoregressive Chain-of-Thought Reasoning
Penalize to Verify: A Multi-Domain Benchmark for Trustworthy LLM Evaluation
Gradient-based Graph Structure Optimisation for Research Networks
Harnessing Data Asymmetry in Manifold Learning
Spectral Re-Basin for Linear Mode Connectivity
Targeted Synthetic Control Method
Assessing the robustness of heterogeneous treatment effects in survival analysis under informative censoring
Generalized Bayes for Causal Inference
WorldCoder-Bench: Benchmarking Physically Grounded 3D World Synthesis
Think2SQL: Blueprinting Reward Density and Advantage Scaling for Effective Text-to-SQL Reasoning
Differentiable Knapsack and Top-k Operators via Dynamic Programming
Split the Differences, Pool the Rest: Provably Efficient Multi-Objective Imitation
From Isolated feature to Orbits:\\Discovering Music Concepts via Multi-SAE Alignment
Finite Resources False Discovery Rate Control on Structured Hypothesis Spaces
2D Spatial Reasoning with Adaptive Neural Cellular Automata
Attention Trajectories as a Diagnostic Axis for Deep Reinforcement Learning
Prior Text-Informed Gate Attention Framework for Multimodal Psychiatric Disorder Diagnosis
Computing Thiele Rules on Interval Elections and their Generalizations
CHAIN: Continual Heterogeneous Cooperation with Information Bottleneck for Multi-Agent Reinforcement Learning
GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models
Multi-Bridge Denoising Diffusion Probabilistic Models
Coresets for Clustering Using Noisy Comparisons and Few Distance Queries
Your Self-Supervised Projection Head Captures Object Co-Occurrence Statistics
Constrained MDPs with Trajectory Constraints
CS-DICE: Offline Reinforcement Learning with Coherent Occupancy Regularization
Causal Abstractions, Categorically Unified
Where to Approximate in Neurosymbolic Inference?
Overcoming Rank Collapse in Feedback Alignment
Predict-Project-Renoise: Sampling Diffusion Models under Hard Constraints
EM-NeSy: Expectation Maximization for Neurosymbolic Learning
Independent Learning of Nash Equilibria in Partially Observable Markov Potential Games with Decoupled Dynamics
Scaling Full Conformal Image Classifiers
Discovering Mechanistic Models of Neural Activity: System Identification in an in Silico Zebrafish
Chaining 2-FWL GNNs for Combinatorial Graph Alignment
Regularized Large Neighborhood Search
How Do Language Models Understand Tables? A Mechanistic Analysis of Cell Location
SMOG: Scalable Meta-Learning for Multi-Objective Bayesian Optimization
Instability of Meta-Learning Intrinsic Rewards for Policy Gradient Reinforcement Learning
Learning to target with network interference
Settling the Sample Complexity of Deterministic Agnostic PAC Learning
Generate in Reconstruction Space, Match in Semantic Space: Transport Geometry for One-Step Generation
Fail-Closed Alignment for Large Language Models
The Geometric Inductive Bias of Grokking: Bypassing Phase Transitions via Architectural Topology
Latent Motion Alignment for Video Diffusion
The Future of Facts: Tracing the Factual Generation-Verification Gap
Partition Tree: Conditional Density Estimation over General Outcome Spaces
Geometric Factual Recall in Transformers
Multilevel and Sequential Monte Carlo for Training-Free Diffusion Guidance
Towards more general control of diffusion models using Jeffrey Guidance
When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation
Causal Attribution via Activation Patching
Auditing AI peer reviewers: a dose-response and false-positive benchmark on real scientific papers
NIKA: Efficient Neural Video Representation via Structured Latent Diversity
LEAN: Library-Based Adaptation for Asynchronous, Federated Fine-Tuning
An exact information theory of generalization phase transitions in Bayesian diffusion models
Meta-memorization and memorization scaling laws in transformers
Learning to Learn from Multimodal Experience
Inverse Linear Bandits via Linear Programs
Grokking or Glitching? How Low-Precision Drives Slingshot Loss Spikes
Self-Distillation of Hidden Layers for Masked Self-Supervised Representation Learning
A probabilistic model of visual segmentation explains early visual cortical dynamics
NTK Regression under dual power-law model: Deterministic Equivalents via SDE and PDE Methods
Learning Domain Trajectories with Flow Matching for Gradual Domain Adaptation
A Free Lunch in LLM Compression: Revisiting Retraining after Pruning
NRF-GS: Neural Residual Fields for Expressive and Compact Gaussian Splatting
Learning Where to Simulate: Generative Active Sampling for Online PDE Surrogate Training
Memoir: Let the Model Direct Its Own Story for Robust Cross-Domain Knowledge Editing
Probing Persona-Dependent Preferences in Language Models
FogGS: Physics-Grounded 3D Foggy Effects
Handwritten Text Recognition Lives in the High-Pixel Variance Subspace
Constrained Bombieri Point Processes
Curvature-Dependent Lower Bounds for Frank-Wolfe
A Topological Sorting Criterion for Random Causal Directed Acyclic Graphs
OpenSearcher: Democratizing Deep Search through a Fully Offline Pipeline with Programmatic Verification
Alloy Agents Can Be More Dangerous Than Either Model Alone
Rethinking Neural Nonlinearity as Gating
Belief Engine: Configurable Stance Dynamics for Multi-Agent LLM Deliberation
Lost in the Slots: Revisiting Object-Centric Representations in the era of Foundation Models
Causal Edit Serialization
When Does Trimming Help Conformal Prediction? A Retained-Law Diagnostic under Calibration Contamination
From Cortical Synchronous Rhythm to Brain Inspired Learning Mechanism: An Oscillatory Spiking Neural Network with Time-Delayed Coordination
We use cookies to store which papers have been visited.
I agree
Successful Page Load
NeurIPS uses cookies for essential functions only. We do not sell your personal information.
Our Privacy Policy »
Accept
We use cookies to store which papers have been visited.
I agree
