NeurIPS 2025 Schedule

Filter Events

MON 1 DEC

noon

Registration Desk

(ends 6:00 PM)

TUE 2 DEC

7:30 a.m.

Registration Desk

(ends 6:00 PM)

8 a.m.

Affinity Workshop:

Women in Machine Learning

(ends 5:00 PM)

8:30 a.m.

Expo Talk Panel:

Multimodal Data Foundation at Industry-Scale

(ends 9:30 AM)

Expo Talk Panel:

Data Scout: “From Prompt to Corpus: Accelerating Domain-Specific Data Collection with LLMGuided Discovery”

(ends 9:30 AM)

Expo Talk Panel:

Toward General Full Autonomy: Open Research Challenges in Scalable Self-Driving

(ends 9:30 AM)

Expo Talk Panel:

Beyond Benchmarks: Rethinking Reasoning in Language Models

(ends 9:30 AM)

Expo Talk Panel:

Telling Stories at Scale: Multimodal ML in the Global Media Landscape

(ends 9:30 AM)

Expo Talk Panel:

Foundational Generative Recommendations for E-Commerce

(ends 9:30 AM)

Expo Talk Panel:

GRAID: Synthetic Data Generation with Geometric Constraints and Multi-Agentic Reflection for Harmful Content Detection

(ends 9:30 AM)

9 a.m.

Affinity Workshop:

LatinX in AI

(ends 5:00 PM)

Break:

Coffee Break

(ends 10:00 AM)

9:30 a.m.

Tutorial:

New Frontiers of Hyperparameter Optimization: Recent advances and open challenges in theory and practice

(ends 12:00 PM)

Tutorial:

Model Merging: Theory, Practice and Applications

(ends 12:00 PM)

Tutorial:

Planning in the Era of Language Models

(ends 12:00 PM)

Tutorial:

Energy and Power as First-Class ML Design Metrics

(ends 12:00 PM)

Tutorial:

Foundations of Tensor/Low-Rank Computations for AI

(ends 12:00 PM)

Tutorial:

Explain AI Models: Methods and Opportunities in Explainable AI, Data-Centric AI, and Mechanistic Interpretability

(ends 12:00 PM)

Tutorial:

Human-AI Alignment: Foundations, Methods, Practice, and Challenges

(ends 12:00 PM)

10 a.m.

Education Track [10:00-5:00]

s 10:00-5:00

[10:00] Education Material Showcase

[10:00] Tutorial led by Julien Besset

[11:00] Coffee Break

[11:30] Contributed Talk #1 - Application of Multi-Agent Systems for Essay Scoring

[11:40] Contributed Talk #2 - Understanding How Neural Networks See

[11:50] Contributed Talk #3 - MCP Explorer: Interactive Learning Experience

[12:00] Contributed Talk #4 - The Invisible Fingerprints: Protecting Your Digital Images

[12:10] Contributed Talk #5 - How to Train a Model: A hands-on, interactive guide to understanding how calculus is used to train AI models.

[12:20] Contributed Talk #6 - IoT-MCP: Design and Control IoT Systems via LLMs

[12:30] Lunch Break

[1:30] Invited Talk #1 - Serena Booth

[2:00] Invited Talk #2 - Eunice Jun

[2:30] Coffee Break

[3:00] Contributed Talk #7 - Understanding Bias and Ethics in AI

[3:12] Contributed Talk #8 - Benchmarks 101

[3:24] Contributed Talk #9 - AI-Powered Agritourism Toolkit: Revolutionizing Agritourism with AI and Machine Learning

[3:36] Contributed Talk #10 - Interpreting Large Language Models (LLMs) with Geometry

[3:48] Contributed Talk #11 - AI & Human Co-Creativity: LLM Hallucinations are Features, Prompts are Experiments, AI is not a being

[4:00] Panel Discussion

(ends 5:00 PM)

noon

Expo Demonstration:

ContextForge

(ends 3:00 PM)

Expo Workshop:

Creative and Protective AI for Music and Entertainment

(ends 1:30 PM)

Expo Demonstration:

Mobile Video Diffusion Transformers

(ends 3:00 PM)

Expo Demonstration:

SwiftEdit: Fast Text-guided Image Editing via One-step Diffusion on a Mobile Device

(ends 3:00 PM)

Expo Demonstration:

Disaggregated LLM Serving on AI Accelerators

(ends 3:00 PM)

Expo Demonstration:

Reasoning through Multimodal End-to-End Decision Transformer Networks and Vision Language Action (VLA) models

(ends 3:00 PM)

Expo Demonstration:

Generating group photos of multiple people from text and reference images

(ends 3:00 PM)

Expo Demonstration:

Soft Prompts for On-Device Content Moderation

(ends 3:00 PM)

Expo Demonstration:

Parallel generation with verification on device

(ends 3:00 PM)

Expo Demonstration:

Efficient LiDAR Processing with AI Models Leveraging Heterogeneous Compute

(ends 3:00 PM)

Expo Demonstration:

Multimodal AI Forensic Search for Video Surveillance

(ends 3:00 PM)

Expo Demonstration:

Pushing the boundaries of chemical synthesis with RetroChimera

(ends 3:00 PM)

Expo Demonstration:

BeeAI

(ends 3:00 PM)

Expo Demonstration:

Interpretable AI for Risk-Based Assessment in Global Supply Chains

(ends 3:00 PM)

Expo Demonstration:

Build verifiable apps using Generative AI and Automated Reasoning

(ends 3:00 PM)

Break:

Hosted Lunch

(ends 1:30 PM)

Expo Workshop:

CausalFairness: An Open-Source Python Library for Causal Fairness Analysis

(ends 1:30 PM)

Expo Demonstration:

Building Safe, Compliant, and Observable Agentic Systems for Generative AI Applications

(ends 3:00 PM)

Expo Demonstration:

ALICE: Agentic Logic for Incident and Codebug Elimination

(ends 3:00 PM)

Expo Workshop:

Checkmate: Fine-tune your own small language model for real-time chess reasoning and gameplay on AWS Trainium

(ends 1:30 PM)

Expo Workshop:

Multimodal Superintelligence Workshop

(ends 1:30 PM)

Expo Workshop:

Large-Scale Real-World Physical AI Systems

(ends 1:30 PM)

Expo Workshop:

Introduction to Generative Computing

(ends 1:30 PM)

Expo Workshop:

Exploring Trust and Reliability in LLM Evaluation

(ends 1:30 PM)

Exhibitor Spot Talks - Session 1 [12:00-6:00]

Talks 12:00-6:00

Exhibitor Talk - Simular

Recycling the World Computer: Fault-Tolerant LLM Training on Idle GPU Capacity

Half Is Heroic: Rewarding Non-Answers for Responsible AI Decision-Making

Auto-SWE-Bench: Scalable, Real-World Benchmarks for LLM Coding Evaluation

Exhibitor Talk - Optiver

Tabular and Causal Foundation Modelling: TabDPT and CausalPFN

Exhibitor Talk

Rights Management Capabilities and Enforcement for AI Music

Exploring Pathways into Quantitative Research

Semantic Parsing at Bloomberg

Entropy by Design: Synthetic Data at Scale

ATLAS: AdapTive-LeArning Speculator System for Real-Time LLM Inference Acceleration with Together AI

Exhibitor Talk - Cohere

Drug Discovery with Large-Scale, Physics-Based Synthetic Data at D. E. Shaw Research

Agentic AI: Exploring Evolution and Evaluation

Measuring Enterprise Agents - Production Readiness Index and Evaluation Environment

Measuring Emergent Behavior in AI Agents - Weights & Biases

New Frontier of AI: Eval, RL, and What's Next

Latent Thought Models with Variational Bayes Inference-Time Computation

Exhibitor Talk - MathWorks: Would you trust your AI model with your life?

I for Code: What We’ve Learned (and Whats Next)

From Agent Soup to Proper Software Design: Putting the Developer Back in Control of Generative AI with Mellea

Realizing Personal and Enterprise AI Twins - Lenovo

From RLHF to RL Environments - Welcoming Agents to the Real World

Exhibitor Talk - WRITER

Exhibitor Talk - Rennaissance Philanthropy

Algorithmic Trading with Large-Scale Deep Learning

Automated Curation of Foundation-Scale Pretraining Datasets

Databricks Presents a New IDP Benchmark

Decentralized Diffusion Models

The State of Open Source AI and a Look Into the Future

(ends 6:00 PM)

Expo Demonstration:

Learning to Steer LLMs with AI Steerability 360 and In-Context Explainability 360

(ends 3:00 PM)

Exhibit Sponsor Hall:

Exhibit Sponsor Hall

(ends 8:00 PM)

Expo Demonstration:

Who Needs Attention Anyway? Elastic State Models for Real-Time Streaming Tasks

(ends 3:00 PM)

Expo Demonstration:

LLM-Powered Intelligent Data Engineering: From Workflow Design to Ingestion andQuality Assurance

(ends 3:00 PM)

1 p.m.

Affinity Workshop:

Muslims in ML

(ends 5:30 PM)

Affinity Workshop:

New in ML

(ends 5:00 PM)

1:30 p.m.

Tutorial:

Foundations of Imitation Learning: From Language Modeling to Continuous Control

(ends 4:00 PM)

Tutorial:

Autoregressive Models Beyond Language

(ends 4:00 PM)

Tutorial:

Recent Developments in Geometric Machine Learning: Foundations, Models, and More

(ends 4:00 PM)

Tutorial:

The Science of Benchmarking: What’s Measured, What’s Missed, and What’s Next

(ends 4:00 PM)

Tutorial:

Theoretical Insights on Training Instability in Deep Learning

(ends 4:00 PM)

Tutorial:

Scale Test-Time Compute on Modern Hardware

(ends 4:00 PM)

Tutorial:

Data Privacy, Memorization, & Legal Implications in Generative AI: A Practical Guide

(ends 4:00 PM)

4 p.m.

Expo Talk Panel:

Agentic AI/RL

(ends 5:00 PM)

Expo Talk Panel:

Distributed Orthonormal Updates for Large-Scale Training

(ends 5:00 PM)

Expo Talk Panel:

Building Foundational Models for Robotics at Tesla

(ends 5:00 PM)

Expo Talk Panel:

Building an AI Ecosystem for Multiscale Biological Discovery

(ends 5:00 PM)

Break:

Coffee Break

(ends 4:30 PM)

Expo Talk Panel:

Ring-1T, Ring-linear and Ming-Flash-Omni: Scaling Knowledge-Enhanced Large Language Models for Reasoning and Efficiency

(ends 5:00 PM)

Expo Talk Panel:

Recent developments in embodied AI

(ends 5:00 PM)

5:30 p.m.

Remarks:

Welcome Remarks

(ends 6:00 PM)

6 p.m.

Reception:

Welcome Reception

(ends 8:00 PM)

Affinity Poster Session:

Affinity Joint Poster Session

(ends 9:00 PM)

WED 3 DEC

7:30 a.m.

Registration Desk

(ends 6:00 PM)

8 a.m.

Break:

Coffee Break

(ends 8:30 AM)

8:30 a.m.

San Diego Invited Talk:

The Oak Architecture: A Vision of SuperIntelligence from Experience

Rich Sutton

(ends 9:30 AM)

9 a.m.

Exhibit Sponsor Hall:

Exhibit Sponsor Hall

(ends 5:00 PM)

9:30 a.m.

Exhibitor Spot Talks - Session 2 [9:30-4:45]

Talks 9:30-5:00

Arm AI Acceleration in Action: ExecuTorch + ONNX on Mobile and Edge

The Importance and Fragility of CoT Monitorability

Financial Markets: The Ultimate Testbed for Intelligence (Susquehanna)

Scaling AI Workloads with Decentralized GPU Networks: A Systems Perspective

Dolphin: A Large-Scale ASR Model for Eastern Languages

AI for Creativity

Building Enterprise AI to Transform Productivity: Lessons from Atlassian

Bridging Research & Reality - Applied AI, Lessons from CommBank on Applied AI

Exhibitor Talk - Yokogawa Digital Corporation

Scaling Data Quality in the Era of LLMs: A Quality Framework

Exploring Diffusion Transformer Designs via Grafting

Exhibitor Talk - Uber AI Solutions

Behind SWE-rebench: infrastructure to build massive datasets of SWE tasks

Pearl: A Foundation Model Advancing Small Molecule Drug Discovery

Agentic Full-Stack Benchmarking for Knowledge Work

The Quiet Enabler: AI-Amplified Discovery

Towards A Blueprint for Open Science of Foundation Models

T1: A Tool-Oriented Conversational Dataset for Multi-Turn Agentic Planning

Gen AI Firsts - Qualcomm

Personalized Dental Care: 3D generative models for biomimetic dental restorations

Building close-loop simulation with realtime generative modeling

Charting the Course for Human+AI Collaboration at Upwork

Open Source Models in Trading: Free Like a Puppy, Not Like a Beer

Accelerating AI for the Real World: Strategies for safe deployment and rapid scaling

(ends 4:45 PM)

Break:

Coffee Break

(ends 10:00 AM)

10 a.m.

Oral 1A Language Model 1 [10:00-11:00]

Orals 10:00-11:00

[10:00] Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference

[10:20] Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)

[10:40] SAVVY: Spatial Awareness via Audio-Visual LLMs through Seeing and Hearing

(ends 11:00 AM)

Oral 1B Generation/Simulation 1 [10:00-11:00]

Orals 10:00-11:00

[10:00] Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think

[10:20] On the Closed-Form of Flow Matching: Generalization Does Not Arise from Target Stochasticity

[10:40] Why Diffusion Models Don’t Memorize: The Role of Implicit Dynamical Regularization in Training

(ends 11:00 AM)

Oral 1C Theory 1 [10:00-11:00]

Orals 10:00-11:00

[10:00] Optimal Mistake Bounds for Transductive Online Learning

[10:20] High-Dimensional Calibration from Swap Regret

[10:40] Does Stochastic Gradient really succeed for bandits?

(ends 11:00 AM)

Oral 1D Multimodal 1 [10:00-11:00]

Orals 10:00-11:00

[10:00] Dynam3D: Dynamic Layered 3D Tokens Empower VLM for Vision-and-Language Navigation

[10:20] Perception Encoder: The best visual embeddings are not at the output of the network

[10:40] Interactive Cross-modal Learning for Text-3D Scene Retrieval

(ends 11:00 AM)

Oral 1E Algorithm 1 [10:00-11:00]

Orals 10:00-11:00

[10:00] Adjoint Schrödinger Bridge Sampler

[10:20] Rethinking Joint Maximum Mean Discrepancy for Visual Domain Adaptation

[10:40] Class-wise Balancing Data Replay for Federated Class-Incremental Learning

(ends 11:00 AM)

11 a.m.

Creative AI Panel:

Design for Intelligence: Humans, Machines and Nature in Emergent Co-Creation

(ends 12:00 PM)

San Diego Poster Session 1 [11:00-2:00]

Posters 11:00-2:00

Group-Level Data Selection for Efficient Pretraining

Learning Provably Improves the Convergence of Gradient Descent

LittleBit: Ultra Low-Bit Quantization via Latent Factorization

Cost-Efficient LLM Training with Lifetime-Aware Tensor Offloading via GPUDirect Storage

Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awareness

LLM Strategic Reasoning: Agentic Study through Behavioral Game Theory

Modeling the Economic Impacts of AI Openness Regulation

Social World Model-Augmented Mechanism Design Policy Learning

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training

Concept Incongruence: An Exploration of Time and Death in Role Playing

For Better or for Worse, Transformers Seek Patterns for Memorization

Taming Hyperparameter Sensitivity in Data Attribution: Practical Selection Without Costly Retraining

LeapFactual: Reliable Visual Counterfactual Explanation Using Conditional Flow Matching

Deferring Concept Bottleneck Models: Learning to Defer Interventions to Inaccurate Experts

Head Pursuit: Probing Attention Specialization in Multimodal Transformers

The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?

Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework

On the creation of narrow AI: hierarchy and nonlocality of neural network skills

Evaluating LLM-contaminated Crowdsourcing Data Without Ground Truth

Neural Networks for Learnable and Scalable Influence Estimation of Instruction Fine-Tuning Data

Bootstrapping Hierarchical Autoregressive Formal Reasoner with Chain-of-Proxy-Autoformalization

Sculpting Features from Noise: Reward-Guided Hierarchical Diffusion for Task-Optimal Feature Transformation

CXReasonBench: A Benchmark for Evaluating Structured Diagnostic Reasoning in Chest X-rays

Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective

Enhancing Multilingual LLM Pretraining with Model-Based Data Selection

STARC-9: A Large-scale Dataset for Multi-Class Tissue Classification for CRC Histopathology

ChemPile: A 250 GB Diverse and Curated Dataset for Chemical Foundation Models

Fair Continuous Resource Allocation with Equality of Impact

The Boundaries of Fair AI in Medical Image Prognosis: A Causal Perspective

DEGauss: Defending Against Malicious 3D Editing for Gaussian Splatting

Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack

Adjacent Words, Divergent Intents: Jailbreaking Large Language Models via Task Concurrency

GUARDIAN: Safeguarding LLM Multi-Agent Collaborations with Temporal Graph Modeling

Efficient Fairness-Performance Pareto Front Computation

Epistemic Uncertainty for Generated Image Detection

Semantic Surgery: Zero-Shot Concept Erasure in Diffusion Models

Information Retrieval Induced Safety Degradation in AI Agents

Improving Deep Learning for Accelerated MRI With Data Filtering

Redefining Experts: Interpretable Decomposition of Language Models for Toxicity Mitigation

DeceptionBench: A Comprehensive Benchmark for AI Deception Behaviors in Real-world Scenarios

NeuroRenderedFake: A Challenging Benchmark to Detect Fake Images Generated by Advanced Neural Rendering Methods

Comprehensive Assessment and Analysis for NSFW Content Erasure in Text-to-Image Diffusion models

CARES: Comprehensive Evaluation of Safety and Adversarial Robustness in Medical LLMs

Interpretable and Parameter Efficient Graph Neural Additive Models with Random Fourier Features

COCONut-PanCap: Joint Panoptic Segmentation and Grounded Captions for Fine-Grained Understanding and Generation

SWE-smith: Scaling Data for Software Engineering Agents

UtilGen: Utility-Centric Generative Data Augmentation with Dual-Level Task Adaptation

Limited Preference Data? Learning Better Reward Model with Latent Space Synthesis

Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning

More of the Same: Persistent Representational Harms Under Increased Representation

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents

Fairness-aware Bayes Optimal Functional Classification

Individual Fairness In Strategic Classification

Panacea: Mitigating Harmful Fine-tuning for Large Language Models via Post-fine-tuning Perturbation

Size-adaptive Hypothesis Testing for Fairness

Semantic Representation Attack against Aligned Large Language Models

Privacy Reasoning in Ambiguous Contexts

Query-Efficient Locally Private Hypothesis Selection via the Scheffe Graph

DictPFL: Efficient and Private Federated Learning on Encrypted Gradients

CryptoMoE: Privacy-Preserving and Scalable Mixture of Experts Inference via Balanced Expert Routing

Secure and Confidential Certificates of Online Fairness

Sum Estimation under Personalized Local Differential Privacy

A Private Approximation of the 2nd-Moment Matrix of Any Subsamplable Input

What Really is a Member? Discrediting Membership Inference via Poisoning

Instance-Optimality for Private KL Distribution Estimation

Generative Model Inversion Through the Lens of the Manifold Hypothesis

ConfTuner: Training Large Language Models to Express Their Confidence Verbally

WMCopier: Forging Invisible Watermarks on Arbitrary Images

A Reliable Cryptographic Framework for Empirical Machine Unlearning Evaluation

Beyond Expectations: Quantile-Guided Alignment for Risk-Calibrated Language Models

LORE: Lagrangian-Optimized Robust Embeddings for Visual Encoders

Sloth: scaling laws for LLM skills to predict multi-benchmark performance across families

LoSplit: Loss-Guided Dynamic Split for Training-Time Defense Against Graph Backdoor Attacks

Provable Gradient Editing of Deep Neural Networks

Absence Bench: Language Models Can’t See What’s Missing

Private Evolution Converges

Boosting Resilience of Large Language Models through Causality-Driven Robust Optimization

ObCLIP: Oblivious CLoud-Device Hybrid Image Generation with Privacy Preservation

Private Set Union with Multiple Contributions

From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization

AC-LoRA: (Almost) Training-Free Access Control Aware Multi-Modal LLMs

One Token Embedding Is Enough to Deadlock Your Large Reasoning Model

Inference-Time Reward Hacking in Large Language Models

Long-tailed Recognition with Model Rebalancing

Neural Rule Lists: Learning Discretizations, Rules, and Order in One Go

Backdoor Cleaning without External Guidance in MLLM Fine-tuning

Probabilistic Stability Guarantees for Feature Attributions

Empowering Decision Trees via Shape Function Branching

Finding and Reactivating Post-Trained LLMs' Hidden Safety Mechanisms

Understanding and Improving Adversarial Robustness of Neural Probabilistic Circuits

Fair Representation Learning with Controllable High Confidence Guarantees via Adversarial Inference

Backdoor Mitigation via Invertible Pruning Masks

Bridging Symmetry and Robustness: On the Role of Equivariance in Enhancing Adversarial Robustness

Evaluating the Inductive Abilities of Large Language Models: Why Chain-of-Thought Reasoning Sometimes Hurts More Than Helps

JADE: Joint Alignment and Deep Embedding for Multi-Slice Spatial Transcriptomics

The Omni-Expert: A Computationally Efficient Approach to Achieve a Mixture of Experts in a Single Expert Model

VeriLoC: Line-of-Code Level Prediction of Hardware Design Quality from Verilog Code

LLM-PySC2: Starcraft II learning environment for Large Language Models

SymRTLO: Enhancing RTL Code Optimization with LLMs and Neuron-Inspired Symbolic Reasoning

MaintainCoder: Maintainable Code Generation Under Dynamic Requirements

Learning Interestingness in Automated Mathematical Theory Formation

Fine-grained List-wise Alignment for Generative Medication Recommendation

Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Models

SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tokens

STEER-ME: Assessing the Microeconomic Reasoning of Large Language Models

GTPBD: A Fine-Grained Global Terraced Parcel and Boundary Dataset

CPRet: A Dataset, Benchmark, and Model for Retrieval in Competitive Programming

Open-Insect: Benchmarking Open-Set Recognition of Novel Species in Biodiversity Monitoring

Does Representation Guarantee Welfare?

Validating LLM-as-a-Judge Systems under Rating Indeterminacy

Precise Information Control in Long-Form Text Generation

Transferable Black-Box One-Shot Forging of Watermarks via Image Preference Models

AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems

IGD: Token Decisiveness Modeling via Information Gain in LLMs for Personalized Recommendation

CPSea: Large-scale cyclic peptide-protein complex dataset for machine learning in cyclic peptide design

FGBench: A Dataset and Benchmark for Molecular Property Reasoning at Functional Group-Level in Large Language Models

KnowMol: Advancing Molecular Large Language Models with Multi-Level Chemical Knowledge

NeuralPLexer3: Accurate Biomolecular Complex Structure Prediction with Flow Models

Mol-LLaMA: Towards General Understanding of Molecules in Large Molecular Language Model

MOOSE-Chem2: Exploring LLM Limits in Fine-Grained Scientific Hypothesis Discovery via Hierarchical Search

AANet: Virtual Screening under Structural Uncertainty via Alignment and Aggregation

CellCLIP - Learning Perturbation Effects in Cell Painting via Text-Guided Contrastive Learning

Template-Guided 3D Molecular Pose Generation via Flow Matching and Differentiable Optimization

FIGRDock: Fast Interaction-Guided Regression for Flexible Docking

Symmetry-Preserving Conformer Ensemble Networks for Molecular Representation Learning

Dynamic and Chemical Constraints to Enhance the Molecular Masked Graph Autoencoders

Learning Repetition-Invariant Representations for Polymer Informatics

TreeFinder: A US-Scale Benchmark Dataset for Individual Tree Mortality Monitoring Using High-Resolution Aerial Imagery

SentinelKilnDB: A Large-Scale Dataset and Benchmark for OBB Brick Kiln Detection in South Asia Using Satellite Imagery

scGeneScope: A Treatment-Matched Single Cell Imaging and Transcriptomics Dataset and Benchmark for Treatment Response Modeling

An Investigation of Memorization Risk in Healthcare Foundation Models

Towards Doctor-Like Reasoning: Medical RAG Fusing Knowledge with Patient Analogy through Textual Gradients

DoseSurv: Predicting Personalized Survival Outcomes under Continuous-Valued Treatments

MedMax: Mixed-Modal Instruction Tuning for Training Biomedical Assistants

FEEL: Quantifying Heterogeneity in Physiological Signals for Generalizable Emotion Recognition

MedicalNarratives: Connecting Medical Vision and Language with Localized Narratives

PatientSim: A Persona-Driven Simulator for Realistic Doctor-Patient Interactions

PRSformer: Disease Prediction from Million-Scale Individual Genotypes

ShapeEmbed: a self-supervised learning framework for 2D contour quantification

Bidirectional Representations Augmented Autoregressive Biological Sequence Generation: Application in De Novo Peptide Sequencing

Understanding protein function with a multimodal retrieval-augmented foundation model

Joint Velocity-Growth Flow Matching for Single-Cell Dynamics Modeling

Tabula: A Tabular Self-Supervised Foundation Model for Single-Cell Transcriptomics

KINDLE: Knowledge-Guided Distillation for Prior-Free Gene Regulatory Network Inference

Zero-shot protein stability prediction by inverse folding models: a free energy interpretation

Gene Regulatory Network Inference in the Presence of Selection Bias and Latent Confounders

OCTDiff: Bridged Diffusion Model for Portable OCT Super-Resolution and Enhancement

PhysioWave: A Multi-Scale Wavelet-Transformer for Physiological Signal Representation

D-VST: Diffusion Transformer for Pathology-Correct Tone-Controllable Cross-Dye Virtual Staining of Whole Slide Images

Sequential Attention-based Sampling for Histopathological Analysis

EmergentTTS-Eval: Evaluating TTS Models on Complex Prosodic, Expressiveness, and Linguistic Challenges Using Model-as-a-Judge

WritingBench: A Comprehensive Benchmark for Generative Writing

TimE: A Multi-level Benchmark for Temporal Reasoning of LLMs in Real-World Scenarios

FocalCodec: Low-Bitrate Speech Coding via Focal Modulation Networks

Unbiased Sliced Wasserstein Kernels for High-Quality Audio Captioning

Benford’s Curse: Tracing Digit Bias to Numerical Hallucination in LLMs

SALMONN-omni: A Standalone Speech LLM without Codec Injection for Full-duplex Conversation

Probabilistic Reasoning with LLMs for Privacy Risk Estimation

ZeroSep: Separate Anything in Audio with Zero Training

Learning to Instruct for Visual Instruction Tuning

The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning

Geo-Sign: Hyperbolic Contrastive Regularisation for Geometrically Aware Sign Language Translation

STEP: A Unified Spiking Transformer Evaluation Platform for Fair and Reproducible Benchmarking

Execution Guided Line-by-Line Code Generation

TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling

DETree: DEtecting Human-AI Collaborative Texts via Tree-Structured Hierarchical Representation Learning

QiMeng-SALV: Signal-Aware Learning for Verilog Code Generation

SimulMEGA: MoE Routers are Advanced Policy Makers for Simultaneous Speech Translation

Hogwild! Inference: Parallel LLM Generation via Concurrent Attention

Atom of Thoughts for Markov LLM Test-Time Scaling

Exploring Polyglot Harmony: On Multilingual Data Allocation for Large Language Models Pretraining

Reverse Engineering Human Preferences with Reinforcement Learning

The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning

Preference Distillation via Value based Reinforcement Learning

VITA-Audio: Fast Interleaved Audio-Text Token Generation for Efficient Large Speech-Language Model

BlockDecoder: Boosting ASR Decoders with Context and Merger Modules

The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity

SkyLadder: Better and Faster Pretraining via Context Window Scheduling

Who Reasons in the Large Language Models?

Bohdi: Heterogeneous LLM Fusion with Automatic Data Exploration

Generalizable, real-time neural decoding with hybrid state-space models

Bridging Scales: Spectral Theory Reveals How Local Connectivity Rules Sculpt Global Neural Dynamics in Spatially Extended Networks

Finding separatrices of dynamical flows with Deep Koopman Eigenfunctions

SplashNet: Split‑and‑Share Encoders for Accurate and Efficient Typing with Surface Electromyography

Learning to cluster neuronal function

CRRL: Learning Channel-invariant Neural Representations for High-performance Cross-day Decoding

Error Broadcast and Decorrelation as a Potential Artificial and Natural Learning Mechanism

Riemannian Flow Matching for Brain Connectivity Matrices via Pullback Geometry

OMiSO: Adaptive optimization of state-dependent brain stimulation to shape neural population states

Jacobian-Based Interpretation of Nonlinear Neural Encoding Model

ORBIT - Open Recommendation Benchmark for Reproducible Research with Hidden Tests

Generating Computational Cognitive models using Large Language Models

Brain-Like Processing Pathways Form in Models With Heterogeneous Experts

Volume Transmission Implements Context Factorization to Target Online Credit Assignment and Enable Compositional Generalization

Self-Calibrating BCIs: Ranking and Recovery of Mental Targets Without Labels

Explicitly Modeling Subcortical Vision with a Neuro-Inspired Front-End Improves CNN Robustness

HetSyn: Versatile Timescale Integration in Spiking Neural Networks via Heterogeneous Synapses

PANORAMA: A Dataset and Benchmarks Capturing Decision Trails and Rationales in Patent Examination

BRACE: A Benchmark for Robust Audio Caption Quality Evaluation

IRRISIGHT: A Large-Scale Multimodal Dataset and Scalable Pipeline to Address Irrigation and Water Management in Agriculture

Words That Unite The World: A Unified Framework for Deciphering Central Bank Communications

On Efficiency-Effectiveness Trade-off of Diffusion-based Recommenders

How Benchmark Prediction from Fewer Data Misses the Mark

Fast Inference for Augmented Large Language Models

Risk-Averse Total-Reward Reinforcement Learning

Value-Guided Decision Transformer: A Unified Reinforcement Learning Framework for Online and Offline Settings

Boundary-Value PDEs Meet Higher-Order Differential Topology-aware GNNs

FP64 is All You Need: Rethinking Failure Modes in Physics-Informed Neural Networks

Understanding Generalization in Physics Informed Models through Affine Variety Dimensions

AutoHood3D: A Multi‑Modal Benchmark for Automotive Hood Design and Fluid–Structure Interaction

ML4CFD Competition: Results and Retrospective Analysis

DrivAerStar: An Industrial-Grade CFD Dataset for Vehicle Aerodynamic Optimization

Scaling Physical Reasoning with the PHYSICS Dataset

Dendritic Resonate-and-Fire Neuron for Effective and Efficient Long Sequence Modeling

Let Brain Rhythm Shape Machine Intelligence for Connecting Dots on Graphs

Extracting task-relevant preserved dynamics from contrastive aligned neural recordings

Incremental Sequence Classification with Temporal Consistency

Unveiling the Spatial-temporal Effective Receptive Fields of Spiking Neural Networks

Spectral Analysis of Representational Similarity with Limited Neurons

Caption This, Reason That: VLMs Caught in the Middle

Estimating cognitive biases with attention-aware inverse planning

Local-Global Coupling Spiking Graph Transformer for Brain Disorders Diagnosis from Two Perspectives

Cross-Modal Representational Knowledge Distillation for Enhanced Spike-informed LFP Modeling

Model Selection for Off-policy Evaluation: New Algorithms and Experimental Protocol

Scaling Offline RL via Efficient and Expressive Shortcut Models

RLtools: A Fast, Portable Deep Reinforcement Learning Library for Continuous Control

MyoChallenge 2024: A New Benchmark for Physiological Dexterity and Agility in Bionic Humans

Uncertainty-Sensitive Privileged Learning

PALQO: Physics-informed model for Accelerating Large-scale Quantum Optimization

Efficient Parametric SVD of Koopman Operator for Stochastic Dynamical Systems

STNet: Spectral Transformation Network for Solving Operator Eigenvalue Problem

AiDE-Q: Synthetic Labeled Datasets Can Enhance Learning Models for Quantum Property Estimation

PINN Balls: Scaling Second-Order Methods for PINNs with Domain Decomposition and Adaptive Sampling

Revisiting End-to-End Learning with Slide-level Supervision in Computational Pathology

PAC Bench: Do Foundation Models Understand Prerequisites for Executing Manipulation Policies?

Embodied Cognition Augmented End2End Autonomous Driving

AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning

Accelerating Visual-Policy Learning through Parallel Differentiable Simulation

What Do Latent Action Models Actually Learn?

Active Test-time Vision-Language Navigation

FreqPolicy: Frequency Autoregressive Visuomotor Policy with Continuous Tokens

DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge

VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching

EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models

Rotary Masked Autoencoders are Versatile Learners

Self-Perturbed Anomaly-Aware Graph Dynamics for Multivariate Time-Series Anomaly Detection

Channel Simulation and Distributed Compression with Ensemble Rejection Sampling

ScatterAD: Temporal-Topological Scattering Mechanism for Time Series Anomaly Detection

Single-Step Operator Learning for Conditioned Time-Series Diffusion Models

xLSTM-Mixer: Multivariate Time Series Forecasting by Mixing via Scalar Memories

TARFVAE: Efficient One-Step Generative Time Series Forecasting via TARFLOW based VAE

COOPERA: Continual Open-Ended Human-Robot Assistance

Aux-Think: Exploring Reasoning Strategies for Data-Efficient Vision-Language Navigation

BEAST: Efficient Tokenization of B-Splines Encoded Action Sequences for Imitation Learning

DynaRend: Learning 3D Dynamics via Masked Future Rendering for Robotic Manipulation

AC-DiT: Adaptive Coordination Diffusion Transformer for Mobile Manipulation

EfficientNav: Towards On-Device Object-Goal Navigation with Navigation Map Caching and Retrieval

Contact Map Transfer with Conditional Diffusion Model for Generalizable Dexterous Grasp Generation

Compliant Residual DAgger: Improving Real-World Contact-Rich Manipulation with Human Corrections

Learning 3D Persistent Embodied World Models

Real-Time Execution of Action Chunking Flow Policies

Enhancing Tactile-based Reinforcement Learning for Robotic Control

VideoCAD: A Dataset and Model for Learning Long‑Horizon 3D CAD UI Interactions from Video

Demystifying Network Foundation Models

RADAR: Benchmarking Language Models on Imperfect Tabular Data

AstroVisBench: A Code Benchmark for Scientific Computing and Visualization in Astronomy

Quantifying Generalisation in Imitation Learning

ArchPower: Dataset for Architecture-Level Power Modeling of Modern CPU Design

Towards A Translative Model of Sperm Whale Vocalization

SMARTraj$^2$: A Stable Multi-City Adaptive Method for Multi-View Spatio-Temporal Trajectory Representation Learning

Synthesizing Performance Constraints for Evaluating and Improving Code Efficiency

DualMPNN: Harnessing Structural Alignments for High-Recovery Inverse Protein Folding

Personalized Decision Modeling: Utility Optimization or Textualized-Symbolic Reasoning

RobustMerge: Parameter-Efficient Model Merging for MLLMs with Direction Robustness

R$^2$ec: Towards Large Recommender Models with Reasoning

Predicting Empirical AI Research Outcomes with Language Models

Seeing What Matters: Generalizable AI-generated Video Detection with Forensic-Oriented Augmentation

IneqSearch: Hybrid Reasoning for Olympiad Inequality Proofs

SmartCache: Context-aware Semantic Cache for Efficient Multi-turn LLM Inference

DoDo-Code: an Efficient Levenshtein Distance Embedding-based Code for 4-ary IDS Channel

Data Fusion for Partial Identification of Causal Effects

Causal Explanation-Guided Learning for Organ Allocation

Practical do-Shapley Explanations with Estimand-Agnostic Causal Inference

Efficient Randomized Experiments Using Foundation Models

ProDAG: Projected Variational Inference for Directed Acyclic Graphs

Counterfactual Implicit Feedback Modeling

Handling Missing Responses under Cluster Dependence with Applications to Language Model Evaluation

Do-PFN: In-Context Learning for Causal Effect Estimation

It’s Hard to Be Normal: The Impact of Noise on Structure-agnostic Estimation

Estimating Interventional Distributions with Uncertain Causal Graphs through Meta-Learning

Beyond the Average: Distributional Causal Inference under Imperfect Compliance

Confounding Robust Deep Reinforcement Learning: A Causal Approach

Root Cause Analysis of Outliers with Missing Structural Knowledge

Structural Causal Bandits under Markov Equivalence

Conformal Prediction for Causal Effects of Continuous Treatments

Multivariate Dynamic Mediation Analysis under a Reinforcement Learning Framework

FuncGenFoil: Airfoil Generation and Editing Model in Function Space

Look Before You Leap: A GUI-Critic-R1 Model for Pre-Operative Error Diagnosis in GUI Automation

Demystifying Spectral Feature Learning for Instrumental Variable Regression

Curious Causality-Seeking Agents Learn Meta Causal World

Decomposing Interventional Causality into Synergistic, Redundant, and Unique Components

Learning CAD Modeling Sequences via Projection and Part Awareness

Connecting Jensen–Shannon and Kullback–Leibler Divergences: A New Bound for Representation Learning

Copresheaf Topological Neural Networks: A Generalized Deep Learning Framework

VESSA: Video-based objEct-centric Self-Supervised Adaptation for Visual Foundation Models

Graph Your Own Prompt

TREND: Unsupervised 3D Representation Learning via Temporal Forecasting for LiDAR Perception

Ultrametric Cluster Hierarchies: I Want ‘em All!

Structure-Aware Fusion with Progressive Injection for Multimodal Molecular Representation Learning

HELM: Hyperbolic Large Language Models via Mixture-of-Curvature Experts

Randomized-MLP Regularization Improves Domain Adaptation and Interpretability in DINOv2

Joint‑Embedding vs Reconstruction: Provable Benefits of Latent Space Prediction for Self‑Supervised Learning

Emergence of Linear Truth Encodings in Language Models

Contrastive Representations for Temporal Reasoning

SparseMVC: Probing Cross-view Sparsity Variations for Multi-view Clustering

Adaptive Cannistraci-Hebb Network Automata Modelling of Complex Networks for Path-based Link Prediction

Aeolus: A Multi-structural Flight Delay Dataset

Test-Time Adaptation by Causal Trimming

Continual Model Merging without Data: Dual Projections for Balancing Stability and Plasticity

Merging on the Fly Without Retraining: A Sequential Approach to Scalable Continual Model Merging

Enhancing Visual Prompting through Expanded Transformation Space and Overfitting Mitigation

Memory-Integrated Reconfigurable Adapters: A Unified Framework for Settings with Multiple Tasks

Wasserstein Transfer Learning

Rethinking Out-of-Distribution Detection and Generalization with Collective Behavior Dynamics

Fantastic Features and Where to Find Them: A Probing Method to combine Features from Multiple Foundation Models

PAID: Pairwise Angular-Invariant Decomposition for Continual Test-Time Adaptation

Searching Latent Program Spaces

Few-Shot Knowledge Distillation of LLMs With Counterfactual Explanations

Plug-and-play Feature Causality Decomposition for Multimodal Representation Learning

In-Context Compositional Learning vis Sparse Coding Transformer

ProteinConformers: Benchmark Dataset for Simulating Protein Conformational Landscape Diversity and Plausibility

Lorentz Local Canonicalization: How to make any Network Lorentz-Equivariant

Benchmarking Large Language Models with Integer Sequence Generation Tasks

SpecMAS: A Multi-Agent System for Self-Verifying System Generation via Formal Model Checking

AF-UMC: An Alignment-Free Fusion Framework for Unaligned Multi-View Clustering

SORTeD Rashomon Sets of Sparse Decision Trees: Anytime Enumeration

Confidence-Aware With Prototype Alignment for Partial Multi-label Learning

QuanDA: Quantile-Based Discriminant Analysis for High-Dimensional Imbalanced Classification

Near-Exponential Savings for Population Mean Estimation with Active Learning

Breaking the Gradient Barrier: Unveiling Large Language Models for Strategic Classification

Reliably detecting model failures in deployment without labels

Imbalances in Neurosymbolic Learning: Characterization and Mitigating Strategies

Incomplete Multi-view Deep Clustering with Data Imputation and Alignment

Scalable and adaptive prediction bands with kernel sum-of-squares

Evolutionary Multi-View Classification via Eliminating Individual Fitness Bias

Distributionally Robust Learning for Multi-source Unsupervised Domain Adaptation

DUET: Dual-Perspective Pseudo Labeling and Uncertainty-aware Exploration & Exploitation Training for Source-Free Domain Adaptation

Purest Quantum State Identification

The Power of Iterative Filtering for Supervised Learning with (Heavy) Contamination

On Minimax Estimation of Parameters in Softmax-Contaminated Mixture of Experts

Formal Models of Active Learning from Contrastive Examples

Efficient PAC Learning for Realizable-Statistic Models via Convex Surrogates

Thompson Sampling for Multi-Objective Linear Contextual Bandit

IMPROVED LEARNING THEORY FOR KERNEL DISTRIBUTION REGRESSION WITH TWO-STAGE SAMPLING

Online Bilateral Trade With Minimal Feedback: Don’t Waste Seller’s Time

Evolutionary Prediction Games

Robust Equilibria in Continuous Games: From Strategic to Dynamic Robustness

Combinatorial Ski Rental Problem: Robust and Learning-Augmented Algorithms

Learning-Augmented Facility Location Mechanisms for the Envy Ratio Objective

Assignments for Congestion-Averse Agents: Seeking Competitive and Envy-Free Solutions

The Complexity of Symmetric Equilibria in Min-Max Optimization and Team Zero-Sum Games

On the Existence and Complexity of Core-Stable Data Exchanges

Rethinking Joint Maximum Mean Discrepancy for Visual Domain Adaptation

Continuous Domain Generalization

MALinZero: Efficient Low-Dimensional Search for Mastering Complex Multi-Agent Planning

Temperature is All You Need for Generalization in Langevin Dynamics and other Markov Processes

Optimal Mistake Bounds for Transductive Online Learning

On Traceability in $\ell_p$ Stochastic Convex Optimization

Johnson-Lindenstrauss Lemma Beyond Euclidean Geometry

From Information to Generative Exponent: Learning Rate Induces Phase Transitions in SGD

Improved Balanced Classification with Theoretically Grounded Loss Functions

High-Dimensional Calibration from Swap Regret

Unveiling the Power of Multiple Gossip Steps: A Stability-Based Generalization Analysis in Decentralized Training

Absorb and Converge: Provable Convergence Guarantee for Absorbing Discrete Diffusion Models

Greedy Algorithms for Structured Bandits: A Sharp Characterization of Asymptotic Success / Failure

Multi-Agent Imitation by Learning and Sampling from Factorized Soft Q-Function

Self-Verification Provably Prevents Model Collapse in Recursive Synthetic Training

Optimality and NP-Hardness of Transformers in Learning Markovian Dynamical Functions

Towards Understanding Transformers in Learning Random Walks

Conservative classifiers do consistently well with improving agents: characterizing statistical and online learning

Provable Sample-Efficient Transfer Learning Conditional Diffusion Models via Representation Learning

Computable universal online learning

Marginal-Nonuniform PAC Learnability

Eliciting Reasoning in Language Models with Cognitive Tools

Wonder Wins Ways: Curiosity-Driven Exploration through Multi-Agent Contextual Calibration

Bootstrap Off-policy with World Model

Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts

Agentic RL Scaling Law: Spontaneous Code Execution for Mathematical Problem Solving

Robust and Scalable Autonomous Reinforcement Learning in Irreversible Environments

Reinforcing the Diffusion Chain of Lateral Thought with Diffusion Language Models

DyMoDreamer: World Modeling with Dynamic Modulation

Continual Knowledge Adaptation for Reinforcement Learning

Active Seriation: Efficient Ordering Recovery with Statistical Guarantees

Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel

Can Diffusion Models Disentangle? A Theoretical Perspective

Efficiently Maintaining the Multilingual Capacity of MCLIP in Downstream Cross-Modal Retrieval Tasks

Pareto Optimal Risk-Agnostic Distributional Bandits with Heavy-Tail Rewards

Generalization Bounds for Rank-sparse Neural Networks

Consistency of the $k_n$-nearest neighbor rule under adaptive sampling

Exploration via Feature Perturbation in Contextual Bandits

Discrete Diffusion Models: Novel Analysis and New Sampler Guarantees

From Kolmogorov to Cauchy: Shallow XNet Surpasses KANs

Split conformal classification with unsupervised calibration

Hybrid Latent Reasoning via Reinforcement Learning

Off-policy Reinforcement Learning with Model-based Exploration Augmentation

CORE: Collaborative Optimization with Reinforcement Learning and Evolutionary Algorithm for Floorplanning

Turning Sand to Gold: Recycling Data to Bridge On-Policy and Off-Policy Learning via Causal Bound

DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Distribution Learning Meets Graph Structure Sampling

REINFORCEMENT LEARNING FOR INDIVIDUAL OPTIMAL POLICY FROM HETEROGENEOUS DATA

ADG: Ambient Diffusion-Guided Dataset Recovery for Corruption-Robust Offline Reinforcement Learning

Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RL

Finite-Sample Analysis of Policy Evaluation for Robust Average Reward Reinforcement Learning

Efficient and Near-Optimal Algorithm for Contextual Dueling Bandits with Offline Regression Oracles

Learning Personalized Ad Impact via Contextual Reinforcement Learning under Delayed Rewards

Zero-Shot Trajectory Planning for Signal Temporal Logic Tasks

True Impact of Cascade Length in Contextual Cascading Bandits

ActiveVOO: Value of Observation Guided Active Knowledge Acquisition for Open-World Embodied Lifted Regression Planning

NaDRO: Leveraging Dual-Reward Strategies for LLMs Training on Noisy Data

Reinforcement Learning Finetunes Small Subnetworks in Large Language Models

Tight Bounds for Maximum Weight Matroid Independent Set and Matching in the Zero Communication Model

Revisiting Glorot Initialization for Long-Range Linear Recurrences

Learning-Augmented Online Bipartite Fractional Matching

Learning-Augmented Algorithms for $k$-median via Online Learning

Unbalanced Optimal Total Variation Transport: A Theoretical Approach to Spatial Resource Allocation Problems

Reasoning by Superposition: A Theoretical Perspective on Chain of Continuous Thought

Robust Estimation Under Heterogeneous Corruption Rates

STAR-Bets: Sequential TArget-Recalculating Bets for Tighter Confidence Intervals

Nearly-Linear Time and Massively Parallel Algorithms for $k$-anonymity

Optimal Minimum Width for the Universal Approximation of Continuously Differentiable Functions by Deep Narrow MLPs

One Filters All: A Generalist Filter For State Estimation

Pragmatic Heterogeneous Collaborative Perception via Generative Communication Mechanism

Taming Adversarial Constraints in CMDPs

Sharp Gap-Dependent Variance-Aware Regret Bounds for Tabular MDPs

Efficient Spectral Control of Partially Observed Linear Dynamical Systems

From Contextual Combinatorial Semi-Bandits to Bandit List Classification: Improved Sample Complexity with Sparse Rewards

Does Stochastic Gradient really succeed for bandits?

SOMBRL: Scalable and Optimistic Model-Based RL

Stackelberg Self-Annotation: A Robust Approach to Data-Efficient LLM Alignment

UMoE: Unifying Attention and FFN with Shared Experts

Learn2Mix: Training Neural Networks Using Adaptive Data Integration

Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning

From Pretraining to Pathology: How Noise Leads to Catastrophic Inheritance in Medical Models

MODEL SHAPLEY: Find Your Ideal Parameter Player via One Gradient Backpropagation

DenoiseRotator: Enhance Pruning Robustness for LLMs via Importance Concentration

Reducing the Probability of Undesirable Outputs in Language Models Using Probabilistic Inference

Efficient Representativeness-Aware Coreset Selection

Efficient Data Selection at Scale via Influence Distillation

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs

Model Merging in Pre-training of Large Language Models

Semantic-guided Diverse Decoding for Large Language Model

Distribution-Aligned Decoding for Efficient LLM Task Adaptation

MoleBridge: Synthetic Space Projecting with Discrete Markov Bridges

Self-Adapting Language Models

Matryoshka Pilot: Learning to Drive Black-Box LLMs with LLMs

Neural Fractional Attention Differential Equations

EasySpec: Layer-Parallel Speculative Decoding for Efficient Multi-GPU Utilization

On the Sample Complexity Bounds of Bilevel Reinforcement Learning

Activated LoRA: Fine-tuned LLMs for Intrinsics

Blending Complementary Memory Systems in Hybrid Quadratic-Linear Transformers

Tensor Product Attention Is All You Need

Linear Attention for Efficient Bidirectional Sequence Modeling

From Sequence to Structure: Uncovering Substructure Reasoning in Transformers

Learning Cocoercive Conservative Denoisers via Helmholtz Decomposition for Poisson Imaging Inverse Problems

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections

DataRater: Meta-Learned Dataset Curation

Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation

Point4Bit: Post Training 4-bit Quantization for Point Cloud 3D Detection

G-Net: A Provably Easy Construction of High-Accuracy Random Binary Neural Networks

Integration Matters for Learning PDEs with Backwards SDEs

Adaptive Inference-Time Scaling via Cyclic Diffusion Search

Unlocker: Disentangle the Deadlock of Learning between Label-noisy and Long-tailed Data

Effective Neural Approximations for Geometric Optimization Problems

Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search

Computational Budget Should Be Considered in Data Selection

$\texttt{BetaConform}$: Efficient MAP Estimation of LLM Ensemble Judgment Performance with Prior Transfer

LookWhere? Efficient Visual Recognition by Learning Where to Look and What to See from Self-Supervision

DuSA: Fast and Accurate Dual-Stage Sparse Attention Mechanism Accelerating Both Training and Inference

EngiBench: A Framework for Data-Driven Engineering Design Research

Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordia

Streaming Audio Generation from Discrete Tokens via Streaming Flow Matching

PANTHER: Generative Pretraining Beyond Language for Sequential User Behavior Modeling

EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test

CCS: Controllable and Constrained Sampling with Diffusion Models via Initial Noise Perturbation

Probabilistic Token Alignment for Large Language Model Fusion

Transition Matching: Scalable and Flexible Generative Modeling

Why Diffusion Models Don’t Memorize: The Role of Implicit Dynamical Regularization in Training

Video Diffusion Models Excel at Tracking Similar-Looking Objects Without Supervision

Schrödinger Bridge Matching for Tree-Structured Costs and Entropic Wasserstein Barycentres

Seeds of Structure: Patch PCA Reveals Universal Compositional Cues in Diffusion Models

P-Law: Predicting Quantitative Scaling Law with Entropy Guidance in Large Recommendation Models

Constrained Discrete Diffusion

Fractional Diffusion Bridge Models

Generative Modeling of Full-Atom Protein Conformations using Latent Diffusion on Graph Embeddings

GRIFFIN: Effective Token Alignment for Faster Speculative Decoding

Flow Density Control: Generative Optimization Beyond Entropy-Regularized Fine-Tuning

Point Cloud Synthesis Using Inner Product Transforms

On the Closed-Form of Flow Matching: Generalization Does Not Arise from Target Stochasticity

TRIM: Scalable 3D Gaussian Diffusion Inference with Temporal and Spatial Trimming

Why Knowledge Distillation Works in Generative Models: A Minimal Working Explanation

Sequence Modeling with Spectral Mean Flows

Omni-Mol: Multitask Molecular Model for Any-to-any Modalities

Physics-Constrained Flow Matching: Sampling Generative Models with Hard Constraints

Diffusion Adaptive Text Embedding for Text-to-Image Diffusion Models

Cross-fluctuation phase transitions reveal sampling dynamics in diffusion models

Constrained Entropic Unlearning: A Primal-Dual Framework for Large Language Models

Dense Associative Memory with Epanechnikov Energy

Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention

Two-Steps Diffusion Policy for Robotic Manipulation via Genetic Denoising

Energy Matching: Unifying Flow Matching and Energy-Based Models for Generative Modeling

Multi-Token Prediction Needs Registers

Learned Prefix Caching for Efficient LLM Inference

Normalized Attention Guidance: Universal Negative Guidance for Diffusion Models

Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference

Fast Solvers for Discrete Diffusion Models: Theory and Applications of High-Order Algorithms

A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank Clone

Efficient Part-level 3D Object Generation via Dual Volume Packing

Inference-Time Scaling for Flow Models via Stochastic Generation and Rollover Budget Forcing

SpecEM: Training-Free LLM Ensembling via Iterative Drafting, Verification, and Online Feedback

AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Document Understanding

Active Target Discovery under Uninformative Priors: The Power of Permanent and Transient Memory

MDNS: Masked Diffusion Neural Sampler via Stochastic Optimal Control

Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanation

Shortcutting Pre-trained Flow Matching Diffusion Models is Almost Free Lunch

PDPO: Parametric Density Path Optimization

Scalable In-context Ranking with Generative Models

The Temporal Graph of Bitcoin Transactions

Cross-Domain Graph Data Scaling: A Showcase with Diffusion Models

OPTFM: A Scalable Multi-View Graph Transformer for Hierarchical Pre-Training in Combinatorial Optimization

Restricted Global-Aware Graph Filters Bridging GNNs and Transformer for Node Classification

Understanding and Enhancing Message Passing on Heterophilic Graphs via Compatibility Matrix

The Underappreciated Power of Vision Models for Graph Structural Understanding

HeroFilter: Adaptive Spectral Graph Filter for Varying Heterophilic Relations

SONAR: Long-Range Graph Propagation Through Information Waves

Making Classic GNNs Strong Baselines Across Varying Homophily: A Smoothness–Generalization Perspective

Towards Multiscale Graph-based Protein Learning with Geometric Secondary Structural Motifs

Pool Me Wisely: On the Effect of Pooling in Transformer-Based Models

A Little Depth Goes a Long Way: The Expressive Power of Log-Depth Transformers

Visual Instruction Bottleneck Tuning

Auditing Meta-Cognitive Hallucinations in Reasoning Large Language Models

Learning with Calibration: Exploring Test-Time Computing of Spatio-Temporal Forecasting

CIDD: Collaborative Intelligence for Structure-Based Drug Design Empowered by LLMs

Double Descent Meets Out-of-Distribution Detection: Theoretical Insights and Empirical Analysis on the Role of Model Complexity

Adversary Aware Optimization for Robust Defense

Clip-and-Verify: Linear Constraint-Driven Domain Clipping for Accelerating Neural Network Verification

Asymmetric Duos: Sidekicks Improve Uncertainty

Adjusting Initial Noise to Mitigate Memorization in Text-to-Image Diffusion Models

Path-Enhanced Contrastive Learning for Recommendation

SSTAG: Structure-Aware Self-Supervised Learning Method for Text-Attributed Graphs

DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs

SALoM: Structure Aware Temporal Graph Networks with Long-Short Memory Updater

Probing Equivariance and Symmetry Breaking in Convolutional Networks

Taxonomy of reduction matrices for Graph Coarsening

Geometry-Aware Edge Pooling for Graph Neural Networks

Training Robust Graph Neural Networks by Modeling Noise Dependencies

Permutation Equivariant Neural Controlled Differential Equations for Dynamic Graph Representation Learning

LOPT: Learning Optimal Pigovian Tax in Sequential Social Dilemmas

When Do Transformers Outperform Feedforward and Recurrent Networks? A Statistical Perspective

How Classifier Features Transfer to Downstream: An Asymptotic Analysis in a Two-Layer Model

Test Time Scaling for Neural Processes

Token Embeddings Violate the Manifold Hypothesis

Physics of Language Models: Part 4.1, Architecture Design and the Magic of Canon Layers

A Statistical Theory of Contrastive Learning via Approximate Sufficient Statistics

Large Stepsizes Accelerate Gradient Descent for Regularized Logistic Regression

Escaping Collapse: The Strength of Weak Data for Large Language Model Training

SWE-bench Goes Live!

Rethinking Optimal Verification Granularity for Compute-Efficient Test-Time Scaling

Results of the Big ANN: NeurIPS’23 competition

The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models

Block-Biased Mamba for Long-Range Sequence Processing

Federated Continual Learning via Orchestrating Multi-Scale Expertise

QFFT, Question-Free Fine-Tuning for Adaptive Reasoning

Can LLMs Reason Over Non-Text Modalities in a Training-Free Manner? A Case Study with In-Context Representation Learning

Permissioned LLMs: Enforcing Access Control in Large Language Models

RL Tango: Reinforcing Generator and Verifier Together for Language Reasoning

Geometry of Decision Making in Language Models

Multi-Agent Collaboration via Evolving Orchestration

Causality Meets Locality: Provably Generalizable and Scalable Policy Learning for Networked Systems

Meta-World+: An Improved, Standardized, RL Benchmark

NS-Gym: A Comprehensive and Open-Source Simulation Framework for Non-Stationary Markov Decision Processes

Reasoning as an Adaptive Defense for Safety

Efficient Policy Optimization in Robust Constrained MDPs with Iteration Complexity Guarantees

Training Language Models to Generate Quality Code with Program Analysis Feedback

Strategyproof Reinforcement Learning from Human Feedback

DAPO : Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage-Based Policy Optimization

What Makes a Reward Model a Good Teacher? An Optimization Perspective

In-Context Learning of Stochastic Differential Equations with Foundation Inference Models

Vision Transformers Don't Need Trained Registers

Balanced Active Inference

Remarkable Robustness of LLMs: Stages of Inference?

The Overthinker's DIET: Cutting Token Calories with DIfficulty-AwarE Training

Reward Reasoning Models

Exploiting Vocabulary Frequency Imbalance in Language Model Pre-training

SATURN: SAT-based Reinforcement Learning to Unleash LLMs Reasoning

Monotone and Separable Set Functions: Characterizations and Neural Models

How to Train Your LLM Web Agent: A Statistical Diagnosis

Constructing an Optimal Behavior Basis for the Option Keyboard

Communication-Efficient Diffusion Denoising Parallelization via Reuse-then-Predict Mechanism

HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid Normalization

Contextual Thompson Sampling via Generation of Missing Data

Imitation Learning with Temporal Logic Constraints

Learning from Demonstrations via Capability-Aware Goal Sampling

SPOT: Scalable Policy Optimization with Trees for Markov Decision Processes

Conformal Prediction Beyond the Horizon: Distribution-Free Inference for Policy Evaluation

Silencer: From Discovery to Mitigation of Self-Bias in LLM-as-Benchmark-Generator

STaRFormer: Semi-Supervised Task-Informed Representation Learning via Dynamic Attention-Based Regional Masking for Sequential Data

msf-CNN: Patch-based Multi-Stage Fusion with Convolutional Neural Networks for TinyML

Don’t Think Longer, Think Wisely: Optimizing Thinking Dynamics for Large Reasoning Models

HiFC: High-efficiency Flash-based KV Cache Swapping for Scaling LLM Inference

Transforming Generic Coder LLMs to Effective Binary Code Embedding Models for Similarity Detection

What Happens During the Loss Plateau? Understanding Abrupt Learning in Transformers

Set-LLM: A Permutation-Invariant LLM

Shapley-Coop: Credit Assignment for Emergent Cooperation in Self-Interested LLM Agents

A Pre-training Framework for Relational Data with Information-theoretic Principles

Revisiting Bi-Linear State Transitions in Recurrent Neural Networks

DNA-DetectLLM: Unveiling AI-Generated Text via a DNA-Inspired Mutation-Repair Paradigm

Increasing the Utility of Synthetic Images through Chamfer Guidance

ScaleDiff: Higher-Resolution Image Synthesis via Efficient and Model-Agnostic Diffusion

GeoRemover: Removing Objects and Their Causal Visual Artifacts

Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Generation

AccuQuant: Simulating Multiple Denoising Steps for Quantizing Diffusion Models

Rectified CFG++ for Flow Based Models

Blockwise Flow Matching: Improving Flow Matching Models For Efficient High-Quality Generation

MindJourney: Test-Time Scaling with World Models for Spatial Reasoning

MagCache: Fast Video Generation with Magnitude-Aware Cache

FerretNet: Efficient Synthetic Image Detection via Local Pixel Dependencies

Pro3D-Editor: A Progressive Framework for Consistent and Precise 3D Editing

SCoT: Unifying Consistency Models and Rectified Flows via Straight-Consistent Trajectories

Enhancing Consistency of Flow-Based Image Editing through Kalman Control

RelationAdapter: Learning and Transferring Visual Relation with Diffusion Transformers

GPSToken: Gaussian Parameterized Spatially-adaptive Tokenization for Image Representation and Generation

PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation

PocketSR: The Super-Resolution Expert in Your Pocket Mobiles

ALTER: All-in-One Layer Pruning and Temporal Expert Routing for Efficient Diffusion Generation

UVE: Are MLLMs Unified Evaluators for AI-Generated Videos?

Reviving DSP for Advanced Theorem Proving in the Era of Reasoning Models

Hierarchical Koopman Diffusion: Fast Generation with Interpretable Diffusion Trajectory

Whole-Body Conditioned Egocentric Video Prediction

DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models

Selftok-Zero: Reinforcement Learning for Visual Generation via Discrete and Autoregressive Visual Tokens

WorldMem: Long-term Consistent World Simulation with Memory

ComfyMind: Toward General-Purpose Generation via Tree-Based Planning and Reactive Feedback

Preventing Shortcuts in Adapter Training via Providing the Shortcuts

PhysDiff-VTON: Cross-Domain Physics Modeling and Trajectory Optimization for Virtual Try-On

RODS: Robust Optimization Inspired Diffusion Sampling for Detecting and Reducing Hallucination in Generative Models

Cameras as Relative Positional Encoding

Virtual Fitting Room: Generating Arbitrarily Long Videos of Virtual Try-On from a Single Image

ShoeFit: A New Dataset and Dual-image-stream DiT Framework for Virtual Footwear Try-On

FSI-Edit: Frequency and Stochasticity Injection for Flexible Diffusion-Based Image Editing

VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models

Improved Training Technique for Shortcut Models

PolyVivid: Vivid Multi-Subject Video Generation with Cross-Modal Interaction and Enhancement

Foresight: Adaptive Layer Reuse for Accelerated and High-Quality Text-to-Video Generation

TTS-VAR: A Test-Time Scaling Framework for Visual Auto-Regressive Generation

Self-Supervised Selective-Guided Diffusion Model for Old-Photo Face Restoration

Latent Harmony: Synergistic Unified UHD Image Restoration via Latent Space Regularization and Controllable Refinement

Puppeteer: Rig and Animate Your 3D Models

HoliGS: Holistic Gaussian Splatting for Embodied View Synthesis

MPMAvatar: Learning 3D Gaussian Avatars with Accurate and Robust Physics-Based Dynamics

APML: Adaptive Probabilistic Matching Loss for Robust 3D Point Cloud Reconstruction

CLiFT: Compressive Light-Field Tokens for Compute Efficient and Adaptive Neural Rendering

EAG3R: Event-Augmented 3D Geometry Estimation for Dynamic and Extreme-Lighting Scenes

Are Pixel-Wise Metrics Reliable for Computerized Tomography Reconstruction?

ML4CO-Bench-101: Benchmark Machine Learning for Classic Combinatorial Problems on Graphs

BevSplat: Resolving Height Ambiguity via Feature-Based Gaussian Primitives for Weakly-Supervised Cross-View Localization

GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction

InstaInpaint: Instant 3D-Scene Inpainting with Masked Large Reconstruction Model

MIND: Material Interface Generation from UDFs for Non-Manifold Surface Reconstruction

Anti-Aliased 2D Gaussian Splatting

Rooms from Motion: Un-posed Indoor 3D Object Detection as Localization and Mapping

E-MoFlow: Learning Egomotion and Optical Flow from Event Data via Implicit Regularization

Seeing in the Dark: Benchmarking Egocentric 3D Vision with the Oxford Day-and-Night Dataset

EPA: Boosting Event-based Video Frame Interpolation with Perceptually Aligned Learning

SceneDesigner: Controllable Multi-Object Image Generation with 9-DoF Pose Manipulation

VFRTok: Variable Frame Rates Video Tokenizer with Duration-Proportional Information Assumption

RoboScape: Physics-informed Embodied World Model

DGS-LRM: Real-Time Deformable 3D Gaussian Reconstruction From Monocular Videos

VA-GS: Enhancing the Geometric Representation of Gaussian Splatting via View Alignment

MS-GS: Multi-Appearance Sparse-View 3D Gaussian Splatting in the Wild

PhysX-3D: Physical-Grounded 3D Asset Generation

VASA-3D: Lifelike Audio-Driven Gaussian Head Avatars from a Single Image

Robust Neural Rendering in the Wild with Asymmetric Dual 3D Gaussian Splatting

CLIPGaussian: Universal and Multimodal Style Transfer Based on Gaussian Splatting

Neural Atlas Graphs for Dynamic Scene Decomposition and Editing

D$^2$GS: Dense Depth Regularization for LiDAR-free Urban Scene Reconstruction

4DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videos

MM-OPERA: Benchmarking Open-ended Association Reasoning for Large Vision-Language Models

SURDS: Benchmarking Spatial Understanding and Reasoning in Driving Scenarios with Vision Language Models

Collaborating Vision, Depth, and Thermal Signals for Multi-Modal Tracking: Dataset and Algorithm

MIRAGE: A Benchmark for Multimodal Information-Seeking and Reasoning in Agricultural Expert-Guided Conversations

MimeQA: Towards Socially-Intelligent Nonverbal Foundation Models

CineTechBench: A Benchmark for Cinematographic Technique Understanding and Generation

STSBench: A Spatio-temporal Scenario Benchmark for Multi-modal Large Language Models in Autonomous Driving

Benchmarking Egocentric Multimodal Goal Inference for Assistive Wearable Agents

PASS: Path-selective State Space Model for Event-based Recognition

Vgent: Graph-based Retrieval-Reasoning-Augmented Generation For Long Video Understanding

LiveStar: Live Streaming Assistant for Real-World Online Video Understanding

CroPe: Cross-Modal Semantic Compensation Adaptation for All Adverse Scene Understanding

Enhancing Text-to-Image Diffusion Transformer via Split-Text Conditioning

Improve Temporal Reasoning in Multimodal Large Language Models via Video Contrastive Decoding

ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models

FlexSelect: Flexible Token Selection for Efficient Long Video Understanding

CAPability: A Comprehensive Visual Caption Benchmark for Evaluating Both Correctness and Thoroughness

ChartMuseum: Testing Visual Reasoning Capabilities of Large Vision-Language Models

Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers

MMMG: A Massive, Multidisciplinary, Multi-Tier Generation Benchmark for Text-to-Image Reasoning

ExAct: A Video-Language Benchmark for Expert Action Analysis

What’s in Common? Multimodal Models Hallucinate When Reasoning Across Scenes

TaiwanVQA: Benchmarking and Enhancing Cultural Understanding in Vision-Language Models

WorldModelBench: Judging Video Generation Models As World Models

In the Eye of MLLM: Benchmarking Egocentric Video Intent Understanding with Gaze-Guided Prompting

LISAt: Language-Instructed Segmentation Assistant for Satellite Imagery

Benchmarking Retrieval-Augmented Multimomal Generation for Document Question Answering

MMPerspective: Do MLLMs Understand Perspective? A Comprehensive Benchmark for Perspective Perception, Reasoning, and Robustness

Rebalancing Contrastive Alignment with Bottlenecked Semantic Increments in Text-Video Retrieval

Temporal Chain of Thought: Long-Video Understanding by Thinking in Frames

Video Perception Models for 3D Scene Synthesis

Unveiling Chain of Step Reasoning for Vision-Language Models with Fine-grained Rewards

VisualLens: Personalization through Task-Agnostic Visual History

HermesFlow: Seamlessly Closing the Gap in Multimodal Understanding and Generation

First SFT, Second RL, Third UPT: Continual Improving Multi-Modal LLM Reasoning via Unsupervised Post-Training

Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations

Perception Encoder: The best visual embeddings are not at the output of the network

ChA-MAEViT: Unifying Channel-Aware Masked Autoencoders and Multi-Channel Vision Transformers for Improved Cross-Channel Learning

TRoVe: Discovering Error-Inducing Static Feature Biases in Temporal Vision-Language Models

Panoptic Captioning: An Equivalence Bridge for Image and Text

Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs

Towards Robust Uncertainty Calibration for Composed Image Retrieval

OSKAR: Omnimodal Self-supervised Knowledge Abstraction and Representation

FlowCut: Rethinking Redundancy via Information Flow for Efficient Vision-Language Models

JavisGPT: A Unified Multi-modal LLM for Sounding-Video Comprehension and Generation

Object Concepts Emerge from Motion

Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical Findings

MIP against Agent: Malicious Image Patches Hijacking Multimodal OS Agents

UniGen: Enhanced Training & Test-Time Strategies for Unified Multimodal Understanding and Generation

Exploiting the Asymmetric Uncertainty Structure of Pre-trained VLMs on the Unit Hypersphere

Reliable Lifelong Multimodal Editing: Conflict-Aware Retrieval Meets Multi-Level Guidance

SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning

Glance2Gaze: Efficient Vision-Language Models from Glance Fusion to Gaze Compression

Interactive Cross-modal Learning for Text-3D Scene Retrieval

Systematic Reward Gap Optimization for Mitigating VLM Hallucinations

Self-Supervised Learning of Motion Concepts by Optimizing Counterfactuals

ESCA: Contextualizing Embodied Agents via Scene-Graph Generation

Scaling Laws for Robust Comparison of Open Foundation Language-Vision Models and Datasets

Counterfactual Evolution of Multimodal Datasets via Visual Programming

VLMs have Tunnel Vision: Evaluating Nonlocal Visual Reasoning in Leading VLMs

Balancing Multimodal Training Through Game-Theoretic Regularization

Meta CLIP 2: A Worldwide Scaling Recipe

Co-Reinforcement Learning for Unified Multimodal Understanding and Generation

To Think or Not To Think: A Study of Thinking in Rule-Based Visual Reinforcement Fine-Tuning

Vision-centric Token Compression in Large Language Model

SaFiRe: Saccade-Fixation Reiteration with Mamba for Referring Image Segmentation

Mitigating Semantic Collapse in Partially Relevant Video Retrieval

Native Segmentation Vision Transformers

Brain-like Variational Inference

Guiding Cross-Modal Representations with MLLM Priors via Preference Alignment

Towards Comprehensive Scene Understanding: Integrating First and Third-Person Views for LVLMs

Walking the Schrödinger Bridge: A Direct Trajectory for Text-to-3D Generation

End-to-End Vision Tokenizer Tuning

SQS: Enhancing Sparse Perception Models via Query-based Splatting in Autonomous Driving

When Thinking Drifts: Evidential Grounding for Robust Video Reasoning

EgoDTM: Towards 3D-Aware Egocentric Video-Language Pretraining

NoisyGRPO: Incentivizing Multimodal CoT Reasoning via Noise Injection and Bayesian Estimation

Dynam3D: Dynamic Layered 3D Tokens Empower VLM for Vision-and-Language Navigation

On the rankability of visual embeddings

EUGens: Efficient, Unified and General Dense Layers

Multi-scale Temporal Prediction via Incremental Generation and Multi-agent Collaboration

Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Models

DyMU: Dynamic Merging and Virtual Unmerging for Efficient Variable-Length VLMs

Don't Just Chase “Highlighted Tokens” in MLLMs: Revisiting Visual Holistic Context Retention

SAVVY: Spatial Awareness via Audio-Visual LLMs through Seeing and Hearing

SHF: Symmetrical Hierarchical Forest with Pretrained Vision Transformer Encoder for High-Resolution Medical Segmentation

Diffusion-Driven Two-Stage Active Learning for Low-Budget Semantic Segmentation

OpenWorldSAM: Extending SAM2 for Universal Image Segmentation with Language Prompts

ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and Localization

DrVD-Bench: Do Vision-Language Models Reason Like Human Doctors in Medical Image Diagnosis?

STACI: Spatio-Temporal Aleatoric Conformal Inference

Multivariate Latent Recalibration for Conditional Normalizing Flows

Reverse-Annealed Sequential Monte Carlo for Efficient Bayesian Optimal Experiment Design

A Latent Multilayer Graphical Model For Complex, Interdependent Systems

Personalized Federated Conformal Prediction with Localization

S-GRPO: Early Exit via Reinforcement Learning in Reasoning Models

Efficient Prompt Compression with Evaluator Heads for Long-Context Transformer Inference

Preference Learning with Lie Detectors can Induce Honesty or Evasion

To Distill or Decide? Understanding the Algorithmic Trade-off in Partially Observable RL

Alligat0R: Pre-Training through Covisibility Segmentation for Relative Camera Pose Regression

Part-Aware Bottom-Up Group Reasoning for Fine-Grained Social Interaction Detection

Diffusion-Classifier Synergy: Reward-Aligned Learning via Mutual Boosting Loop for FSCIL

GeoLink: Empowering Remote Sensing Foundation Model with OpenStreetMap Data

ADPretrain: Advancing Industrial Anomaly Detection via Anomaly Representation Pretraining

DitHub: A Modular Framework for Incremental Open-Vocabulary Object Detection

Holistic Order Prediction in Natural Scenes

Alias-Free ViT: Fractional Shift Invariance via Linear Attention

Object-Centric Representation Learning for Enhanced 3D Semantic Scene Graph Prediction

Frequency-Aware Token Reduction for Efficient Vision Transformer

ToolRL: Reward is All Tool Learning Needs

Dual Data Alignment Makes AI-Generated Image Detector Easier Generalizable

Evolving and Regularizing Meta-Environment Learner for Fine-Grained Few-Shot Class-Incremental Learning

Enhancing the Outcome Reward-based RL Training of MLLMs with Self-Consistency Sampling

Accelerating RL for LLM Reasoning with Optimal Advantage Regression

Surprise3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes

CVGL: Causal Learning and Geometric Topology

L2RSI: Cross-view LiDAR-based Place Recognition for Large-scale Urban Scenes via Remote Sensing Imagery

Single-Teacher View Augmentation: Boosting Knowledge Distillation via Angular Diversity

Direct Numerical Layout Generation for 3D Indoor Scene Synthesis via Spatial Reasoning

Dual-Path Temporal Decoder for End-to-End Multi-Object Tracking

Bio-Inspired Image Restoration

CoDA: Coordinated Diffusion Noise Optimization for Whole-Body Manipulation of Articulated Objects

Dense Metric Depth Estimation via Event-based Differential Focus Volume Prompting

Injecting Frame-Event Complementary Fusion into Diffusion for Optical Flow in Challenging Scenes

MobileODE: An Extra Lightweight Network

OSCAR: One-Step Diffusion Codec Across Multiple Bit-rates

Learn and Ensemble Bridge Adapters for Multi-domain Task Incremental Learning

DeepDiver: Adaptive Web-Search Intensity Scaling via Reinforcement Learning

Self-Supervised Direct Preference Optimization for Text-to-Image Diffusion Models

ORIGEN: Zero-Shot 3D Orientation Grounding in Text-to-Image Generation

CADGrasp: Learning Contact and Collision Aware General Dexterous Grasping in Cluttered Scenes

Deployment Efficient Reward-Free Exploration with Linear Function Approximation

Dynamic View Synthesis as an Inverse Problem

HyPlaneHead: Rethinking Tri-plane-like Representations in Full-Head Image Synthesis

Understanding Representation Dynamics of Diffusion Models via Low-Dimensional Modeling

DualCnst: Enhancing Zero-Shot Out-of-Distribution Detection via Text-Image Consistency in Vision-Language Models

Bi-Level Knowledge Transfer for Multi-Task Multi-Agent Reinforcement Learning

ESCA: Enabling Seamless Codec Avatar Execution through Algorithm and Hardware Co-Optimization for Virtual Reality

A Driving-Style-Adaptive Framework for Vehicle Trajectory Prediction

Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)

WearVQA: A Visual Question Answering Benchmark for Wearables in Egocentric Authentic Real-world scenarios

Towards Better Dental AI: A Multimodal Benchmark and Instruction Dataset for Panoramic X-ray Analysis

SciArena: An Open Evaluation Platform for Non-Verifiable Scientific Literature-Grounded Tasks

AnomalyCoT: A Multi-Scenario Chain-of-Thought Dataset for Multimodal Large Language Models

Asymptotic Theory of Geometric and Adaptive $k$-Means Clustering

MODEM: A Morton-Order Degradation Estimation Mechanism for Adverse Weather Image Recovery

Bits Leaked per Query: Information-Theoretic Bounds for Adversarial Attacks on LLMs

Janus-Pro-R1: Advancing Collaborative Visual Comprehension and Generation via Reinforcement Learning

Web-Shepherd: Advancing PRMs for Reinforcing Web Agents

Can Multi-Modal LLMs Provide Live Step-by-Step Task Guidance?

TAI3: Testing Agent Integrity in Interpreting User Intent

JAFAR: Jack up Any Feature at Any Resolution

SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning

GRAPE: Optimize Data Mixture for Group Robust Multi-target Adaptive Pretraining

DINGO: Constrained Inference for Diffusion LLMs

OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

SafePTR: Token-Level Jailbreak Defense in Multimodal LLMs via Prune-then-Restore Mechanism

NoPo-Avatar: Generalizable and Animatable Avatars from Sparse Inputs without Human Poses

Bootstrap Your Uncertainty: Adaptive Robust Classification Driven by Optimal-Transport

Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation

Enhancing LLM Watermark Resilience Against Both Scrubbing and Spoofing Attacks

TS-MOF: Two-Stage Multi-Objective Fine-tuning for Long-Tailed Recognition

RAPID Hand: Robust, Affordable, Perception-Integrated, Dexterous Manipulation Platfrom for Embodied Intelligence

RobotSmith: Generative Robotic Tool Design for Acquisition of Complex Manipulation Skills

AdaReasoner: Adaptive Reasoning Enables More Flexible Thinking

TTRL: Test-Time Reinforcement Learning

Position: Benchmarking is Broken - Don't Let AI be Its Own Judge

StruDiCO: Structured Denoising Diffusion with Gradient-free Inference-stage Boosting for Memory and Time Efficient Combinatorial Optimization

VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents

VividFace: A Robost and High-Fidelity Video Face Swapping Framework

HOComp: Interaction-Aware Human-Object Composition

Generalizing Single-Frame Supervision to Event-Level Understanding for Video Anomaly Detection

Federated Multi-armed Bandits with Efficient Bit-Level Communications

G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems

Mitigating Reward Over-optimization in Direct Alignment Algorithms with Importance Sampling

Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think

Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models

Robust and Diverse Multi-Agent Learning via Rational Policy Gradient

Graph-Based Attention for Differentiable MaxSAT Solving

AnimateQR: Bridging Aesthetics and Functionality in Dynamic QR Code Generation

OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles

Fast Training of Large Kernel Models with Delayed Projections

The Emergence of Abstract Thought in Large Language Models Beyond Any Language

Thoughts Are All Over the Place: On the Underthinking of Long Reasoning Models

TokenSqueeze: Performance-Preserving Compression for Reasoning LLMs

Variational Polya Tree

Max Entropy Moment Kalman Filter for Polynomial Systems with Arbitrary Noise

ALINE: Joint Amortization for Bayesian Inference and Active Data Acquisition

An Adaptive Quantum Circuit of Dempster's Rule of Combination for Uncertain Pattern Classification

Infinite Neural Operators: Gaussian processes on functions

Feel-Good Thompson Sampling for Contextual Bandits: a Markov Chain Monte Carlo Showdown

Approximately Aligned Decoding

Reverse Diffusion Sequential Monte Carlo Samplers

Constrained Sampling for Language Models Should Be Easy: An MCMC Perspective

Split Gibbs Discrete Diffusion Posterior Sampling

The Adaptive Complexity of Minimizing Relative Fisher Information

On scalable and efficient training of diffusion samplers

Adjoint Schrödinger Bridge Sampler

Preconditioned Langevin Dynamics with Score-based Generative Models for Infinite-Dimensional Linear Bayesian Inverse Problems

Tree-Sliced Entropy Partial Transport

Rethinking Entropy in Test-Time Adaptation: The Missing Piece from Energy Duality

Inexact Column Generation for Bayesian Network Structure Learning via Difference-of-Submodular Optimization

MISA: Memory-Efficient LLMs Optimization with Module-wise Importance Sampling

Gradient-Variation Online Adaptivity for Accelerated Optimization with Hölder Smoothness

Fast Last-Iterate Convergence of SGD in the Smooth Interpolation Regime

Accelerated Distance-adaptive Methods for Hölder Smooth and Convex Optimization

PaZO: Preconditioned Accelerated Zeroth-Order Optimization for Fine-Tuning LLMs

New Perspectives on the Polyak Stepsize: Surrogate Functions and Negative Results

Probing Neural Combinatorial Optimization Models

Non-Convex Tensor Recovery from Tube-Wise Sensing

On the Complexity of Finding Stationary Points in Nonconvex Simple Bilevel Optimization

Extragradient Method for $(L_0, L_1)$-Lipschitz Root-finding Problems

Affine-Invariant Global Non-Asymptotic Convergence Analysis of BFGS under Self-Concordance

Differentiable extensions with rounding guarantees for combinatorial optimization over permutations

Convergence Rates for Gradient Descent on the Edge of Stability for Overparametrised Least Squares

Accelerating Optimization via Differentiable Stopping Time

Rethinking Gradient Step Denoiser: Towards Truly Pseudo-Contractive Operator

DesignX: Human-Competitive Algorithm Designer for Black-Box Optimization

Rethinking Neural Combinatorial Optimization for Vehicle Routing Problems with Different Constraint Tightness Degrees

Statistical Inference for Decentralized Federated Learning

Block-Diagonal LoRA for Eliminating Communication Overhead in Tensor Parallel LoRA Serving

Efficient Federated Learning against Byzantine Attacks and Data Heterogeneity via Aggregating Normalized Gradients

FedLPA: Local Prior Alignment for Heterogeneous Federated Generalized Category Discovery

Exact and Linear Convergence for Federated Learning under Arbitrary Client Participation is Attainable

NestedFP: High-Performance, Memory-Efficient Dual-Precision Floating Point Support for LLMs

Sketched Adaptive Distributed Deep Learning: A Sharp Convergence Analysis

Synergistic Tensor and Pipeline Parallelism

Layer-wise Update Aggregation with Recycling for Communication-Efficient Federated Learning

KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems

Mozart: Modularized and Efficient MoE Training on 3.5D Wafer-Scale Chiplet Architectures

The Bias-Variance Tradeoff in Data-Driven Optimization: A Local Misspecification Perspective

What Data Enables Optimal Decisions? An Exact Characterization for Linear Optimization

Conformal Mixed-Integer Constraint Learning with Feasibility Guarantees

Conformal Risk Training: End-to-End Optimization of Conformal Risk Control

Statistical Inference under Performativity

Computation and Memory-Efficient Model Compression with Gradient Reweighting

Memory-Efficient Training with In-Place FFT Implementation

Compress & Cache: Vision token compression for efficient generation and retrieval

Purifying Shampoo: Investigating Shampoo's Heuristics by Decomposing its Preconditioner

Convergence of the Gradient Flow for Shallow ReLU Networks on Weakly Interacting Data

PROFIT: A Specialized Optimizer for Deep Fine Tuning

The Rich and the Simple: On the Implicit Bias of Adam and SGD

SAD Neural Networks: Divergent Gradient Flows and Asymptotic Optimality via o-minimal Structures

KOALA++: Efficient Kalman-Based Optimization with Gradient-Covariance Products

Reparameterized LLM Training via Orthogonal Equivalence Transformation

SUMO: Subspace-Aware Moment-Orthogonalization for Accelerating Memory-Efficient LLM Training

QSCA: Quantization with Self-Compensating Auxiliary for Monocular Depth Estimation

Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning

Compress Large Language Models via Collaboration Between Learning and Matrix Approximation

MOBO-OSD: Batch Multi-Objective Bayesian Optimization via Orthogonal Search Directions

Omnipresent Yet Overlooked: Heat Kernels in Combinatorial Bayesian Optimization

Coresets for Clustering Under Stochastic Noise

(ends 2:00 PM)

Creative AI Session 1 [11:00-2:00]

s 11:00-2:00

[11:00] AI as intermediary in modern-day ritual: An immersive, interactive production of the roller disco musical Xanadu at UCLA

[11:00] AI is Misled by GenAI: Stylistic Bias in Automated Assessment of Creativity in Large Language Models

[11:00] CoTextor: Training-Free Modular Multilingual Text Editing via Layered Disentanglement and Depth-Aware Fusion

[11:00] Digital Plankton

[11:00] Echoes of Humanity: Exploring the Perceived Humanness of AI Music

[11:00] EmoNest: Crafting Emotionally-Adaptive Experiences with Generative AI

[11:00] EMPATHIA: Multi-Faceted Human-AI Collaboration for Refugee Integration

[11:00] Evaluating In Silico Creativity: An Expert Review of AI Chess Compositions

[11:00] How Foundation Models are Reshaping Non-Invasive Brain–Computer Interfaces: A Case for Novel Human Expression and Alignment

[11:00] Interactive Artistic Text-To-Voice: Tungnaá and Bla Blavatar vs Jaap Blonk

[11:00] Large-Scale Training Data Attribution for Music Generative Models via Unlearning

[11:00] Melody Slot Machine III for Automatic Fingering Saxophone using Servomotors

[11:00] Orchestrating Emergent Storytelling with Embodied Multi-Agent Systems

[11:00] Painting with Paintings

[11:00] Plan Before You Write: Improve LLM writing by planning

[11:00] Real-Time Intuitive AI Drawing System for Collaboration: Enhancing Human Creativity through Formal and Contextual Intent Integration

[11:00] Stroke Patches: Customizable Artistic Image Styling Using Regression

[11:00] Surface Tension

[11:00] Synthaesthetic Art: Human-Machine Creative Collaboration

[11:00] The Anemoia Device: A Tangible AI System for the Co-creation of Synthetic Memories through Scent

[11:00] The Ghost in the Keys: A Disklavier Demo for Human-AI Musical Co-Creativity

[11:00] The Stochastic Parrot: a physical AI Cohabitant

[11:00] The Sublime Ordinary: A Tool for Analysing Temporal City Soundscapes

(ends 2:00 PM)

noon

Expo Workshop:

AI Assistants in the Wild: Agents, Adaptation, and Memory-Augmented Deployment

(ends 1:30 PM)

Expo Workshop:

Multi-Agent Systems in Industry: From Research to Real-World Impact

(ends 1:30 PM)

Expo Workshop:

On Device/Edge AI

(ends 1:30 PM)

Expo Workshop:

Using the Virtual Cell Platform to Accelerate Machine Learning in Biology

(ends 1:30 PM)

1 p.m.

Break:

Hosted Lunch

(ends 2:30 PM)

1:30 p.m.

Affinity Workshop:

Indigenous in AI/ML

(ends 5:30 PM)

2 p.m.

Test Of Time:

Test of Time Award

(ends 2:30 PM)

2:30 p.m.

San Diego Invited Talk:

Are We Having the Wrong Nightmares About AI?

Zeynep Tufekci

(ends 3:30 PM)

3:30 p.m.

Oral 2A Multimodal 2 [3:30-4:30]

Orals 3:30-4:30

[3:30] Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing

[3:50] CoralVQA: A Large-Scale Visual Question Answering Dataset for Coral Reef Image Understanding

[4:10] OpenHOI: Open-World Hand-Object Interaction Synthesis with Multimodal Large Language Model

(ends 4:30 PM)

Oral 2B Deep Learning 1 [3:30-4:30]

Orals 3:30-4:30

[3:30] A multiscale analysis of mean-field transformers in the moderate interaction regime

[3:50] The emergence of sparse attention: impact of data distribution and benefits of repetition

[4:10] From Condensation to Rank Collapse: A Two-Stage Analysis of Transformer Training Dynamics

(ends 4:30 PM)

Oral 2C Reinforcement/State-space 1 [3:30-4:30]

Orals 3:30-4:30

[3:30] PRIMT: Preference-based Reinforcement Learning with Multimodal Feedback and Trajectory Synthesis from Foundation Models

[3:50] Adaptive Surrogate Gradients for Sequential Reinforcement Learning in Spiking Neural Networks

[4:10] SAGE: A Unified Framework for Generalizable Object State Recognition with State-Action Graph Embedding

(ends 4:30 PM)

Oral 2D Application 1 [3:30-4:30]

Orals 3:30-4:30

[3:30] PhySense: Sensor Placement Optimization for Accurate Physics Sensing

[3:50] TransferTraj: A Vehicle Trajectory Learning Model for Region and Task Transferability

[4:10] OrthoLoC: UAV 6-DoF Localization and Calibration Using Orthographic Geodata

(ends 4:30 PM)

Oral 2E Theory 2 [3:30-4:30]

Orals 3:30-4:30

[3:30] Agnostic Active Learning Is Always Better Than Passive Learning

[3:50] Dynamical Decoupling of Generalization and Overfitting in Large Two-Layer Networks

[4:10] Tighter CMI-Based Generalization Bounds via Stochastic Projection and Quantization

(ends 4:30 PM)

4:30 p.m.

Expo Talk Panel:

The Co-X Framework: Versatile AI Agents for Automating and Augmenting Professional Workflows

(ends 5:30 PM)

Expo Talk Panel:

Cosmos World Foundation Model Platform for Physical AI

(ends 5:30 PM)

Creative AI Panel:

Art Content Creation: When demands are met by pipelines (or not)

(ends 5:30 PM)

Expo Talk Panel:

Juries, Not Judges! Industry-Scale Evaluation of Trustworthy AI via Dynamic LLM Panels

(ends 5:30 PM)

Break:

Coffee Break

(ends 5:30 PM)

Expo Talk Panel:

Building the Open AI Ecosystem: Models, Infrastructure and Community Adoption

(ends 5:30 PM)

Creative AI Session 2 [4:30-7:30]

s 4:30-7:30

[4:30] Assembloid Agency: Unreal Engine API for brain-on-a-chip platforms

[4:30] Best Friends Forever

[4:30] Brushes in Motion: Vector Guided Strokes for Computational Painting

[4:30] Cultural Alien Sampler: Open-ended Art Generation Balancing Originality and Coherence

[4:30] Go witheFlow: Real-time Emotion Driven Audio Effects Modulation

[4:30] Human-Machine Ritual: Synergic Performance through Real-Time Motion Recognition

[4:30] Knolling Bot: Teaching Robots the Human Notion of Tidiness

[4:30] Learning to Move with Style: Few-Shot Cross-Modal Style Transfer for Creative Robot Motion Generation

[4:30] LLMscape

[4:30] LUMIA: A Handheld Vision-to-Music System for Real-Time, Embodied Composition

[4:30] MCP-Driven Parametric Modeling: Integrating LLM Agents into Architectural and Landscape Design Workflows

[4:30] Music Arena: Live Evaluation for Text-to-Music

[4:30] Musings on AI Muses: Support for Human Creativity

[4:30] My AI Agent Feels Gray on Her Period

[4:30] Panel-by-Panel Souls: A Performative Workflow for Expressive Faces in AI-Assisted Manga Creation

[4:30] ProGress: Structured Music Generation via Graph Diffusion and Hierarchical Music Analysis

[4:30] Prompt-Character Divergence: A Responsibility Compass for Human-AI Creative Collaboration

[4:30] Sound Clouds: Exploring ambient intelligence in public spaces to elicit deep human experience of awe, wonder, and beauty

[4:30] ‘Studies for’ : A Human-AI Co-Creative Sound Artwork Using a Real-time Multi-channel Sound Generation Model

[4:30] Visualizing Our Changing Earth: A Creative AI Framework for Democratizing Environmental Storytelling Through Satellite Imagery

[4:30] yammer

(ends 7:30 PM)

San Diego Poster Session 2 [4:30-7:30]

Posters 4:30-7:30

KARMA: Leveraging Multi-Agent LLMs for Automated Knowledge Graph Enrichment

Monoculture or Multiplicity: Which Is It?

MultiScale Contextual Bandits for Long Term Objectives

Direct Alignment with Heterogeneous Preferences

MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems

From Replication to Redesign: Exploring Pairwise Comparisons for LLM-Based Peer Review

Audits Under Resource, Data, and Access Constraints: Scaling Laws For Less Discriminatory Alternatives

Smoothed Differentiation Efficiently Mitigates Shattered Gradients in Explanations

Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models

Unifying Attention Heads and Task Vectors via Hidden State Geometry in In-Context Learning

Cross City Traffic Flow Generation via Retrieval Augmented Diffusion Model

Can Large Language Models Master Complex Card Games?

Proxy-SPEX: Sample-Efficient Interpretability via Sparse Feature Interactions in LLMs

From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuit

Performative Validity of Recourse Explanations

Regression-adjusted Monte Carlo Estimators for Shapley Values and Probabilistic Values

Make Information Diffusion Explainable: LLM-based Causal Framework for Diffusion Prediction

Unveiling Concept Attribution in Diffusion Models

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers

FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation

Data Mixture Optimization: A Multi-fidelity Multi-scale Bayesian Framework

LayerIF: Estimating Layer Quality for Large Language Models using Influence Functions

Diversity as a Reward: Fine-Tuning LLMs on a Mixture of Domain-Undetermined Data

The Best Instruction-Tuning Data are Those That Fit

CovMatch: Cross-Covariance Guided Multimodal Dataset Distillation with Trainable Text Encoder

ThinkBench: Dynamic Out-of-Distribution Evaluation for Robust LLM Reasoning

Rethinking Evaluation of Infrared Small Target Detection

Robust Distortion-Free Watermark for Autoregressive Audio Generation Models

Understanding challenges to the interpretation of disaggregated evaluations of algorithmic fairness

Unmasking Puppeteers: Leveraging Biometric Leakage to Expose Impersonation in AI-Based Videoconferencing

Distillation Robustifies Unlearning

A Unified Framework for Fair Graph Generation: Theoretical Guarantees and Empirical Advances

Training-Free Safe Denoisers for Safe Use of Diffusion Models

StableGuard: Towards Unified Copyright Protection and Tamper Localization in Latent Diffusion Models

RespoDiff: Dual-Module Bottleneck Transformation for Responsible & Faithful T2I Generation

ErrorTrace: A Black-Box Traceability Mechanism Based on Model Family Error Space

Dynamic Risk Assessments for Offensive Cybersecurity Agents

R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization

AI Testing Should Account for Sophisticated Strategic Behaviour

Embracing Contradiction: Theoretical Inconsistency Will Not Impede the Road of Building Responsible AI Systems

LLMs Encode Harmfulness and Refusal Separately

On the Coexistence and Ensembling of Watermarks

Learning Gradient Boosted Decision Trees with Algorithmic Recourse

Representational Difference Explanations

Fixing It in Post: A Comparative Study of LLM Post-Training Data Quality and Model Performance

LogicTree: Improving Complex Reasoning of LLMs via Instantiated Multi-step Synthetic Logical Data

Extremely Simple Multimodal Outlier Synthesis for Out-of-Distribution Detection and Segmentation

Generating Informative Samples for Risk-Averse Fine-Tuning of Downstream Tasks

HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages

SNEAKDOOR: Stealthy Backdoor Attacks against Distribution Matching-based Dataset Condensation

Temporal Logic-Based Multi-Vehicle Backdoor Attacks against Offline RL Agents in End-to-end Autonomous Driving

Language Models Are Capable of Metacognitive Monitoring and Control of Their Internal Activations

Continuous Concepts Removal in Text-to-image Diffusion Models

Setting $\varepsilon$ is not the Issue in Differential Privacy

Diffusion Federated Dataset

Understanding and Improving Fast Adversarial Training against $l_0$ Bounded Perturbations

InvisibleInk: High-Utility and Low-Cost Text Generation with Differential Privacy

Privacy amplification by random allocation

GeoClip: Geometry-Aware Clipping for Differentially Private SGD

Impact of Dataset Properties on Membership Inference Vulnerability of Deep Transfer Learning

Mitigating the Privacy–Utility Trade-off in Decentralized Federated Learning via f-Differential Privacy

Data-Free Model Extraction for Black-box Recommender Systems via Graph Convolutions

A Fair Federated Learning Method for Handling Client Participation Probability Inconsistencies in Heterogeneous Environments

Detoxifying Large Language Models via Autoregressive Reward Guided Representation Editing

Online robust locally differentially private learning for nonparametric regression

Analogy-based Multi-Turn Jailbreak against Large Language Models

Reliable Decision‑Making via Calibration‑Oriented Retrieval‑Augmented Generation

Shape it Up! Restoring LLM Safety during Finetuning

V-CECE: Visual Counterfactual Explanations via Conceptual Edits

A Theory for Worst-Case vs. Average-Case Guarantees for LLMs

From Counterfactuals to Trees: Competitive Analysis of Model Extraction Attacks

Human Texts Are Outliers: Detecting LLM-generated Texts via Out-of-distribution Detection

Why Do Some Language Models Fake Alignment While Others Don't?

PolyGuard: Massive Multi-Domain Safety Policy-Grounded Guardrail Dataset

BackdoorDM: A Comprehensive Benchmark for Backdoor Learning on Diffusion Model

VMDT: Decoding the Trustworthiness of Video Foundation Models

WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks

OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents

Neither Valid nor Reliable? Investigating the Use of LLMs as Judges

Sequentially Auditing Differential Privacy

IF-Guide: Influence Function-Guided Detoxification of LLMs

GLSim: Detecting Object Hallucinations in LVLMs via Global-Local Similarity

Harnessing the Computation Redundancy in ViTs to Boost Adversarial Transferability

TimeWak: Temporal Chained-Hashing Watermark for Time Series Data

LoRO: Real-Time on-Device Secure Inference for LLMs via TEE-Based Low Rank Obfuscation

SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment

Removing Concepts from Text-to-Image Models with Only Negative Samples

Many LLMs Are More Utilitarian Than One

Beyond Prediction: Managing the Repercussions of Machine Learning Applications

MetaDefense: Defending Fine-tuning based Jailbreak Attack Before and During Generation

DCcluster-Opt: Benchmarking Dynamic Multi-Objective Optimization for Geo-Distributed Data Center Workloads

CLEVER: A Curated Benchmark for Formally Verified Code Generation

GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents

Hierarchical Demonstration Order Optimization for Many-shot In-Context Learning

CodeMerge: Codebook-Guided Model Merging for Robust Test-Time Adaptation in Autonomous Driving

Latent Retrieval Augmented Generation of Cross-Domain Protein Binders

Manipulating 3D Molecules in a Fixed-Dimensional E(3)-Equivariant Latent Space

Towards precision protein-ligand affinity prediction benchmark: A Complete and Modification-Aware DAVIS Dataset

DecoyDB: A Dataset for Graph Contrastive Learning in Protein-Ligand Binding Affinity Prediction

BOOM: Benchmarking Out-Of-distribution Molecular Property Predictions of Machine Learning Models

OligoGym: Curated Datasets and Benchmarks for Oligonucleotide Drug Discovery

CheMixHub: Datasets and Benchmarks for Chemical Mixture Property Prediction

MonoLift: Learning 3D Manipulation Policies from Monocular RGB via Distillation

MetaFind: Scene-Aware 3D Asset Retrieval for Coherent Metaverse Scene Generation

Constrained Diffusers for Safe Planning and Control

Optimizing Distributional Geometry Alignment with Optimal Transport for Generative Dataset Distillation

Language Modeling by Language Models

Enhancing Diffusion-based Unrestricted Adversarial Attacks via Adversary Preferences Alignment

SE-GUI: Enhancing Visual Grounding for GUI Agents via Self-Evolutionary Reinforcement Learning

Generation as Search Operator for Test-Time Scaling of Diffusion-based Combinatorial Optimization

Stitch and Tell: A Structured Data Augmentation Method for Spatial Understanding

ProfiX: Improving Profile-Guided Optimization in Compilers with Graph Neural Networks

3D-GSRD: 3D Molecular Graph Auto-Encoder with Selective Re-mask Decoding

3D Interaction Geometric Pre-training for Molecular Relational Learning

Aligning Transformers with Continuous Feedback via Energy Rank Alignment

UMA: A Family of Universal Models for Atoms

Multiscale guidance of protein structure prediction with heterogeneous cryo-EM data

Universally Invariant Learning in Equivariant GNNs

High-order Equivariant Flow Matching for Density Functional Theory Hamiltonian Prediction

Curriculum Model Merging: Harmonizing Chemical LLMs for Enhanced Cross-Task Generalization

Retrosynthesis Planning via Worst-path Policy Optimisation in Tree-structured MDPs

Geometric Mixture Models for Electrolyte Conductivity Prediction

SeasonBench-EA: A Multi-Source Benchmark for Seasonal Prediction and Numerical Model Post-Processing in East Asia

SmokeViz: A Large-Scale Satellite Dataset for Wildfire Smoke Detection and Segmentation

OceanBench: A Benchmark for Data-Driven Global Ocean Forecasting systems

Partial Physics Informed Diffusion Model for Ocean Chlorophyll Concentration Reconstruction

Learning Urban Climate Dynamics via Physics-Guided Urban Surface–Atmosphere Interactions

Measuring Scientific Capabilities of Language Models with a Systems Biology Dry Lab

UniZyme: A Unified Protein Cleavage Site Predictor Enhanced with Enzyme Active-Site Knowledge

Curly Flow Matching for Learning Non-gradient Field Dynamics

DIsoN: Decentralized Isolation Networks for Out-of-Distribution Detection in Medical Imaging

SAM2Flow: Interactive Optical Flow Estimation with Dual Memory for in vivo Microcirculation Analysis

Better Tokens for Better 3D: Advancing Vision-Language Modeling in 3D Medical Imaging

Unleashing Foundation Vision Models: Adaptive Transfer for Diverse Data-Limited Scientific Domains

MIRA: Medical Time Series Foundation Model for Real-World Health Data

FAPEX: Fractional Amplitude-Phase Expressor for Robust Cross-Subject Seizure Prediction

BrainODE: Neural Shape Dynamics for Age- and Disease-aware Brain Trajectories

Offline Guarded Safe Reinforcement Learning for Medical Treatment Optimization Strategies

Reinforcement Learning for Out-of-Distribution Reasoning in LLMs: An Empirical Study on Diagnosis-Related Group Coding

ClinBench: A Standardized Multi-Domain Framework for Evaluating Large Language Models in Clinical Information Extraction

EndoBench: A Comprehensive Evaluation of Multi-Modal Large Language Models for Endoscopy Analysis

TCM-Ladder: A Benchmark for Multimodal Question Answering on Traditional Chinese Medicine

CogPhys: Assessing Cognitive Load via Multimodal Remote and Contact-based Physiological Sensing

Simulating Viva Voce Examinations to Evaluate Clinical Reasoning in Large Language Models

Bilevel Network Learning via Hierarchically Structured Sparsity

From Likelihood to Fitness: Improving Variant Effect Prediction in Protein and Genome Language Models

LawShift: Benchmarking Legal Judgment Prediction Under Statute Shifts

NaturalReasoning: Reasoning in the Wild with 2.8M Challenging Questions

C-SEO Bench: Does Conversational SEO Work?

RESPIN-S1.0: A read speech corpus of 10000+ hours in dialects of nine Indian Languages

MMTU: A Massive Multi-Task Table Understanding and Reasoning Benchmark

Distributional LLM-as-a-Judge

Cypher-RI: Reinforcement Learning for Integrating Schema Selection into Cypher Generation

Cooperative Retrieval-Augmented Generation for Question Answering: Mutual Information Exchange and Ranking by Contrasting Layers

GenPO: Generative Diffusion Models Meet On-Policy Reinforcement Learning

Tool-Augmented Spatiotemporal Reasoning for Streamlining Video Question Answering Task

Conflict-Aware Knowledge Editing in the Wild: Semantic-Augmented Graph Representation for Unstructured Text

Word-Level Emotional Expression Control in Zero-Shot Text-to-Speech Synthesis

Latent Principle Discovery for Language Model Self-Improvement

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models

SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond

Ada-R1: Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization

SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning

Calibrating Translation Decoding with Quality Estimation on LLMs

Better Estimation of the Kullback--Leibler Divergence Between Language Models

Signal and Noise: A Framework for Reducing Uncertainty in Language Model Evaluation

Can Dependencies Induced by LLM-Agent Workflows Be Trusted?

Self Iterative Label Refinement via Robust Unlabeled Learning

AudSemThinker: Enhancing Audio-Language Models Through Reasoning over Semantics of Sound

Bridging Sign and Spoken Languages: Pseudo Gloss Generation for Sign Language Translation

SQLens: An End-to-End Framework for Error Detection and Correction in Text-to-SQL

KVLink: Accelerating Large Language Models via Efficient KV Cache Reuse

Learning to Watermark: A Selective Watermarking Framework for Large Language Models via Multi-Objective Optimization

MoME: Mixture of Matryoshka Experts for Audio-Visual Speech Recognition

Steering When Necessary: Flexible Steering Large Language Models with Backtracking

Explainable Reinforcement Learning from Human Feedback to Improve Alignment

FastLongSpeech: Enhancing Large Speech-Language Models for Efficient Long-Speech Processing

Private Training Large-scale Models with Efficient DP-SGD

RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving

T-SHIRT: Token-Selective Hierarchical Data Selection for Instruction Tuning

ARM: Adaptive Reasoning Model

STSBench: A Large-Scale Dataset for Modeling Neuronal Activity in the Dorsal Stream of Primate Visual Cortex

Listening to the Brain: Multi-Band sEEG Auditory Reconstruction via Dynamic Spatio-Temporal Hypergraphs

BrainMoE: Cognition Joint Embedding via Mixture-of-Expert Towards Robust Brain Foundation Model

Time-Masked Transformers with Lightweight Test-Time Adaptation for Neural Speech Decoding

Localist Topographic Expert Routing: A Barrel Cortex-Inspired Modular Network for Sensorimotor Processing

Scaling and context steer LLMs along the same computational path as the human brain

Brain-tuning Improves Generalizability and Efficiency of Brain Alignment in Speech Models

Multiplication-Free Parallelizable Spiking Neurons with Efficient Spatio-Temporal Dynamics

$i$MIND: Insightful Multi-subject Invariant Neural Decoding

Versatile Transferable Unlearnable Example Generator

Vision-and-Language Training Helps Deploy Taxonomic Knowledge but Does Not Fundamentally Alter It

BaRISTA: Brain Scale Informed Spatiotemporal Representation of Human Intracranial Neural Activity

MI-TRQR: Mutual Information-Based Temporal Redundancy Quantification and Reduction for Energy-Efficient Spiking Neural Networks

SPINT: Spatial Permutation-Invariant Neural Transformer for Consistent Intracortical Motor Decoding

TRACE: Contrastive learning for multi-trial time series data in neuroscience

Learning the Plasticity: Plasticity-Driven Learning Framework in Spiking Neural Networks

Intrinsic Goals for Autonomous Agents: Model-Based Exploration in Virtual Zebrafish Predicts Ethological Behavior and Whole-Brain Dynamics

Final-Model-Only Data Attribution with a Unifying View of Gradient-Based Methods

Solving Inequality Proofs with Large Language Models

The Impact of Coreset Selection on Spurious Correlations and Group Robustness

miniF2F-Lean Revisited: Reviewing Limitations and Charting a Path Forward

ATLAS: Autoformalizing Theorems through Lifting, Augmentation, and Synthesis of Data

RePO: Understanding Preference Learning Through ReLU-Based Optimization

State-Covering Trajectory Stitching for Diffusion Planners

Tackling Continual Offline RL through Selective Weights Activation on Aligned Spaces

Online Optimization for Offline Safe Reinforcement Learning

Hamiltonian Neural PDE Solvers through Functional Approximation

UGM2N: An Unsupervised and Generalizable Mesh Movement Network via M-Uniform Loss

Information-Driven Design of Imaging Systems

Geometry Aware Operator Transformer as an efficient and accurate neural surrogate for PDEs on arbitrary domains

Learning Chern Numbers of Multiband Topological Insulators with Gauge Equivariant Neural Networks

Geometric Algebra-Enhanced Bayesian Flow Network for RNA Inverse Design

FlowDAS: A Stochastic Interpolant-based Framework for Data Assimilation

Flow Field Reconstruction with Sensor Placement Policy Learning

PhysGym: Benchmarking LLMs in Interactive Physics Discovery with Controlled Priors

RNNs perform task computations by dynamically warping neural representations

Adaptive Neighborhood-Constrained Q Learning for Offline Reinforcement Learning

LUNA: Efficient and Topology-Agnostic Foundation Model for EEG Signal Analysis

Time-Evolving Dynamical System for Learning Latent Representations of Mouse Visual Neural Activity

Scalable inference of functional neural connectivity at submillisecond timescales

Improving Task-Specific Multimodal Sentiment Analysis with General MLLMs via Prompting

Joint Modeling of fMRI and EEG Imaging Using Ordinary Differential Equation-Based Hypergraph Neural Networks

Bipolar Self-attention for Spiking Transformers

Meta-Learning Objectives for Preference Optimization

Learning Human-Like RL Agents Through Trajectory Optimization With Action Quantization

Composite Flow Matching for Reinforcement Learning with Shifted-Dynamics Data

Unlocking Multimodal Mathematical Reasoning via Process Reward Model

Periodic Skill Discovery

DeltaPhi: Physical States Residual Learning for Neural Operators in Data-Limited PDE Solving

INC: An Indirect Neural Corrector for Auto-Regressive Hybrid PDE Solvers

PhySense: Sensor Placement Optimization for Accurate Physics Sensing

Emerging Risks from Embodied AI Require Urgent Policy Action

LabUtopia: High-Fidelity Simulation and Hierarchical Benchmark for Scientific Embodied Agents

Robo2VLM: Improving Visual Question Answering using Large-Scale Robot Manipulation Data

SonoGym: High Performance Simulation for Challenging Surgical Tasks with Robotic Ultrasound

Quantization-Free Autoregressive Action Transformer

Model-Based Policy Adaptation for Closed-Loop End-to-end Autonomous Driving

PRIMT: Preference-based Reinforcement Learning with Multimodal Feedback and Trajectory Synthesis from Foundation Models

Synthesizing Photorealistic and Dynamic Urban Environments for Multimodal Robot Navigation and Collaboration

EgoBridge: Domain Adaptation for Generalizable Imitation from Egocentric Human Data

FreqPolicy: Efficient Flow-based Visuomotor Policy via Frequency Consistency

SAMPO: Scale-wise Autoregression with Motion Prompt for Generative World Models

Act to See, See to Act: Diffusion-Driven Perception-Action Interplay for Adaptive Policies

Building 3D Representations and Generating Motions From a Single Image via Video-Generation

Toward Interpretable Evaluation Measures for Time Series Segmentation

Learning Pattern-Specific Experts for Time Series Forecasting Under Patch-level Distribution Shift

FlowNet: Modeling Dynamic Spatio-Temporal Systems via Flow Propagation

Time-IMM: A Dataset and Benchmark for Irregular Multimodal Multivariate Time Series

SynTSBench: Rethinking Temporal Pattern Learning in Deep Learning Models for Time Series

CLEAR: Command Level Annotated Dataset for Ransomware Detection

4D-VLA: Spatiotemporal Vision-Language-Action Pretraining with Cross-Scene Calibration

PANGEA: Projection-Based Augmentation with Non-Relevant General Data for Enhanced Domain Adaptation in LLMs

Adaptive Surrogate Gradients for Sequential Reinforcement Learning in Spiking Neural Networks

Towards Realistic Earth-Observation Constellation Scheduling: Benchmark and Methodology

Chain-of-Action: Trajectory Autoregressive Modeling for Robotic Manipulation

Talk2Event: Grounded Understanding of Dynamic Scenes from Event Cameras

Bidirectional Motion Transformer for Safety-Critical Traffic Scenario Generation

Safe and Stable Control via Lyapunov-Guided Diffusion Models

Seeing through Uncertainty: Robust Task-Oriented Optimization in Visual Navigation

Learning to Control Free-Form Soft Swimmers

ReSim: Reliable World Simulation for Autonomous Driving

WeatherPrompt: Multi-modality Representation Learning for All-Weather Drone Visual Geo-Localization

TimePerceiver: An Encoder-Decoder Framework for Generalized Time-Series Forecasting

Structured Temporal Causality for Interpretable Multivariate Time Series Anomaly Detection

Constrained Posterior Sampling: Time Series Generation with Hard Constraints

Wavelet Canonical Coherence for Nonstationary Signals

ConnectomeBench: Can LLMs proofread the connectome?

MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering

AgMMU: A Comprehensive Agricultural Multimodal Understanding Benchmark

Time Travel is Cheating: Going Live with DeepFund for Real-Time Fund Investment Benchmarking

LiveCodeBench Pro: How Do Olympiad Medalists Judge LLMs in Competitive Programming?

BikeBench: A Bicycle Design Benchmark for Generative Models with Objectives and Constraints

MGE-LDM: Joint Latent Diffusion for Simultaneous Music Generation and Source Extraction

Train on Pins and Test on Obstacles for Rectilinear Steiner Minimum Tree

Can Agent Fix Agent Issues?

Fading to Grow: Growing Preference Ratios via Preference Fading Discrete Diffusion for Recommendation

Repo2Run: Automated Building Executable Environment for Code Repository at Scale

APOLLO: Automated LLM and Lean Collaboration for Advanced Formal Reasoning

TokMan:Tokenize Manhattan Mask Optimization for Inverse Lithography

Co-PatcheR: Collaborative Software Patching with Component-specific Small Reasoning Models

Breaking the Batch Barrier (B3) of Contrastive Learning via Smart Batch Mining

Learning Without Augmenting: Unsupervised Time Series Representation Learning via Frame Projections

TopER: Topological Embeddings in Graph Representation Learning

Single-pass Adaptive Image Tokenization for Minimum Program Search

seq-JEPA: Autoregressive Predictive Learning of Invariant-Equivariant World Models

MetaSlot: Break Through the Fixed Number of Slots in Object-Centric Learning

Follow the Energy, Find the Path: Riemannian Metrics from Energy-Based Models

Massive Sound Embedding Benchmark (MSEB)

Exploring Neural Granger Causality with xLSTMs: Unveiling Temporal Dependencies in Complex Data

LLM-Driven Treatment Effect Estimation Under Inference Time Text Confounding

Statistical Inference for Gradient Boosting Regression

Efficient Adaptive Experimentation with Noncompliance

Agents Robust to Distribution Shifts Learn Causal World Models Even Under Mediation

Prediction-Powered Causal Inferences

Characterization and Learning of Causal Graphs from Hard Interventions

Transferring Causal Effects using Proxies

Conditional Forecasts and Proper Scoring Rules for Reliable and Accurate Performative Predictions

CausalDynamics: A large‐scale benchmark for structural discovery of dynamical causal models

Scalable Feature Learning on Huge Knowledge Graphs for Downstream Machine Learning

Generalized Contrastive Learning for Universal Multimodal Retrieval

Joint Hierarchical Representation Learning of Samples and Features via Informed Tree-Wasserstein Distance

TransferTraj: A Vehicle Trajectory Learning Model for Region and Task Transferability

UAV-Flow Colosseo: A Real-World Benchmark for Flying-on-a-Word UAV Imitation Learning

Contrastive Self-Supervised Learning As Neural Manifold Packing

Generative Data Augmentation via Diffusion Distillation, Adversarial Alignment, and Importance Reweighting

Scalable Evaluation and Neural Models for Compositional Generalization

Functional data analysis for multivariate distributions through Wasserstein slicing

Reconciling Geospatial Prediction and Retrieval via Sparse Representations

Diverse Influence Component Analysis: A Geometric Approach to Nonlinear Mixture Identifiability

Enhancing Contrastive Learning with Variable Similarity

Scalable Cross-View Sample Alignment for Multi-View Clustering with View Structure Similarity

Bridging Arbitrary and Tree Metrics via Differentiable Gromov Hyperbolicity

Disentangled Representation Learning via Modular Compositional Bias

LCDB 1.1: A Database Illustrating Learning Curves Are More Ill-Behaved Than Previously Thought

Exploring Tradeoffs through Mode Connectivity for Multi-Task Learning

QiMeng-NeuComBack: Self-Evolving Translation from IR to Assembly Code

Scaling Up Parameter Generation: A Recurrent Diffusion Approach

KSP: Kolmogorov-Smirnov metric-based Post-Hoc Calibration for Survival Analysis

An Efficient Local Search Approach for Polarized Community Discovery in Signed Networks

MEMOIR: Lifelong Model Editing with Minimal Overwrite and Informed Retention for LLMs

Buffer layers for Test-Time Adaptation

Optimization Inspired Few-Shot Adaptation for Large Language Models

Learning to Route: Per-Sample Adaptive Routing for Multimodal Multitask Prediction

TabDPT: Scaling Tabular Foundation Models on Real Data

VIPAMIN: Visual Prompt Initialization via Embedding Selection and Subspace Expansion

UGoDIT: Unsupervised Group Deep Image Prior Via Transferable Weights

Transfer Faster, Price Smarter: Minimax Dynamic Pricing under Cross-Market Preference Shift

All You Need is One: Capsule Prompt Tuning with a Single Vector

Uncertainty-Informed Meta Pseudo Labeling for Surrogate Modeling with Limited Labeled Data

Training-Free Test-Time Adaptation via Shape and Style Guidance for Vision-Language Models

Decoupled Entropy Minimization

MetaKoopman: Bayesian Meta-Learning of Koopman Operators for Modeling Structured Dynamics under Distribution Shifts

$\texttt{G1}$: Teaching LLMs to Reason on Graphs with Reinforcement Learning

LEDiT: Your Length-Extrapolatable Diffusion Transformer without Positional Encoding

Curriculum Abductive Learning

A Few Moments Please: Scalable Graphon Learning via Moment Matching

RGNMR: A Gauss-Newton method for robust matrix completion with theoretical guarantees

Scalable, Explainable and Provably Robust Anomaly Detection with One-Step Flow Matching

A Unified Framework for Variable Selection in Model-Based Clustering with Missing Not at Random

Missing Data Imputation by Reducing Mutual Information with Rectified Flows

ComRank: Ranking Loss for Multi-Label Complementary Label Learning

Tackling Feature-Classifier Mismatch in Federated Learning via Prompt-Driven Feature Transformation

Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining

Contextual Online Pricing with (Biased) Offline Data

Parsimonious Predictions for Strategyproof Scheduling

Incentivizing Truthful Language Models via Peer Elicitation Games

Explaining the Law of Supply and Demand via Online Learning

Smoothed Agnostic Learning of Halfspaces over the Hypercube

Tightening Regret Lower and Upper Bounds in Restless Rising Bandits

Understanding LLM Behaviors via Compression: Data Generation, Knowledge Acquisition and Scaling Laws

Bandit and Delayed Feedback in Online Structured Prediction

On Learning Verifiers and Implications to Chain-of-Thought Reasoning

Non-stationary Bandit Convex Optimization: A Comprehensive Study

Walking the Tightrope: Autonomous Disentangling Beneficial and Detrimental Drifts in Non-Stationary Custom-Tuning

Rescaled Influence Functions: Accurate Data Attribution in High Dimension

A duality framework for analyzing random feature and two-layer neural networks

Impartial Selection with Predictions

Stochastic Principal-Agent Problems: Computing and Learning Optimal History-Dependent Policies

Procurement Auctions with Predictions: Improved Frugality for Facility Location

Strategic Hypothesis Testing

The Price of Opportunity Fairness in Matroid Allocation Problems

The Burden of Interactive Alignment with Inconsistent Preferences

No-Regret Learning Under Adversarial Resource Constraints: A Spending Plan Is All You Need!

Near-Optimal Quantum Algorithms for Computing (Coarse) Correlated Equilibria of General-Sum Games

HMARL-CBF – Hierarchical Multi-Agent Reinforcement Learning with Control Barrier Functions for Safety-Critical Autonomous Systems

Precise Asymptotics and Refined Regret of Variance-Aware UCB

Establishing Linear Surrogate Regret Bounds for Convex Smooth Losses via Convolutional Fenchel–Young Losses

The Persistence of Neural Collapse Despite Low-Rank Bias

A Unified Stability Analysis of SAM vs SGD: Role of Data Coherence and Emergence of Simplicity Bias

Towards the Resistance of Neural Network Fingerprinting to Fine-tuning

Dynamical Decoupling of Generalization and Overfitting in Large Two-Layer Networks

Riemannian Proximal Sampler for High-accuracy Sampling on Manifolds

Algorithm- and Data-Dependent Generalization Bounds for Diffusion Models

Attention Mechanism, Max-Affine Partition, and Universal Approximation

Minimax-Optimal Univariate Function Selection in Sparse Additive Models: Rates, Adaptation, and the Estimation-Selection Gap

Partner Modelling Emerges in Recurrent Agents (But Only When It Matters)

In-context Learning of Linear Dynamical Systems with Transformers: Approximation Bounds and Depth-separation

Tackling Biased Evaluators in Dueling Bandits

Regularized least squares learning with heavy-tailed noise is minimax optimal

Improved Confidence Regions and Optimal Algorithms for Online and Offline Linear MNL Bandits

Risk Bounds For Distributional Regression

Agnostic Active Learning Is Always Better Than Passive Learning

Robust learning of halfspaces under log-concave marginals

Learning Equilibria from Data: Provably Efficient Multi-Agent Imitation Learning

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs

PARCO: Parallel AutoRegressive Models for Multi-Agent Combinatorial Optimization

Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners

Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoning

EDELINE: Enhancing Memory in Diffusion-based World Models via Linear-Time Sequence Modeling

General-Reasoner: Advancing LLM Reasoning Across All Domains

SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learning

Staggered Environment Resets Improve Massively Parallel On-Policy Reinforcement Learning

Accelerating data-driven algorithm selection for combinatorial partitioning problems

Provable Watermarking for Data Poisoning Attacks

Improved Bounds for Swap Multicalibration and Swap Omniprediction

Instance-Dependent Regret Bounds for Nonstochastic Linear Partial Monitoring

Kernel Learning with Adversarial Features: Numerical Efficiency and Adaptive Regularization

On the Stability and Generalization of Meta-Learning: the Impact of Inner-Levels

The Parameterized Complexity of Computing the VC-Dimension

Kernel conditional tests from learning-theoretic bounds

Private Online Learning against an Adaptive Adversary: Realizable and Agnostic Settings

Distributed Multi-Agent Bandits Over Erdős-Rényi Random Networks

Mixture-of-Experts Meets In-Context Reinforcement Learning

Revisiting Agnostic Boosting

Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model

Incentivizing LLMs to Self-Verify Their Answers

Reasoning Models Hallucinate More: Factuality-Aware Reinforcement Learning for Large Reasoning Models

AlphaZero Neural Scaling and Zipf's Law: a Tale of Board Games and Power Laws

COLA: Towards Efficient Multi-Objective Reinforcement Learning with Conflict Objective Regularization in Latent Space

Block Coordinate Descent for Neural Networks Provably Finds Global Minima

Dimension-adapted Momentum Outscales SGD

Comparing Uniform Price and Discriminatory Multi-Unit Auctions through Regret Minimization

Posterior Contraction for Sparse Neural Networks in Besov Spaces with Intrinsic Dimensionality

Lyapunov-Stable Adaptive Control for Multimodal Concept Drift

Tight Generalization Bounds for Large-Margin Halfspaces

Performative Risk Control: Calibrating Models for Reliable Deployment under Performativity

On the Convergence of Projected Policy Gradient for Any Constant Step Sizes

A Principled Path to Fitted Distributional Evaluation

Certifying Stability of Reinforcement Learning Policies using Generalized Lyapunov Functions

On the Convergence of Single-Timescale Actor-Critic

Kernel von Mises Formula of the Influence Function

Fully Dynamic Algorithms for Chamfer Distance

Minimum Width for Deep, Narrow MLP: A Diffeomorphism Approach

Conformal Prediction Beyond the Seen: A Missing Mass Perspective for Uncertainty Quantification in Generative Models

LLM Query Scheduling with Prefix Reuse and Latency Constraints

Rewind-to-Delete: Certified Machine Unlearning for Nonconvex Functions

Machine Unlearning under Overparameterization

Adversarial Robustness of Nonparametric Regression

Conformal Inference under High-Dimensional Covariate Shifts via Likelihood-Ratio Regularization

Maximizing the Value of Predictions in Control: Accuracy Is Not Enough

Efficient $k$-Sparse Band–Limited Interpolation with Improved Approximation Ratio

DCAD-2000: A Multilingual Dataset across 2000+ Languages with Data Cleaning as Anomaly Detection

Efficient Preference-Based Reinforcement Learning: Randomized Exploration meets Experimental Design

Greedy Sampling Is Provably Efficient For RLHF

Don’t Trade Off Safety: Diffusion Regularization for Constrained Offline RL

Variance-Aware Feel-Good Thompson Sampling for Contextual Bandits

Eluder dimension: localise it!

Towards Provable Emergence of In-Context Reinforcement Learning

Avoiding exp(R) scaling in RLHF through Preference-based Exploration

Optimal Nuisance Function Tuning for Estimating a Doubly Robust Functional under Proportional Asymptotics

Product Distribution Learning with Imperfect Advice

Adaptive Prediction-Powered AutoEval with Reliability and Efficiency Guarantees

Network two-sample test for block models

The Logical Expressiveness of Temporal GNNs via Two-Dimensional Product Logics

metaTextGrad: Automatically optimizing language model optimizers

Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning

Self-Challenging Language Model Agents

DOVE: Efficient One-Step Diffusion Model for Real-World Video Super-Resolution

GradMetaNet: An Equivariant Architecture for Learning on Gradients

AcuRank: Uncertainty-Aware Adaptive Computation for Listwise Reranking

Rethinking Residual Distribution in Locate-then-Edit Model Editing

ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization

Harmony in Divergence: Towards Fast, Accurate, and Memory-efficient Zeroth-order LLM Fine-tuning

Learning to Rank for In-Context Example Retrieval

GVPO: Group Variance Policy Optimization for Large Language Model Post-Training

Pre-Trained Policy Discriminators are General Reward Models

X-Mahalanobis: Transformer Feature Mixing for Reliable OOD Detection

Wider or Deeper? Scaling LLM Inference-Time Compute with Adaptive Branching Tree Search

IPFormer: Visual 3D Panoptic Scene Completion with Context-Adaptive Instance Proposals

CAT: Circular-Convolutional Attention for Sub-Quadratic Transformers

Dynamics of Spontaneous Topic Changes in Next Token Prediction with Self-Attention

Infinite-Width Limit of a Single Attention Layer: Analysis via Tensor Programs

FAME: Adaptive Functional Attention with Expert Routing for Function-on-Function Regression

PaTH Attention: Position Encoding via Accumulating Householder Transformations

MonarchAttention: Zero-Shot Conversion to Fast, Hardware-Aware Structured Attention

A multiscale analysis of mean-field transformers in the moderate interaction regime

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models

Scale-invariant attention

ZeroS: Zero‑Sum Linear Attention for Efficient Transformers

LoRASuite: Efficient LoRA Adaptation Across Large Language Model Upgrades

SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training

Degrees of Freedom for Linear Attention: Distilling Softmax Attention with Optimal Feature Efficiency

Quantum Doubly Stochastic Transformers

Normalize Filters! Classical Wisdom for Deep Vision

Dimensional Collapse in VQVAEs: Evidence and Remedies

Corrector Sampling in Language Models

Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning

Dense Backpropagation Improves Training for Sparse Mixture-of-Experts

SAS: Simulated Attention Score

SALS: Sparse Attention in Latent Space for KV Cache Compression

REAL: Benchmarking Autonomous Agents on Deterministic Simulations of Real Websites

PoGDiff: Product-of-Gaussians Diffusion Models for Imbalanced Text-to-Image Generation

ReDi: Rectified Discrete Flow

On-Policy Optimization with Group Equivalent Preference for Multi-Programming Language Understanding

The Rise of Parameter Specialization for Knowledge Storage in Large Language Models

AltLoRA: Towards Better Gradient Approximation in Low-Rank Adaptation with Alternating Projections

Exploring the Design Space of Diffusion Bridge Models

Multitask Learning with Stochastic Interpolants

See through the Dark: Learning Illumination-affined Representations for Nighttime Occupancy Prediction

Posterior Sampling by Combining Diffusion Models with Annealed Langevin Dynamics

COME: Adding Scene-Centric Forecasting Control to Occupancy World Model

Entropic Time Schedulers for Generative Diffusion Models

zip2zip: Inference-Time Adaptive Tokenization via Online Compression

ROOT: Rethinking Offline Optimization as Distributional Translation via Probabilistic Bridge

Optical Coherence Tomography Harmonization with Anatomy-Guided Latent Metric Schrödinger Bridges

Beyond Scores: Proximal Diffusion Models

Learning to Integrate Diffusion ODEs by Averaging the Derivatives

DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization

LayerNavigator: Finding Promising Intervention Layers for Efficient Activation Steering in Large Language Models

Why Masking Diffusion Works: Condition on the Jump Schedule for Improved Discrete Diffusion

Flex-Judge: Text-Only Reasoning Unleashes Zero-Shot Multimodal Evaluators

SAEMark: Steering Personalized Multilingual LLM Watermarks with Sparse Autoencoders

Training-Free Guidance Beyond Differentiability: Scalable Path Steering with Tree Search in Diffusion and Flow Models

Efficiently Scaling LLM Reasoning Programs with Certaindex

Nested Learning: The Illusion of Deep Learning Architectures

RoMa: A Robust Model Watermarking Scheme for Protecting IP in Diffusion Models

Tracing the Roots: Leveraging Temporal Dynamics in Diffusion Trajectories for Origin Attribution

Zebra-Llama: Towards Extremely Efficient Hybrid Models

High-Order Flow Matching: Unified Framework and Sharp Statistical Rates

Towards General Modality Translation with Contrastive and Predictive Latent Diffusion Bridge

Think Only When You Need with Large Hybrid-Reasoning Models

Kuramoto Orientation Diffusion Models

Joint Relational Database Generation via Graph-Conditional Diffusion Models

On the Empirical Power of Goodness-of-Fit Tests in Watermark Detection

Once Upon an Input: Reasoning via Per-Instance Program Synthesis

CDFlow: Building Invertible Layers with Circulant and Diagonal Matrices

Ask a Strong LLM Judge when Your Reward Model is Uncertain

GraphLand: Evaluating Graph Machine Learning Models on Diverse Industrial Data

CosmoBench: A Multiscale, Multiview, Multitask Cosmology Benchmark for Geometric Deep Learning

MiNT: Multi-Network Transfer Benchmark for Temporal Graph Learning

GFM-RAG: Graph Foundation Model for Retrieval Augmented Generation

Hierarchical Shortest-Path Graph Kernel Network

Out-of-Distribution Generalized Graph Anomaly Detection with Homophily-aware Environment Mixup

Towards Effective Federated Graph Foundation Model via Mitigating Knowledge Entanglement

Influence Functions for Edge Edits in Non-Convex Graph Neural Networks

MoEMeta: Mixture-of-Experts Meta Learning for Few-Shot Relational Learning

Optimal Graph Clustering without Edge Density Signals

Equivariance Everywhere All At Once: A Recipe for Graph Foundation Models

Future Link Prediction Without Memory or Aggregation

Pruning Spurious Subgraphs for Graph Out-of-Distribution Generalization

MOTION: Multi-Sculpt Evolutionary Coarsening for Federated Continual Graph Learning

Subgraph Federated Learning via Spectral Methods

Logical Expressiveness of Graph Neural Networks with Hierarchical Node Individualization

Torch-Uncertainty: Deep Learning Uncertainty Quantification

SNAP: Low-Latency Test-Time Adaptation with Sparse Updates

Competitive Advantage Attacks to Decentralized Federated Learning

CCL: Causal-aware In-context Learning for Out-of-Distribution Generalization

Generalization vs Specialization under Concept Shift

Improved Scaling Laws in Linear Regression via Data Reuse

The emergence of sparse attention: impact of data distribution and benefits of repetition

On the Surprising Effectiveness of Large Learning Rates under Standard Width Scaling

From Condensation to Rank Collapse: A Two-Stage Analysis of Transformer Training Dynamics

Go With the Flow: Fast Diffusion for Gaussian Mixture Models

Exact Expressive Power of Transformers with Padding

Lost in Transmission: When and Why LLMs Fail to Reason Globally

How Does Label Noise Gradient Descent Improve Generalization in the Low SNR Regime?

Nonparametric Quantile Regression with ReLU-Activated Recurrent Neural Networks

RSAVQ: Riemannian Sensitivity-Aware Vector Quantization for Large Language Models

The Implicit Bias of Structured State Space Models Can Be Poisoned With Clean Labels

Reproducing Kernel Banach Space Models for Neural Networks with Application to Rademacher Complexity Analysis

Deep Nonlinear Sufficient Dimension Reduction

Scaling Data-Driven Probabilistic Robustness Analysis for Semantic Segmentation Neural Networks

Fit the Distribution: Cross-Image/Prompt Adversarial Attacks on Multimodal Large Language Models

Scalable Neural Network Geometric Robustness Validation via Hölder Optimisation

Towards Building Model/Prompt-Transferable Attackers against Large Vision-Language Models

Robustness in Both Domains: CLIP Needs a Robust Text Encoder

Latency NMS Attacks: Is It Real Life or Is It Just Fantasy?

ReMA: Learning to Meta-Think for LLMs with Multi-agent Reinforcement Learning

Don't be lazy: CompleteP enables compute-efficient deep transformers

From Shortcut to Induction Head: How Data Diversity Shapes Algorithm Selection in Transformers

What One Cannot, Two Can: Two-Layer Transformers Provably Represent Induction Heads on Any-Order Markov Chains

Streaming Attention Approximation via Discrepancy Theory

MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts Systems

Self-Verifying Reflection Helps Transformers with CoT Reasoning

Beyond Components: Singular Vector-Based Interpretability of Transformer Circuits

Masked Diffusion Models as Energy Minimization

Representation Consistency for Accurate and Coherent LLM Answer Aggregation

The Lighthouse of Language: Enhancing LLM Agents via Critique-Guided Improvement

GSO: Challenging Software Optimization Tasks for Evaluating SWE-Agents

Towards Fully FP8 GEMM LLM Training at Scale

Do Language Models Use Their Depth Efficiently?

Chain of Execution Supervision Promotes General Reasoning in Large Language Models

Efficient Multi-bit Quantization Network Training via Weight Bias Correction and Bit-wise Coreset Sampling

Sherlock: Self-Correcting Reasoning in Vision-Language Models

Thinkless: LLM Learns When to Think

BLEUBERI: BLEU is a surprisingly effective reward for instruction following

ZEUS: Zero-shot Embeddings for Unsupervised Separation of Tabular Data

Continuous Subspace Optimization for Continual Learning

Self-Evolving Pseudo-Rehearsal for Catastrophic Forgetting with Task Similarity in LLMs

TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks

EVAAA: A Virtual Environment Platform for Essential Variables in Autonomous and Adaptive Agents

KL Penalty Control via Perturbation for Direct Preference Optimization

Continuous Soft Actor-Critic: An Off-Policy Learning Method Robust to Time Discretization

Learning Parameterized Skills from Demonstrations

Diffusion Guided Adversarial State Perturbations in Reinforcement Learning

Reinforcement learning for one-shot DAG scheduling with comparability identification and dense reward

STAIR: Addressing Stage Misalignment through Temporal-Aligned Preference Reinforcement Learning

A Generalized Bisimulation Metric of State Similarity between Markov Decision Processes: From Theoretical Propositions to Applications

Rendering-Aware Reinforcement Learning for Vector Graphics Generation

MMIG-Bench: Towards Comprehensive and Explainable Evaluation of Multi-Modal Image Generation Models

EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Videos Generation

OverLayBench: A Benchmark for Layout-to-Image Generation with Dense Overlaps

AdaSPEC: Selective Knowledge Distillation for Efficient Speculative Decoders

70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float (DFloat11)

Searching Efficient Semantic Segmentation Architectures via Dynamic Path Selection

Listwise Preference Diffusion Optimization for User Behavior Trajectories Prediction

DP-LLM: Runtime Model Adaptation with Dynamic Layer-wise Precision Assignment

CAS-Spec: Cascade Adaptive Self-Speculative Decoding for On-the-Fly Lossless Inference Acceleration of LLMs

SeRL: Self-play Reinforcement Learning for Large Language Models with Limited Data

GOOD: Training-Free Guided Diffusion Sampling for Out-of-Distribution Detection

CORE: Reducing UI Exposure in Mobile Agents via Collaboration Between Cloud and Local LLMs

Incentivizing Dual Process Thinking for Efficient Large Language Model Reasoning

Skill-Driven Neurosymbolic State Abstractions

Approximating Shapley Explanations in Reinforcement Learning

Rectifying Shortcut Behaviors in Preference-based Reward Learning

Enhancing Safety in Reinforcement Learning with Human Feedback via Rectified Policy Optimization

XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation

Mind-the-Glitch: Visual Correspondence for Detecting Inconsistencies in Subject-Driven Generation

Self-diffusion for Solving Inverse Problems

Let the LLM Stick to Its Strengths: Learning to Route Economical LLM

PanoWan: Lifting Diffusion Video Generation Models to 360$^\circ$ with Latitude/Longitude-aware Mechanisms

Imagine360: Immersive 360 Video Generation from Perspective Anchor

Training-Free Efficient Video Generation via Dynamic Token Carving

Stable Cinemetrics : Structured Taxonomy and Evaluation for Professional Video Generation

RoomEditor: High-Fidelity Furniture Synthesis with Parameter-Sharing U-Net

Dimension-Reduction Attack! Video Generative Models are Experts on Controllable Image Synthesis

Smooth and Flexible Camera Movement Synthesis via Temporal Masked Generative Modeling

FreeInv: Free Lunch for Improving DDIM Inversion

Seg2Any: Open-set Segmentation-Mask-to-Image Generation with Precise Shape and Semantic Control

Improving Video Generation with Human Feedback

Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation

HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidance

SViMo: Synchronized Diffusion for Video and Motion Generation in Hand-object Interaction Scenarios

DINO-Foresight: Looking into the Future with DINO

Universal Few-shot Spatial Control for Diffusion Models

A Gradient Guidance Perspective on Stepwise Preference Optimization for Diffusion Models

IntrinsiX: High-Quality PBR Generation using Image Priors

Diffusion Model as a Noise-Aware Latent Reward Model for Step-Level Preference Optimization

DiCo: Revitalizing ConvNets for Scalable and Efficient Diffusion Modeling

Localizing Knowledge in Diffusion Transformers

MoCha: Towards Movie-Grade Talking Character Generation

DEFT: Decompositional Efficient Fine-Tuning for Text-to-Image Models

PairEdit: Learning Semantic Variations for Exemplar-based Image Editing

Native-Resolution Image Synthesis

The Matrix: Infinite-Horizon World Generation with Real-Time Moving Control

Image Editing As Programs with Diffusion Models

Hawk: Leveraging Spatial Context for Faster Autoregressive Text-to-Image Generation

Simple Distillation for One-Step Diffusion Models

Solving Inverse Problems with FLAIR

ROSE: Remove Objects with Side Effects in Videos

Towards a Golden Classifier-Free Guidance Path via Foresight Fixed Point Iterations

MotionRAG: Motion Retrieval-Augmented Image-to-Video Generation

Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validity

C3Po: Cross-View Cross-Modality Correspondence by Pointmap Prediction

GS2E: Gaussian Splatting is an Effective Data Generator for Event Stream Generation

RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes

ODG: Occupancy Prediction Using Dual Gaussians

PBR-SR: Mesh PBR Texture Super Resolution from 2D Image Priors

I2-NeRF: Learning Neural Radiance Fields Under Physically-Grounded Media Interactions

Learning Neural Exposure Fields for View Synthesis

RaySt3R: Predicting Novel Depth Maps for Zero-Shot Object Completion

Dynamic Gaussian Splatting from Defocused and Motion-blurred Monocular Videos

Omnidirectional 3D Scene Reconstruction from Single Image

X-Field: A Physically Informed Representation for 3D X-ray Reconstruction

SRHand: Super-Resolving Hand Images and 3D Shapes via View/Pose-aware Neural Image Representations and Explicit Meshes

FlexWorld: Progressively Expanding 3D Scenes for Flexible-View Exploration

ROGR: Relightable 3D Objects using Generative Relighting

LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPS

OrthoLoC: UAV 6-DoF Localization and Calibration Using Orthographic Geodata

Face-Human-Bench: A Comprehensive Benchmark of Face and Human Understanding for Multi-modal Assistants

CHOICE: Benchmarking the Remote Sensing Capabilities of Large Vision-Language Models

MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models

EmoNet-Face: An Expert-Annotated Benchmark for Synthetic Emotion Recognition

Intend to Move: A Multimodal Dataset for Intention-Aware Human Motion Understanding

HAIF-GS: Hierarchical and Induced Flow-Guided Gaussian Splatting for Dynamic Scene

Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer Memory

Segment then Splat: Unified 3D Open-Vocabulary Segmentation via Gaussian Splatting

ARMesh: Autoregressive Mesh Generation via Next-Level-of-Detail Prediction

Rig3R: Rig-Aware Conditioning and Discovery for 3D Reconstruction

3D Visual Illusion Depth Estimation

ShapeCraft: LLM Agents for Structured, Textured and Interactive 3D Modeling

Fin3R: Fine-tuning Feed-forward 3D Reconstruction Models via Monocular Knowledge Distillation

LuxDiT: Lighting Estimation with Video Diffusion Transformer

Towards Generalizable 3D Human Pose Estimation via Ensembles on Flat Loss Landscapes

RPG360: Robust 360 Depth Estimation with Perspective Foundation Models and Graph Optimization

Learning Generalizable Shape Completion with SIM(3) Equivariance

QuadricFormer: Scene as Superquadrics for 3D Semantic Occupancy Prediction

MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds

Situat3DChange: Situated 3D Change Understanding Dataset for Multimodal Large Language Model

SMMILE: An expert-driven benchmark for multimodal medical in-context learning

EgoBlind: Towards Egocentric Visual Assistance for the Blind

3EED: Ground Everything Everywhere in 3D

DynamicVL: Benchmarking Multimodal Large Language Models for Dynamic City Understanding

Model-Guided Dual-Role Alignment for High-Fidelity Open-Domain Video-to-Audio Generation

UniPixel: Unified Object Referring and Segmentation for Pixel-Level Visual Reasoning

Simulation-Based Inference for Adaptive Experiments

VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning

PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding

Multi-Kernel Correlation-Attention Vision Transformer for Enhanced Contextual Understanding and Multi-Scale Integration

InfMasking: Unleashing Synergistic Information by Contrastive Multimodal Interactions

LaViDa: A Large Diffusion Model for Vision-Language Understanding

Show-o2: Improved Native Unified Multimodal Models

OpenBox: Annotate Any Bounding Boxes in 3D

Unified Reinforcement and Imitation Learning for Vision-Language Models

FRN: Fractal-Based Recursive Spectral Reconstruction Network

FOCUS: Internal MLLM Representations for Efficient Fine-Grained Visual Question Answering

INST-IT: Boosting Instance Understanding via Explicit Visual Prompt Instruction Tuning

OpenMMEgo: Enhancing Egocentric Understanding for LMMs with Open Weights and Data

Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding

REOrdering Patches Improves Vision Models

MERIT: Multilingual Semantic Retrieval with Interleaved Multi-Condition Query

One Token per Highly Selective Frame: Towards Extreme Compression for Long Video Understanding

OnlineSplatter: Pose-Free Online 3D Reconstruction for Free-Moving Objects

Vision Transformers with Self-Distilled Registers

ExGra-Med: Extended Context Graph Alignment for Medical Vision-Language Models

UFM: A Simple Path towards Unified Dense Correspondence with Flow

ReID5o: Achieving Omni Multi-modal Person Re-identification in a Single Model

VITRIX-UniViTAR: Unified Vision Transformer with Native Resolution

Towards Self-Refinement of Vision-Language Models with Triangular Consistency

Confusion-Driven Self-Supervised Progressively Weighted Ensemble Learning for Non-Exemplar Class Incremental Learning

VL-SAM-V2: Open-World Object Detection with General and Specific Query Fusion

MEgoHand: Multimodal Egocentric Hand-Object Interaction Motion Generation

Fact-R1: Towards Explainable Video Misinformation Detection with Deep Reasoning

SegMASt3R: Geometry Grounded Segment Matching

RePIC: Reinforced Post-Training for Personalizing Multi-Modal Language Models

Event-Guided Consistent Video Enhancement with Modality-Adaptive Diffusion Pipeline

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT

Chirality in Action: Time-Aware Video Representation Learning by Latent Straightening

Taming generative video models for zero-shot optical flow extraction

MixPrompt: Efficient Mixed Prompting for Multimodal Semantic Segmentation

Where Does It Exist from the Low-Altitude: Spatial Aerial Video Grounding

iFinder: Structured Zero-Shot Vision-Based LLM Grounding for Dash-Cam Video Reasoning

From Human Attention to Diagnosis: Semantic Patch-Level Integration of Vision-Language Models in Medical Imaging

SCOPE: Saliency-Coverage Oriented Token Pruning for Efficient Multimodel LLMs

CausalVTG: Towards Robust Video Temporal Grounding via Causal Inference

TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs

From Forecasting to Planning: Policy World Model for Collaborative State-Action Prediction

Automatic Synthetic Data and Fine-grained Adaptive Feature Alignment for Composed Person Retrieval

MotionBind: Multi-Modal Human Motion Alignment for Retrieval, Recognition, and Generation

Scaling Image Geo-Localization to Continent Level

Balanced Token Pruning: Accelerating Vision Language Models Beyond Local Optimization

InstructRestore: Region-Customized Image Restoration with Human Instructions

SpaceServe: Spatial Multiplexing of Complementary Encoders and Decoders for Multimodal LLMs

HopaDIFF: Holistic-Partial Aware Fourier Conditioned Diffusion for Referring Human Action Segmentation in Multi-Person Scenarios

Distil-E2D: Distilling Image-to-Depth Priors for Event-Based Monocular Depth Estimation

Iterative Tool Usage Exploration for Multimodal Agents via Step-wise Preference Tuning

BioCLIP 2: Emergent Properties from Scaling Hierarchical Contrastive Learning

Learning the Wrong Lessons: Syntactic-Domain Spurious Correlations in Language Models

Interaction-Centric Knowledge Infusion and Transfer for Open Vocabulary Scene Graph Generation

CQ-DINO: Mitigating Gradient Dilution via Category Queries for Vast Vocabulary Object Detection

Knowledge Graph Enhanced Generative Multi-modal Models for Class-Incremental Learning

OmniGaze: Reward-inspired Generalizable Gaze Estimation in the Wild

Diffusing DeBias: Synthetic Bias Amplification for Model Debiasing

Dual-Space Semantic Synergy Distillation for Continual Learning of Unlabeled Streams

CoralVQA: A Large-Scale Visual Question Answering Dataset for Coral Reef Image Understanding

egoEMOTION: Egocentric Vision and Physiological Signals for Emotion and Personality Recognition in Real-world Tasks

Mamba Goes HoME: Hierarchical Soft Mixture-of-Experts for 3D Medical Image Segmentation

Differentiable Hierarchical Visual Tokenization

Continual Gaussian Mixture Distribution Modeling for Class Incremental Semantic Segmentation

Towards Unsupervised Domain Bridging via Image Degradation in Semantic Segmentation

MATCH: Multi-faceted Adaptive Topo-Consistency for Semi-Supervised Histopathology Segmentation

Gate to the Vessel: Residual Experts Restore What SAM Overlooks

CamSAM2: Segment Anything Accurately in Camouflaged Videos

VQ-Seg: Vector-Quantized Token Perturbation for Semi-Supervised Medical Image Segmentation

GauSAM: Contour‑Guided 2D Gaussian Fields for Multi‑Scale Medical Image Segmentation with Segment Anything

Bringing SAM to new heights: leveraging elevation data for tree crown segmentation from drone imagery

C-LoRA: Contextual Low-Rank Adaptation for Uncertainty Estimation in Large Language Models

Convolution Goes Higher-Order: A Biologically Inspired Mechanism Empowers Image Classification

Smooth Regularization for Efficient Video Recognition

PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understanding

AGC-Drive: A Large-Scale Dataset for Real-World Aerial-Ground Collaboration in Driving Scenarios

HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object Interaction

UrbanIng-V2X: A Large-Scale Multi-Vehicle, Multi-Infrastructure Dataset Across Multiple Intersections for Cooperative Perception

How to Scale Second-Order Optimization

GTR-Loc: Geospatial Text Regularization Assisted Outdoor LiDAR Localization

Unraveling Metameric Dilemma for Spectral Reconstruction: A High-Fidelity Approach via Semi-Supervised Learning

DualEqui: A Dual-Space Hierarchical Equivariant Network for Large Biomolecules

VIKING: Deep variational inference with stochastic projections

FRBNet: Revisiting Low-Light Vision through Frequency-Domain Radial Basis Network

Instant Video Models: Universal Adapters for Stabilizing Image-Based Networks

ELDET: Early-Learning Distillation with Noisy Labels for Object Detection

Dual-Stage Value-Guided Inference with Margin-Based Reward Adjustment for Fast and Faithful VLM Captioning

SynCL: A Synergistic Training Strategy with Instance-Aware Contrastive Learning for End-to-End Multi-Camera 3D Tracking

Under the Shadow: Exploiting Opacity Variation for Fine-grained Shadow Detection

BitMark: Watermarking Bitwise Autoregressive Image Generative Models

Spiking Meets Attention: Efficient Remote Sensing Image Super-Resolution with Attention Spiking Neural Networks

3DPE-Gaze:Unlocking the Potential of 3D Facial Priors for Generalized Gaze Estimation

Bézier Splatting for Fast and Differentiable Vector Graphics Rendering

Bayesian Concept Bottleneck Models with LLM Priors

Personalized Bayesian Federated Learning with Wasserstein Barycenter Aggregation

How many measurements are enough? Bayesian recovery in inverse problems with general distributions

Quantifying Uncertainty in the Presence of Distribution Shifts

Conformal Prediction for Ensembles: Improving Efficiency via Score-Based Aggregation

Synergy Between the Strong and the Weak: Spiking Neural Networks are Inherently Self-Distillers

Smooth Sailing: Lipschitz-Driven Uncertainty Quantification for Spatial Associations

SING: SDE Inference via Natural Gradients

Conformal Prediction for Time-series Forecasting with Change Points

Can LLMs Correct Themselves? A Benchmark of Self-Correction in LLMs

SoMi-ToM: Evaluating Multi-Perspective Theory of Mind in Embodied Social Interactions

PSMBench: A Benchmark and Dataset for Evaluating LLMs Extraction of Protocol State Machines from RFC Specifications

BMMR: A Large-Scale Bilingual Multimodal Multi-Discipline Reasoning Dataset

Position: Towards Bidirectional Human-AI Alignment

Statistics Caching Test-Time Adaptation for Vision-Language Models

Real-Time Scene-Adaptive Tone Mapping for High-Dynamic Range Object Detection

Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations

3D Gaussian Splatting based Scene-independent Relocalization with Unidirectional and Bidirectional Feature Fusion

RayFusion: Ray Fusion Enhanced Collaborative Visual Perception

Flow based approach for Dynamic Temporal Causal models with non-Gaussian or Heteroscedastic Noises

Event-Driven Dynamic Scene Depth Completion

Breaking the Discretization Barrier of Continuous Physics Simulation Learning

Deep Continuous-Time State-Space Models for Marked Event Sequences

Towards Robust Zero-Shot Reinforcement Learning

Zero-shot World Models via Search in Memory

Thinking vs. Doing: Improving Agent Reasoning by Scaling Test-Time Interaction

Scientists' First Exam: Probing Cognitive Abilities of MLLM via Perception, Understanding, and Reasoning

OmniBench: Towards The Future of Universal Omni-Language Models

Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing

KRIS-Bench: Benchmarking Next-Level Intelligent Image Editing Models

AHa-Bench: Benchmarking Audio Hallucinations in Large Audio-Language Models

GenSpace: Benchmarking Spatially-Aware Image Generation

Online Time Series Forecasting with Theoretical Guarantees

VLMs can Aggregate Scattered Training Patches

FlowPrune: Accelerating Attention Flow Calculation by Pruning Flow Network

4D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time

Learning to Generalize: An Information Perspective on Neural Processes

OpenOmni: Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-time Emotional Speech Synthesis

REMI: Reconstructing Episodic Memory During Internally Driven Path Planning

Why and How LLMs Hallucinate: Connecting the Dots with Subsequence Associations

Differentially Private Bilevel Optimization: Efficient Algorithms with Near-Optimal Rates

CoCoA: A Minimum Bayes Risk Framework Bridging Confidence and Consistency for Uncertainty Quantification in LLMs

4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos

FOCUS: Unified Vision-Language Modeling for Interactive Editing Driven by Referential Segmentation

Class-aware Domain Knowledge Fusion and Fission for Continual Test-Time Adaptation

Generative RLHF-V: Learning Principles from Multi-modal Human Preference

Fast Projection-Free Approach (without Optimization Oracle) for Optimization over Compact Convex Set

Balancing Positive and Negative Classification Error Rates in Positive-Unlabeled Learning

Solving the Asymmetric Traveling Salesman Problem via Trace-Guided Cost Augmentation

Measuring AI Ability to Complete Long Software Tasks

Guarantees for Alternating Least Squares in Overparameterized Tensor Decompositions

Feedback Guidance of Diffusion Models

On Geometry-Enhanced Parameter-Efficient Fine-Tuning for 3D Scene Segmentation

SIFusion: A Unified Fusion Framework for Multi-granularity Arctic Sea Ice Forecasting

On the SAC-BL Algorithm for Anomaly Detection

Towards Visualization-of-Thought Jailbreak Attack against Large Visual Language Models

URLs Help, Topics Guide: Understanding Metadata Utility in LLM Training

MPS-Prover: Advancing Stepwise Theorem Proving by Multi-Perspective Search and Data Curation

Length Generalization via Auxiliary Tasks

CAD-Coder: Text-to-CAD Generation with Chain-of-Thought and Geometric Reward

DIPO: Dual-State Images Controlled Articulated Object Generation Powered by Diverse Data

ShiQ: Bringing back Bellman to LLMs

FlexAC: Towards Flexible Control of Associative Reasoning in Multimodal Large Language Models

Probing Hidden Knowledge Holes in Unlearned LLMs

Generative Trajectory Stitching through Diffusion Composition

Alignment of Large Language Models with Constrained Learning

Composition and Alignment of Diffusion Models using Constrained Learning

JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent

Unified Transferability Metrics for Time Series Foundation Models

VeriThinker: Learning to Verify Makes Reasoning Model Efficient

KGGen: Extracting Knowledge Graphs from Plain Text with Language Models

Is Your Diffusion Model Actually Denoising?

AlignedGen: Aligning Style Across Generated Images

Meta-learning how to Share Credit among Macro-Actions

Generalized and Invariant Single-Neuron In-Vivo Activity Representation Learning

Hardware-aligned Hierarchical Sparse Attention for Efficient Long-term Memory Access

DIFFSSR: Stereo Image Super-resolution Using Differential Transformer

Large Language Bayes

Spiking Neural Networks Need High-Frequency Information

Rebalancing Return Coverage for Conditional Sequence Modeling in Offline Reinforcement Learning

Fair Cooperation in Mixed-Motive Games via Conflict-Aware Gradient Adjustment

RoME: Domain-Robust Mixture-of-Experts for MILP Solution Prediction across Domains

OWMM-Agent: Open World Mobile Manipulation With Multi-modal Agentic Data Synthesis

Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPO

Composing Global Solutions to Reasoning Tasks via Algebraic Objects in Neural Nets

Enhancing CLIP Robustness via Cross-Modality Alignment

A Set of Generalized Components to Achieve Effective Poison-only Clean-label Backdoor Attacks with Collaborative Sample Selection and Triggers

Vinci: Deep Thinking in Text-to-Image Generation using Unified Model with Reinforcement Learning

Object-centric 3D Motion Field for Robot Learning from Human Videos

SAGE: A Unified Framework for Generalizable Object State Recognition with State-Action Graph Embedding

A Closer Look to Positive-Unlabeled Learning from Fine-grained Perspectives: An Empirical Study

Fast exact recovery of noisy matrix from few entries: the infinity norm approach

UniLumos: Fast and Unified Image and Video Relighting with Physics-Plausible Feedback

Gaussian Processes for Shuffled Regression

A Black-Box Debiasing Framework for Conditional Sampling

Sampling by averaging: A multiscale approach to score estimation

Sampling from multi-modal distributions with polynomial query complexity in fixed dimension via reverse diffusion

Learning Latent Variable Models via Jarzynski-adjusted Langevin Algorithm

Asymptotically exact variational flows via involutive MCMC kernels

Small Resamples, Sharp Guarantees: Convergence Rates for Resampled Studentized Quantile Estimators

Discrete Neural Flow Samplers with Locally Equivariant Transformer

SimpleStrat: Diversifying Language Model Generation with Stratification

Low-Rank Graphon Learning for Networks

Neural Stochastic Flows: Solver-Free Modelling and Inference for SDE Solutions

RoboCerebra: A Large-scale Benchmark for Long-horizon Robotic Manipulation Evaluation

MetaBox-v2: A Unified Benchmark Platform for Meta-Black-Box Optimization

How Memory in Optimization Algorithms Implicitly Modifies the Loss

GraLoRA: Granular Low-Rank Adaptation for Parameter-Efficient Fine-Tuning

UniteFormer: Unifying Node and Edge Modalities in Transformers for Vehicle Routing Problems

Bridging Crypto with ML-based Solvers: the SAT Formulation and Benchmarks

Fractional Langevin Dynamics for Combinatorial Optimization via Polynomial-Time Escape

Efficiently Escaping Saddle Points under Generalized Smoothness via Self-Bounding Regularity

Enhanced Cyclic Coordinate Descent Methods for Elastic Net Penalized Linear Models

Deep learning for continuous-time stochastic control with jumps

Decreasing Entropic Regularization Averaged Gradient for Semi-Discrete Optimal Transport

Natural Gradient VI: Guarantees for Non-Conjugate Models

On the Convergence of Stochastic Smoothed Multi-Level Compositional Gradient Descent Ascent

Isotropic Noise in Stochastic and Quantum Convex Optimization

Constrained Optimization From a Control Perspective via Feedback Linearization

Problem-Parameter-Free Decentralized Bilevel Optimization

Fast Zeroth-Order Convex Optimization with Quantum Gradient Methods

Sharper Convergence Rates for Nonconvex Optimisation via Reduction Mappings

Quantum Speedups for Minimax Optimization and Beyond

CATransformers: Carbon Aware Transformers Through Joint Model-Hardware Optimization

DPAIL: Training Diffusion Policy for Adversarial Imitation Learning without Policy Optimization

Differentiation Through Black-Box Quadratic Programming Solvers

Generative diffusion for perceptron problems: statistical physics analysis and efficient algorithms

Preference-Driven Multi-Objective Combinatorial Optimization with Conditional Computation

Neural Combinatorial Optimization for Time Dependent Traveling Salesman Problem

Online Two-Stage Submodular Maximization

A Unified Approach to Submodular Maximization Under Noise

Improved Algorithms for Fair Matroid Submodular Maximization

Dynamic Configuration for Cutting Plane Separators via Reinforcement Learning on Incremental Graph

Efficient Algorithms for Robust and Partial Semi-Discrete Optimal Transport

PipeFusion: Patch-level Pipeline Parallelism for Diffusion Transformers Inference

Revisiting 1-peer exponential graph for enhancing decentralized learning efficiency

FedRTS: Federated Robust Pruning via Combinatorial Thompson Sampling

Error Feedback under $(L_0,L_1)$-Smoothness: Normalization and Momentum

DUO: No Compromise to Accuracy Degradation

Efficient Pre-Training of LLMs via Topology-Aware Communication Alignment on More Than 9600 GPUs

Preference Optimization on Pareto Sets: On a Theory of Multi-Objective Optimization

Distributionally Robust Performative Optimization

Smart Surrogate Losses for Contextual Stochastic Linear Optimization with Robust Constraints

FSNet: Feasibility-Seeking Neural Network for Constrained Optimization with Guarantees

Prior Forgetting and In-Context Overfitting

Gradient Multi-Normalization for Efficient LLM Training

ASGO: Adaptive Structured Gradient Optimization

On the $O(\frac{\sqrt{d}}{K^{1/4}})$ Convergence Rate of AdamW Measured by $\ell_1$ Norm

Energy Landscape-Aware Vision Transformers: Layerwise Dynamics and Adaptive Task-Specific Training via Hopfield States

Exploring Landscapes for Better Minima along Valleys

Pay Attention to Small Weights

Understanding Adam Requires Better Rotation Dependent Assumptions

ACCO: Accumulate While You Communicate for Communication-Overlapped Sharded LLM Training

A Stable Whitening Optimizer for Efficient Neural Network Training

FSEO: Few-Shot Evolutionary Optimization via Meta-Learning for Expensive Multi-Objective Optimization

PRESTO: Preimage-Informed Instruction Optimization for Prompting Black-Box LLMs

Why Popular MOEAs are Popular: Proven Advantages in Approximating the Pareto Front

BO4Mob: Bayesian Optimization Benchmarks for High-Dimensional Urban Mobility Problem

Preference-Guided Diffusion for Multi-Objective Offline Optimization

Near-Optimal Regret-Queue Length Tradeoff in Online Learning for Two-Sided Markets

(ends 7:30 PM)

7 p.m.

Reception:

Muslims in ML Reception

(ends 9:00 PM)

THU 4 DEC

7:30 a.m.

Registration Desk

(ends 6:00 PM)

8 a.m.

Break:

Coffee Break

(ends 8:30 AM)

8:30 a.m.

San Diego Invited Talk:

The Art of (Artificial) Reasoning

Yejin Choi

(ends 9:30 AM)

9 a.m.

Exhibit Sponsor Hall:

Exhibit Sponsor Hall

(ends 5:00 PM)

Affinity Workshop:

Queer in AI

(ends 5:00 PM)

9:30 a.m.

Exhibitor Spot Talks - Session 3 [9:30-4:45]

Talks 9:30-4:42

Optimizing AI Efficiency from Silicon to Model

EMM-1: Expanding embedding space to be multimodal and multilingual

Exhibitor Talk - NEC

Towards reference models for Engineering Abstract

How GM builds Practical AI for the Physical World

Modular Agents and Orchestrated Coordination using Open Agentic Protocols: Foundations for the Next Wave of Agentic AI

Reasoning in Motion: How Agents Learn to Think

Takes two to Tangle: showcasing an experimentation platform with the focus on collaboration and ease of editing

LFM2: Capable and efficient on-device multimodal foundation models.

tsuzumi: Advanced and Sovereign Japanese LLM

Ling 2.0 and Ling-1T: Scaling Knowledge-Enhanced Large Language Models for Reasoning and Efficiency

Exhibitor Talk - Thomson Reuters

ATOM: RBC’s proprietary AI Foundation Model for Financial Services

Exhibitor Talk - Intuit

Exhibitor Talk - Datadog

Exhibitor Talk - Boson.AI Talk to me - engineering conversational intelligence

Unify Vector and Relational Search for Smarter, Faster Applications

Semantic latent variables inference for improved generative modeling

Empowering Financial Services with Trustworthy Frontier AI at Wells Fargo

Exhibitor Talk - Lightning AI

Scaling Agentic AI with Compute Orchestration and Local Runners

Building an Open Agentic Future

How to make your AI models faster, smaller, cheaper, greener?

(ends 4:45 PM)

Break:

Coffee Break

(ends 10:00 AM)

10 a.m.

Oral 3A Reinforcement/State-space 2 [10:00-11:00]

Orals 10:00-11:00

[10:00] State Entropy Regularization for Robust Reinforcement Learning

[10:20] A Clean Slate for Offline Reinforcement Learning

[10:40] Breaking the Performance Ceiling in Reinforcement Learning requires Inference Strategies

(ends 11:00 AM)

Oral 3B Deep Learning 2 [10:00-11:00]

Orals 10:00-11:00

[10:00] Auto-Compressing Networks

[10:20] Dynamical Low-Rank Compression of Neural Networks with Robustness under Adversarial Attacks

[10:40] ImageNet-trained CNNs are not biased towards texture: Revisiting feature reliance through controlled suppression

(ends 11:00 AM)

Oral 3C Position Paper Orals [10:00-11:00]

Orals 10:00-11:00

[10:00] Position: If Innovation in AI systematically Violates Fundamental Rights, Is It Innovation at All?

[10:20] More effort is needed to protect pedestrian privacy in the era of AI

[10:40] Real-Time Hyper-Personalized Generative AI Should Be Regulated to Prevent the Rise of "Digital Heroin"

(ends 11:00 AM)

Oral 3D Application 2 [10:00-11:00]

Orals 10:00-11:00

[10:00] ControlFusion: A Controllable Image Fusion Network with Language-Vision Degradation Prompts

[10:20] Pan-LUT: Efficient Pan-sharpening via Learnable Look-Up Tables

[10:40] FuXi-Ocean: A Global Ocean Forecasting System with Sub-Daily Resolution

(ends 11:00 AM)

Oral 3E Theory 3 [10:00-11:00]

Orals 10:00-11:00

[10:00] Identifiability of Deep Polynomial Neural Networks

[10:20] Depth-Bounds for Neural Networks via the Braid Arrangement

[10:40] Learning Linear Attention in Polynomial Time

(ends 11:00 AM)

11 a.m.

Creative AI Panel:

Emergent Stories: AI Agents and New Narratives

(ends 12:00 PM)

Creative AI Session 3 [11:00-2:00]

s 11:00-2:00

[11:00] 8bit-GPT: Exploring Human-AI Interaction on Obsolete Macintosh Operating Systems

[11:00] A(I)nimism: Re-enchanting the World Through AI-Mediated Object Interaction

[11:00] Artism: AI-Driven Dual-Engine System for Art Generation and Critique

[11:00] ArtPeer: Artistic Alignment via Reflection-based Prompt Evolution with Simulated Artist

[11:00] AugTwins

[11:00] CraftGraffiti: Exploring Human Identity with Custom Graffiti Art via Facial-Preserving Diffusion Models

[11:00] Encoding Values: Injecting Morality into Machines via Prompt-Conditioned Moral Frames

[11:00] Experiencing of Sensorium Arc: AI Agent System for Oceanic Data Exploration and Interactive Eco-Art

[11:00] Exploring Human-AI Conceptual Alignment through the Prism of Chess

[11:00] Gaze to the Stars: AI and Public Art from Personal Affect and Collective Empathy

[11:00] Gaze to the Stars: AI, Storytelling and Public Art

[11:00] Human-AI Co-Development of a Geometric Algorithm for Infinite Shuriken Artwork Design Generation

[11:00] Large Language Label

[11:00] Live Music Models

[11:00] MambaKit: Towards Modular Intelligence - Cognitive Scaffolding in Next-Generation Drum Synthesis

[11:00] Neural Palate Kueh

[11:00] Pareiduo: A Human–LLM Dialogue in Sand

[11:00] Possible You: AI-Generated Digital Twins as Creative Mirrors for Future Self Modeling

[11:00] princi/pal: A Moral Dilemma Tamagotchi Game

[11:00] ReTracing: An Archaeological Approach Through Body, Machine, and Generative Systems

[11:00] Semantic Glitch: Agency and Artistry in an Autonomous Pixel Cloud

[11:00] Sensorium Arc: AI Agent System for Oceanic Data Exploration and Interactive Eco-Art

[11:00] Supporting Creative Ownership through Deep Learning-Based Music Variation

[11:00] Text to Robotic Assembly of Multi Component Objects using 3D Generative AI and Vision Language Models

(ends 2:00 PM)

San Diego Poster Session 3 [11:00-2:00]

Posters 11:00-2:00

Channel Matters: Estimating Channel Influence for Multivariate Time Series

A Regularized Newton Method for Nonconvex Optimization with Global and Local Complexity Guarantees

Per-Architecture Training-Free Metric Optimization for Neural Architecture Search

SDPGO: Efficient Self-Distillation Training Meets Proximal Gradient Optimization

Learning Memory-Enhanced Improvement Heuristics for Flexible Job Shop Scheduling

PseuZO: Pseudo-Zeroth-Order Algorithm for Training Deep Neural Networks

ReplaceMe: Network Simplification via Depth Pruning and Transformer Block Linearization

MeCeFO: Enhancing LLM Training Robustness via Fault-Tolerant Optimization

Real-Time Hyper-Personalized Generative AI Should Be Regulated to Prevent the Rise of "Digital Heroin"

Rigor in AI: Doing Rigorous AI Work Requires a Broader, Responsible AI-Informed Conception of Rigor

World Models Should Prioritize the Unification of Physical and Social Dynamics

KAIROS: Scalable Model-Agnostic Data Valuation

Knowledge Distillation Detection for Open-weights Models

Incentivizing Desirable Effort Profiles in Strategic Classification: The Role of Causality and Uncertainty

The Future Unmarked: Watermark Removal in AI-Generated Images via Next-Frame Prediction

A Statistical Framework of Watermarks for Large Language Models: Pivot, Detection Efficiency and Optimal Rules

We Should Chart an Atlas of All the World's Models

Military AI Needs Technically-Informed Regulation to Safeguard AI Research and its Applications

BenchmarkCards: Standardized Documentation for Large Language Model Benchmarks

Quality-Driven Curation of Remote Sensing Vision-Language Data via Learned Scoring Models

Analyzing Similarity Metrics for Data Selection for Language Model Pretraining

EnzyControl: Adding Functional and Substrate-Specific Control for Enzyme Backbone Generation

Graph Data Selection for Domain Adaptation: A Model-Free Approach

SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents

Measuring what Matters: Construct Validity in Large Language Model Benchmarks

Measuring Fingerprints of Web-filtered Text Datasets and Fingerprint Propagation Through Training

AGI-Elo: How Far Are We From Mastering A Task?

Why Do Multi-Agent LLM Systems Fail?

Dense SAE Latents Are Features, Not Bugs

EAP-GP: Mitigating Saturation Effect in Gradient-based Automated Circuit Identification

Collective Counterfactual Explanations: Balancing Individual Goals and Collective Dynamics

CHiQPM: Calibrated Hierarchical Interpretable Image Classification

Layer-Wise Modality Decomposition for Interpretable Multimodal Sensor Fusion

Angular Steering: Behavior Control via Rotation in Activation Space

Transferring Linear Features Across Language Models With Model Stitching

A Unified Framework for Provably Efficient Algorithms to Estimate Shapley Values

Contimask: Explaining Irregular Time Series via Perturbations in Continuous Time

ElliCE: Efficient and Provably Robust Algorithmic Recourse via the Rashomon Sets

DATE-LM: Benchmarking Data Attribution Evaluation for Large Language Models

FLAME: Fast Long-context Adaptive Memory for Event-based Vision

Same Task, Different Circuits: Disentangling Modality-Specific Mechanisms in VLMs

Detecting High-Stakes Interactions with Activation Probes

Robust Explanations of Graph Neural Networks via Graph Curvatures

IPAD: Inverse Prompt for AI Detection - A Robust and Interpretable LLM-Generated Text Detector

Additive Models Explained: A Computational Complexity Approach

Clean First, Align Later: Benchmarking Preference Data Cleaning for Reliable LLM Alignment

QUT-DV25: A Dataset for Dynamic Analysis of Next-Gen Software Supply Chain Attacks

Enabling Differentially Private Federated Learning for Speech Recognition: Benchmarks, Adaptive Optimizers, and Gradient Clipping

Puzzles: Unbounded Video-Depth Augmentation for Scalable End-to-End 3D Reconstruction

MASTER: Enhancing Large Language Model via Multi-Agent Simulated Teaching

FACE: Faithful Automatic Concept Extraction

Uncovering a Universal Abstract Algorithm for Modular Addition in Neural Networks

Collective Bargaining in the Information Economy Can Address AI-Driven Power Concentration

SafeVid: Toward Safety Aligned Video Large Multimodal Models

Video-SafetyBench: A Benchmark for Safety Evaluation of Video LVLMs

Path-specific effects for pulse-oximetry guided decisions in critical care

On Fairness of Unified Multimodal Large Language Model for Image Generation

Grounding Language with Vision: A Conditional Mutual Information Calibrated Decoding Strategy for Reducing Hallucinations in LVLMs

CTRL-ALT-DECEIT Sabotage Evaluations for Automated AI R&D

EVOREFUSE: Evolutionary Prompt Optimization for Evaluation and Mitigation of LLM Over-Refusal to Pseudo-Malicious Instructions

Fairness-aware Anomaly Detection via Fair Projection

Truth over Tricks: Measuring and Mitigating Shortcut Learning in Misinformation Detection

Unifying Proportional Fairness in Centroid and Non-Centroid Clustering

Who Speaks for the Trigger? Dynamic Expert Routing in Backdoored Mixture-of-Experts Transformers

DataSIR: A Benchmark Dataset for Sensitive Information Recognition

FracFace: Breaking The Visual Clues—Fractal-Based Privacy-Preserving Face Recognition

Non-exchangeable Conformal Prediction with Optimal Transport: Tackling Distribution Shift with Unlabeled Data

KScope: A Framework for Characterizing the Knowledge Status of Language Models

Theoretically Grounded Framework for LLM Watermarking: A Distribution-Adaptive Approach

Advancing Machine-Generated Text Detection from an Easy to Hard Supervision Perspective

DualOptim: Enhancing Efficacy and Stability in Machine Unlearning with Dual Optimizers

SteerConf: Steering LLMs for Confidence Elicitation

GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMs

Jailbreak-AudioBench: In-Depth Evaluation and Analysis of Jailbreak Threats for Large Audio Language Models

Position: If Innovation in AI systematically Violates Fundamental Rights, Is It Innovation at All?

Differentially Private Quantiles with Smaller Error

Efficient Verified Unlearning For Distillation

Quantifying Cross-Modality Memorization in Vision-Language Models

Private Statistical Estimation via Truncation

Controlling The Spread of Epidemics on Networks with Differential Privacy

Multi-Class Support Vector Machine with Differential Privacy

Your Pre-trained LLM is Secretly an Unsupervised Confidence Calibrator

Wisdom is Knowing What not to Say: Hallucination-Free LLMs Unlearning via Attention Shifting

Keeping an Eye on LLM Unlearning: The Hidden Risk and Remedy

MixAT: Combining Continuous and Discrete Adversarial Training for LLMs

BAM-ICL: Causal Hijacking In-Context Learning with Budgeted Adversarial Manipulation

FedGPS: Statistical Rectification Against Data Heterogeneity in Federated Learning

DiffEye: Diffusion-Based Continuous Eye-Tracking Data Generation Conditioned on Natural Images

Fortifying Time Series: DTW-Certified Robust Anomaly Detection

Unveiling Environmental Sensitivity of Individual Gains in Influence Maximization

Let a Neural Network be Your Invariant

HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representation

The Mirage of Performance Gains: Why Contrastive Decoding Fails to Mitigate Object Hallucinations in MLLMs?

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

Look-Ahead Reasoning on Learning Platforms

Unveiling the Uncertainty in Embodied and Operational Carbon of Large AI Models through a Probabilistic Carbon Accounting Model

Praxis-VLM: Vision-Grounded Decision Making via Text-Driven Reinforcement Learning

Role-aware Multi-agent Reinforcement Learning for Coordinated Emergency Traffic Control

A Unified Reasoning Framework for Holistic Zero-Shot Video Anomaly Analysis

CoIDO: Efficient Data Selection for Visual Instruction Tuning via Coupled Importance-Diversity Optimization

MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinement

Protein Design with Dynamic Protein Vocabulary

Ultra-high Resolution Watermarking Framework Resistant to Extreme Cropping and Scaling

MiCADangelo: Fine-Grained Reconstruction of Constrained CAD Models from 3D Scans

Tail-Optimized Caching for LLM Inference

OpenCUA: Open Foundations for Computer-Use Agents

TranSUN: A Preemptive Paradigm to Eradicate Retransformation Bias Intrinsically from Regression Models in Recommender Systems

CURV: Coherent Uncertainty-Aware Reasoning in Vision-Language Models for X-Ray Report Generation

RealMath: A Continuous Benchmark for Evaluating Language Models on Research-Level Mathematics

Evaluating Program Semantics Reasoning with Type Inference in System $F$

Crucible: Quantifying the Potential of Control Algorithms through LLM Agents

FailureSensorIQ: A Multi-Choice QA Dataset for Understanding Sensor Relationships and Failure Modes

Position: Biology is the Challenge Physics-Informed ML Needs to Evolve

When Models Know More Than They Can Explain: Quantifying Knowledge Transfer in Human-AI Collaboration

FuXi-Ocean: A Global Ocean Forecasting System with Sub-Daily Resolution

Mixing Expert Knowledge: Bring Human Thoughts Back To the Game of Go

QiMeng-MuPa: Mutual-Supervised Learning for Sequential-to-Parallel Code Translation

From Pose to Muscle: Multimodal Learning for Piano Hand Muscle Electromyography

PreFM: Online Audio-Visual Event Parsing via Predictive Future Modeling

REDOUBT: Duo Safety Validation for Autonomous Vehicle Motion Planning

3D Human Pose Estimation with Muscles

Which Algorithms Have Tight Generalization Bounds?

A Standardized Benchmark for Multilabel Antimicrobial Peptide Classification

Rationalized All-Atom Protein Design with Unified Multi-Modal Bayesian Flow

DMol: A Highly Efficient and Chemical Motif-Preserving Molecule Generation Platform

LLM Meets Diffusion: A Hybrid Framework for Crystal Material Generation

Reaction Prediction via Interaction Modeling of Symmetric Difference Shingle Sets

Unified all-atom molecule generation with neural fields

Amortized Sampling with Transferable Normalizing Flows

HollowFlow: Efficient Sample Likelihood Evaluation using Hollow Message Passing

MS-BART: Unified Modeling of Mass Spectra and Molecules for Structure Elucidation

CodeAssistBench (CAB): Dataset & Benchmarking for Multi-turn Chat-Based Code Assistance

AlphaFold Database Debiasing for Robust Inverse Folding

Unsupervised Trajectory Optimization for 3D Registration in Serial Section Electron Microscopy using Neural ODEs

CGBench: Benchmarking Language Model Scientific Reasoning for Clinical Genetics Research

Augmenting Biological Fitness Prediction Benchmarks with Landscapes Features from GraphFLA

PIPE: Physics-Informed Position Encoding for Alignment of Satellite Images and Time Series in Typhoon Forecasting

Causal Climate Emulation with Bayesian Filtering

NUTS: Eddy-Robust Reconstruction of Surface Ocean Nutrients via Two-Scale Modeling

OmniCast: A Masked Latent Diffusion Model for Weather Forecasting Across Time Scales

Scalable and Cost-Efficient de Novo Template-Based Molecular Generation

Sampling 3D Molecular Conformers with Diffusion Transformers

Flash Invariant Point Attention

Flexible MOF Generation with Torsion-Aware Flow Matching

RiboFlow: Conditional De Novo RNA Co-Design via Synergistic Flow Matching

Controllable 3D Molecular Generation for Structure-Based Drug Design Through Bayesian Flow Networks and Gradient Integration

Ambient Proteins - Training Diffusion Models on Noisy Structures

E2Former: An Efficient and Equivariant Transformer with Linear-Scaling Tensor Products

SAINT: Sequence-Aware Integration for Spatial Transcriptomics Multi-View Clustering

Variational Regularized Unbalanced Optimal Transport: Single Network, Least Action

Ctrl-DNA: Controllable Cell-Type-Specific Regulatory DNA Design via Constrained RL

HiPoNet: A Multi-View Simplicial Complex Network for High Dimensional Point-Cloud and Single-Cell data

Securing the Language of Life: Inheritable Watermarks from DNA Language Models to Proteins

Learning Crossmodal Interaction Patterns via Attributed Bipartite Graphs for Single-Cell Omics

ChromFound: Towards A Universal Foundation Model for Single-Cell Chromatin Accessibiltiy Data

GeneFlow: Translation of Single-cell Gene Expression to Histopathological Images via Rectified Flow

RAM-W600: A Multi-Task Wrist Dataset and Benchmark for Rheumatoid Arthritis

Democratizing Clinical Risk Prediction with Cross-Cohort Cross-Modal Knowledge Transfer

Doctor Approved: Generating Medically Accurate Skin Disease Images through AI-Expert Feedback

RAD: Towards Trustworthy Retrieval-Augmented Multi-modal Clinical Diagnosis

Dual-Res Tandem Mamba-3D: Bilateral Breast Lesion Detection and Classification on Non-contrast Chest CT

Timely Clinical Diagnosis through Active Test Selection

Towards Generalizable Retina Vessel Segmentation with Deformable Graph Priors

EuroSpeech: A Multilingual Speech Corpus

ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning

MoonCast: High-Quality Zero-Shot Podcast Generation

ReliabilityRAG: Effective and Provably Robust Defense for RAG-based Web-Search

Exploiting LLMs for Automatic Hypothesis Assessment via a Logit-Based Calibrated Prior

CAM: A Constructivist View of Agentic Memory for LLM-Based Reading Comprehension

WebThinker: Empowering Large Reasoning Models with Deep Research Capability

Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

Scent of Knowledge: Optimizing Search-Enhanced Reasoning with Information Foraging

Automated Composition of Agents: A Knapsack Approach for Agentic Component Selection

Explaining and Mitigating Crosslingual Tokenizer Inequities

MLRC-Bench: Can Language Agents Solve Machine Learning Research Challenges?

A Controllable Examination for Long-Context Language Models

Toward Engineering AGI: Benchmarking the Engineering Design Capabilities of LLMs

SeniorTalk: A Chinese Conversation Dataset with Rich Annotations for Super-Aged Seniors

AVerImaTeC: A Dataset for Automatic Verification of Image-Text Claims with Evidence from the Web

Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge

CoreaSpeech: Korean Speech Corpus via JAMO-based Coreset Selection for Efficient and Robust Korean Speech Generation

Scaling Code-Assisted Chain-of-Thoughts and Instructions for Model Reasoning

ARECHO: Autoregressive Evaluation via Chain-Based Hypothesis Optimization for Speech Multi-Metric Estimation

Metis: A Foundation Speech Generation Model with Masked Generative Pre-training

Codifying Character Logic in Role-Playing

Distilling LLM Agent into Small Models with Retrieval and Code Tools

Retrieval is Not Enough: Enhancing RAG through Test-Time Critique and Optimization

Causal LLM Routing: End-to-End Regret Minimization from Observational Data

Hyper-Modality Enhancement for Multimodal Sentiment Analysis with Missing Modalities

Enhancing Personalized Multi-Turn Dialogue with Curiosity Reward

Mellow: a small audio language model for reasoning

Feedback-Aware MCTS for Goal-Oriented Information Seeking

Hyperbolic Dataset Distillation

Learning “Partner-Aware” Collaborators in Multi-Party Collaboration

Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems

CleverBirds: A Multiple-Choice Benchmark for Fine-grained Human Knowledge Tracing

EyeBench: Predictive Modeling from Eye Movements in Reading

MUniverse: A Simulation and Benchmarking Suite for Motor Unit Decomposition

Group-in-Group Policy Optimization for LLM Agent Training

OPHR: Mastering Volatility Trading with Multi-Agent Deep Reinforcement Learning

Influence Guided Context Selection for Effective Retrieval-Augmented Generation

A Sustainable AI Economy Needs Data Deals That Work for Generators

Position: AI Should Sense Better, Not Just Scale Bigger: Adaptive Sensing as a Paradigm Shift

OctoNet: A Large-Scale Multi-Modal Dataset for Human Activity Understanding Grounded in Motion-Captured 3D Pose Labels

Structural Entropy Guided Agent for Detecting and Repairing Knowledge Deficiencies in LLMs

A Clean Slate for Offline Reinforcement Learning

Adaptable Safe Policy Learning from Multi-task Data with Constraint Prioritized Decision Transformer

Flattening Hierarchies with Policy Bootstrapping

Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimization

Modeling Dynamic Neural Activity by combining Naturalistic Video Stimuli and Stimulus-independent Latent Factors

Efficient Training of Minimal and Maximal Low-Rank Recurrent Neural Networks

Seemingly Redundant Modules Enhance Robust Odor Learning in Fruit Flies

BrainOmni: A Brain Foundation Model for Unified EEG and MEG Signals

Quantifying Task-relevant Similarities in Representations Using Decision Variable Correlations

Flexible inference for animal learning rules using neural networks

Spike-timing-dependent Hebbian learning as noisy gradient descent

Neurons as Detectors of Coherent Sets in Sensory Dynamics

Brain-Inspired fMRI-to-Text Decoding via Incremental and Wrap-Up Language Modeling

Toward Relative Positional Encoding in Spiking Transformers

FANS: A Flatness-Aware Network Structure for Generalization in Offline Reinforcement Learning

AI-Generated Video Detection via Perceptual Straightening

Characterizing control between interacting subsystems with deep Jacobian estimation

Identifying interactions across brain areas while accounting for individual-neuron dynamics with a Transformer-based variational autoencoder

Anatomically inspired digital twins capture hierarchical object representations in visual cortex

Self supervised learning for in vivo localization of microelectrode arrays using raw local field potential

Does Object Binding Naturally Emerge in Large Pretrained Vision Transformers?

Dynamics-Aligned Latent Imagination in Contextual World Models for Zero-Shot Generalization

Leveraging Conditional Dependence for Efficient World Model Denoising

Text-to-Decision Agent: Offline Meta-Reinforcement Learning from Natural Language Supervision

Optimal Dynamic Regret by Transformers for Non-Stationary Reinforcement Learning

Physics-informed Value Learner for Offline Goal-Conditioned Reinforcement Learning

BrainFlow: A Holistic Pathway of Dynamic Neural System on Manifold

Dimensionality Mismatch Between Brains and Artificial Neural Networks

TractoTransformer: Diffusion MRI Streamline Tractography using CNN and Transformer Networks

BioOSS: A Bio-Inspired Oscillatory State System with Spatio-Temporal Dynamics

Predicting Functional Brain Connectivity with Context-Aware Deep Neural Networks

$\mu$PC: Scaling Predictive Coding to 100+ Layer Networks

Contrastive Consolidation of Top-Down Modulations Achieves Sparsely Supervised Continual Learning

Are Large Language Models Sensitive to the Motives Behind Communication?

Far from the Shallow: Brain-Predictive Reasoning Embedding through Residual Disentanglement

Modeling Neural Activity with Conditionally Linear Dynamical Systems

FAIR Universe HiggsML Uncertainty Dataset and Competition

ConStellaration: A dataset of QI-like stellarator plasma boundaries and optimization benchmarks

GlobalTomo: A global dataset for physics-ML seismic wavefield modeling and FWI

STAR: A Benchmark for Astronomical Star Fields Super-Resolution

UniFoil: A Universal Dataset of Airfoils in Transitional and Turbulent Regimes for Subsonic and Transonic Flows

A Physics-preserved Transfer Learning Method for Differential Equations

C-NAV: Towards Self-Evolving Continual Object Navigation in Open World

Real-World Reinforcement Learning of Active Perception Behaviors

Dynamic Focused Masking for Autoregressive Embodied Occupancy Prediction

Taccel: Scaling Up Vision-based Tactile Robotics via High-performance GPU Simulation

MutualVPR: A Mutual Learning Framework for Resolving Supervision Inconsistencies via Adaptive Clustering

CogVLA: Cognition-Aligned Vision-Language-Action Models via Instruction-Driven Routing & Sparsification

Towards Reliable LLM-based Robots Planning via Combined Uncertainty Estimation

Fast-in-Slow: A Dual-System VLA Model Unifying Fast Manipulation within Slow Reasoning

Provable Ordering and Continuity in Vision-Language Pretraining for Generalizable Embodied Agents

DEAL: Diffusion Evolution Adversarial Learning for Sim-to-Real Transfer

Gradient Alignment in Physics-informed Neural Networks: A Second-Order Optimization Perspective

SpiderSolver: A Geometry-Aware Transformer for Solving PDEs on Complex Geometries

GyroSwin: 5D Surrogates for Gyrokinetic Plasma Turbulence Simulations

SymMaP: Improving Computational Efficiency in Linear Solvers through Symbolic Preconditioning

Learning non-equilibrium diffusions with Schrödinger bridges: from exactly solvable to simulation-free

Local-Global Associative Frames for Symmetry-Preserving Crystal Structure Modeling

Hybrid Boundary Physics-Informed Neural Networks for Solving Navier-Stokes Equations with Complex Boundary

Hybrid Latent Representations for PDE Emulation

Touch in the Wild: Learning Fine-Grained Manipulation with a Portable Visuo-Tactile Gripper

SAFE: Multitask Failure Detection for Vision-Language-Action Models

PointMapPolicy: Structured Point Cloud Processing for Multi-Modal Imitation Learning

$\textit{Hyper-GoalNet}$: Goal-Conditioned Manipulation Policy Learning with HyperNetworks

Reinventing Multi-Agent Collaboration through Gaussian-Image Synergy in Diffusion Policies

Human-assisted Robotic Policy Refinement via Action Preference Optimization

A Practical Guide for Incorporating Symmetry in Diffusion Policy

A Smooth Sea Never Made a Skilled SAILOR: Robust Imitation via Learning to Search

DanmakuTPPBench: A Multi-modal Benchmark for Temporal Point Process Modeling and Understanding

MAESTRO : Adaptive Sparse Attention and Robust Learning for Multimodal Dynamic Time Series

Delving into Large Language Models for Effective Time-Series Anomaly Detection

Eulerian Neural Network Informed by Chemical Transport for Air Quality Forecasting

AliO: Output Alignment Matters in Long-Term Time Series Forecasting

ShapeX: Shapelet-Driven Post Hoc Explanations for Time Series Classification Models

Improving Time Series Forecasting via Instance-aware Post-hoc Revision

FlowMixer: A Depth-Agnostic Neural Architecture for Interpretable Spatiotemporal Forecasting

Topology-Aware Conformal Prediction for Stream Networks

Let's Revise Step-by-Step: A Unified Local Search Framework for Code Generation with LLMs

CausalVerse: Benchmarking Causal Representation Learning with Configurable High-Fidelity Simulations

AutoData: A Multi-Agent System for Open Web Data Collection

Photography Perspective Composition: Towards Aesthetic Perspective Recommendation

Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay

Mitigating Instability in High Residual Adaptive Sampling for PINNs via Langevin Dynamics

MIHC: Multi-View Interpretable Hypergraph Neural Networks with Information Bottleneck for Chip Congestion Prediction

SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Tasks

How to Auto-optimize Prompts for Domain Tasks? Adaptive Prompting and Reasoning through Evolutionary Domain Knowledge Adaptation

MathArena: Evaluating LLMs on Uncontaminated Math Competitions

AgentRecBench: Benchmarking LLM Agent-based Personalized Recommender Systems

Satellites Reveal Mobility: A Commuting Origin-destination Flow Generator for Global Cities

SGN: Shifted Window-Based Hierarchical Variable Grouping for Multivariate Time Series Classification

Investigating Hallucinations of Time Series Foundation Models through Signal Subspace Analysis

On the Integration of Spatial-Temporal Knowledge: A Lightweight Approach to Atmospheric Time Series Forecasting

Glocal Information Bottleneck for Time Series Imputation

Selective Learning for Deep Time Series Forecasting

Learning to Factorize Spatio-Temporal Foundation Models

PMLF: A Physics-Guided Multiscale Loss Framework for Structurally Heterogeneous Time Series

Learning Counterfactual Outcomes Under Rank Preservation

A Cautionary Tale on Integrating Studies with Disparate Outcome Measures for Causal Inference

An Analysis of Causal Effect Estimation using Outcome Invariant Data Augmentation

Non-Stationary Structural Causal Bandits

Estimation of Treatment Effects in Extreme and Unobserved Data

Universal Causal Inference in a Topos

Score-informed Neural Operator for Enhancing Ordering-based Causal Discovery

Meta-D2AG: Causal Graph Learning with Interventional Dynamic Data

Disentangling misreporting from genuine adaptation in strategic settings: a causal approach

Counterfactual Image Editing with Disentangled Causal Latent Space

DGCBench: A Deep Graph Clustering Benchmark

Theory-Driven Label-Specific Representation for Incomplete Multi-View Multi-Label Learning

A TRIANGLE Enables Multimodal Alignment Beyond Cosine Similarity

Connecting Neural Models Latent Geometries with Relative Geodesic Representations

Bit-swapping Oriented Twin-memory Multi-view Clustering in Lifelong Incomplete Scenarios

DUAL: Learning Diverse Kernels for Aggregated Two-sample and Independence Testing

Harnessing Feature Resonance under Arbitrary Target Alignment for Out-of-Distribution Node Detection

Hypergraph-Enhanced Contrastive Learning for Multi-View Clustering with Hyper-Laplacian Regularization

IA-GGAD: Zero-shot Generalist Graph Anomaly Detection via Invariant and Affinity Learning

Heterogeneous Adversarial Play in Interactive Environments

Are Greedy Task Orderings Better Than Random in Continual Linear Regression?

Covariances for Free: Exploiting Mean Distributions for Training-free Federated Learning

A compressive-expressive communication framework for compositional representations

Minimal Semantic Sufficiency Meets Unsupervised Domain Generalization

Thought Communication in Multiagent Collaboration

Exploring Structural Degradation in Dense Representations for Self-supervised Learning

Understanding Contrastive Learning via Gaussian Mixture Models

CyIN: Cyclic Informative Latent Space for Bridging Complete and Incomplete Multimodal Learning

Auto-Compressing Networks

Place Cells as Multi-Scale Position Embeddings: Random Walk Transition Kernels for Path Planning

Equivariant Eikonal Neural Networks: Grid-Free, Scalable Travel-Time Prediction on Homogeneous Spaces

The Structure of Relation Decoding Linear Operators in Large Language Models

Soft Task-Aware Routing of Experts for Equivariant Representation Learning

Random Forest Autoencoders for Guided Representation Learning

Exploiting Task Relationships in Continual Learning via Transferability-Aware Task Embeddings

Diffusion-Driven Progressive Target Manipulation for Source-Free Domain Adaptation

Transfer Learning for Benign Overfitting in High-Dimensional Linear Regression

Towards Large-Scale In-Context Reinforcement Learning by Meta-Training in Randomized Worlds

Mixed-Sample SGD: an End-to-end Analysis of Supervised Transfer Learning

A High-Dimensional Statistical Method for Optimizing Transfer Quantities in Multi-Source Transfer Learning

MoORE: SVD-based Model MoE-ization for Conflict- and Oblivion-Resistant Multi-Task Adaptation

Self-Training with Dynamic Weighting for Robust Gradual Domain Adaptation

SMRS: advocating a unified reporting standard for surrogate models in the artificial intelligence era.

TabArena: A Living Benchmark for Machine Learning on Tabular Data

Martingale Score: An Unsupervised Metric for Bayesian Rationality in LLM Reasoning

WALL-E: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents

Improving Decision Trees through the Lens of Parameterized Local Search

Semi-supervised Vertex Hunting, with Applications in Network and Text Analysis

Provable Scaling Laws for the Test-Time Compute of Large Language Models

Two‑Stage Learning of Stabilizing Neural Controllers via Zubov Sampling and Iterative Domain Expansion

Matching Markets Meet LLMs: Algorithmic Reasoning with Ranked Preferences

GUARD: Constructing Realistic Two-Player Matrix and Security Games for Benchmarking Game-Theoretic Algorithms

Parameter Dynamics of Online Machine Learning and Test-time Adaptation

SPACE: SPike-Aware Consistency Enhancement for Test-Time Adaptation in Spiking Neural Networks

Vicinity-Guided Discriminative Latent Diffusion for Privacy-Preserving Domain Adaptation

Controlled Visual Hallucination via Thalamus-Driven Decoupling Network for Domain Adaptation of Black-Box Predictors

Vertical Federated Feature Screening

CTSketch: Compositional Tensor Sketching for Scalable Neurosymbolic Learning

Exploiting Dynamic Sparsity in Einsum

SHGR: A Generalized Maximal Correlation Coefficient

Improving Monte Carlo Tree Search for Symbolic Regression

A$^3$E: Towards Compositional Model Editing

Conformal Online Learning of Deep Koopman Linear Embeddings

Gradient-Guided Epsilon Constraint Method for Online Continual Learning

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models

Fourier Clouds: Fast Bias Correction for Imbalanced Semi-Supervised Learning

You Can Trust Your Clustering Model: A Parameter-free Self-Boosting Plug-in for Deep Clustering

Thinker: Learning to Think Fast and Slow

A Cramér–von Mises Approach to Incentivizing Truthful Data Sharing

Certifying Concavity and Monotonicity in Games via Sum-of-Squares Hierarchies

Clustering via Hedonic Games: New Concepts and Algorithms

Learning from Delayed Feedback in Games via Extra Prediction

Beyond Last-Click: An Optimal Mechanism for Ad Attribution

Online Strategic Classification With Noise and Partial Feedback

Multidimensional Bayesian Utility Maximization: Tight Approximations to Welfare

Strategic Classification with Non-Linear Classifiers

Metritocracy: Representative Metrics for Lite Benchmarks

Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks

Memory-Enhanced Neural Solvers for Routing Problems

Reconstruction and Secrecy under Approximate Distance Queries

A solvable model of learning generative diffusion: theory and insights

On Agnostic PAC Learning in the Small Error Regime

Selective Omniprediction and Fair Abstention

Statistical Guarantees for High-Dimensional Stochastic Gradient Descent

Principled Long-Tailed Generative Modeling via Diffusion Models

On the sample complexity of semi-supervised multi-objective learning

Understanding Data Influence in Reinforcement Finetuning

Uni-RL: Unifying Online and Offline RL via Implicit Value Regularization

Horizon Reduction Makes RL Scalable

Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning

Adaptive Divergence Regularized Policy Optimization for Fine-tuning Generative Models

Multi-Objective Reinforcement Learning with Max-Min Criterion: A Game-Theoretic Approach

Coarse-to-fine Q-Network with Action Sequence for Data-Efficient Reinforcement Learning

LLM-Explorer: A Plug-in Reinforcement Learning Policy Exploration Enhancement Driven by Large Language Models

Improving Regret Approximation for Unsupervised Dynamic Environment Generation

Continuous Q-Score Matching: Diffusion Guided Reinforcement Learning for Continuous-Time Control

Minimax Adaptive Online Nonparametric Regression over Besov spaces

Tractable Multinomial Logit Contextual Bandits with Non-Linear Utilities

Non-Uniform Multiclass Learning with Bandit Feedback

Generalizing while preserving monotonicity in comparison-based preference learning models

Self-Boost via Optimal Retraining: An Analysis via Approximate Message Passing

Robust Minimax Boosting with Performance Guarantees

Improved Robust Estimation for Erdős-Rényi Graphs: The Sparse Regime and Optimal Breakdown Point

Implicit Bias of Spectral Descent and Muon on Multiclass Separable Data

Finite Sample Analyses for Continuous-time Linear Systems: System Identification and Online Control

Breaking the Performance Ceiling in Reinforcement Learning requires Inference Strategies

Dynamic Algorithm for Explainable $k$-medians Clustering under $\ell_p$ Norm

Learning Preferences without Interaction for Cooperative AI: A Hybrid Offline-Online Approach

Time Reversal Symmetry for Efficient Robotic Manipulations in Deep Reinforcement Learning

$Q\sharp$: Provably Optimal Distributional RL for LLM Post-Training

Training a Scientific Reasoning Model for Chemistry

A Bayesian Fast-Slow Framework to Mitigate Interference in Non-Stationary Reinforcement Learning

The Price of Sparsity: Sufficient Conditions for Sparse Recovery using Sparse and Sparsified Measurements

Kernel Regression in Structured Non-IID Settings: Theory and Implications for Denoising Score Learning

Tradeoffs between Mistakes and ERM Oracle Calls in Online and Transductive Online Learning

Benign Overfitting in Single-Head Attention

Optimal Best Arm Identification under Differential Privacy

Asymptotic theory of SGD with a general learning-rate

Accelerating Feature Conformal Prediction via Taylor Approximation

Mean-Field Sampling for Cooperative Multi-Agent Reinforcement Learning

Scalable Policy-Based RL Algorithms for POMDPs

Improved Best-of-Both-Worlds Regret for Bandits with Delayed Feedback

Classical Planning with LLM-Generated Heuristics: Challenging the State of the Art with Python Code

FedEL: Federated Elastic Learning for Heterogeneous Devices

Accelerating Block Coordinate Descent for LLM Finetuning via Landscape Expansion

TADA: Improved Diffusion Sampling with Training-free Augmented DynAmics

HoPE: Hybrid of Position Embedding for Long Context Vision-Language Models

Top-H Decoding: Adapting the Creativity and Coherence with Bounded Entropy in Text Generation

Improving Formal Reasoning of Transformer with State Stack

ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference

Gaussian Process Upper Confidence Bound Achieves Nearly-Optimal Regret in Noise-Free Gaussian Process Bandits

Multi-modal contrastive learning adapts to intrinsic dimensions of shared latent variables

Heavy-Ball Momentum Method in Continuous Time and Discretization Error Analysis

Generalized Top-k Mallows Model for Ranked Choices

Exponential Convergence Guarantees for Iterative Markovian Fitting

On the Hardness of Conditional Independence Testing In Practice

Risk-Averse Constrained Reinforcement Learning with Optimized Certainty Equivalents

Offline imitation learning in $Q^\pi$-realizable MDPs without expert realizability

Interactive and Hybrid Imitation Learning: Provably Beating Behavior Cloning

Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation

A Near-optimal, Scalable and Parallelizable Framework for Stochastic Bandits Robust to Adversarial Corruptions and Beyond

Projection-based Lyapunov method for fully heterogeneous weakly-coupled MDPs

Gains: Fine-grained Federated Domain Adaptation in Open Set

AmorLIP: Efficient Language-Image Pretraining via Amortization

Fixed-Point RNNs: Interpolating from Diagonal to Dense

Teaching Transformers to Solve Combinatorial Problems through Efficient Trial & Error

Pan-LUT: Efficient Pan-sharpening via Learnable Look-Up Tables

Alleviating Hallucinations in Large Language Models through Multi-Model Contrastive Decoding and Dynamic Hallucination Detection

Quartet: Native FP4 Training Can Be Optimal for Large Language Models

InfiFPO: Implicit Model Fusion via Preference Optimization in Large Language Models

GoRA: Gradient-driven Adaptive Low Rank Adaptation

Learning in Compact Spaces with Approximately Normalized Transformer

FP4 All the Way: Fully Quantized Training of Large Language Models

Adaptive Latent-Space Constraints in Personalized Federated Learning

Language Ranker: A Lightweight Ranking framework for LLM Decoding

The Primacy of Magnitude in Low-Rank Adaptation

Scaling Laws for Optimal Data Mixtures

DISCO: DISCrete nOise for Conditional Control in Text-to-Image Diffusion Models

From Softmax to Score: Transformers Can Effectively Implement In-Context Denoising Steps

FlashBias: Fast Computation of Attention with Bias

Inference-Time Hyper-Scaling with KV Cache Compression

GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents

MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?

LIFEBENCH: Evaluating Length Instruction Following in Large Language Models

Prompting as Scientific Inquiry

Large Language Models Miss the Multi-agent Mark

Single GPU Task Adaptation of Pathology Foundation Models for Whole Slide Image Analysis

DePass: Unified Feature Attributing by Simple Decomposed Forward Pass

ZeCO: Zero-Communication Overhead Sequence Parallelism for Linear Attention

Understanding Differential Transformer Unchains Pretrained Self-Attentions

Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels

One SPACE to Rule Them All: Jointly Mitigating Factuality and Faithfulness Hallucinations in LLMs

Compress, Gather, and Recompute: REFORMing Long-Context Processing in Transformers

Accurate KV Cache Eviction via Anchor Direction Projection for Efficient LLM Inference

TransMLA: Migrating GQA Models to MLA with Full DeepSeek Compatibility and Speedup

DeltaProduct: Improving State-Tracking in Linear RNNs via Householder Products

Learning Linear Attention in Polynomial Time

What are you sinking? A geometric approach on attention sink

Delta Attention: Fast and Accurate Sparse Attention Inference by Delta Correction

Polyline Path Masked Attention for Vision Transformer

Linear Differential Vision Transformer: Learning Visual Contrasts via Pairwise Differentials

A Closer Look at Model Collapse: From a Generalization-to-Memorization Perspective

Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification

Traversal Verification for Speculative Tree Decoding

Information-Theoretic Discrete Diffusion

Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning

Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models

Quantifying Elicitation of Latent Capabilities in Language Models

Learning to Generate Human-Human-Object Interactions from Textual Descriptions

From Bytes to Ideas: Language Modeling with Autoregressive U-Nets

Scaling Speculative Decoding with Lookahead Reasoning

Inv-Entropy: A Fully Probabilistic Framework for Uncertainty Quantification in Language Models

BREAD: Branched Rollouts from Expert Anchors Bridge SFT & RL for Reasoning

From Style to Facts: Mapping the Boundaries of Knowledge Injection with Finetuning

SPACE: Noise Contrastive Estimation Stabilizes Self-Play Fine-Tuning for Large Language Models

When and how can inexact generative models still sample from the data manifold?

One-Step Offline Distillation of Diffusion-based Models via Koopman Modeling

Improving the Euclidean Diffusion Generation of Manifold Data by Mitigating Score Function Singularity

Training-Free Constrained Generation With Stable Diffusion Models

Continuous Diffusion Model for Language Modeling

CORAL: Disentangling Latent Representations in Long-Tailed Diffusion

MESS+: Dynamically Learned Inference-Time LLM Routing in Model Zoos with Service Level Guarantees

Support Vector Generation: Kernelizing Large Language Models for Efficient Zero‑Shot NLP

Disentangled Cross-Modal Representation Learning with Enhanced Mutual Supervision

On the Edge of Memorization in Diffusion Models

Multiverse: Your Language Models Secretly Decide How to Parallelize and Merge Generation

InfiGFusion: Graph-on-Logits Distillation via Efficient Gromov-Wasserstein for Model Fusion

LaM-SLidE: Latent Space Modeling of Spatial Dynamical Systems via Linked Entities

Asymmetric Dual Self-Distillation for 3D Self-Supervised Representation Learning

ALTo: Adaptive-Length Tokenizer for Autoregressive Mask Generation

Gemstones: A Model Suite for Multi-Faceted Scaling Laws

Online Feedback Efficient Active Target Discovery in Partially Observable Environments

Learnable Sampler Distillation for Discrete Diffusion Models

Training-Free Safe Text Embedding Guidance for Text-to-Image Diffusion Models

Neural Entropy

Weaver: Shrinking the Generation-Verification Gap by Scaling Compute for Verification

TreeGen: A Bayesian Generative Model for Hierarchies

System-Embedded Diffusion Bridge Models

GPO: Learning from Critical Steps to Improve LLM Reasoning

Optimal Neural Compressors for the Rate-Distortion-Perception Tradeoff

Pairwise Optimal Transports for Training All-to-All Flow-Based Condition Transfer Model

Diffusion on Demand: Selective Caching and Modulation for Efficient Generation

PID-controlled Langevin Dynamics for Faster Sampling on Generative Models

Spectral Analysis of Diffusion Models with Application to Schedule Design

NeedleInATable: Exploring Long-Context Capability of Large Language Models towards Long-Structured Tables

RDB2G-Bench: A Comprehensive Benchmark for Automatic Graph Modeling of Relational Databases

GC4NC: A Benchmark Framework for Graph Condensation on Node Classification with New Insights

Random Search Neural Networks for Efficient and Expressive Graph Learning

Effects of Dropout on Performance in Long-range Graph Learning Tasks

Conditional Diffusion Anomaly Modeling on Graphs

Preference-driven Knowledge Distillation for Few-shot Node Classification

AMBER: Adaptive Mesh Generation by Iterative Mesh Resolution Prediction

GraphTOP: Graph Topology-Oriented Prompting for Graph Neural Networks

HubGT: Fast Graph Transformer with Decoupled Hierarchy Labeling

GAMMA: Gated Multi-hop Message Passing for Homophily-Agnostic Node Representation in GNNs

Disentangling Hyperedges through the Lens of Category Theory

Pseudo-Riemannian Graph Transformer

Where Graph Meets Heterogeneity: Multi-View Collaborative Graph Experts

Memorization in Graph Neural Networks

Learning Sparse Approximate Inverse Preconditioners for Conjugate Gradient Solvers on GPUs

Enhancing Graph Classification Robustness with Singular Pooling

Characterizing the Expressivity of Fixed-Precision Transformer Language Models

Interpretable Global Minima of Deep ReLU Neural Networks on Sequentially Separable Data

RepGuard: Adaptive Feature Decoupling for Robust Backdoor Defense in Large Language Models

Uncertainty Quantification for Deep Regression using Contextualised Normalizing Flows

Monitoring Risks in Test-Time Adaptation

Fuz-RL: A Fuzzy-Guided Robust Framework for Safe Reinforcement Learning under Uncertainty

Ditch the Denoiser: Emergence of Noise Robustness in Self-Supervised Learning from Data Curriculum

Consensus-Robust Transfer Attacks via Parameter and Representation Perturbations

MIBP-Cert: Certified Training against Data Perturbations with Mixed-Integer Bilinear Programs

Defending Multimodal Backdoored Models by Repulsive Visual Prompt Tuning

Robust LLM Alignment via Distributionally Robust Direct Preference Optimization

From Faults to Features: Pretraining to Learn Robust Representations against Sensor Failures

Dynamical Low-Rank Compression of Neural Networks with Robustness under Adversarial Attacks

Impact of Layer Norm on Memorization and Generalization in Transformers

TransferBench: Benchmarking Ensemble-based Black-box Transfer Attacks

Learning to Flow from Generative Pretext Tasks for Neural Architecture Encoding

Deeper with Riemannian Geometry: Overcoming Oversmoothing and Oversquashing for Graph Foundation Models

GD$^2$: Robust Graph Learning under Label Noise via Dual-View Prediction Discrepancy

MaNGO — Adaptable Graph Network Simulators via Meta-Learning

Rethinking Tokenized Graph Transformers for Node Classification

What Can RL Bring to VLA Generalization? An Empirical Study

Unveiling Transformer Perception by Exploring Input Manifolds

Neural Collapse is Globally Optimal in Deep Regularized ResNets and Transformers

Better NTK Conditioning: A Free Lunch from (ReLU) Nonlinear Activation in Wide Neural Networks

Stable Minima of ReLU Neural Networks Suffer from the Curse of Dimensionality: The Neural Shattering Phenomenon

Born a Transformer -- Always a Transformer? On the Effect of Pretraining on Architectural Abilities

Contrastive Learning with Data Misalignment: Feature Purity, Training Dynamics and Theoretical Generalization Guarantees

Agnostic Learning under Targeted Poisoning: Optimal Rates and the Role of Randomness

The Nuclear Route: Sharp Asymptotics of ERM in Overparameterized Quadratic Networks

Identifiability of Deep Polynomial Neural Networks

Attention-based clustering

Intrinsic Benefits of Categorical Distributional Loss: Uncertainty-aware Regularized Exploration in Reinforcement Learning

Spectral Conditioning of Attention Improves Transformer Performance

Is Grokking a Computational Glass Relaxation?

Partial Information Decomposition via Normalizing Flows in Latent Gaussian Distributions

Depth-Bounds for Neural Networks via the Braid Arrangement

Continuity and Isolation Lead to Doubts or Dilemmas in Large Language Models

Learning to Add, Multiply, and Execute Algorithmic Instructions Exactly with Neural Networks

Emergence and scaling laws in SGD learning of shallow neural networks

Flatness is Necessary, Neural Collapse is Not: Rethinking Generalization via Grokking

Compositional Reasoning with Transformers, RNNs, and Chain of Thought

Analyzing the Power of Chain of Thought through Memorization Capabilities

Learnable Burst-Encodable Time-of-Flight Imaging for High-Fidelity Long-Distance Depth Sensing

Adaptive Context Length Optimization with Low-Frequency Truncation for Multi-Agent Reinforcement Learning

HyperMARL: Adaptive Hypernetworks for Multi-Agent RL

Inner Speech as Behavior Guides: Steerable Imitation of Diverse Behaviors for Human-AI coordination

Scalable Neural Incentive Design with Parameterized Mean-Field Approximation

Planning with Quantized Opponent Models

ForceVLA: Enhancing VLA Models with a Force-aware MoE for Contact-rich Manipulation

Spectral Learning for Infinite-Horizon Average-Reward POMDPs

Learning Interactive World Model for Object-Centric Reinforcement Learning

SEGA: Shaping Semantic Geometry for Robust Hashing under Noisy Supervision

HM3: Hierarchical Multi-Objective Model Merging for Pretrained Models

Cognitive Mirrors: Exploring the Diverse Functional Roles of Attention Heads in LLM Reasoning

Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens

On the Loss of Context Awareness in General Instruction Fine-tuning

LLM Layers Immediately Correct Each Other

Less is More: Improving LLM Alignment via Preference Data Selection

RAGRouter: Learning to Route Queries to Multiple Retrieval-Augmented Language Models

RidgeLoRA: Matrix Ridge Enhanced Low-Rank Adaptation of Large Language Models

The Leaderboard Illusion

Robust Reinforcement Learning in Finance: Modeling Market Impact with Elliptic Uncertainty Sets

Linearization Explains Fine-Tuning in Large Language Models

Alternating Gradient Flows: A Theory of Feature Learning in Two-layer Neural Networks

Progress Reward Model for Reinforcement Learning via Large Language Models

Exploring Data Scaling Trends and Effects in Reinforcement Learning from Human Feedback

Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems

Reinforcement Learning with Action Chunking

RF-Agent: Automated Reward Function Design via Language Agent Tree Search

Flat Channels to Infinity in Neural Loss Landscapes

FedRW: Efficient Privacy-Preserving Data Reweighting for Enhancing Federated Learning of Language Models

Distribution-Aware Tensor Decomposition for Compression of Convolutional Neural Networks

EventMG: Efficient Multilevel Mamba-Graph Learning for Spatiotemporal Event Representation

Mamba Modulation: On the Length Generalization of Mamba Models

Aligning Text-to-Image Diffusion Models to Human Preference by Classification

Small Singular Values Matter: A Random Matrix Analysis of Transformer Models

GeoRanker: Distance-Aware Ranking for Worldwide Image Geolocalization

LLM Safety Alignment is Divergence Estimation in Disguise

Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks

Recursive Inference Scaling: A Winning Path to Scalable Inference in Language and Multimodal Systems

Adaptive LoRA Experts Allocation and Selection for Federated Fine-Tuning

Reinforcement Learning Meets Masked Generative Models: Mask-GRPO for Text-to-Image Generation

EchoShot: Multi-Shot Portrait Video Generation

CoT-lized Diffusion: Let's Reinforce T2I Generation Step-by-step

OmniZoom: A Universal Plug-and-Play Paradigm for Cross-Device Smooth Zoom Interpolation

Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer

MJ-Video: Benchmarking and Rewarding Video Generation with Fine-Grained Video Preference

Tortoise and Hare Guidance: Accelerating Diffusion Model Inference with Multirate Integration

CamEdit: Continuous Camera Parameter Control for Photorealistic Image Editing

UniRelight: Learning Joint Decomposition and Synthesis for Video Relighting

VideoUFO: A Million-Scale User-Focused Dataset for Text-to-Video Generation

FineGRAIN: Evaluating Failure Modes of Text-to-Image Models with Vision Language Model Judges

vHector and HeisenVec: Scalable Vector Graphics Generation Through Large Language Models

OneIG-Bench: Omni-dimensional Nuanced Evaluation for Image Generation

Sekai: A Video Dataset towards World Exploration

An Analysis of Concept Bottleneck Models: Measuring, Understanding, and Mitigating the Impact of Noisy Annotations

Breaking the Compression Ceiling: Data-Free Pipeline for Ultra-Efficient Delta Compression

ConTextTab: A Semantics-Aware Tabular In-Context Learner

SPRINT: Enabling Interleaved Planning and Parallelized Execution in Reasoning Models

REPA Works Until It Doesn’t: Early-Stopped, Holistic Alignment Supercharges Diffusion Training

Think before Recommendation: Autonomous Reasoning-enhanced Recommender

Text to Sketch Generation with Multi-Styles

FreqExit: Enabling Early-Exit Inference for Visual Autoregressive Models via Frequency-Aware Guidance

REGen: Multimodal Retrieval-Embedded Generation for Long-to-Short Video Editing

Improving Diffusion-based Inverse Algorithms under Few-Step Constraint via Linear Extrapolation

ViewPoint: Panoramic Video Generation with Pretrained Diffusion Models

Seg4Diff: Unveiling Open-Vocabulary Semantic Segmentation in Text-to-Image Diffusion Transformers

Video World Models with Long-term Spatial Memory

Stable Part Diffusion 4D: Multi-View RGB and Kinematic Parts Video Generation

DCI: Dual-Conditional Inversion for Boosting Diffusion-Based Image Editing

DNAEdit: Direct Noise Alignment for Text-Guided Rectified Flow Editing

RepLDM: Reprogramming Pretrained Latent Diffusion Models for High-Quality, High-Efficiency, High-Resolution Image Generation

When Are Concepts Erased From Diffusion Models?

StateSpaceDiffuser: Bringing Long Context to Diffusion World Models

PixPerfect: Seamless Latent Diffusion Local Editing with Discriminative Pixel-Space Refinement

Boosting Generative Image Modeling via Joint Image-Feature Synthesis

OmniVCus: Feedforward Subject-driven Video Customization with Multimodal Control Conditions

Accelerating Parallel Diffusion Model Serving with Residual Compression

Image Stitching in Adverse Condition: A Bidirectional-Consistency Learning Framework and Benchmark

GenColor: Generative and Expressive Color Enhancement with Pixel-Perfect Texture Preservation

InstanceAssemble: Layout-Aware Image Generation via Instance Assembling Attention

Quantifying and Alleviating Co-Adaptation in Sparse-View 3D Gaussian Splatting

Multimodal LiDAR-Camera Novel View Synthesis with Unified Pose-free Neural Fields

AtlasGS: Atlanta-world Guided Surface Reconstruction with Implicit Structured Gaussians

Flux4D: Flow-based Unsupervised 4D Reconstruction

Fused View-Time Attention and Feedforward Reconstruction for 4D Scene Generation

Metropolis-Hastings Sampling for 3D Gaussian Reconstruction

IBGS: Image-Based Gaussian Splatting

Cue3D: Quantifying the Role of Image Cues in Single-Image 3D Generation

Complete Structure Guided Point Cloud Completion via Cluster- and Instance-Level Contrastive Learning

LiteReality: Graphic-Ready 3D Scene Reconstruction from RGB-D Scans

SurfelSplat: Learning Efficient and Generalizable Gaussian Surfel Representations for Sparse-View Surface Reconstruction

PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers

InFlux: A Benchmark for Self-Calibration of Dynamic Intrinsics of Video Cameras

Depth-Supervised Fusion Network for Seamless-Free Image Stitching

VETA-DiT: Variance-Equalized and Temporally Adaptive Quantization for Efficient 4-bit Diffusion Transformers

Policy Optimized Text-to-Image Pipeline Design

Role Bias in Diffusion Models: Diagnosing and Mitigating through Intermediate Decomposition

LightFair: Towards an Efficient Alternative for Fair T2I Diffusion via Debiasing Pre-trained Text Encoders

EditInfinity: Image Editing with Binary-Quantized Generative Models

PolyJuice Makes It Real: Black-Box, Universal Red Teaming for Synthetic Image Detectors

Instant4D: 4D Gaussian Splatting in Minutes

Adaptive 3D Reconstruction via Diffusion Priors and Forward Curvature-Matching Likelihood Updates

LODGE: Level-of-Detail Large-Scale Gaussian Splatting with Efficient Rendering

Pose Splatter: A 3D Gaussian Splatting Model for Quantifying Animal Pose and Appearance

MV-CoLight: Efficient Object Compositing with Consistent Lighting and Shadow Generation

WildCAT3D: Appearance-Aware Multi-View Diffusion in the Wild

PyraMotion: Attentional Pyramid-Structured Motion Integration for Co-Speech 3D Gesture Synthesis

Visual Sync: Multi‑Camera Synchronization via Cross‑View Object Motion

Test3R: Learning to Reconstruct 3D at Test Time

Restage4D: Reanimating Deformable 3D Reconstruction from a Single Video

Non-Line-of-Sight 3D Reconstruction with Radar

Repurposing Marigold for Zero-Shot Metric Depth Estimation via Defocus Blur Cues

Towards Dynamic 3D Reconstruction of Hand-Instrument Interaction in Ophthalmic Surgery

Deep Gaussian from Motion: Exploring 3D Geometric Foundation Models for Gaussian Splatting

Wukong's 72 Transformations: High-fidelity Textured 3D Morphing via Flow Models

DAVE: Diagnostic benchmark for Audio Visual Evaluation

MMPB: It’s Time for Multi-Modal Personalization

From Play to Replay: Composed Video Retrieval for Temporally Fine-Grained Videos

ConViS-Bench: Estimating Video Similarity Through Semantic Concepts

Toward a Vision-Language Foundation Model for Medical Data: Multimodal Dataset and Benchmarks for Vietnamese PET/CT Report Generation

More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models

Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model

With Limited Data for Multimodal Alignment, Let the STRUCTURE Guide You

When One Moment Isn't Enough: Multi-Moment Retrieval with Cross-Moment Interactions

Multimodal Causal Reasoning for UAV Object Detection

Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding

MemEIC: A Step Toward Continual and Compositional Knowledge Editing

Elevating Visual Perception in Multimodal LLMs with Visual Embedding Distillation

CoFFT: Chain of Foresight-Focus Thought for Visual Language Models

A Frustratingly Simple Yet Highly Effective Attack Baseline: Over 90% Success Rate Against the Strong Black-box Models of GPT-4.5/4o/o1

Pancakes: Consistent Multi-Protocol Image Segmentation Across Biomedical Domains

VaMP: Variational Multi-Modal Prompt Learning for Vision-Language Models

VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction

SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation

MMOT: The First Challenging Benchmark for Drone-based Multispectral Multi-Object Tracking

DisasterM3: A Remote Sensing Vision-Language Dataset for Disaster Damage Assessment and Response

ColorBench: Can VLMs See and Understand the Colorful World? A Comprehensive Benchmark for Color Perception, Reasoning, and Robustness

Towards Understanding Camera Motions in Any Video

MVU-Eval: Towards Multi-Video Understanding Evaluation for Multimodal LLMs

EOC-Bench: Can MLLMs Identify, Recall, and Forecast Objects in an Egocentric World?

MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO

Decoupling Contrastive Decoding: Robust Hallucination Mitigation in Multimodal Large Language Models

SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement

SD-VLM: Spatial Measuring and Understanding with Depth-Encoded Vision-Language Models

VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning

GUIDED: Granular Understanding via Identification, Detection, and Discrimination for Fine-Grained Open-Vocabulary Object Detection

QuARI: Query Adaptive Retrieval Improvement

Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence

Efficient Rectified Flow for Image Fusion

Towards General Continuous Memory for Vision-Language Models

Few-Shot Learning from Gigapixel Images via Hierarchical Vision-Language Alignment and Modeling

ControlFusion: A Controllable Image Fusion Network with Language-Vision Degradation Prompts

One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-Resolution

Seeing is Believing? Mitigating OCR Hallucinations in Multimodal Large Language Models

SAMA: Towards Multi-Turn Referential Grounded Video Chat with Large Language Models

UniTok: a Unified Tokenizer for Visual Generation and Understanding

FlowFeat: Pixel-Dense Embedding of Motion Profiles

InfiniPot-V: Memory-Constrained KV Cache Compression for Streaming Video Understanding

On Epistemic Uncertainty of Visual Tokens for Object Hallucinations in Large Vision-Language Models

R1-ShareVL: Incentivizing Reasoning Capabilities of Multimodal Large Language Models via Share-GRPO

Point or Line? Using Line-based Representation for Panoptic Symbol Spotting in CAD Drawings

Novel Class Discovery for Point Cloud Segmentation via Joint Learning of Causal Representation and Reasoning

Seg-VAR:Image Segmentation with Visual Autoregressive Modeling

OmniSegmentor: A Flexible Multi-Modal Learning Framework for Semantic Segmentation

UniMRSeg: Unified Modality-Relax Segmentation via Hierarchical Self-Supervised Compensation

UFO: A Unified Approach to Fine-grained Visual Perception via Open-ended Language Interface

OpenHype: Hyperbolic Embeddings for Hierarchical Open-Vocabulary Radiance Fields

Semi-off-Policy Reinforcement Learning for Vision-Language Slow-Thinking Reasoning

Hierarchical Semantic-Augmented Navigation: Optimal Transport and Graph-Driven Reasoning for Vision-Language Navigation

PARTONOMY: Large Multimodal Models with Part-Level Visual Understanding

When Semantics Mislead Vision: Mitigating Large Multimodal Models Hallucinations in Scene Text Spotting and Understanding

VidEmo: Affective-Tree Reasoning for Emotion-Centric Video Foundation Models

SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent

MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning

Less Is More, but Where? Dynamic Token Compression via LLM-Guided Keyframe Prior

Poison as Cure: Visual Noise for Mitigating Object Hallucinations in LVMs

Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos

Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search

Find your Needle: Small Object Image Retrieval via Multi-Object Attention Optimization

Watch and Listen: Understanding Audio-Visual-Speech Moments with Multimodal LLM

Statistical Analysis of an Adversarial Bayesian Weak Supervision Method

Stratify or Die: Rethinking Data Splits in Image Segmentation

ARGenSeg: Image Segmentation with Autoregressive Image Generation Model

Segment Anything Model Meets Semi-supervised Medical Image Segmentation: A Novel Perspective

Robust Egocentric Referring Video Object Segmentation via Dual-Modal Causal Intervention

OpenAD: Open-World Autonomous Driving Benchmark for 3D Object Detection

MomentSeeker: A Task-Oriented Benchmark For Long-Video Moment Retrieval

ReinAD: Towards Real-world Industrial Anomaly Detection with a Comprehensive Contrastive Dataset

SGAR: Structural Generative Augmentation for 3D Human Motion Retrieval

Beyond the Seen: Bounded Distribution Estimation for Open-Vocabulary Learning

Towards Single-Source Domain Generalized Object Detection via Causal Visual Prompts

Collaborative and Confidential Junction Trees for Hybrid Bayesian Networks

DAMamba: Vision State Space Model with Dynamic Adaptive Scan

Learning Dense Hand Contact Estimation from Imbalanced Data

VT-FSL: Bridging Vision and Text with LLMs for Few-Shot Learning

TOMCAT: Test-time Comprehensive Knowledge Accumulation for Compositional Zero-Shot Learning

What We Miss Matters: Learning from the Overlooked in Point Cloud Transformers

ImageNet-trained CNNs are not biased towards texture: Revisiting feature reliance through controlled suppression

Prompt-guided Disentangled Representation for Action Recognition

SPAZER: Spatial-Semantic Progressive Reasoning Agent for Zero-shot 3D Visual Grounding

PANDA: Towards Generalist Video Anomaly Detection via Agentic AI Engineer

Learning Skill-Attributes for Transferable Assessment in Video

Geometry-Aware Collaborative Multi-Solutions Optimizer for Model Fine-Tuning with Parameter Efficiency

Epistemic Uncertainty Estimation in Regression Ensemble Models with Pairwise Epistemic Estimators

Multilevel neural simulation-based inference

Distance-informed Neural Processes

Temporal-Difference Variational Continual Learning

Optimal Adjustment Sets for Nonparametric Estimation of Weighted Controlled Direct Effect

Synthetic-powered predictive inference

Effortless, Simulation-Efficient Bayesian Inference using Tabular Foundation Models

Solving and Learning Partial Differential Equations with Variational Q-Exponential Processes

GOATex: Geometry & Occlusion-Aware Texturing

One-Step Diffusion-Based Image Compression with Semantic Distillation

HAODiff: Human-Aware One-Step Diffusion via Dual-Prompt Guidance

Zero-Shot Blind-Spot Image Denoising via Cross-Scale Non-Local Pixel Refilling

Can NeRFs "See" without Cameras?

DON’T NEED RETRAINING: A Mixture of DETR and Vision Foundation Models for Cross-Domain Few-Shot Object Detection

Looking Into the Water by Unsupervised Learning of the Surface Shape

Autoregressive Motion Generation with Gaussian Mixture-Guided Latent Sampling

Toward Real-world Text Image Forgery Localization: Structured and Interpretable Data Synthesis

Language Model Behavioral Phases are Consistent Across Architecture, Training Data, and Scale

Constrained Feedback Learning for Non-Stationary Multi-Armed Bandits

Boosting Skeleton-based Zero-Shot Action Recognition with Training-Free Test-Time Adaptation

Representation-Level Counterfactual Calibration for Debiased Zero-Shot Recognition

State Entropy Regularization for Robust Reinforcement Learning

A Unifying View of Linear Function Approximation in Off-Policy RL Through Matrix Splitting and Preconditioning

Shift Before You Learn: Enabling Low-Rank Representations in Reinforcement Learning

When Can Model-Free Reinforcement Learning be Enough for Thinking?

Diff-ICMH: Harmonizing Machine and Human Vision in Image Compression with Generative Prior

Towards Implicit Aggregation: Robust Image Representation for Place Recognition in the Transformer Era

Unified Algorithms for RL with Decision-Estimation Coefficients: PAC, Reward-Free, Preference-Based Learning, and Beyond

Foundation Models for Scientific Discovery: From Paradigm Enhancement to Paradigm Transition

Position: Require Frontier AI Labs To Release Small "Analog" Models

IndustryEQA: Pushing the Frontiers of Embodied Question Answering in Industrial Scenarios

DetectiumFire: A Comprehensive Multi-modal Dataset Bridging Vision and Language for Fire Understanding

DyFlow: Dynamic Workflow Framework for Agentic Reasoning

CF-VLM：CounterFactual Vision-Language Fine-tuning

Adaptive Quantization in Generative Flow Networks for Probabilistic Sequential Prediction

Measuring the Faithfulness of Thinking Drafts in Large Reasoning Models

Beyond Least Squares: Uniform Approximation and the Hidden Cost of Misspecification

VERA: Variational Inference Framework for Jailbreaking Large Language Models

Unveiling Extraneous Sampling Bias with Data Missing-Not-At-Random

Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models

Sharp Analysis for KL-Regularized Contextual Bandits and RLHF

Time-o1: Time-Series Forecasting Needs Transformed Label Alignment

AdvPrefix: An Objective for Nuanced LLM Jailbreaks

Flexible Language Modeling in Continuous Space with Transformer-based Autoregressive Flows

Scalable Exploration via Ensemble++

Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models

On the Stability of Graph Convolutional Neural Networks: A Probabilistic Perspective

Personalized Exercise Recommendation with Semantically-Grounded Knowledge Tracing

DeltaFormer: Unlock the state space of Transformer

Reinforcement Learning with Imperfect Transition Predictions: A Bellman-Jensen Approach

LABridge: Text–Image Latent Alignment Framework via Mean-Conditioned OU Process

Understanding Parametric and Contextual Knowledge Reconciliation within Large Language Models

VLForgery Face Triad: Detection, Localization and Attribution via Multimodal Large Language Models

FedRAM: Federated Reweighting and Aggregation for Multi-Task Learning

Correlated Low-Rank Adaptation for ConvNets

STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis

Beyond Single-Task: Robust Multi-Task Length Generalization for LLMs

EvoBrain: Dynamic Multi-Channel EEG Graph Modeling for Time-Evolving Brain Networks

Non-rectangular Robust MDPs with Normed Uncertainty Sets

A Geometry-Aware Metric for Mode Collapse in Time Series Generative Models

Cost-Sensitive Freeze-thaw Bayesian Optimization for Efficient Hyperparameter Tuning

Video-R1: Reinforcing Video Reasoning in MLLMs

CSBrain: A Cross-scale Spatiotemporal Brain Foundation Model for EEG Decoding

Inference-time Alignment in Continuous Space

TV-Rec: Time-Variant Convolutional Filter for Sequential Recommendation

Smooth Quadratic Prediction Markets

C3PO: Optimized Large Language Model Cascades with Probabilistic Cost Constraints for Reasoning

Graph Alignment via Birkhoff Relaxation

UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens

GraphMaster: Automated Graph Synthesis via LLM Agents in Data-Limited Environments

SpatialReasoner: Towards Explicit and Generalizable 3D Spatial Reasoning

VCM: Vision Concept Modeling with Adaptive Vision Token Compression via Instruction Fine-Tuning

Towards Resilient Safety-driven Unlearning for Diffusion Models against Downstream Fine-tuning

Non-Asymptotic Guarantees for Average-Reward Q-Learning with Adaptive Stepsizes

AI-Researcher: Autonomous Scientific Innovation

Not All Data are Good Labels: On the Self-supervised Labeling for Time Series Forecasting

Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL

Individual Regret in Cooperative Stochastic Multi-Armed Bandits

Regret Bounds for Adversarial Contextual Bandits with General Function Approximation and Delayed Feedback

On the Expressive Power of Mixture-of-Experts for Structured Complex Tasks

Sparc3D: Sparse Representation and Construction for High-Resolution 3D Shapes Modeling

Visual Jenga: Discovering Object Dependencies via Counterfactual Inpainting

ORIGAMISPACE: Benchmarking Multimodal LLMs in Multi-Step Spatial Reasoning with Mathematical Constraints

macOSWorld: A Multilingual Interactive Benchmark for GUI Agents

Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models

Generalized Category Discovery under Domain Shift: A Frequency Domain Perspective

Variational Supervised Contrastive Learning

KeyDiff: Key Similarity-Based KV Cache Eviction for Long-Context LLM Inference in Resource-Constrained Environments

Can MLLMs Absorb Math Reasoning Abilities from LLMs as Free Lunch?

OmniSVG: A Unified Scalable Vector Graphics Generation Model

Robust SuperAlignment: Weak-to-Strong Robustness Generalization for Vision-Language Models

Balancing Gradient and Hessian Queries in Non-Convex Optimization

WebDancer: Towards Autonomous Information Seeking Agency

MM-Agent: LLM as Agents for Real-world Mathematical Modeling Problem

Generative Pre-trained Autoregressive Diffusion Transformer

Language Models (Mostly) Know When to Stop Reading

VarFlow: Proper Scoring-Rule Diffusion Distillation via Energy Matching

Training-Free Bayesianization for Low-Rank Adapters of Large Language Models

Rethinking Approximate Gaussian Inference in Classification

Fisher meets Feynman: score-based variational inference with a product of experts

Stationary Kernels and Gaussian Processes on Lie Groups and their Homogeneous Spaces I: the compact case

Spectral Estimation with Free Decompression

Sparse Gaussian Processes: Structured Approximations and Power-EP Revisited

FEAT: Free energy Estimators with Adaptive Transport

Non-equilibrium Annealed Adjoint Sampler

Fast Non-Log-Concave Sampling under Nonconvex Equality and Inequality Constraints with Landing

Variance-Reduced Long-Term Rehearsal Learning with Quadratic Programming Reformulation

Neurosymbolic Diffusion Models

Anytime-valid, Bayes-assisted, Prediction-Powered Inference

Rao-Blackwellised Reparameterisation Gradients

Uncertainty Estimation by Flexible Evidential Deep Learning

Data-Driven Performance Guarantees for Classical and Learned Optimizers

Learning from A Single Markovian Trajectory: Optimality and Variance Reduction

Unveiling m-Sharpness Through the Structure of Stochastic Gradient Noise

Streaming Stochastic Submodular Maximization with On-Demand User Requests

Stochastic Momentum Methods for Non-smooth Non-Convex Finite-Sum Coupled Compositional Optimization

Zeroth-Order Optimization Finds Flat Minima

Optimistic Online-to-Batch Conversions for Accelerated Convergence and Universality

Efficient Quadratic Corrections for Frank-Wolfe Algorithms

Multiclass Loss Geometry Matters for Generalization of Gradient Descent in Separable Classification

Private Zeroth-Order Optimization with Public Data

Solving Discrete (Semi) Unbalanced Optimal Transport with Equivalent Transformation Mechanism and KKT-Multiplier Regularization

MTL-KD: Multi-Task Learning Via Knowledge Distillation for Generalizable Neural Vehicle Routing Solver

Large Language Models as End-to-end Combinatorial Optimization Solvers

Bilevel Optimization for Adversarial Learning Problems: Sharpness, Generation, and Beyond

3BASiL: An Algorithmic Framework for Sparse plus Low-Rank Compression of LLMs

Optimizing the Unknown: Black Box Bayesian Optimization with Energy-Based Model and Reinforcement Learning

Acceleration via silver step-size on Riemannian manifolds with applications to Wasserstein space

NPN: Non-Linear Projections of the Null-Space for Imaging Inverse Problems

Stochastic Regret Guarantees for Online Zeroth- and First-Order Bilevel Optimization

Follow-the-Perturbed-Leader Nearly Achieves Best-of-Both-Worlds for the m-Set Semi-Bandit Problems

Fairness-Regularized Online Optimization with Switching Costs

Purity Law for Neural Routing Problem Solvers with Enhanced Generalizability

OptiTree: Hierarchical Thoughts Generation with Tree Search for LLM Optimization Modeling

Improved Algorithms for Overlapping and Robust Clustering of Edge-Colored Hypergraphs: An LP-Based Combinatorial Approach

Hybrid-Balance GFlowNet for Solving Vehicle Routing Problems

Improving Generalization of Neural Combinatorial Optimization for Vehicle Routing Problems via Test-Time Projection Learning

Hierarchical Optimization via LLM-Guided Objective Evolution for Mobility-on-Demand Systems

KVFlow: Efficient Prefix Caching for Accelerating LLM-Based Multi-Agent Workflows

Partial Correlation Network Estimation by Semismooth Newton Methods

FlowMoE: A Scalable Pipeline Scheduling Framework for Distributed Mixture-of-Experts Training

Communication-Efficient Language Model Training Scales Reliably and Robustly: Scaling Laws for DiLoCo

ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive

A Near-Optimal Algorithm for Decentralized Convex-Concave Finite-Sum Minimax Optimization

Cost-aware LLM-based Online Dataset Annotation

Efficient semantic uncertainty quantification in language models via diversity-steered sampling

$O(\sqrt{T})$ Static Regret and Instance Dependent Constraint Violation for Constrained Online Convex Optimization

Sign-In to the Lottery: Reparameterizing Sparse Training

Power Lines: Scaling laws for weight decay and batch size in LLM pre-training

Q3R: Quadratic Reweighted Rank Regularizer for Effective Low-Rank Training

Momentum-SAM: Sharpness Aware Minimization without Computational Overhead

FFN Fusion: Rethinking Sequential Computation in Large Language Models

Time-Embedded Algorithm Unrolling for Computational MRI

MUSTAFAR: Promoting Unstructured Sparsity for KV Cache Pruning in LLM Inference

Differentiable Sparsity via $D$-Gating: Simple and Versatile Structured Penalization

Small Batch Size Training for Language Models: When Vanilla SGD Works, and Why Gradient Accumulation is Wasteful

Data Efficient Adaptation in Large Language Models via Continuous Low-Rank Fine-Tuning

Modality-Aware SAM: Sharpness-Aware-Minimization Driven Gradient Modulation for Harmonized Multimodal Learning

Neural Evolution Strategy for Black-box Pareto Set Learning

Thompson Sampling in Function Spaces via Neural Operators

Online Portfolio Selection with ML Predictions

Re-coding for Uncertainties: Edge-awareness Semantic Concordance for Resilient Event-RGB Segmentation

Variational Learning Finds Flatter Solutions at the Edge of Stability

Conformal Prediction in The Loop: A Feedback-Based Uncertainty Model for Trajectory Optimization

(ends 2:00 PM)

1 p.m.

Break:

Hosted Lunch

(ends 2:30 PM)

2:30 p.m.

San Diego Invited Talk:

On the Science of “Alien Intelligences”: Evaluating Cognitive Capabilities in Babies, Animals, and AI

Melanie Mitchell

(ends 3:30 PM)

3:30 p.m.

Oral 4A Language Model 2 [3:30-4:30]

Orals 3:30-4:30

[3:30] A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders

[3:50] Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free

[4:10] Superposition Yields Robust Neural Scaling

(ends 4:30 PM)

Oral 4B Generation/Simulation 2 [3:30-4:30]

Orals 3:30-4:30

[3:30] Exploring Diffusion Transformer Designs via Grafting

[3:50] Deep Compositional Phase Diffusion for Long Motion Sequence Generation

[4:10] Mean Flows for One-step Generative Modeling

(ends 4:30 PM)

Oral 4C Position Paper Panels [3:30-4:30]

Responsible AI Research & Unlearning: From Consent to Compliance to Critique

Strengthening the AI Research Ecosystem: Integrity, Critique, and Consensus

(ends 4:30 PM)

Oral 4D Optimization [3:30-4:30]

Orals 3:30-4:30

[3:30] In Search of Adam’s Secret Sauce

[3:50] Analog In-memory Training on General Non-ideal Resistive Elements: The Impact of Response Functions

[4:10] Generalized Gradient Norm Clipping & Non-Euclidean $(L_0,L_1)$-Smoothness

(ends 4:30 PM)

Oral 4E Algorithm 2 [3:30-4:30]

Orals 3:30-4:30

[3:30] MaxSup: Overcoming Representation Collapse in Label Smoothing

[3:50] Advancing Expert Specialization for Better MoE

[4:10] Learning to Learn with Contrastive Meta-Objective

(ends 4:30 PM)

4:30 p.m.

Creative AI Panel:

Objects of AI

(ends 5:30 PM)

Break:

Coffee Break

(ends 5:30 PM)

San Diego Poster Session 4 [4:30-7:30]

Posters 4:30-7:30

MuRating: A High Quality Data Selecting Approach to Multilingual Large Language Model Pretraining

FaCT: Faithful Concept Traces for Explaining Neural Network Decisions

Advancing Interpretability of CLIP Representations with Concept Surrogate Model

Automated Detection of Visual Attribute Reliance with a Self-Reflective Agent

On Logic-based Self-Explainable Graph Neural Networks

A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders

Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry

Causally Reliable Concept Bottleneck Models

MIX: A Multi-view Time-Frequency Interactive Explanation Framework for Time Series Classification

Combining Cost Constrained Runtime Monitors for AI Safety

SHAP zero Explains Biological Sequence Models with Near-zero Marginal Cost for Future Queries

Robust Sampling for Active Statistical Inference

Disentangled Concepts Speak Louder Than Words: Explainable Video Action Recognition

Shortcuts and Identifiability in Concept-based Models from a Neuro-Symbolic Lens

Interpreting Arithmetic Reasoning in Large Language Models using Game-Theoretic Interactions

Reasoning Models Sometimes Output Illegible Chains of Thought

Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning

OVERT: A Benchmark for Over-Refusal Evaluation on Text-to-Image Models

Is Artificial Intelligence Generated Image Detection a Solved Problem?

Preserving LLM Capabilities through Calibration Data Curation: From Analysis to Optimization

Checklists Are Better Than Reward Models For Aligning Language Models

Generative Caching for Structurally Similar Prompts and Responses

Efficient Multimodal Dataset Distillation via Generative Models

Evaluating multiple models using labeled and unlabeled data

Solving Partial Differential Equations via Radon Neural Operator

SECODEPLT: A Unified Benchmark for Evaluating the Security Risks and Capabilities of Code GenAI

APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay

EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code

Simple and Effective Specialized Representations for Fair Classifiers

AegisGuard: RL-Guided Adapter Tuning for TEE-Based Efficient & Secure On-Device Inference

DPA: A one-stop metric to measure bias amplification in classification datasets

SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning

Incentivizing Time-Aware Fairness in Data Sharing

Training-free Detection of AI-generated images via Cropping Robustness

The Fluorescent Veil: A Stealthy and Effective Physical Adversarial Patch Against Traffic Sign Recognition

Kernel-based Equalized Odds: A Quantification of Accuracy-Fairness Trade-off in Fair Representation Learning

StegoZip: Enhancing Linguistic Steganography Payload in Practice with Large Language Models

The Right to Red-Team: Adversarial AI Literacy as a Civic Imperative in K-12 Education

Nemotron-CLIMB: Clustering-based Iterative Data Mixture Bootstrapping for Language Model Pre-training

From Specificity to Generality: Revisiting Generalizable Artifacts in Detecting Face Deepfakes

Obliviator Reveals the Cost of Nonlinear Guardedness in Concept Erasure

T2SMark: Balancing Robustness and Diversity in Noise-as-Watermark for Diffusion Models

Guiding LLM Decision-Making with Fairness Reward Models

Black-Box Membership Inference Attack for LVLMs via Prior Knowledge-Calibrated Memory Probing

Mitigating Sexual Content Generation via Embedding Distortion in Text-conditioned Diffusion Models

IR-OptSet: An Optimization-Sensitive Dataset for Advancing LLM-Based IR Optimizer

Data-Juicer 2.0: Cloud-Scale Adaptive Data Processing for and with Foundation Models

PHANTOM: A Benchmark for Hallucination Detection in Financial Long-Context QA

VeriThoughts: Enabling Automated Verilog Code Generation using Reasoning and Formal Verification

Sample-Efficient Multi-Round Generative Data Augmentation for Long-Tail Instance Segmentation

Individually Fair Diversity Maximization

AgentBreeder: Mitigating the AI Safety Risks of Multi-Agent Scaffolds via Self-Improvement

Fair Minimum Labeling: Efficient Temporal Network Activations for Reachability and Equity

Fair Deepfake Detectors Can Generalize

Some Optimizers are More Equal: Understanding the Role of Optimizers in Group Fairness

Adaptive Defense against Harmful Fine-Tuning for Large Language Models via Bayesian Data Scheduler

$\mathcal{X}^2$-DFD: A framework for e$\mathcal{X}$plainable and e$\mathcal{X}$tendable Deepfake Detection

Scaling Laws For Scalable Oversight

FairImagen: Post-Processing for Bias Mitigation in Text-to-Image Models

Lie Detector: Unified Backdoor Detection via Cross-Examination Framework

Machine Unlearning in 3D Generation: A Perspective-Coherent Acceleration Framework

Perturb a Model, Not an Image: Towards Robust Privacy Protection via Anti-Personalized Diffusion Models

Differentially Private Gomory-Hu Trees

Multi-order Orchestrated Curriculum Distillation for Model-Heterogeneous Federated Graph Learning

Private Continual Counting of Unbounded Streams

Online Locally Differentially Private Conformal Prediction via Binary Inquiries

Distributionally Robust Feature Selection

RLVR-World: Training World Models with Reinforcement Learning

The Unseen Threat: Residual Knowledge in Machine Unlearning under Perturbed Samples

CALM: Culturally Self-Aware Language Models

AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents

Semantic-KG: Using Knowledge Graphs to Construct Benchmarks for Measuring Semantic Similarity

Worse than Zero-shot? A Fact-Checking Dataset for Evaluating the Robustness of RAG Against Misleading Retrievals

Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research

A Generalized Binary Tree Mechanism for Private Approximation of All-Pair Shortest Distances

Locally Optimal Private Sampling: Beyond the Global Minimax

Continual Release Moment Estimation with Differential Privacy

Convex Approximation of Two-Layer ReLU Networks for Hidden State Differential Privacy

Practical Bayes-Optimal Membership Inference Attacks

Can We Infer Confidential Properties of Training Data from LLMs?

SPFL: Sequential updates with Parallel aggregation for Enhanced Federated Learning under Category and Domain Shifts

Geometric Imbalance in Semi-Supervised Node Classification

E2E-VGuard: Adversarial Prevention for Production LLM-based End-To-End Speech Synthesis

Scalable Fingerprinting of Large Language Models

Abstract Rendering: Certified Rendering Under 3D Semantic Uncertainty

BridgePure: Limited Protection Leakage Can Break Black-Box Data Protection

VideoGameQA-Bench: Evaluating Vision-Language Models for Video Game Quality Assurance

HeavyWater and SimplexWater: Distortion-free LLM Watermarks for Low-Entropy Distributions

Blackbox Model Provenance via Palimpsestic Membership Inference

RvLLM: LLM Runtime Verification with Domain Knowledge

DiffBreak: Is Diffusion-Based Purification Robust?

AI Debate Aids Assessment of Controversial Claims

Class conditional conformal prediction for multiple inputs by p-value aggregation

Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?

Quantifying Statistical Significance of Deep Nearest Neighbor Anomaly Detection via Selective Inference

LLM Unlearning via Neural Activation Redirection

FALCON: An ML Framework for Fully Automated Layout-Constrained Analog Circuit Design

FlowRefiner: A Robust Traffic Classification Framework against Label Noise

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning

MLZero: A Multi-Agent System for End-to-end Machine Learning Automation

MigGPT: Harnessing Large Language Models for Automated Migration of Out-of-Tree Linux Kernel Patches Across Versions

BeliefMapNav: 3D Voxel-Based Belief Map for Zero-Shot Object Navigation

IDOL: Meeting Diverse Distribution Shifts with Prior Physics for Tropical Cyclone Multi-Task Estimation

SolidGeo: Measuring Multimodal Spatial Math Reasoning in Solid Geometry

MineAnyBuild: Benchmarking Spatial Planning for Open-world AI Agents

PUO-Bench: A Panel Understanding and Operation Benchmark with A Privacy-Preserving Framework

Machine Unlearning via Task Simplex Arithmetic

Fairshare Data Pricing via Data Valuation for Large Language Models

CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring

TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets

Transstratal Adversarial Attack: Compromising Multi-Layered Defenses in Text-to-Image Models

Position: Bridge the Gaps between Machine Unlearning and AI Regulation

BlurGuard: A Simple Approach for Robustifying Image Protection Against AI-Powered Editing

Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models

Graph-KV: Breaking Sequence via Injecting Structural Biases into Large Language Models

Fast-Slow Thinking GRPO for Large Vision-Language Model Reasoning

Towards Generalizable Multi-Policy Optimization with Self-Evolution for Job Scheduling

Activation-Guided Consensus Merging for Large Language Models

Each Complexity Deserves a Pruning Policy

$\text{S}^2$Q-VDiT: Accurate Quantized Video Diffusion Transformer with Salient Data and Sparse Token Distillation

Deep Compositional Phase Diffusion for Long Motion Sequence Generation

Teaching Language Models to Reason with Tools

Lessons Learned: A Multi-Agent Framework for Code LLMs to Learn and Improve

Online Segment Any 3D Thing as Instance Tracking

TITAN: A Trajectory-Informed Technique for Adaptive Parameter Freezing in Large-Scale VQE

Bridging Equivariant GNNs and Spherical CNNs for Structured Physical Domains

The Catechol Benchmark: Time-series Solvent Selection Data for Few-shot Machine Learning

MolVision: Molecular Property Prediction with Vision Language Models

RoFt-Mol: Benchmarking Robust Fine-tuning with Molecular Graph Foundation Models

All that structure matches does not glitter

A Dataset for Distilling Knowledge Priors from Literature for Therapeutic Design

Revisiting Orbital Minimization Method for Neural Operator Decomposition

GreenHyperSpectra: A multi-source hyperspectral dataset for global vegetation trait prediction

CarbonGlobe: A Global-Scale, Multi-Decade Dataset and Benchmark for Carbon Forecasting in Forest Ecosystems

Scaling Unlocks Broader Generation and Deeper Functional Understanding of Proteins

Prior-Guided Flow Matching for Target-Aware Molecule Design with Learnable Atom Number

Straight-Line Diffusion Model for Efficient 3D Molecular Generation

ProSpero: Active Learning for Robust Protein Design Beyond Wild-Type Neighborhoods

Learning 3D Anisotropic Noise Distributions Improves Molecular Force Fields

DynaPhArM: Adaptive and Physics-Constrained Modeling for Target-Drug Complexes with Drug-Specific Adaptations

FlashMD: long-stride, universal prediction of molecular dynamics

Simultaneous Modeling of Protein Conformation and Dynamics via Autoregression

RETRO SYNFLOW: Discrete Flow-Matching for Accurate and Diverse Single-Step Retrosynthesis

Enhancing Bioactivity Prediction via Spatial Emptiness Representation of Protein-ligand Complex and Union of Multiple Pockets

Implicit Generative Property Enhancer

Protein Inverse Folding From Structure Feedback

Space Group Equivariant Crystal Diffusion

Accurately Predicting Protein Mutational Effects via a Hierarchical Many-Body Attention Network

DAWP: A framework for global observation forecasting via Data Assimilation and Weather Prediction in satellite observation space

RiverMamba: A State Space Model for Global River Discharge and Flood Forecasting

RadarQA: Multi-modal Quality Analysis of Weather Radar Forecasts

CellVerse: Do Large Language Models Really Understand Cell Biology?

PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis

Generative Distribution Embeddings

CPathAgent: An Agent-based Foundation Model for Interpretable High-Resolution Pathology Image Analysis Mimicking Pathologists' Diagnostic Logic

scMRDR: A scalable and flexible framework for unpaired single-cell multi-omics data integration

Prot2Text-V2: Protein Function Prediction with Multimodal Contrastive Alignment

MedAgentBoard: Benchmarking Multi-Agent Collaboration with Conventional Methods for Diverse Medical Tasks

Multimodal Disease Progression Modeling via Spatiotemporal Disentanglement and Multiscale Alignment

MoodAngels: A Retrieval-augmented Multi-agent Framework for Psychiatry Diagnosis

Orochi: Versatile Biomedical Image Processor

Investigating and Mitigating Catastrophic Forgetting in Medical Knowledge Injection through Internal Knowledge Augmentation Learning

Magical: Medical Lay Language Generation via Semantic Invariance and Layperson-tailored Adaptation

Embracing Trustworthy Brain-Agent Collaboration as Paradigm Extension for Intelligent Assistive Technologies

System-1.5 Reasoning: Traversal in Language and Latent Spaces with Dynamic Shortcuts

Fast and Fluent Diffusion Language Models via Convolutional Decoding and Rejective Fine-tuning

Neural Correlates of Serial Dependence: Synaptic Short-term Plasticity Orchestrates Repulsion and Attraction

Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models

Lua-LLM: Learning Unstructured-Sparsity Allocation for Large Language Models

Unveiling the Learning Mind of Language Models: A Cognitive Framework and Empirical Study

Lifelong Safety Alignment for Language Models

AVCD: Mitigating Hallucinations in Audio-Visual Large Language Models through Contrastive Decoding

Creativity or Brute Force? Using Brainteasers as a Window into the Problem-Solving Abilities of Large Language Models

GRIP: A Graph-Based Reasoning Instruction Producer

CoVoMix2: Advancing Zero-Shot Dialogue Generation with Fully Non-Autoregressive Flow Matching

L-MTP: Leap Multi-Token Prediction Beyond Adjacent Context for Large Language Models

T1: A Tool-Oriented Conversational Dataset for Multi-Turn Agentic Planning

MRSAudio: A Large-Scale Multimodal Recorded Spatial Audio Dataset with Refined Annotations

UniEdit: A Unified Knowledge Editing Benchmark for Large Language Models

HawkBench: Investigating Resilience of RAG Methods on Stratified Information-Seeking Tasks

SwitchLingua: The First Large-Scale Multilingual and Multi-Ethnic Code-Switching Dataset

Filter Like You Test: Data-Driven Data Filtering for CLIP Pretraining

On Evaluating LLM Alignment by Evaluating LLMs as Judges

Generalizing Experience for Language Agents with Hierarchical MetaFlows

Skrull: Towards Efficient Long Context Fine-tuning through Dynamic Data Scheduling

Multi-agent KTO: Enhancing Strategic Interactions of Large Language Model in Language Game

Broken Tokens? Your Language Model can Secretly Handle Non-Canonical Tokenizations

Program Synthesis via Test-Time Transduction

DeepASA: An Object-Oriented Multi-Purpose Network for Auditory Scene Analysis

Edit Less, Achieve More: Dynamic Sparse Neuron Masking for Lifelong Knowledge Editing in LLMs

Chain-of-Retrieval Augmented Generation

Correlation Dimension of Autoregressive Large Language Models

ConceptScope: Characterizing Dataset Bias via Disentangled Visual Concepts

AutoJudge: Judge Decoding Without Manual Annotation

SolverLLM: Leveraging Test-Time Scaling for Optimization Problem via LLM-Guided Search

ThinkSound: Chain-of-Thought Reasoning in Multimodal LLMs for Audio Generation and Editing

Agentic Plan Caching: Test-Time Memory for Fast and Cost-Efficient LLM Agents

KORGym: A Dynamic Game Platform for LLM Reasoning Evaluation

MemSim: A Bayesian Simulator for Evaluating Memory of LLM-based Personal Assistants

Document Summarization with Conformal Importance Guarantees

Knowledge Starts with Practice: Knowledge-Aware Exercise Generative Recommendation with Adaptive Multi-Agent Cooperation

SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications

PARROT: A Benchmark for Evaluating LLMs in Cross-System SQL Translation

Dataset Distillation for Pre-Trained Self-Supervised Vision Models

FairDICE: Fairness-Driven Offline Multi-Objective Reinforcement Learning

Offline Actor-Critic for Average Reward MDPs

Uncertainty-Guided Exploration for Efficient AlphaZero Training

AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning

A-Mem: Agentic Memory for LLM Agents

Dynamical modeling of nonlinear latent factors in multiscale neural activity with real-time inference

S$^2$NN: Sub-bit Spiking Neural Networks

Efficient Allocation of Working Memory Resource for Utility Maximization in Humans and Recurrent Neural Networks

What Moves the Eyes: Doubling Mechanistic Model Performance Using Deep Networks to Discover and Test Cognitive Hypotheses

Hierarchical Frequency Tagging Probe (HFTP): A Unified Approach to Investigate Syntactic Structure Representations in Large Language Models and the Human Brain

SynBrain: Enhancing Visual-to-fMRI Synthesis via Probabilistic Representation Learning

Shaping Sequence Attractor Schema in Recurrent Neural Networks

Learning Dynamics of RNNs in Closed-Loop Environments

Identifying multi-compartment Hodgkin-Huxley models with high-density extracellular voltage recordings

Slow Transition to Low-Dimensional Chaos in Heavy-Tailed Recurrent Neural Networks

Mind the GAP! The Challenges of Scale in Pixel-based Deep Reinforcement Learning

ZEBRA: Towards Zero-Shot Cross-Subject Generalization for Universal Brain Visual Decoding

Modelling the control of offline processing with reinforcement learning

Decomposing motor units through elimination for real-time intention driven assistive neurotechnology

Meta-Learning an In-Context Transformer Model of Human Higher Visual Cortex

In Silico Mapping of Visual Categorical Selectivity Across the Whole Brain

Memory by accident: a theory of learning as a byproduct of network stabilization

No Experts, No Problem: Avoidance Learning from Bad Demonstrations

IOSTOM: Offline Imitation Learning from Observations via State Transition Occupancy Matching

Asymmetric REINFORCE for off-Policy Reinforcement Learning: Balancing positive and negative rewards

A Temporal Difference Method for Stochastic Continuous Dynamics

Dyn-O: Building Structured World Models with Object-Centric Representations

Large Language Models Think Too Fast To Explore Effectively

BrainEC-LLM: Brain Effective Connectivity Estimation by Multiscale Mixing LLM

Large Language Models as Model Organisms for Human Associative Learning

AutoToM: Scaling Model-based Mental Inference via Automated Agent Modeling

Interpretable Next-token Prediction via the Generalized Induction Head

DAAC: Discrepancy-Aware Adaptive Contrastive Learning for Medical Time series

Brain Harmony: A Multimodal Foundation Model Unifying Morphology and Function into 1D Tokens

A Generalist Intracortical Motor Decoder

PHYBench: Holistic Evaluation of Physical Perception and Reasoning in Large Language Models

Improving Energy Natural Gradient Descent through Woodbury, Momentum, and Randomization

Neural Tangent Knowledge Distillation for Optical Convolutional Networks

Hierarchical Implicit Neural Emulators

UEPI: Universal Energy-Behavior-Preserving Integrators for Energy Conservative/Dissipative Differential Equations

Predicting partially observable dynamical systems via diffusion models with a multiscale inference scheme

PDEfuncta: Spectrally-Aware Neural Representation for PDE Solution Modeling

Mixture-of-Experts Operator Transformer for Large-Scale PDE Pre-Training

DynaGuide: Steering Diffusion Polices with Active Dynamic Guidance

Scaffolding Dexterous Manipulation with Vision-Language Models

CAML: Collaborative Auxiliary Modality Learning for Multi-Agent Systems

SDTagNet: Leveraging Text-Annotated Navigation Maps for Online HD Map Construction

KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills

Self-Improving Embodied Foundation Models

Tree-Guided Diffusion Planner

Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2)

TopoPoint: Enhance Topology Reasoning via Endpoint Detection in Autonomous Driving

Adversarial Locomotion and Motion Imitation for Humanoid Policy Learning

VIKI‑R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning

Lost in Latent Space: An Empirical Study of Latent Diffusion Models for Physics Emulation

A Plug-and-Play Query Synthesis Active Learning Framework for Neural PDE Solvers

Latent Mixture of Symmetries for Sample-Efficient Dynamic Learning

Physics-informed machine learning with domain decomposition and global dynamics for three-dimensional intersecting flows

Stable Port-Hamiltonian Neural Networks

EddyFormer: Accelerated Neural Simulations of Three-Dimensional Turbulence at Scale

RIGNO: A Graph-based Framework For Robust And Accurate Operator Learning For PDEs On Arbitrary Domains

From Experts to a Generalist: Toward General Whole-Body Control for Humanoid Robots

DexGarmentLab: Dexterous Garment Manipulation Environment with Generalizable Policy

DriveDPO: Policy Learning via Safety DPO For End-to-End Autonomous Driving

BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models

World-aware Planning Narratives Enhance Large Vision-Language Model Planner

URDF-Anything: Constructing Articulated Objects with 3D Multimodal Language Model

Exploring the Limits of Vision-Language-Action Manipulation in Cross-task Generalization

EnerVerse: Envisioning Embodied Future Space for Robotics Manipulation

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization

Generalizable Domain Adaptation for Sim-and-Real Policy Co-Training

TraffiDent: A Dataset for Understanding the Interplay Between Traffic Dynamics and Incidents

Benchmarking Spatiotemporal Reasoning in LLMs and Reasoning Models: Capabilities and Challenges

RHYTHM: Reasoning with Hierarchical Temporal Tokenization for Human Mobility

Forging Time Series with Language: A Large Language Model Approach to Synthetic Data Generation

Distilled Decoding 2: One-step Sampling of Image Auto-regressive Models with Conditional Score Distillation

TRACE: Grounding Time Series in Context for Multimodal Embedding and Retrieval

On the Universal Near Optimality of Hedge in Combinatorial Settings

Less but More: Linear Adaptive Graph Learning Empowering Spatiotemporal Forecasting

Orthogonal Survival Learners for Estimating Heterogeneous Treatment Effects from Time-to-Event Data

GST-UNet: A Neural Framework for Spatiotemporal Causal Inference with Time-Varying Confounding

Differentially Private Federated Low Rank Adaptation Beyond Fixed-Matrix

Heterogeneous Diffusion Structure Inference for Network Cascade

Faster Generic Identification in Tree-Shaped Structural Causal Models

Improving Target Sound Extraction via Disentangled Codec Representations with Privileged Knowledge Distillation

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior

From Euler to AI: Unifying Formulas for Mathematical Constants

MobileUse: A Hierarchical Reflection-Driven GUI Agent for Autonomous Mobile Operation

DynaNav: Dynamic Feature and Layer Selection for Efficient Visual Navigation

Self-Supervised Learning of Graph Representations for Network Intrusion Detection

Resounding Acoustic Fields with Reciprocity

VLMLight: Safety-Critical Traffic Signal Control via Vision-Language Meta-Control and Dual-Branch Reasoning Architecture

Open CaptchaWorld: A Comprehensive Web-based Platform for Testing and Benchmarking Multimodal LLM Agents

AlgoTune: Can Language Models Speed Up General-Purpose Numerical Programs?

Multivariate Time Series Anomaly Detection with Idempotent Reconstruction

Diffusion Transformers as Open-World Spatiotemporal Foundation Models

Less is More: Unlocking Specialization of Time Series Foundation Models via Structured Pruning

Adaptive Data-Borrowing for Improving Treatment Effect Estimation using External Controls

Causal Discovery over Clusters of Variables in Markovian Systems

Evaluating and Learning Optimal Dynamic Treatment Regimes under Truncation by Death

Counterfactual reasoning: an analysis of in-context emergence

Disentanglement Beyond Static vs. Dynamic: A Benchmark and Evaluation Framework for Multi-Factor Sequential Representations

Self-supervised Learning of Echocardiographic Video Representations via Online Cluster Distillation

CoUn: Empowering Machine Unlearning via Contrastive Learning

Learning to Specialize: Joint Gating-Expert Training for Adaptive MoEs in Decentralized Settings

Object-Centric Concept-Bottlenecks

Latent Space Factorization in LoRA

CodeCrash: Exposing LLM Fragility to Misleading Natural Language in Code Reasoning

Incomplete Multi-view Clustering via Hierarchical Semantic Alignment and Cooperative Completion

Flow Equivariant Recurrent Neural Networks

Anchor-based Maximum Discrepancy for Relative Similarity Testing

Scaling Language-centric Omnimodal Representation Learning

MaxSup: Overcoming Representation Collapse in Label Smoothing

Revolutionizing Graph Aggregation: From Suppression to Amplification via BoostGCN

Learning Shared Representations from Unpaired Data

Scalable Signature Kernel Computations via Local Neumann Series Expansions

UMU-Bench: Closing the Modality Gap in Multimodal Unlearning Evaluation

SGCD: Stain-Guided CycleDiffusion for Unsupervised Domain Adaptation of Histopathology Image Classification

Aggregation Hides Out-of-Distribution Generalization Failures from Spurious Correlations

Learning to Learn with Contrastive Meta-Objective

Multi-Objective One-Shot Pruning for Large Language Models

Semi-Supervised Regression with Heteroscedastic Pseudo-Labels

TabSTAR: A Tabular Foundation Model for Tabular Data with Text Fields

Learning Task-Agnostic Representations through Multi-Teacher Distillation

Understanding Bias Terms in Neural Representations

OOD Detection with Relative Angles

Mitra: Mixed Synthetic Priors for Enhancing Tabular Foundation Models

Understanding and Enhancing Mask-Based Pretraining towards Universal Representations

A Closer Look at TabPFN v2: Understanding Its Strengths and Extending Its Capabilities

Hierarchical Retrieval: The Geometry and a Pretrain-Finetune Recipe

T-REGS: Minimum Spanning Tree Regularization for Self-Supervised Learning

Aligning Compound AI Systems via System-level DPO

Gaussian Regression-Driven Tensorized Incomplete Multi-View Clustering with Dual Manifold Regularization

CARE: Decoding-Time Safety Alignment via Rollback and Introspection Intervention

Neural Mutual Information Estimation with Vector Copulas

Rethinking PCA Through Duality

Estimating Model Performance Under Covariate Shift Without Labels

Online Functional Tensor Decomposition via Continual Learning for Streaming Data Completion

Fréchet Geodesic Boosting

AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench

Beyond Modality Collapse: Representation Blending for Multimodal Dataset Distillation

Value Diffusion Reinforcement Learning

Enhancing Deep Batch Active Learning for Regression with Imperfect Data Guided Selection

EraseFlow: Learning Concept Erasure Policies via GFlowNet-Driven Alignment

Gatekeeper: Improving Model Cascades Through Confidence Tuning

Rethinking Hebbian Principle: Low-Dimensional Structural Projection for Unsupervised Learning

The Flood Complex: Large-Scale Persistent Homology on Millions of Points

Uniform Generalization Bounds on Data-Dependent Hypothesis Sets via PAC-Bayesian Theory on Random Sets

Pseudo-Labeling for Kernel Ridge Regression under Covariate Shift

Why Playing Against Diverse and Challenging Opponents Speeds Up Coevolution: A Theoretical Analysis on Combinatorial Games

Truthful Aggregation of LLMs with an Application to Online Advertising

From Average-Iterate to Last-Iterate Convergence in Games: A Reduction and Its Applications

Last Iterate Convergence in Monotone Mean Field Games

Thresholds for sensitive optimality and Blackwell optimality in stochastic games

Efficient Kernelized Learning in Polyhedral Games beyond Full Information: From Colonel Blotto to Congestion Games

Multi-Agent Learning under Uncertainty: Recurrence vs. Concentration

Solving Neural Min-Max Games: The Role of Architecture, Initialization & Dynamics

Mechanism Design for LLM Fine-tuning with Multiple Reward Models

Lifelong Test-Time Adaptation via Online Learning in Tracked Low-Dimensional Subspace

Data Selection Matters: Towards Robust Instruction Tuning of Large Multimodal Models

Conformal Prediction under Lévy-Prokhorov Distribution Shifts: Robustness to Local and Global Perturbations

Composing Linear Layers from Irreducibles

Adversarial Graph Fusion for Incomplete Multi-view Semi-supervised Learning with Tensorial Imputation

Entropy-Calibrated Label Distribution Learning

MisoDICE: Multi-Agent Imitation from Mixed-Quality Demonstrations

Asymptotically Stable Quaternion-valued Hopfield-structured Neural Network with Periodic Projection-based Supervised Learning Rules

Bivariate Matrix-valued Linear Regression (BMLR): Finite-sample performance under Identifiability and Sparsity Assumptions

Replicable Online pricing

Consistency Conditions for Differentiable Surrogate Losses

How Data Mixing Shapes In-Context Learning: Asymptotic Equivalence for Transformers with MLPs

Assessing the quality of denoising diffusion models in Wasserstein distance: noisy score and optimal bounds

Median Selection with Noisy and Structural Information

Any-stepsize Gradient Descent for Separable Data under Fenchel–Young Losses

Hybrid Re-matching for Continual Learning with Parameter-Efficient Tuning

Online Prediction with Limited Selectivity

Enhancing Vision-Language Model Reliability with Uncertainty-Guided Dropout Decoding

Simultaneous Swap Regret Minimization via KL-Calibration

A Geometric Analysis of PCA

Stabilizing LTI Systems under Partial Observability: Sample Complexity and Fundamental Limits

Sharp Matrix Empirical Bernstein Inequalities

Learning from Interval Targets

Learning-Augmented Streaming Algorithms for Correlation Clustering

PAC-Bayes Bounds for Multivariate Linear Regression and Linear Autoencoders

Heterogeneous Graph Transformers for Simultaneous Mobile Multi-Robot Task Allocation and Scheduling under Temporal Constraints

Learning and Planning Multi-Agent Tasks via an MoE-based World Model

Policy Gradient Methods Converge Globally in Imperfect-Information Extensive-Form Games

Rainbow Delay Compensation: A Multi-Agent Reinforcement Learning Framework for Mitigating Observation Delays

High-order Interactions Modeling for Interpretable Multi-Agent Q-Learning

In-Context Fully Decentralized Cooperative Multi-Agent Reinforcement Learning

Bayesian Ego-graph inference for Networked Multi-Agent Reinforcement Learning

Multi-Agent Reinforcement Learning with Communication-Constrained Priors

EconGym: A Scalable AI Testbed with Diverse Economic Tasks

Comparator-Adaptive $\Phi$-Regret: Improved Bounds, Simpler Algorithms, and Applications to Games

Normalization in Attention Dynamics

How Many Domains Suffice for Domain Generalization? A Tight Characterization via the Domain Shattering Dimension

Nonlinear Laplacians: Tunable principal component analysis under directional prior information

Sample-Adaptivity Tradeoff in On-Demand Sampling

Low-degree evidence for computational transition of recovery rate in stochastic block model

Concentration and excess risk bounds for imbalanced classification with synthetic oversampling

Stability and Oracle Inequalities for Optimal Transport Maps between General Distributions

Unlabeled Data Can Provably Enhance In-Context Learning of Transformers

Is the acquisition worth the cost? Surrogate losses for Consistent Two-stage Classifiers

VolleyBots: A Testbed for Multi-Drone Volleyball Game Combining Motion Control and Strategic Play

Subsampled Ensemble Can Improve Generalization Tail Exponentially

Factorio Learning Environment

Prompt Tuning Decision Transformers with Structured and Scalable Bandits

Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learning

1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities

Hadamax Encoding: Elevating Performance in Model-Free Atari

Robust Regression of General ReLUs with Queries

The $\varphi$ Curve: The Shape of Generalization through the Lens of Norm-based Capacity Control

Last-Iterate Convergence of Smooth Regret Matching$^+$ Variants in Learning Nash Equilibria

Globally Optimal Policy Gradient Algorithms for Reinforcement Learning with PID Control Policies

Learning Juntas under Markov Random Fields

Error Forcing in Recurrent Neural Networks

Bridging Distributional and Risk-sensitive Reinforcement Learning with Provable Regret Bounds

No-Regret Thompson Sampling for Finite-Horizon Markov Decision Processes with Gaussian Processes

Finite Sample Analysis of Linear Temporal Difference Learning with Arbitrary Features

Global Convergence for Average Reward Constrained MDPs with Primal-Dual Actor Critic Algorithm

Sample Complexity of Distributionally Robust Average-Reward Reinforcement Learning

The Structural Complexity of Matrix-Vector Multiplication

Pairwise Calibrated Rewards for Pluralistic Alignment

Structure-Aware Spectral Sparsification via Uniform Edge Sampling

Closed-Form Training Dynamics Reveal Learned Features and Linear Structure in Word2Vec-like Models

Hadamard Test is Sufficient for Efficient Quantum Gradient Estimation with Lie Algebraic Symmetries

Asymptotics of SGD in Sequence-Single Index Models and Single-Layer Attention Networks

Foundations of Top-$k$ Decoding for Language Models

Neural Collapse under Gradient Flow on Shallow ReLU Networks for Orthogonally Separable Data

Simple and Optimal Sublinear Algorithms for Mean Estimation

Stochastic Shortest Path with Sparse Adversarial Costs

Preference-based Reinforcement Learning beyond Pairwise Comparisons: Benefits of Multiple Options

Analytic Energy-Guided Policy Optimization for Offline Reinforcement Learning

On the Global Optimality of Policy Gradient Methods in General Utility Reinforcement Learning

Distances for Markov chains from sample streams

Optimal Single-Policy Sample Complexity and Transient Coverage for Average-Reward Offline RL

An Improved Algorithm for Adversarial Linear Contextual Bandits via Reduction

Beyond Average Value Function in Precision Medicine: Maximum Probability-Driven Reinforcement Learning for Survival Analysis

Linear Mixture Distributionally Robust Markov Decision Processes

On the Entropy Calibration of Language Models

Estimation of Stochastic Optimal Transport Maps

Distance Adaptive Beam Search for Provably Accurate Graph-Based Nearest Neighbor Search

On Extending Direct Preference Optimization to Accommodate Ties

Dynamic Bundling with Large Language Models for Zero-Shot Inference on Text-Attributed Graphs

DLoFT: Gradient-Decoupled Fine-Tuning for Generalizable Long Chain-of-Thought Reasoning

AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks

Universal Cross-Tokenizer Distillation via Approximate Likelihood Matching

SpectraLDS: Provable Distillation for Linear Dynamical Systems

Convex Potential Mirror Langevin Algorithm for Efficient Sampling of Energy-Based Models

Bi-Level Decision-Focused Causal Learning for Large-Scale Marketing Optimization: Bridging Observational and Experimental Data

Learning to Solve Complex Problems via Dataset Decomposition

Whitened Score Diffusion: A Structured Prior for Imaging Inverse Problems

Mind the Gap: Removing the Discretization Gap in Differentiable Logic Gate Networks

HPSERec: A Hierarchical Partitioning and Stepwise Enhancement Framework for Long-tailed Sequential Recommendation

Layer as Puzzle Pieces: Compressing Large Language Models through Layer Concatenation

PoLAR: Polar-Decomposed Low-Rank Adapter Representation

ModHiFi: Identifying High Fidelity predictive components for Model Modification

FlyLoRA: Boosting Task Decoupling and Parameter Efficiency via Implicit Rank-Wise Mixture-of-Experts

A Partition Cover Approach to Tokenization

Belief-Calibrated Multi-Agent Consensus Seeking for Complex NLP Tasks

Positional Fragility in LLMs: How Offset Effects Reshape Our Understanding of Memorization Risks

Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?

Distributional Autoencoders Know the Score

NeuroGenPoisoning: Neuron-Guided Attacks on Retrieval-Augmented Generation of LLM via Genetic Optimization of External Knowledge

The ML.ENERGY Benchmark: Toward Automated Inference Energy Measurement and Optimization

Transformers Learn Faster with Semantic Focus

Attention (as Discrete-Time Markov) Chains

Attention Sinks: A 'Catch, Tag, Release' Mechanism for Embeddings

Multi-head Temporal Latent Attention

Linear Transformers Implicitly Discover Unified Numerical Algorithms

Two Heads are Better than One: Simulating Large Transformers with Small Ones

Efficient Low Rank Attention for Long-Context Inference in Large Language Models

Recurrent Self-Attention Dynamics: An Energy-Agnostic Perspective from Jacobians

GSPN-2: Efficient Parallel Sequence Modeling

Titans: Learning to Memorize at Test Time

UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression

Mind the Quote: Enabling Quotation-Aware Dialogue in LLMs via Plug-and-Play Modules

Enforcing convex constraints in Graph Neural Networks

Reinforcement Learning Teachers of Test Time Scaling

Training Language Models to Reason Efficiently

Exploring Diffusion Transformer Designs via Grafting

Nabla-R2D3: Effective and Efficient 3D Diffusion Alignment with 2D Rewards

Dependency Matters: Enhancing LLM Reasoning with Explicit Knowledge Grounding

Fourier Token Merging: Understanding and Capitalizing Frequency Domain for Efficient Image Generation

Remasking Discrete Diffusion Models with Inference-Time Scaling

Beyond Oracle: Verifier-Supervision for Instruction Hierarchy in Reasoning and Instruction-Tuned LLMs

Preference Optimization by Estimating the Ratio of the Data Distribution

Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning

Deep Taxonomic Networks for Unsupervised Hierarchical Prototype Discovery

Sample and Map from a Single Convex Potential: Generation using Conjugate Moment Measures

Measuring and Guiding Monosemanticity

Riemannian Consistency Model

BioCG: Constrained Generative Modeling for Biochemical Interaction Prediction

Linearly Constrained Diffusion Implicit Models

Accelerated Sampling from Masked Diffusion Models via Entropy Bounded Unmasking

Neural MJD: Neural Non-Stationary Merton Jump Diffusion for Time Series Prediction

MRO: Enhancing Reasoning in Diffusion Language Models via Multi-Reward Optimization

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache

HOI-Dyn: Learning Interaction Dynamics for Human-Object Motion Diffusion

Simple and Efficient Heterogeneous Temporal Graph Neural Network

Stealthy Yet Effective: Distribution-Preserving Backdoor Attacks on Graph Classification

OCN: Effectively Utilizing Higher-Order Common Neighbors for Better Link Prediction

Adjusted Count Quantification Learning on Graphs

Towards Pre-trained Graph Condensation via Optimal Transport

How Particle System Theory Enhances Hypergraph Message Passing

Architectural and Inferential Inductive Biases for Exchangeable Sequence Modeling

HumanoidGen: Data Generation for Bimanual Dexterous Manipulation via LLM Reasoning

Let LRMs Break Free from Overthinking via Self-Braking Tuning

Topology-aware Graph Diffusion Model with Persistent Homology

Chain-of-Model Learning for Language Model

Learning to Insert for Constructive Neural Vehicle Routing Solver

Compositional Monte Carlo Tree Diffusion for Extendable Planning

Neptune-X: Active X-to-Maritime Generation for Universal Maritime Object Detection

MF-LLM: Simulating Population Decision Dynamics via a Mean-Field Large Language Model Framework

What's Producible May Not Be Reachable: Measuring the Steerability of Generative Models

Discrete Spatial Diffusion: Intensity-Preserving Diffusion Modeling

Superposition Yields Robust Neural Scaling

Next Semantic Scale Prediction via Hierarchical Diffusion Language Models

MURKA: Multi-Reward Reinforcement Learning with Knowledge Alignment for Optimization Tasks

GMV: A Unified and Efficient Graph Multi-View Learning Framework

Diffusion-Based Hierarchical Graph Neural Networks for Simulating Nonlinear Solid Mechanics

Learning Individual Behavior in Agent-Based Models with Graph Diffusion Networks

L2DGCN: Learnable Enhancement and Label Selection Dynamic Graph Convolutional Networks for Mitigating Degree Bias

Generalizable Insights for Graph Transformers in Theory and Practice

You Only Spectralize Once: Taking a Spectral Detour to Accelerate Graph Neural Network

On topological descriptors for graph products

Axial Neural Networks for Dimension-Free Foundation Models

Relieving the Over-Aggregating Effect in Graph Transformers

A CLT for Polynomial GNNs on Community-Based Graphs

Sketch-Augmented Features Improve Learning Long-Range Dependencies in Graph Neural Networks

HyperMixup: Hypergraph-Augmented with Higher-order Information Mixup

Mixture of Scope Experts at Test: Generalizing Deeper Graph Neural Networks with Shallow Variants

Graph-Theoretic Insights into Bayesian Personalized Ranking for Recommendation

TAMI: Taming Heterogeneity in Temporal Interactions for Temporal Graph Link Prediction

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones

Scalable Valuation of Human Feedback through Provably Robust Model Alignment

StyleGuard: Preventing Text-to-Image-Model-based Style Mimicry Attacks by Style Perturbations

SAFEx: Analyzing Vulnerabilities of MoE-Based LLMs via Stable Safety-critical Expert Identification

SilentStriker: Toward Stealthy Bit-Flip Attacks on Large Language Models

CoreGuard: Safeguarding Foundational Capabilities of LLMs Against Model Stealing in Edge Deployment

L$^2$M: Mutual Information Scaling Law for Long-Context Language Modeling

Learning with Restricted Boltzmann Machines: Asymptotics of AMP and GD in High Dimensions

Neural Collapse in Cumulative Link Models for Ordinal Regression: An Analysis with Unconstrained Feature Model

Knee-Deep in C-RASP: A Transformer Depth Hierarchy

MAP Estimation with Denoisers: Convergence Rates and Guarantees

Vocabulary In-Context Learning in Transformers: Benefits of Positional Encoding

Consistency of Physics-Informed Neural Networks for Second-Order Elliptic Equations

The Cost of Robustness: Tighter Bounds on Parameter Complexity for Robust Memorization in ReLU Nets

Structured Linear CDEs: Maximally Expressive and Parallel-in-Time Sequence Models

When Models Don’t Collapse: On the Consistency of Iterative MLE

Just One Layer Norm Guarantees Stable Extrapolation

Neural Networks Generalize on Low Complexity Data

A Geometrical Analysis of Kernel Ridge Regression and its Applications

AdaptDel: Adaptable Deletion Rate Randomized Smoothing for Certified Robustness

SeCon-RAG: A Two-Stage Semantic Filtering and Conflict-Free Framework for Trustworthy RAG

On the Robustness of Verbal Confidence of LLMs in Adversarial Attacks

Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Models

Generating and Checking DNN Verification Proofs

DepthVanish: Optimizing Adversarial Interval Structures for Stereo-Depth-Invisible Patches

On Feasible Rewards in Multi-Agent Inverse Reinforcement Learning

Cost-Aware Contrastive Routing for LLMs

RAPTR: Radar-based 3D Pose Estimation using Transformer

Diversity-Aware Policy Optimization for Large Language Model Reasoning

AdaMSS: Adaptive Multi-Subspace Approach for Parameter-Efficient Fine-Tuning

PIVNO: Particle Image Velocimetry Neural Operator

Memory Decoder: A Pretrained, Plug-and-Play Memory for Large Language Models

Complexity Scaling Laws for Neural Models using Combinatorial Optimization

SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning

DartQuant: Efficient Rotational Distribution Calibration for LLM Quantization

ShorterBetter: Guiding Reasoning Models to Find Optimal Inference Length for Efficient Reasoning

MindForge: Empowering Embodied Agents with Theory of Mind for Lifelong Cultural Learning

QuadEnhancer: Leveraging Quadratic Transformations to Enhance Deep Neural Networks

REP: Resource-Efficient Prompting for Rehearsal-Free Continual Learning

FUDOKI: Discrete Flow-based Unified Understanding and Generation via Kinetic-Optimal Velocities

Context-Aware Hierarchical Learning: A Two-Step Paradigm towards Safer LLMs

Scaling Law with Learning Rate Annealing

Adaptive Gradient Masking for Balancing ID and MLLM-based Representations in Recommendation

Feature-Based Instance Neighbor Discovery: Advanced Stable Test-Time Adaptation in Dynamic World

ARIA: Training Language Agents with Intention-driven Reward Aggregation

Revitalizing SVD for Global Covariance Pooling: Halley’s Method to Overcome Over-Flattening

Robust Hallucination Detection in LLMs via Adaptive Token Selection

Estimation and Inference in Distributional Reinforcement Learning

Reasoning Gym: Reasoning Environments for Reinforcement Learning with Verifiable Rewards

Graph Neural Network Based Action Ranking for Planning

ResponseRank: Data-Efficient Reward Modeling through Preference Strength Learning

CoT Information: Improved Sample Complexity under Chain-of-Thought Supervision

Prompted Policy Search: Reinforcement Learning through Linguistic and Numerical Reasoning in LLMs

Improving Reward Models with Proximal Policy Exploration for Preference-Based Reinforcement Learning

Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models

OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation

MultiHuman-Testbench: Benchmarking Image Generation for Multiple Humans

Normal-Abnormal Guided Generalist Anomaly Detection

FALQON: Accelerating LoRA Fine-tuning with Low-Bit Floating-Point Arithmetic

Accurate and Efficient Low-Rank Model Merging in Core Space

Continuous Thought Machines

HiMoLE: Towards OOD-Robust LoRA via Hierarchical Mixture of Experts

How Does Sequence Modeling Architecture Influence Base Capabilities of Pre-trained Language Models? Exploring Key Architecture Design Principles to Avoid Base Capabilities Degradation

LASeR: Learning to Adaptively Select Reward Models with Multi-Arm Bandits

Preserving Task-Relevant Information Under Linear Concept Removal

GoalLadder: Incremental Goal Discovery with Vision-Language Models

EvaLearn: Quantifying the Learning Capability and Efficiency of LLMs via Sequential Problem Solving

Federated Dialogue-Semantic Diffusion for Emotion Recognition under Incomplete Modalities

Constrained Best Arm Identification

WHAT MAKES MATH PROBLEMS HARD FOR REINFORCEMENT LEARNING: A CASE STUDY

SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution

GUI Exploration Lab: Enhancing Screen Navigation in Agents via Multi-Turn Reinforcement Learning

Contextual Integrity in LLMs via Reasoning and Reinforcement Learning

Martian World Model: Controllable Video Synthesis with Physically Accurate 3D Reconstructions

ImgEdit: A Unified Image Editing Dataset and Benchmark

BlurDM: A Blur Diffusion Model for Image Deblurring

Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation

FlexVAR: Flexible Visual Autoregressive Modeling without Residual Prediction

Deno-IF: Unsupervised Noisy Visible and Infrared Image Fusion Method

Fast constrained sampling in pre-trained diffusion models

NEP: Autoregressive Image Editing via Next Editing Token Prediction

Switchable Token-Specific Codebook Quantization For Face Image Compression

SPRO: Improving Image Generation via Self-Play

FlashMo: Geometric Interpolants and Frequency-Aware Sparsity for Scalable Efficient Motion Generation

UMAMI: Unifying Masked Autoregressive Models and Deterministic Rendering for View Synthesis

Dynamic Shadow Unveils Invisible Semantics for Video Outpainting

FLOWING: Implicit Neural Flows for Structure-Preserving Morphing

VideoMAR: Autoregressive Video Generation with Continuous Tokens

Kernel Density Steering: Inference-Time Scaling via Mode Seeking for Image Restoration

AutoEdit: Automatic Hyperparameter Tuning for Image Editing

Force Prompting: Video Generation Models Can Learn And Generalize Physics-based Control Signals

LoRAShop: Training-Free Multi-Concept Image Generation and Editing with Rectified Flow Transformers

Scaling Diffusion Transformers Efficiently via $\mu$P

Temporal In‑Context Fine‑Tuning for Versatile Control of Video Diffusion Models

Overcoming Challenges of Long-Horizon Prediction in Driving World Models

Ambient Diffusion Omni: Training Good Models with Bad Data

A Minimalistic Unified Framework for Incremental Learning across Image Restoration Tasks

UltraHR-100K: Enhancing UHR Image Synthesis with A Large-Scale High-Quality Dataset

Foundation Cures Personalization: Improving Personalized Models’ Prompt Consistency via Hidden Foundation Knowledge

ASDSV: Multimodal Generation Made Efficient with Approximate Speculative Diffusion and Speculative Verification

Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment

Re-ttention: Ultra Sparse Visual Generation via Attention Statistical Reshape

Learning World Models for Interactive Video Generation

From Programs to Poses: Factored Real-World Scene Generation via Learned Program Libraries

From Cradle to Cane: A Two-Pass Framework for High-Fidelity Lifespan Face Aging

SparseDiT: Token Sparsification for Efficient Diffusion Transformer

Balanced Conic Rectified Flow

SplitFlow: Flow Decomposition for Inversion-Free Text-to-Image Editing

Where and How to Perturb: On the Design of Perturbation Guidance in Diffusion and Flow Models

NFIG: Multi-Scale Autoregressive Image Generation via Frequency Ordering

Mitigating Occlusions in Virtual Try-On via A Simple-Yet-Effective Mask-Free Framework

Align Your Flow: Scaling Continuous-Time Flow Map Distillation

Consistent Story Generation: Unlocking the Potential of Zigzag Sampling

WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perception

Locality in Image Diffusion Models Emerges from Data Statistics

Hierarchical Fine-grained Preference Optimization for Physically Plausible Video Generation

Semantic and Visual Crop-Guided Diffusion Models for Heterogeneous Tissue Synthesis in Histopathology

Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents

Spik-NeRF: Spiking Neural Networks for Neural Radiance Fields

ProDyG: Progressive Dynamic Scene Reconstruction via Gaussian Splatting from Monocular Videos

VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold

SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction

FHGS: Feature-Homogenized Gaussian Splatting

SIU3R: Simultaneous Scene Understanding and 3D Reconstruction Beyond Feature Alignment

DGH: Dynamic Gaussian Hair

TrackingWorld: World-centric Monocular 3D Tracking of Almost All Pixels

EF-3DGS: Event-Aided Free-Trajectory 3D Gaussian Splatting

Eve3D: Elevating Vision Models for Enhanced 3D Surface Reconstruction via Gaussian Splatting

Unifying Appearance Codes and Bilateral Grids for Driving Scene Gaussian Splatting

Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videos

Enhancing 3D Reconstruction for Dynamic Scenes

KaRF: Weakly-Supervised Kolmogorov-Arnold Networks-based Radiance Fields for Local Color Editing

Orientation-anchored Hyper-Gaussian for 4D Reconstruction from Casual Videos

BecomingLit: Relightable Gaussian Avatars with Hybrid Neural Shading

Rectified Point Flow: Generic Point Cloud Pose Estimation

LinPrim: Linear Primitives for Differentiable Volumetric Rendering

PLANA3R: Zero-shot Metric Planar 3D Reconstruction via Feed-forward Planar Splatting

Unified 2D-3D Discrete Priors for Noise-Robust and Calibration-Free Multiview 3D Human Pose Estimation

GeGS-PCR: Fast and Robust Color 3D Point Cloud Registration with Two-Stage Geometric-3DGS Fusion

MesaTask: Towards Task-Driven Tabletop Scene Generation via 3D Spatial Reasoning

NopeRoomGS: Indoor 3D Gaussian Splatting Optimization without Camera Pose Input

Evaluating Robustness of Monocular Depth Estimation with Procedural Scene Perturbations

DC4GS: Directional Consistency-Driven Adaptive Density Control for 3D Gaussian Splatting

Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimation

Cycle-Sync: Robust Global Camera Pose Estimation through Enhanced Cycle-Consistent Synchronization

Holistic Large-Scale Scene Reconstruction via Mixed Gaussian Splatting

ZPressor: Bottleneck-Aware Compression for Scalable Feed-Forward 3DGS

Novel View Synthesis from A Few Glimpses via Test-Time Natural Video Completion

SeePhys: Does Seeing Help Thinking? – Benchmarking Vision-Based Physics Reasoning

From Objects to Anywhere: A Holistic Benchmark for Multi-level Visual Grounding in 3D Scenes

Hyperphantasia: A Benchmark for Evaluating the Mental Visualization Capabilities of Multimodal LLMs

Fire360: A Benchmark for Robust Perception and Episodic Memory in Degraded 360° Firefighting Video

CrypticBio: A Large Multimodal Dataset for Visually Confusing Species

EgoExoBench: A Benchmark for First- and Third-person View Video Understanding in MLLMs

MONITRS: Multimodal Observations of Natural Incidents Through Remote Sensing

MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video Scenarios

IndEgo: A Dataset of Industrial Scenarios and Collaborative Work for Egocentric Assistants

Impromptu VLA: Open Weights and Open Data for Driving Vision-Language-Action Models

InfoChartQA: A Benchmark for Multimodal Question Answering on Infographic Charts

Table2LaTeX-RL: High-Fidelity LaTeX Code Generation from Table Images via Reinforced Multimodal Language Models

Recurrent Attention-based Token Selection for Efficient Streaming Video-LLMs

VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Set

Eyes Wide Open: Ego Proactive Video-LLM for Streaming Video

Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling

Gaze Beyond the Frame: Forecasting Egocentric 3D Visual Span

Adaptive Re-calibration Learning for Balanced Multimodal Intention Recognition

Actial: Activate Spatial Reasoning Ability of Multimodal Large Language Models

Self-alignment of Large Video Language Models with Refined Regularized Preference Optimization

Amplifying Prominent Representations in Multimodal Learning via Variational Dirichlet Process

RadZero: Similarity-Based Cross-Attention for Explainable Vision-Language Alignment in Chest X-ray with Zero-Shot Multi-Task Capability

Image Token Matters: Mitigating Hallucination in Discrete Tokenizer-based Large Vision-Language Models via Latent Editing

Partition-Then-Adapt: Combating Prediction Bias for Reliable Multi-Modal Test-Time Adaptation

Prioritizing Perception-Guided Self-Supervision: A New Paradigm for Causal Modeling in End-to-End Autonomous Driving

Advancing Compositional Awareness in CLIP with Efficient Fine-Tuning

Elastic ViTs from Pretrained Models without Retraining

RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics

ROVER: Recursive Reasoning Over Videos with Vision-Language Models for Embodied Tasks

UniViT: Unifying Image and Video Understanding in One Vision Encoder

LongVPO: From Anchored Cues to Self-Reasoning for Long-Form Video Preference Optimization

Learning Source-Free Domain Adaptation for Visible-Infrared Person Re-Identification

Fully Spiking Neural Networks for Unified Frame-Event Object Tracking

Towards Reliable and Holistic Visual In-Context Learning Prompt Selection

VIBE: Annotation-Free Video-to-Text Information Bottleneck Evaluation for TL;DR

Why 1 + 1 < 1 in Visual Token Pruning: Beyond Naive Integration via Multi-Objective Balanced Covering

Retrv-R1: A Reasoning-Driven MLLM Framework for Universal and Efficient Multimodal Retrieval

PC-Net: Weakly Supervised Compositional Moment Retrieval via Proposal-Centric Network

Vision Function Layer in Multimodal LLMs

Deep Video Discovery: Agentic Search with Tool Use for Long-form Video Understanding

Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors

Empower Words: DualGround for Structured Phrase and Sentence-Level Temporal Grounding

Towards Physics-informed Spatial Intelligence with Human Priors: An Autonomous Driving Pilot Study

3DLLM-Mem: Long-Term Spatial-Temporal Memory for Embodied 3D Large Language Model

Backpropagation-Free Test-Time Adaptation via Probabilistic Gaussian Alignment

PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient Generation

Mitigating Hallucination Through Theory-Consistent Symmetric Multimodal Preference Optimization

Rare Text Semantics Were Always There in Your Diffusion Transformer

OmniResponse: Online Multimodal Conversational Response Generation in Dyadic Interactions

STRIDER: Navigation via Instruction-Aligned Structural Decision Space Optimization

Towards 3D Objectness Learning in an Open World

Visual Thoughts: A Unified Perspective of Understanding Multimodal Chain-of-Thought

Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing

Spatially-aware Weights Tokenization for NeRF-Language Models

Dynamic Masking and Auxiliary Hash Learning for Enhanced Cross-Modal Retrieval

COS3D: Collaborative Open-Vocabulary 3D Segmentation

InstructSAM: A Training-free Framework for Instruction-Oriented Remote Sensing Object Recognition

Right for the Right Reasons: Avoiding Reasoning Shortcuts via Prototypical Neurosymbolic AI

Do LVLMs Truly Understand Video Anomalies? Revealing Hallucination via Co-Occurrence Patterns

Towards Reliable Identification of Diffusion-based Image Manipulations

DevFD : Developmental Face Forgery Detection by Learning Shared and Orthogonal LoRA Subspaces

Unbiased Prototype Consistency Learning for Multi-Modal and Multi-Task Object Re-Identification

Unlabeled Data Improves Fine-Grained Image Zero-shot Classification with Multimodal LLMs

Mamba Only Glances Once (MOGO): A Lightweight Framework for Efficient Video Action Detection

Model Editing for Vision Transformers

DSRF: A Dynamic and Scalable Reasoning Framework for Solving RPMs

Guard Me If You Know Me: Protecting Specific Face-Identity from Deepfakes

EA3D: Online Open-World 3D Object Extraction from Streaming Videos

Accident Anticipation via Temporal Occurrence Prediction

Object-centric binding in Contrastive Language-Image Pretraining

Looking Beyond the Known: Towards a Data Discovery Guided Open-World Object Detection

Denoising Trajectory Biases for Zero-Shot AI-Generated Image Detection

mmWalk: Towards Multi-modal Multi-view Walking Assistance

Reasoning Beyond Points: A Visual Introspective Approach for Few-Shot 3D Segmentation

SAM-R1: Leveraging SAM for Reward Feedback in Multimodal Segmentation via Reinforcement Learning

SegGraph: Leveraging Graphs of SAM Segments for Few-Shot 3D Part Segmentation

LoMix: Learnable Weighted Multi-Scale Logits Mixing for Medical Image Segmentation

Inference with correlated priors using sisters cells

YOLOv12: Attention-Centric Real-Time Object Detectors

Handling Label Noise via Instance-Level Difficulty Modeling and Dynamic Optimization

Vocabulary-Guided Gait Recognition

LT-Soups: Bridging Head and Tail Classes via Subsampled Model Soups

Doodle to Detect: A Goofy but Powerful Approach to Skeleton-based Hand Gesture Recognition

FastDINOv2: Frequency Based Curriculum Learning Improves Robustness and Training Speed

FlareX: A Physics-Informed Dataset for Lens Flare Removal via 2D Synthesis and 3D Rendering

GPLQ: A General, Practical, and Lightning QAT Method for Vision Transformers

Lattice Boltzmann Model for Learning Real-World Pixel Dynamicity

Zero-shot Denoising via Neural Compression: Theoretical and algorithmic framework

Latent Chain-of-Thought for Visual Reasoning

Bridging the gap to real-world language-grounded visual concept learning

Quantum Visual Fields with Neural Amplitude Encoding

PMQ-VE: Progressive Multi-Frame Quantization for Video Enhancement

DualFocus: Depth from Focus with Spatio-Focal Dual Variational Constraints

Learning Differential Pyramid Representation for Tone Mapping

RigAnyFace: Scaling Neural Facial Mesh Auto-Rigging with Unlabeled Data

FlexEvent: Towards Flexible Event-Frame Object Detection at Varying Operational Frequencies

FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving

LoRATv2: Enabling Low-Cost Temporal Modeling in One-Stream Trackers

Rethinking Scale-Aware Temporal Encoding for Event-based Object Detection

Learning to Condition: A Neural Heuristic for Scalable MPE Inference

NeuSymEA: Neuro-symbolic Entity Alignment via Variational Inference

Stochastic Process Learning via Operator Flow Matching

Spectral Convolutional Conditional Neural Process

Generator-Mediated Bandits: Thompson Sampling for GenAI-Powered Adaptive Interventions

Beyond Verifiable Rewards: Scaling Reinforcement Learning in Language Models to Unverifiable Data

PoE-World: Compositional World Modeling with Products of Programmatic Experts

Improving LLM General Preference Alignment via Optimistic Online Mirror Descent

KL-Regularized RLHF with Multiple Reference Models: Exact Solutions and Sample Complexity

MedChain: Bridging the Gap Between LLM Agents and Clinical Practice with Interactive Sequence

RAG-IGBench: Innovative Evaluation for RAG-based Interleaved Generation in Open-domain Question Answering

A Technical Report on “Erasing the Invisible”: The 2024 NeurIPS Competition on Stress Testing Image Watermarks

SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines

NeurIPS should lead scientific consensus on AI policy

Position: Machine Learning Conferences Should Establish a "Refutations and Critiques" Track

Policy learning “without” overlap: Pessimism and generalized empirical Bernstein’s inequality

Implicit-ARAP: Efficient Handle-Guided Neural Field Deformation via Local Patch Meshing

Towards Syn-to-Real IQA: A Novel Perspective on Reshaping Synthetic Data Distributions

UltraLED: Learning to See Everything in Ultra-High Dynamic Range Scenes

Multi-Task Vehicle Routing Solver via Mixture of Specialized Experts under State-Decomposable MDP

Coarse-to-Fine 3D Part Assembly via Semantic Super-Parts and Symmetry-Aware Pose Estimation

Revisiting Generative Infrared and Visible Image Fusion Based on Human Cognitive Laws

Plasticity as the Mirror of Empowerment

Bernstein–von Mises for Adaptively Collected Data

Sequential Monte Carlo for Policy Optimization in Continuous POMDPs

Imitation Beyond Expectation Using Pluralistic Stochastic Dominance

MMCSBench: A Fine-Grained Benchmark for Large Vision-Language Models in Camouflage Scenes

RBench-V: A Primary Assessment for Visual Reasoning Models with Multimodal Outputs

Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free

FlexOLMo: Open Language Models for Flexible Data Use

Scalable Best-of-N Selection for Large Language Models via Self-Certainty

ReCon: Region-Controllable Data Augmentation with Rectification and Alignment for Object Detection

A Signed Graph Approach to Understanding and Mitigating Oversmoothing

Exploring the Translation Mechanism of Large Language Models

Theoretical Insights into In-context Learning with Unlabeled Data

RFMPose: Generative Category-level Object Pose Estimation via Riemannian Flow Matching

Safety Pretraining: Toward the Next Generation of Safe AI

Self-Guided Hierarchical Exploration for Generalist Foundation Model Web Agents

PUATE: Efficient ATE Estimation from Treated (Positive) and Unlabeled Units

Achieving $\tilde{\mathcal{O}}(1/N)$ Optimality Gap in Restless Bandits through Gaussian Approximation

SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoning

Emergent Temporal Correspondences from Video Diffusion Transformers

DynaAct: Large Language Model Reasoning with Dynamic Action Spaces

Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback

T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT

Uncoupled and Convergent Learning in Monotone Games under Bandit Feedback

LMFusion: Adapting Pretrained Language Models for Multimodal Generation

Noise Consistency Training: A Native Approach for One-step Generator in Learning Additional Controls

OmniGen-AR: AutoRegressive Any-to-Image Generation

Understanding Softmax Attention Layers:\\ Exact Mean-Field Analysis on a Toy Problem

Improving Generative Behavior Cloning via Self-Guidance and Adaptive Chunking

HumanCrafter: Synergizing Generalizable Human Reconstruction and Semantic 3D Segmentation

GAM-Agent: Game-Theoretic and Uncertainty-Aware Collaboration for Complex Visual Reasoning

The Graphon Limit Hypothesis: Understanding Neural Network Pruning via Infinite Width Analysis

Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning

R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing

ChartSketcher: Reasoning with Multimodal Feedback and Reflection for Chart Understanding

Personalized Image Editing in Text-to-Image Diffusion Models via Collaborative Direct Preference Optimization

PolyPose: Deformable 2D/3D Registration via Polyrigid Transformations

Fundamental Limitations in Pointwise Defences of LLM Finetuning APIs

Antidistillation Sampling

ChemOrch: Empowering LLMs with Chemical Intelligence via Groundbreaking Synthetic Instructions

Information-Computation Tradeoffs for Noiseless Linear Regression with Oblivious Contamination

MAT-Agent: Adaptive Multi-Agent Training Optimization

UFT: Unifying Supervised and Reinforcement Fine-Tuning

Wide-Horizon Thinking and Simulation-Based Evaluation for Real-World LLM Planning with Multifaceted Constraints

VaporTok: RL-Driven Adaptive Video Tokenizer with Prior & Task Awareness

Quadratic Coreset Selection: Certifying and Reconciling Sequence and Token Mining for Efficient Instruction Tuning

Online Experimental Design With Estimation-Regret Trade-off Under Network Interference

Geometric Logit Decoupling for Energy-Based Graph Out-of-distribution Detection

WKV-sharing embraced random shuffle RWKV high-order modeling for pan-sharpening

Information-Theoretic Reward Decomposition for Generalizable RLHF

Radial Attention: $\mathcal O(n \log n)$ Sparse Attention for Long Video Generation

ZeroPatcher: Training-free Sampler for Video Inpainting and Editing

Advancing Expert Specialization for Better MoE

Contribution of task-irrelevant stimuli to drift of neural representations

Optimizing Anytime Reasoning via Budget Relative Policy Optimization

Value-Guided Search for Efficient Chain-of-Thought Reasoning

Uncertainty-aware Preference Alignment for Diffusion Policies

Dynamic Siamese Expansion Framework for Improving Robustness in Online Continual Learning

Learning Expandable and Adaptable Representations for Continual Learning

Learning Multi-Source and Robust Representations for Continual Learning

Unifying Symbolic Music Arrangement: Track-Aware Reconstruction and Structured Tokenization

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

Point-RFT: Improving Multimodal Reasoning with Visually Grounded Reinforcement Finetuning

Moment- and Power-Spectrum-Based Gaussianity Regularization for Text-to-Image Models

Regional Explanations: Bridging Local and Global Variable Importance

Mean Flows for One-step Generative Modeling

EquiTabPFN: A Target-Permutation Equivariant Prior Fitted Network

Reward-Instruct: A Reward-Centric Approach to Fast Photo-Realistic Image Generation

LaX: Boosting Low-Rank Training of Foundation Models via Latent Crossing

Domain-RAG: Retrieval-Guided Compositional Image Generation for Cross-Domain Few-Shot Object Detection

One for All: Universal Topological Primitive Transfer for Graph Structure Learning

CSGO: Content-Style Composition in Text-to-Image Generation

Orient Anything V2: Unifying Orientation and Rotation Understanding

Integrating Drug Substructures and Longitudinal Electronic Health Records for Personalized Drug Recommendation

Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion

Plug-and-Play Context Feature Reuse for Efficient Masked Generation

CoLT: The conditional localization test for assessing the accuracy of neural posterior estimates

Amortized Variational Transdimensional Inference

Functional Complexity-adaptive Temporal Tensor Decomposition

Score-Based Diffusion Modeling for Nonparametric Empirical Bayes in Heteroscedastic Gaussian Mixtures

Squared families are useful conjugate priors

Efficient Bayesian Experiment Design with Equivariant Networks

Model-Informed Flows for Bayesian Inference

Turbocharging Gaussian Process Inference with Approximate Sketch-and-Project

Zero-Shot Performance Prediction for Probabilistic Scaling Laws

Robust and Computation-Aware Gaussian Processes

Least squares variational inference

Informed Correctors for Discrete Diffusion Models

Rethinking Losses for Diffusion Bridge Samplers

From stability of Langevin diffusion to convergence of proximal MCMC for non-log-concave sampling

Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration

AutoOpt: A Dataset and a Unified Framework for Automating Optimization Problem Solving

Hephaestus: Mixture Generative Modeling with Energy Guidance for Large-scale QoS Degradation

A Learning-Augmented Dynamic Programming Approach for Orienteering Problem with Time Windows

ALE-Bench: A Benchmark for Long-Horizon Objective-Driven Algorithm Engineering

Learning with Statistical Equality Constraints

Stochastic Optimization in Semi-Discrete Optimal Transport: Convergence Analysis and Minimax Rate

Quasi-Self-Concordant Optimization with $\ell_{\infty}$ Lewis Weights

Analog In-memory Training on General Non-ideal Resistive Elements: The Impact of Response Functions

Convergence of Clipped SGD on Convex $(L_0,L_1)$-Smooth Functions

MGUP: A Momentum-Gradient Alignment Update Policy for Stochastic Optimization

On the Sample Complexity of Differentially Private Policy Optimization

Deep Legendre Transform

Enhancing Zero-Shot Black-Box Optimization via Pretrained Models with Efficient Population Modeling, Interaction, and Stable Gradient Approximation

A Single-Loop Gradient Algorithm for Pessimistic Bilevel Optimization via Smooth Approximation

Finding Low-Rank Matrix Weights in DNNs via Riemannian Optimization: RAdaGrad and RAdamW

Hamiltonian Descent Algorithms for Optimization: Accelerated Rates via Randomized Integration Time

An Adaptive Algorithm for Bilevel Optimization on Riemannian Manifolds

Escaping saddle points without Lipschitz smoothness: the power of nonlinear preconditioning

FlowerTune: A Cross-Domain Benchmark for Federated Fine-Tuning of Large Language Models

FLiP: Towards Comprehensive and Reliable Evaluation of Federated Prompt Learning

PubSub-VFL: Towards Efficient Two-Party Split Learning in Heterogeneous Environments via Publisher/Subscriber Architecture

Unextractable Protocol Models: Collaborative Training and Inference without Weight Materialization

Bi-Directional Communication-Efficient Stochastic FL via Remote Source Generation

FORLA: Federated Object-centric Representation Learning with Slot Attention

HyGen: Efficient LLM Serving via Elastic Online-Offline Request Co-location

Tight analyses of first-order methods with error feedback

Streaming Federated Learning with Markovian Data

QuestBench: Can LLMs ask the right question to acquire information in reasoning tasks?

A Single-Loop First-Order Algorithm for Linearly Constrained Bilevel Optimization

Learning-Augmented Online Bidding in Stochastic Settings

Revisiting Follow-the-Perturbed-Leader with Unbounded Perturbations in Bandit Problems

ESCORT: Efficient Stein-variational and Sliced Consistency-Optimized Temporal Belief Representation for POMDPs

Solver-Free Decision-Focused Learning for Linear Optimization Problems

CAMO: Convergence-Aware Multi-Fidelity Bayesian Optimization

Convergence Rates of Constrained Expected Improvement

Transformer Key-Value Memories Are Nearly as Interpretable as Sparse Autoencoders

Correcting misinterpretations of additive models

Stop the Nonconsensual Use of Nude Images in Research

AutoRedTeamer: Autonomous Red Teaming with Lifelong Attack Integration

Valid Inference with Imperfect Synthetic Data

LARGO: Latent Adversarial Reflection through Gradient Optimization for Jailbreaking LLMs

Deep Value Benchmark: Measuring Whether Models Generalize Deep values or Shallow Preferences

Can DPO Learn Diverse Human Values? A Theoretical Scaling Law

CodeGEMM: A Codebook-Centric Approach to Efficient GEMM in Quantized LLMs

Generalized Gradient Norm Clipping & Non-Euclidean $(L_0,L_1)$-Smoothness

BIPNN: Learning to Solve Binary Integer Programming via Hypergraph Neural Networks

Attribution-Driven Adaptive Token Pruning for Transformers

In Search of Adam’s Secret Sauce

LoTA-QAF: Lossless Ternary Adaptation for Quantization-Aware Fine-Tuning

Bayesian Optimization with Preference Exploration using a Monotonic Neural Network Ensemble

Covering Multiple Objectives with a Small Set of Solutions Using Bayesian Optimization

Robust Satisficing Gaussian Process Bandits Under Adversarial Attacks

(ends 7:30 PM)

Creative AI Session 4 [4:30-7:30]

s 4:30-7:30

[4:30] An Inference Zoo for Real-Time Media Arts: Avendish as a Bridge Between AI and Creative Environments

[4:30] Artificial "Authentic" Intelligence: Can AI Systems Embody and Evolve Cultural Heritage? A Case Study of "Cyber Subin" and Thai Traditional Dance

[4:30] "Artificial Spectator" Developing AI Audiences for Watching AI-Generated Films: A Speculative Exploration on the Future of Media and AI

[4:30] Between Reality and AI Hallucinations: Reimagining the Sacred Soundscape of Ming Rituals

[4:30] BioArtlas: Computational Clustering of Multi-Dimensional Complexity in Bioart

[4:30] Blankscope: Real-time Bridging of Human Perception with AI Imagination

[4:30] Craving Checkpoint: An Interactive Fridge Lock for Mindful Eating

[4:30] Creative Synthesis of Kinematic Mechanisms

[4:30] From Movement Memories to Robotic Dialogue: A Language-Mediated Pipeline for Somatic Machine Translation

[4:30] Green Topics, Deep Roots: Energy-Aware Topic Modelling of Multilingual Nigerian Lyrics

[4:30] "Jutters''

[4:30] Little Martians: From Desert Clay to Generative Agents

[4:30] MCP2OSC: Parametric Control by Natural Language

[4:30] Opt-In Art: Learning Art Styles Only from Few Examples

[4:30] Pocket Ink - Heaven’s mandate: a hyper-individualized tangible card game platform in the Age of AI

[4:30] Roulettective: Repurposing a Vintage Slide Projector into an AI-Driven Physical Detective Game

[4:30] Scene-Aware Urban Design: A Human–AI Recommendation Framework Using Co-Occurrence Embeddings and Vision-Language Models

[4:30] SPICE: A Synergistic, Precise, Iterative, and Customizable Image Editing Workflow

[4:30] Superradiance

[4:30] The Glitching Therapist: Performing the Limits of AI Empathy

[4:30] TinyTim: a family of language models for divergent generation

[4:30] (Un)Natural Language

[4:30] Writing in Symbiosis: Mapping Human Creative Agency in the AI Era

(ends 7:30 PM)

7 p.m.

FRI 5 DEC

7:30 a.m.

Registration Desk

(ends 6:00 PM)

8 a.m.

Break:

Coffee Break

(ends 8:30 AM)

8:30 a.m.

San Diego Invited Talk:

From Benchmarks to Problems - A Perspective on Problem Finding in AI

Kyunghyun Cho

(ends 9:30 AM)

9 a.m.

Exhibit Sponsor Hall:

Exhibit Sponsor Hall

(ends 12:00 PM)

9:30 a.m.

Break:

Coffee Break

(ends 10:00 AM)

10 a.m.

Oral 5A Language Model 3 [10:00-11:00]

Orals 10:00-11:00

[10:00] EvoLM: In Search of Lost Language Model Training Dynamics

[10:20] Large Language Diffusion Models

[10:40] Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

(ends 11:00 AM)

Oral 5B Multimodel 3 [10:00-11:00]

Orals 10:00-11:00

[10:00] Boosting Knowledge Utilization in Multimodal Large Language Models via Adaptive Logits Fusion and Attention Reallocation

[10:20] HyperET: Efficient Training in Hyperbolic Space for Multi-modal Large Language Models

[10:40] Rethinking Multimodal Learning from the Perspective of Mitigating Classification Ability Disproportion

(ends 11:00 AM)

Oral 5C Generation/Simulation 3 [10:00-11:00]

Orals 10:00-11:00

[10:00] InfinityStar: Uniﬁed Spacetime AutoRegressive Modeling for Visual Generation

[10:20] PlayerOne: Egocentric World Simulator

[10:40] BEDLAM2.0: Synthetic humans and cameras in motion

(ends 11:00 AM)

Oral 5D Application 3 [10:00-11:00]

Orals 10:00-11:00

[10:00] WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratch

[10:20] QoQ-Med: Building Multimodal Clinical Foundation Models with Domain-Aware GRPO Training

[10:40] NOVA: A Benchmark for Rare Anomaly Localization and Clinical Reasoning in Brain MRI

(ends 11:00 AM)

Oral 5E Neuroscience [10:00-11:00]

Orals 10:00-11:00

[10:00] High-dimensional neuronal activity from low-dimensional latent dynamics: a solvable model

[10:20] Task-Optimized Convolutional Recurrent Networks Align with Tactile Processing in the Rodent Brain

[10:40] Memory Mosaics at scale

(ends 11:00 AM)

11 a.m.

San Diego Poster Session 5 [11:00-2:00]

Posters 11:00-2:00

Decompile-Bench: Million-Scale Binary-Source Function Pairs for Real-World Binary Decompilation

Differentiable Generalized Sliced Wasserstein Plans

Tight High-Probability Bounds for Nonconvex Heavy-Tailed Scenario under Weaker Assumptions

Robust Integrated Learning and Pauli Noise Mitigation for Parametrized Quantum Circuits

FlashMoE: Fast Distributed MoE in a Single Kernel

Counterfactual Reasoning for Steerable Pluralistic Value Alignment of Large Language Models

Model Provenance Testing for Large Language Models

Risk Management for Mitigating Benchmark Failure Modes: BenchRisk

Rethinking Circuit Completeness in Language Models: AND, OR, and ADDER Gates

Large language models can learn and generalize steganographic chain-of-thought under process supervision

From Black-box to Causal-box: Towards Building More Interpretable Models

Towards A Generalist Code Embedding Model Based On Massive Data Synthesis

Fast Data Attribution for Text-to-Image Models

Improving Perturbation-based Explanations by Understanding the Role of Uncertainty Calibration

A Implies B: Circuit Analysis in LLMs for Propositional Logical Reasoning

Boosting the Uniqueness of Neural Networks Fingerprints with Informative Triggers

Interpreting vision transformers via residual replacement model

In-Context Learning Strategies Emerge Rationally

DEXTER: Diffusion-Guided EXplanations with TExtual Reasoning for Vision Models

The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text

What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions

Faithful Group Shapley Value

Unlocking SLM Potential for Data Analysis Code Generation via Non-Parametric Knowledge Distillation

Steering Generative Models with Experimental Data for Protein Fitness Optimization

Jury-and-Judge Chain-of-Thought for Uncovering Toxic Data in 3D Visual Grounding

Beyond Random: Automatic Inner-loop Optimization in Dataset Distillation

Whose Instructions Count? Resolving Preference Bias in Instruction Fine-Tuning

Scaling Up Active Testing to Large Language Models

Physics-Driven Spatiotemporal Modeling for AI-Generated Video Detection

Auto-Search and Refinement: An Automated Framework for Gender Bias Mitigation in Large Language Models

FedFACT: A Provable Framework for Controllable Group-Fairness Calibration in Federated Learning

Discretization-free Multicalibration through Loss Minimization over Tree Ensembles

SAGE-Eval: Evaluating LLMs for Systematic Generalizations of Safety Facts

Whose View of Safety? A Deep DIVE Dataset for Pluralistic Alignment of Text-to-Image Models

From Noise to Narrative: Tracing the Origins of Hallucinations in Transformers

Regression Trees Know Calculus

AdaptGrad: Adaptive Sampling to Reduce Noise

DiCoFlex: Model-Agnostic Diverse Counterfactuals with Flexible Control

DroneAudioset: An Audio Dataset for Drone-based Search and Rescue

Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders

OrdShap: Feature Position Importance for Sequential Black-Box Models

SpEx: A Spectral Approach to Explainable Clustering

ProtoPairNet: Interpretable Regression through Prototypical Pair Reasoning

Refusal Direction is Universal Across Safety-Aligned Languages

Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training

CLIMB: Class-imbalanced Learning Benchmark on Tabular Data

CSI-Bench: A Large-Scale In-the-Wild Dataset for Multi-task WiFi Sensing

nvBench 2.0: Resolving Ambiguity in Text-to-Visualization through Stepwise Reasoning

FreshStack: Building Realistic Benchmarks for Evaluating Retrieval on Technical Documents

MIDAS: Misalignment-based Data Augmentation Strategy for Imbalanced Multimodal Learning

Residual Stream Analysis of Overfitting And Structural Disruptions

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling

Towards Generalizable Detector for Generated Image

ImageSentinel: Protecting Visual Datasets from Unauthorized Retrieval-Augmented Image Generation

Non-Adaptive Adversarial Face Generation

Strategic Costs of Perceived Bias in Fair Selection

Distortion of AI Alignment: Does Preference Optimization Optimize for Preferences?

Mask Image Watermarking

The VLLM Safety Paradox: Dual Ease in Jailbreak Attack and Defense

From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monitoring

Accelerated Vertical Federated Adversarial Learning through Decoupling Layer-Wise Dependencies

One Head to Rule Them All: Amplifying LVLM Safety through a Single Critical Attention Head

FairNet: Dynamic Fairness Correction without Performance Loss via Contrastive Conditional LoRA

Emergent Risk Awareness in Rational Agents under Resource Constraints

Train to Defend: First Defense Against Cryptanalytic Neural Network Parameter Extraction Attacks

Do You Really Need Public Data? Surrogate Public Data for Differential Privacy on Tabular Data

Exploring the limits of strong membership inference attacks on large language models

Unifying Re-Identification, Attribute Inference, and Data Reconstruction Risks in Differential Privacy

Vid-SME: Membership Inference Attacks against Large Video Understanding Models

Private Geometric Median in Nearly-Linear Time

Rethinking the Role of Verbatim Memorization in LLM Privacy

Differential Privacy for Euclidean Jordan Algebra with Applications to Private Symmetric Cone Programming

ToxicTextCLIP: Text-Based Poisoning and Backdoor Attacks on CLIP Pre-training

Time-uniform and Asymptotic Confidence Sequence of Quantile under Local Differential Privacy

Ascent Fails to Forget

OASIS: One-Shot Federated Graph Learning via Wasserstein Assisted Knowledge Integration

FALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Model

Sketched Gaussian Mechanism for Private Federated Learning

Flick: Empowering Federated Learning with Commonsense Knowledge

Fostering the Ecosystem of AI for Social Impact Requires Expanding and Strengthening Evaluation Standards

How Well Can Differential Privacy Be Audited in One Run?

Personalized Subgraph Federated Learning with Differentiable Auxiliary Projections

Private Hyperparameter Tuning with Ex-Post Guarantee

AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions

Fantastic Bugs and Where to Find Them in AI Benchmarks

Escaping the SpuriVerse: Can Large Vision-Language Models Generalize Beyond Seen Spurious Correlations?

BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models

Detecting Generated Images by Fitting Natural Image Distributions

Exploring the Noise Robustness of Online Conformal Prediction

Unlearned but Not Forgotten: Data Extraction after Exact Unlearning in LLM

Personalized Safety in LLMs: A Benchmark and A Planning-Based Agent Approach

Differentially Private Relational Learning with Entity-level Privacy Guarantees

ICLScan: Detecting Backdoors in Black-Box Large Language Models via Targeted In-context Illumination

Memory Injection Attacks on LLM Agents via Query-Only Interaction

Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model Merging

TRAP: Targeted Redirecting of Agentic Preferences

RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning

SRA-CL: Semantic Retrieval Augmented Contrastive Learning for Sequential Recommendation

Non-stationary Equivariant Graph Neural Networks for Physical Dynamics Simulation

Can Large Multimodal Models Understand Agricultural Scenes? Benchmarking with AgroMind

PhyBlock: A Progressive Benchmark for Physical Understanding and Planning via 3D Block Assembly

WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratch

HARDMath2: A Benchmark for Applied Mathematics Built by Students as Part of a Graduate Class

Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis

TAPAS: Datasets for Learning the Learning with Errors Problem

Blameless Users in a Clean Room: Defining Copyright Protection for Generative Models

Safety Depth in Large Language Models: A Markov Chain Perspective

ALMGuard: Safety Shortcuts and Where to Find Them as Guardrails for Audio–Language Models

Attractive Metadata Attack: Inducing LLM Agents to Invoke Malicious Tools

Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment

Watermarking Autoregressive Image Generation

Bridging Human and LLM Judgments: Understanding and Narrowing the Gap

Generalization or Hallucination? Understanding Out-of-Context Reasoning in Transformers

Among Us: A Sandbox for Measuring and Detecting Agentic Deception

CReFT-CAD: Boosting Orthographic Projection Reasoning for CAD via Reinforcement Fine-Tuning

ReMindRAG: Low-Cost LLM-Guided Knowledge Graph Traversal for Efficient RAG

InfantAgent-Next: A Multimodal Generalist Agent for Automated Computer Interaction

Partition to Evolve: Niching-enhanced Evolution with LLMs for Automated Algorithm Discovery

Adaptive Variance Inflation in Thompson Sampling: Efficiency, Safety, Robustness, and Beyond

STEAD: Robust Provably Secure Linguistic Steganography with Diffusion Language Model

SensorLM: Learning the Language of Wearable Sensors

BlockScan: Detecting Anomalies in Blockchain Transactions

Causal-R: A Causal-Reasoning Geometry Problem Solver for Optimized Solution Exploration

Knowledge-based Visual Question Answer with Multimodal Processing, Retrieval and Filtering

AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise

ArchCAD-400K: A Large-Scale CAD drawings Dataset and New Baseline for Panoptic Symbol Spotting

SpatialLM: Training Large Language Models for Structured Indoor Modeling

Towards Prospective Medical Image Reconstruction via Knowledge-Informed Dynamic Optimal Transport

Beyond Chemical QA: Evaluating LLM's Chemical Reasoning with Modular Chemical Operations

ProtInvTree: Deliberate Protein Inverse Folding with Reward-guided Tree Search

JAMUN: Bridging Smoothed Molecular Dynamics and Score-Based Learning for Conformational Ensemble Generation

Tensor Decomposition Networks for Accelerating Machine Learning Force Field Computations

Decoding Causal Structure: End-to-End Mediation Pathways Inference

Thousand Voices of Trauma: A Large-Scale Synthetic Dataset for Modeling Prolonged Exposure Therapy Conversations

DermaCon-IN: A Multiconcept-Annotated Dermatological Image Dataset of Indian Skin Disorders for Clinical AI Research

3D-RAD: A Comprehensive 3D Radiology Med-VQA Dataset with Multi-Temporal Analysis and Diverse Diagnostic Tasks

Equi-mRNA: Protein Translation Equivariant Encoding for mRNA Language Models

BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model

Learning Relative Gene Expression Trends from Pathology Images in Spatial Transcriptomics

GLID$^2$E: A Gradient-Free Lightweight Fine-tune Approach for Discrete Biological Sequence Design

PRESCRIBE: Predicting Single-Cell Responses with Bayesian Estimation

JanusDNA: A Powerful Bi-directional Hybrid DNA Foundation Model

MTBBench: A Multimodal Sequential Clinical Decision-Making Benchmark in Oncology

DiffLiG: Diffusion-enhanced Liquid Graph with Attention Propagation for Grid-to-Station Precipitation Correction

GeoAda: Efficiently Finetune Geometric Diffusion Models with Equivariant Adapters

ELECTRA: A Cartesian Network for 3D Charge Density Prediction with Floating Orbitals

TRIDENT: Tri-Modal Molecular Representation Learning with Taxonomic Annotations and Local Correspondence

UniSite: The First Cross-Structure Dataset and Learning Framework for End-to-End Ligand Binding Site Detection

PathVQ: Reforming Computational Pathology Foundation Model for Whole Slide Image Analysis via Vector Quantization

Improving the Generation and Evaluation of Synthetic Data for Downstream Medical Causal Inference

Learning to Zoom with Anatomical Relations for Medical Structure Detection

QoQ-Med: Building Multimodal Clinical Foundation Models with Domain-Aware GRPO Training

From Indicators to Insights: Diversity-Optimized for Medical Series-Text Decoding via LLMs

Chiron-o1: Igniting Multimodal Large Language Models towards Generalizable Medical Reasoning via Mentor-Intern Collaborative Search

D2SA: Dual-Stage Distribution and Slice Adaptation for Efficient Test-Time Adaptation in MRI Reconstruction

Generating Multi-Table Time Series EHR from Latent Space with Minimal Preprocessing

Ineq-Comp: Benchmarking Human-Intuitive Compositional Reasoning in Automated Theorem Proving of Inequalities

XIFBench: Evaluating Large Language Models on Multilingual Instruction Following

Are Language Models Efficient Reasoners? A Perspective from Logic Programming

System Prompt Optimization with Meta-Learning

S'MoRE: Structural Mixture of Residual Experts for Parameter-Efficient LLM Fine-tuning

Uncertain Knowledge Graph Completion via Semi-Supervised Confidence Distribution Learning

Erasing Conceptual Knowledge from Language Models

Practical and Effective Code Watermarking for Large Language Models

Simulating Society Requires Simulating Thought

RAST: Reasoning Activation in LLMs via Small-model Transfer

Optimizing Retrieval for RAG via Reinforced Contrastive Learning

Objective Soups: Multilingual Multi-Task Modeling for Speech Processing

Optimizing Chain-of-Thought Reasoners via Gradient Variance Minimization in Rejection Sampling and RL

K-DeCore: Facilitating Knowledge Transfer in Continual Structured Knowledge Reasoning via Knowledge Decoupling

QiMeng-CodeV-R1: Reasoning-Enhanced Verilog Generation

Mixture of Inputs: Text Generation Beyond Discrete Token Sampling

AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play

Adaptive Preference Arithmetic: A Personalized Agent with Adaptive Preference Arithmetic for Dynamic Preference Modeling

Thinking in Character: Advancing Role-Playing Agents with Role-Aware Reasoning

Do Automatic Factuality Metrics Measure Factuality? A Critical Evaluation

Target Speaker Extraction through Comparing Noisy Positive and Negative Audio Enrollments

A Semantic Parsing Framework for End-to-End Time Normalization

ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models

E-BATS: Efficient Backpropagation-Free Test-Time Adaptation for Speech Foundation Models

Language Models can Self-Improve at State-Value Estimation for Better Search

Atomic Thinking of LLMs: Decoupling and Exploring Mathematical Reasoning Abilities

REFED: A Subject Real-time Dynamic Labeled EEG-fNIRS Synchronized Recorded Emotion Dataset

Long-term Intracortical Neural activity and Kinematics (LINK): An intracortical neural dataset for chronic brain-machine interfaces, neuroscience, and machine learning

LibriBrain: Over 50 Hours of Within-Subject MEG to Improve Speech Decoding Methods at Scale

Adaptive Fission: Post-training Encoding for Low-latency Spike Neural Networks

A Multimodal BiMamba Network with Test-Time Adaptation for Emotion Recognition Based on Physiological Signals

Decomposing stimulus-specific sensory neural information via diffusion models

Self-Supervised Discovery of Neural Circuits in Spatially Patterned Neural Responses with Graph Neural Networks

Exponential Dynamic Energy Network for High Capacity Sequence Memory

SimSort: A Data-Driven Framework for Spike Sorting by Large-Scale Electrophysiology Simulation

Brain-Informed Fine-Tuning for Improved Multilingual Understanding in Language Models

TESTING STATIONARITY AND CHANGE POINT DETECTION IN REINFORCEMENT LEARNING

Bridging Brains and Concepts: Interpretable Visual Decoding from fMRI with Semantic Bottlenecks

Vector Quantization in the Brain: Grid-like Codes in World Models

MEIcoder: Decoding Visual Stimuli from Neural Activity by Leveraging Most Exciting Inputs

Separating the 'what' and 'how' of compositional computation to enable reuse and continual learning

REVE: A Foundation Model for EEG - Adapting to Any Setup with Large-Scale Pretraining on 25,000 Subjects

A data and task-constrained mechanistic model of the mouse outer retina shows robustness to contrast variations

High-dimensional neuronal activity from low-dimensional latent dynamics: a solvable model

Forecasting in Offline Reinforcement Learning for Non-stationary Environments

A Provable Approach for End-to-End Safe Reinforcement Learning

Simultaneous Statistical Inference for Off-Policy Evaluation in Reinforcement Learning

Less is More: an Attention-free Sequence Prediction Modeling for Offline Embodied Learning

Tapered Off-Policy REINFORCE - Stable and efficient reinforcement learning for large language models

Boundary-to-Region Supervision for Offline Safe Reinforcement Learning

LVLM-Driven Attribute-Aware Modeling for Visible-Infrared Person Re-Identification

On the Effect of Negative Gradient in Group Relative Deep Reinforcement Optimization

d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning

Generating Full-field Evolution of Physical Dynamics from Irregular Sparse Observations

ENMA: Tokenwise Autoregression for Continuous Neural PDE Operators

Transformers for Mixed-type Event Sequences

MLIP Arena: Advancing Fairness and Transparency in Machine Learning Interatomic Potentials via an Open, Accessible Benchmark Platform

PF∆: A Benchmark Dataset for Power Flow under Load, Generation, and Topology Variations

TIDMAD: Time Series Dataset for Discovering Dark Matter with AI Denoising

Bubbleformer: Forecasting Boiling with Transformers

Know Thyself by Knowing Others: Learning Neuron Identity from Population Context

From Synapses to Dynamics: Obtaining Function from Structure in a Connectome Constrained Model of the Head Direction Circuit

Predictive Coding Enhances Meta-RL To Achieve Interpretable Bayes-Optimal Belief Representation Under Partial Observability

How Ensembles of Distilled Policies Improve Generalisation in Reinforcement Learning

Multi-dataset Joint Pre-training of Emotional EEG Enables Generalizable Affective Computing

DeepHalo: A Neural Choice Model with Controllable Context Effects

A Scalable, Causal, and Energy Efficient Framework for Neural Decoding with Spiking Neural Networks

Concept-Guided Interpretability via Neural Chunking

Task-Optimized Convolutional Recurrent Networks Align with Tactile Processing in the Rodent Brain

MoRE-Brain: Routed Mixture of Experts for Interpretable and Generalizable Cross-Subject fMRI Visual Decoding

Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains

Scaling Off-Policy Reinforcement Learning with Batch and Weight Normalization

Measure gradients, not activations! Enhancing neuronal activity in deep reinforcement learning

Focus-Then-Reuse: Fast Adaptation in Visual Perturbation Environments

Open-World Drone Active Tracking with Goal-Centered Rewards

AION-1: Omnimodal Foundation Model for Astronomical Sciences

Dual-Comb Ghost Imaging with Transformer-Based Reconstruction for Optical Fiber Endomicroscopy

Learning Stochastic Multiscale Models

Inductive Domain Transfer In Misspecified Simulation-Based Inference

Guided Diffusion Sampling on Function Spaces with Applications to PDEs

Neural Green’s Functions

ChatbotID: Identifying Chatbots with Granger Causality Test

HCRMP: An LLM-Hinted Contextual Reinforcement Learning Framework for Autonomous Driving

Diversifying Parallel Ergodic Search: A Signature Kernel Evolution Strategy

Blindfolded Experts Generalize Better: Insights from Robotic Manipulation and Videogames

ReinFlow: Fine-tuning Flow Matching Policy with Online Reinforcement Learning

Convergent Functions, Divergent Forms

Latent Policy Barrier: Learning Robust Visuomotor Policies by Staying In-Distribution

VLA-OS: Structuring and Dissecting Planning Representations and Paradigms in Vision-Language-Action Models

UniMotion: A Unified Motion Framework for Simulation, Prediction and Planning

VideoVLA: Video Generators Can Be Generalizable Robot Manipulators

Text-to-Code Generation for Modular Building Layouts in Building Information Modeling

Task-Specific Data Selection for Instruction Tuning via Monosemantic Neuronal Activations

BountyBench: Dollar Impact of AI Agent Attackers and Defenders on Real-World Cybersecurity Systems

MS-Bench: Evaluating LMMs in Ancient Manuscript Study through a Dunhuang Case Study

Benchmarking End-To-End Performance of AI-Based Chip Placement Algorithms

MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning Research

Towards Accurate Time Series Forecasting via Implicit Decoding

TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loop

TS-RAG: Retrieval-Augmented Generation based Time Series Foundation Models are Stronger Zero-Shot Forecaster

Multi-Modal View Enhanced Large Vision Models for Long-Term Time Series Forecasting

PhysDiff: A Physically-Guided Diffusion Model for Multivariate Time Series Anomaly Detection

NoBOOM: Chemical Process Datasets for Industrial Anomaly Detection

RDD: Retrieval-Based Demonstration Decomposer for Planner Alignment in Long-Horizon Tasks

Dynamic Test-Time Compute Scaling in Control Policy: Difficulty-Aware Stochastic Interpolant Policy

Grasp2Grasp: Vision-Based Dexterous Grasp Translation via Schrödinger Bridges

Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning

OSVI-WM: One-Shot Visual Imitation for Unseen Tasks using World-Model-Guided Trajectory Generation

Distilling LLM Prior to Flow Model for Generalizable Agent’s Imagination in Object Goal Navigation

PurpCode: Reasoning for Safer Code Generation

NeSyPr: Neurosymbolic Proceduralization For Efficient Embodied Reasoning

ToF-IP: Time-of-Flight Enhanced Sparse Inertial Poser for Real-time Human Motion Capture

RSafe: Incentivizing proactive reasoning to build robust and adaptive LLM safeguards

SIGMA: Refining Large Language Model Reasoning via Sibling-Guided Monte Carlo Augmentation

Sparse Meets Dense: Unified Generative Recommendations with Cascaded Sparse-Dense Representations

Doubly-Robust Estimation of Counterfactual Policy Mean Embeddings

Differentiable Constraint-Based Causal Discovery

Differentiable Cyclic Causal Discovery Under Unmeasured Confounders

Pattern-Guided Adaptive Prior for Structure Learning

Reward-oriented Causal Representation Learning

Practical Kernel Selection for Kernel-based Conditional Independence Test

CausalPFN: Amortized Causal Effect Estimation via In-Context Learning

Density Ratio-Free Doubly Robust Proxy Causal Learning

Data-Adaptive Exposure Thresholds under Network Interference

Causal Mixture Models: Characterization and Discovery

Local Learning for Covariate Selection in Nonparametric Causal Effect Estimation with Latent Variables

The third pillar of causal analysis? A measurement perspective on causal representations

Angular Constraint Embedding via SpherePair Loss for Constrained Clustering

Global Minimizers of Sigmoid Contrastive Loss

FoGE: Fock Space inspired encoding for graph prompting

$\boldsymbol{\lambda}$-Orthogonality Regularization for Compatible Representation Learning

Autoencoding Random Forests

NeurIPT: Foundation Model for Neural Interfaces

The Indra Representation Hypothesis

Learning from Disjoint Views: A Contrastive Prototype Matching Network for Fully Incomplete Multi-View Clustering

HEIR: Learning Graph-Based Motion Hierarchies

VisDiff: SDF-Guided Polygon Generation for Visibility Reconstruction, Characterization and Recognition

Feature-aware Modulation for Learning from Temporal Tabular Data

Shape-Informed Clustering of Multi-Dimensional Functional Data via Deep Functional Autoencoders

GSAlign: Geometric and Semantic Alignment Network for Aerial-Ground Person Re-Identification

When Additive Noise Meets Unobserved Mediators: Bivariate Denoising Diffusion for Causal Discovery

Differentiable Structure Learning and Causal Discovery for General Binary Data

Less Greedy Equivalence Search

Coupling Generative Modeling and an Autoencoder with the Causal Bridge

A Unified Framework for the Transportability of Population-Level Causal Measures

Revising and Falsifying Sparse Autoencoder Feature Explanations

Registration is a Powerful Rotation-Invariance Learner for 3D Anomaly Detection

Stochastic Forward-Forward Learning through Representational Dimensionality Compression

OmniDraft: A cross-vocabulary, online adaptive drafter for on-device speculative decoding

Beyond Value Functions: Single-Loop Bilevel Optimization under Flatness Conditions

CaliGCL: Calibrated Graph Contrastive Learning via Partitioned Similarity and Consistency Discrimination

Class-wise Balancing Data Replay for Federated Class-Incremental Learning

Measure-Theoretic Anti-Causal Representation Learning

Harnessing the Universal Geometry of Embeddings

Equivariance by Contrast: Identifiable Equivariant Embeddings from Unlabeled Finite Group Actions

When Does Closeness in Distribution Imply Representational Similarity? An Identifiability Perspective

Evolutionary Reasoning Does Not Arise in Standard Usage of Protein Language Models

3D-Prover: Diversity Driven Theorem Proving With Determinantal Point Processes

CrossSpectra: Exploiting Cross-Layer Smoothness for Parameter-Efficient Fine-Tuning

Unleashing Diffusion Transformers for Visual Correspondence by Modulating Massive Activations

Disentangling Latent Shifts of In-Context Learning with Weak Supervision

Multiresolution Analysis and Statistical Thresholding on Dynamic Networks

LLM-DAMVC: A Large Language Model Assisted Dynamic Agent for Multi-View Clustering

An Efficient Orlicz-Sobolev Approach for Transporting Unbalanced Measures on a Graph

Optimal Online Change Detection via Random Fourier Features

A learnability analysis on neuro-symbolic learning

Differentiable Decision Tree via "ReLU+Argmin" Reformulation

Model Inversion with Layer-Specific Modeling and Alignment for Data-Free Continual Learning

Mixture of Noise for Pre-Trained Model-Based Class-Incremental Learning

UniTransfer: Video Concept Transfer via Progressive Spatio-Temporal Decomposition

Parameter Efficient Fine-tuning via Explained Variance Adaptation

RrED: Black-box Unsupervised Domain Adaptation via Rectifying-reasoning Errors of Diffusion

Diversity-oriented Deep Multi-modal Clustering

DreamPRM: Domain-reweighted Process Reward Model for Multimodal Reasoning

Compact Memory for Continual Logistic Regression

SEAL: Semantic-Aware Hierarchical Learning for Generalized Category Discovery

Synergy over Discrepancy: A Partition-Based Approach to Multi-Domain LLM Fine-Tuning

MergeBench: A Benchmark for Merging Domain-Specialized LLMs

PhySwin: An Efficient and Physically-Informed Foundation Model for Multispectral Earth Observation

Bandit Guided Submodular Curriculum for Adaptive Subset Selection

ShortListing Model: A Streamlined Simplex Diffusion for Discrete Variable Generation

Learning Robust Spectral Dynamics for Temporal Domain Generalization

Inference-Time Personalized Alignment with a Few User Preference Queries

Prediction-Powered Semi-Supervised Learning with Online Power Tuning

A Single-Swap Local Search Algorithm for k-Means of Lines

Learning Reconfigurable Representations for Multimodal Federated Learning with Missing Data

Universal Sequence Preconditioning

A faster training algorithm for regression trees with linear leaves, and an analysis of its complexity

Learning to Clean: Reinforcement Learning for Noisy Label Correction

Anomaly Detection by an Ensemble of Random Pairs of Hyperspheres

Conformal Information Pursuit for Interactively Guiding Large Language Models

Optimistic Query Routing in Clustering-based Approximate Maximum Inner Product Search

Learning a Cross-Modal Schrödinger Bridge for Visual Domain Generalization

Leveraging Depth and Language for Open-Vocabulary Domain-Generalized Semantic Segmentation

Graph–Smoothed Bayesian Black-Box Shift Estimator and Its Information Geometry

The Generative Leap: Tight Sample Complexity for Efficiently Learning Gaussian Multi-Index Models

Dimension-free Score Matching and Time Bootstrapping for Diffusion Models

Online Inverse Linear Optimization: Efficient Logarithmic-Regret Algorithm, Robustness to Suboptimality, and Lower Bound

Geometric Learning with Positively Decomposable Kernels

From Self-Check to Consensus: Bayesian Strategic Decoding in Large Language Models

On Hierarchies of Fairness Notions in Cake Cutting: From Proportionality to Super Envy-Freeness

Strategic Cost Selection in Participatory Budgeting

Stochastically Dominant Peer Prediction

Theoretical Guarantees for the Retention of Strict Nash Equilibria by Coevolutionary Algorithms

Learning in Stackelberg Mean Field Games: A Non-Asymptotic Analysis

The Complexity of Correlated Equilibria in Generalized Games

Markov Persuasion Processes: Learning to Persuade From Scratch

Efficient Last-Iterate Convergence in Solving Extensive-Form Games

Stable Matching with Ties: Approximation Ratios and Learning

Robust Policy Expansion for Offline-to-Online RL under Diverse Data Corruption

The Effect of Optimal Self-Distillation in Noisy Gaussian Mixture Model

Test-Time Spectrum-Aware Latent Steering for Zero-Shot Generalization in Vision-Language Models

Imagined Autocurricula

On Union-Closedness of Language Generation

Oracle-Efficient Combinatorial Semi-Bandits

Optimal Rates for Generalization of Gradient Descent for Deep ReLU Classification

Contextual Dynamic Pricing with Heterogeneous Buyers

On the Optimality of the Median-of-Means Estimator under Adversarial Contamination

Understanding the Generalization of Stochastic Gradient Adam in Learning Neural Networks

A Closer Look at NTK Alignment: Linking Phase Transitions in Deep Image Regression

Low Precision Streaming PCA

Stochastic Gradients under Nuisances

On Transferring Transferability: Towards a Theory for Size Generalization

Value Improved Actor Critic Algorithms

Parameter-free Algorithms for the Stochastically Extended Adversarial Model

On the necessity of adaptive regularisation: Optimal anytime online learning on $\boldsymbol{\ell_p}$-balls

Multimodal Negative Learning

Valid Selection among Conformal Sets

Curl Descent : Non-Gradient Learning Dynamics with Sign-Diverse Plasticity

Replicable Online Learning

Computational Efficiency under Covariate Shift in Kernel Ridge Regression

Counteractive RL: Rethinking Core Principles for Efficient and Scalable Deep Reinforcement Learning

Reinforced Context Order Recovery for Adaptive Reasoning and Planning

Option-aware Temporally Abstracted Value for Offline Goal-Conditioned Reinforcement Learning

Real-DRL: Teach and Learn in Reality

Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards

Efficient Safe Meta-Reinforcement Learning: Provable Near-Optimality and Anytime Safety

Enhancing Interpretability in Deep Reinforcement Learning through Semantic Clustering

Imagine Beyond ! Distributionally Robust Autoencoding for State Space Coverage in Online Reinforcement Learning

Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning

Multi-head Transformers Provably Learn Symbolic Multi-step Reasoning via Gradient Descent

Sample complexity of data-driven tuning of model hyperparameters in neural networks with structured parameter-dependent dual function

Learning Across the Gap: Hybrid Multi-armed Bandits with Heterogeneous Offline and Online Data

Robustly Learning Monotone Single-Index Models

Probably Approximately Precision and Recall Learning

Algorithms and SQ Lower Bounds for Robustly Learning Real-valued Multi-Index Models

Sharp Gaussian approximations for Decentralized Federated Learning

Gaussian Approximation and Concentration of Constant Learning-Rate Stochastic Gradient Descent

Optimal Spectral Transitions in High-Dimensional Multi-Index Models

Evolution of Information in Interactive Decision Making: A Case Study for Multi-Armed Bandits

Generating Creative Chess Puzzles

Adversarial generalization of unfolding (model-based) networks

GraphChain: Large Language Models for Large-scale Graph Analysis via Tool Chaining

Sequential Multi-Agent Dynamic Algorithm Configuration

Deep RL Needs Deep Behavior Analysis: Exploring Implicit Planning by Model-Free Agents in Open-Ended Environments

Retrospective In-Context Learning for Temporal Credit Assignment with Large Language Models

Centralized Reward Agent for Knowledge Sharing and Transfer in Multi-Task Reinforcement Learning

Approximation and Generalization Abilities of Score-based Neural Network Generative Models for Sub-Gaussian Distributions

Replicable Distribution Testing

Quantitative convergence of trained neural networks to Gaussian processes

Breaking AR’s Sampling Bottleneck: Provable Acceleration via Diffusion Language Models

Data-Dependent Regret Bounds for Constrained MABs

Online Statistical Inference in Decision Making with Matrix Context

A General-Purpose Theorem for High-Probability Bounds of Stochastic Approximation with Polyak Averaging

Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback

Protocols for Verifying Smooth Strategies in Bandits and Games

Put CASH on Bandits: A Max K-Armed Problem for Automated Machine Learning

Diffusion Models Meet Contextual Bandits

PLEIADES: Building Temporal Kernels with Orthogonal Polynomials

BMW: Bidirectionally Memory bank reWriting for Unsupervised Person Re-Identification

Revolutionizing Training-Free NAS: Towards Efficient Automatic Proxy Discovery via Large Language Models

pLSTM: parallelizable Linear Source Transition Mark networks

Sampled Estimators For Softmax Must Be Biased

On the Mechanisms of Weak-to-Strong Generalization: A Theoretical Perspective

The Complexity of Finding Local Optima in Contrastive Learning

On the Bias of Next-Token Predictors Toward Systematically Inefficient Reasoning: A Shortest-Path Case Study

Adaptive Data Analysis for Growing Data

Optimal Estimation of the Best Mean in Multi-Armed Bandits

Robust Distributed Estimation: Extending Gossip Algorithms to Ranking and Trimmed Means

Tight Bounds for Answering Adaptively Chosen Concentrated Queries

A Reinforcement Learning-based Bidding Strategy for Data Consumers in Auction-based Federated Learning

A Novel General Framework for Sharp Lower Bounds in Succinct Stochastic Bandits

A Differential and Pointwise Control Approach to Reinforcement Learning

Faster Fixed-Point Methods for Multichain MDPs

Non-Stationary Lipschitz Bandits

Zero-Shot Context Generalization in Reinforcement Learning from Few Training Contexts

Balancing Performance and Costs in Best Arm Identification

Bigram Subnetworks: Mapping to Next Tokens in Transformer Language Models

AdaSTaR: Adaptive Data Sampling for Training Self-Taught Reasoners

Knowledge Distillation of Uncertainty using Deep Latent Factor Model

SPMDM: Enhancing Masked Diffusion Models through Simplifing Sampling Path

Memory Mosaics at scale

AlphaDecay: Module-wise Weight Decay for Heavy-Tailed Balancing in LLMs

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression

Brain network science modelling of sparse neural networks enables Transformers and LLMs to perform as fully connected

A Difference-of-Convex Functions Approach to Energy-Based Iterative Reasoning

Activation-Informed Merging of Large Language Models

Progressive Data Dropout: An Embarrassingly Simple Approach to Train Faster

Elastic Robust Unlearning of Specific Knowledge in Large Language Models

Multi-Agent Debate for LLM Judges with Adaptive Stability Detection

Improving Model Representation and Reducing KV Cache via Skip Connections with First Value Heads

RAT: Bridging RNN Efficiency and Attention Accuracy via Chunk-based Sequence Modeling

Tensor-Parallelism with Partially Synchronized Activations

Hybrid Autoencoders for Tabular Data: Leveraging Model-Based Augmentation in Low-Label Settings

TANDEM: Bi-Level Data Mixture Optimization with Twin Networks

Bilevel ZOFO: Efficient LLM Fine-Tuning and Meta-Training

Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-based Decoding

Cascaded Language Models for Cost-Effective Human–AI Decision-Making

Diffusion Tree Sampling: Scalable inference‑time alignment of diffusion models

Precise Diffusion Inversion: Towards Novel Samples and Few-Step Models

Mitigating Forgetting in LLM Fine-Tuning via Low-Perplexity Token Learning

Compositional Discrete Latent Code for High Fidelity, Productive Diffusion Models

Diffusion Transformers for Imputation: Statistical Efficiency and Uncertainty Quantification

ComPO: Preference Alignment via Comparison Oracles

Efficient Utility-Preserving Machine Unlearning with Implicit Gradient Surgery

Wavy Transformer

Self-Refining Language Model Anonymizers via Adversarial Distillation

Structured Initialization for Vision Transformers

Technical Debt in In-Context Learning: Diminishing Efficiency in Long Context

Polar Sparsity: High Throughput Batched LLM Inferencing with Scalable Contextual Sparsity

Overcoming Long Context Limitations of State Space Models via Context Dependent Sparse Attention

Order-Level Attention Similarity Across Language Models: A Latent Commonality

SeerAttention: Self-distilled Attention Gating for Efficient Long-context Prefilling

Variational Task Vector Composition

Every Rollout Counts: Optimal Resource Allocation for Efficient Test-Time Scaling

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer

Discovering Important Experts for Mixture-of-Experts Models Pruning Through a Theoretical Perspective

GenIR: Generative Visual Feedback for Mental Image Retrieval

A Data-Driven Prism: Multi-View Source Separation with Diffusion Model Priors

How to build a consistency model: Learning flow maps via self-distillation

Anchored Diffusion Language Model

Controlling Thinking Speed in Reasoning Models

SAO-Instruct: Free-form Audio Editing using Natural Language Instructions

MoESD: Unveil Speculative Decoding's Potential for Accelerating Sparse MoE

Triplets Better Than Pairs: Towards Stable and Effective Self-Play Fine-Tuning for LLMs

Fast Monte Carlo Tree Diffusion: 100× Speedup via Parallel and Sparse Planning

CGS-GAN: 3D Consistent Gaussian Splatting GANs for High Resolution Human Head Synthesis

Diffusion Generative Modeling on Lie Group Representations

Large Language Diffusion Models

Variational Uncertainty Decomposition for In-Context Learning

Elucidated Rolling Diffusion Models for Probabilistic Forecasting of Complex Dynamics

Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach

The quest for the GRAph Level autoEncoder (GRALE)

Diffusion Beats Autoregressive in Data-Constrained Settings

Graph Diffusion that can Insert and Delete

Is Noise Conditioning Necessary? A Unified Theory of Unconditional Graph Diffusion Models

Learning normalized image densities via dual score matching

Sparse Image Synthesis via Joint Latent and RoI Flow

On the Relation between Rectified Flows and Optimal Transport

A*-Thought: Efficient Reasoning via Bidirectional Compression for Low-Resource Settings

Greed is Good: A Unifying Perspective on Guided Generation

Fine-Tuning Discrete Diffusion Models with Policy Gradient Methods

Non-Markovian Discrete Diffusion with Causal Language Models

Uni-Instruct: One-step Diffusion Model through Unified Diffusion Divergence Instruction

Time Series Generation Under Data Scarcity: A Unified Generative Modeling Approach

Is PRM Necessary? Problem-Solving RL Implicitly Induces PRM Capability in LLMs

Spark Transformer: Reactivating Sparsity in Transformer FFN and Attention

FEEDBACK FRICTION: LLMs Struggle to Fully Incorporate External Feedback

Language Models Can Predict Their Own Behavior

DICEPTION: A Generalist Diffusion Model for Visual Perceptual Tasks

Efficient Multi-modal Large Language Models via Progressive Consistency Distillation

KLASS: KL-Guided Fast Inference in Masked Diffusion Models

Theoretical Benefit and Limitation of Diffusion Language Model

ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMs

Flatten Graphs as Sequences: Transformers are Scalable Graph Generators

Generating Physically Sound Designs from Text and a Set of Physical Constraints

FACT: Mitigating Inconsistent Hallucinations in LLMs via Fact-Driven Alternating Code-Text Training

Causality Meets the Table: Debiasing LLMs for Faithful TableQA via Front-Door Intervention

Self-Assembling Graph Perceptrons

Sound Logical Explanations for Mean Aggregation Graph Neural Networks

Unifying Text Semantics and Graph Structures for Temporal Text-attributed Graphs with Large Language Models

What Expressivity Theory Misses: Message Passing Complexity for GNNs

SignFlow Bipartite Subgraph Network For Large-Scale Graph Link Sign Prediction

Redundancy-Aware Test-Time Graph Out-of-Distribution Detection

Dual Prototype-Enhanced Contrastive Framework for Class-Imbalanced Graph Domain Adaptation

Association-Focused Path Aggregation for Graph Fraud Detection

Defining and Discovering Hyper-meta-paths for Heterogeneous Hypergraphs

Continuous Simplicial Neural Networks

Hybrid-Collaborative Augmentation and Contrastive Sample Adaptive-Differential Awareness for Robust Attributed Graph Clustering

Towards Unsupervised Open-Set Graph Domain Adaptation via Dual Reprogramming

Graphs Help Graphs: Multi-Agent Graph Socialized Learning

Principled Data Augmentation for Learning to Solve Quadratic Programming Problems

Return of ChebNet: Understanding and Improving an Overlooked GNN on Long Range Tasks

DuetGraph: Coarse-to-Fine Knowledge Graph Reasoning with Dual-Pathway Global-Local Fusion

Uncertainty Estimation on Graphs with Structure Informed Stochastic Partial Differential Equations

Generative Graph Pattern Machine

Generalization Error Analysis for Selective State-Space Models Through the Lens of Attention

Distributional Training Data Attribution: What do Influence Functions Sample?

Bayes optimal learning of attention-indexed models

Understanding the Evolution of the Neural Tangent Kernel at the Edge of Stability

Stab-SGD: Noise-Adaptivity in Smooth Optimization with Stability Ratios

Sinusoidal Initialization, Time for a New Start

Non-Singularity of the Gradient Descent Map for Neural Networks with Piecewise Analytic Activations

Depth-Width Tradeoffs for Transformers on Graph Tasks

Dual-Flow: Transferable Multi-Target, Instance-Agnostic Attacks via $\textit{In-the-wild}$ Cascading Flow Optimization

Towards Irreversible Attack: Fooling Scene Text Recognition via Multi-Population Coevolution Search

Beyond Higher Rank: Token-wise Input-Output Projections for Efficient Low-Rank Adaptation

Tracing Back the Malicious Clients in Poisoning Attacks to Federated Learning

GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation

Best-of-N Jailbreaking

$\texttt{AVROBUSTBENCH}$: Benchmarking the Robustness of Audio-Visual Recognition Models at Test-Time

MultiNet: Adaptive Multi-Viewed Subgraph Convolutional Networks for Graph Classification

One Prompt Fits All: Universal Graph Adaptation for Pretrained Models

Parameter-Free Hypergraph Neural Network for Few-Shot Node Classification

Towards Graph Foundation Models: Training on Knowledge Graphs Enables Transferability to General Graphs

Graph Few-Shot Learning via Adaptive Spectrum Experts and Cross-Set Distribution Calibration

URB - Urban Routing Benchmark for RL-equipped Connected Autonomous Vehicles

Scaling can lead to compositional generalization

Do Neural Networks Need Gradient Descent to Generalize? A Theoretical Study

Learning quadratic neural networks in high dimensions: SGD dynamics and scaling laws

From Linear to Nonlinear: Provable Weak-to-Strong Generalization through Feature Learning

A Minimalist Example of Edge-of-Stability and Progressive Sharpening

Who You Are Matters: Bridging Interests and Social Roles via LLM-Enhanced Logic Recommendation

Loquetier: A Virtualized Multi-LoRA Framework for Unified LLM Fine-tuning and Serving

Achilles' Heel of Mamba: Essential difficulties of the Mamba architecture demonstrated by synthetic data

Beyond the Surface: Enhancing LLM-as-a-Judge Alignment with Human via Internal Representations

ExPO: Unlocking Hard Reasoning with Self-Explanation-Guided Reinforcement Learning

SimWorld: An Open-ended Simulator for Agents in Physical and Social Worlds

Discovering Data Structures: Nearest Neighbor Search and Beyond

Uncertainty Quantification for Physics-Informed Neural Networks with Extended Fiducial Inference

No Loss, No Gain: Gated Refinement and Adaptive Compression for Prompt Optimization

SharpZO: Hybrid Sharpness-Aware Vision Language Model Prompt Tuning via Forward-Only Passes

The Curse of Depth in Large Language Models

Beyond Greedy Exits: Improved Early Exit Decisions for Risk Control and Reliability

DuoGPT: Training-free Dual Sparsity through Activation-aware Pruning in LLMs

SpikingVTG: A Spiking Detection Transformer for Video Temporal Grounding

Fourier Analysis Network

LBMKGC: Large Model-Driven Balanced Multimodal Knowledge Graph Completion

Multi-agent Markov Entanglement

Adaptively Coordinating with Novel Partners via Learned Latent Strategies

A Principle of Targeted Intervention for Multi-Agent Reinforcement Learning

Towards Principled Unsupervised Multi-Agent Reinforcement Learning

Regret-Optimal Q-Learning with Low Cost for Single-Agent and Federated Reinforcement Learning

HYPRL: Reinforcement Learning of Control Policies for Hyperproperties

OrbitZoo: Real Orbital Systems Challenges for Reinforcement Learning

Revisiting Multi-Agent World Modeling from a Diffusion-Inspired Perspective

Compiler-R1: Towards Agentic Compiler Auto-tuning with Reinforcement Learning

Demystifying Language Model Forgetting with Low-rank Example Associations

Reasoning Models Better Express Their Confidence

GPAS: Accelerating Convergence of LLM Pretraining via Gradient-Preserving Activation Scaling

ReCAP: Recursive Context-Aware Reasoning and Planning for Large Language Model Agents

Tree-Based Premise Selection for Lean4

Table as a Modality for Large Language Models

BundleFlow: Deep Menus for Combinatorial Auctions by Diffusion-Based Optimization

CrossAD: Time Series Anomaly Detection with Cross-scale Associations and Cross-window Modeling

Spend Wisely: Maximizing Post-Training Gains in Iterative Synthetic Data Bootstrapping

Extrapolation by Association: Length Generalization Transfer In Transformers

Equilibrium Policy Generalization: A Reinforcement Learning Framework for Cross-Graph Zero-Shot Generalization in Pursuit-Evasion Games

MIRAGE: Assessing Hallucination in Multimodal Reasoning Chains of MLLM

Quantization Error Propagation: Revisiting Layer-Wise Post-Training Quantization

Generalizing Verifiable Instruction Following

Provably Efficient Online RLHF with One-Pass Reward Modeling

NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation

STITCH-OPE: Trajectory Stitching with Guided Diffusion for Off-Policy Evaluation

Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space

Longer Context, Deeper Thinking: Uncovering the Role of Long-Context Ability in Reasoning

Accelerating Diffusion LLMs via Adaptive Parallel Decoding

Through the Lens: Benchmarking Deepfake Detectors Against Moiré-Induced Distortions

Alchemist: Turning Public Text-to-Image Data into Generative Gold

GeoComplete: Geometry-Aware Diffusion for Reference-Driven Image Completion

Conditional Panoramic Image Generation via Masked Autoregressive Modeling

WISA: World simulator assistant for physics-aware text-to-video generation

VideoTitans: Scalable Video Prediction with Integrated Short- and Long-term Memory

CAMILA: Context-Aware Masking for Image Editing with Language Alignment

Future-Aware End-to-End Driving: Bidirectional Modeling of Trajectory Planning and Scene Evolution

PlayerOne: Egocentric World Simulator

LayerCraft: Enhancing Text-to-Image Generation with CoT Reasoning and Layered Object Integration

IllumiCraft: Unified Geometry and Illumination Diffusion for Controllable Video Generation

Unifying Reconstruction and Density Estimation via Invertible Contraction Mapping in One-Class Classification

ThermalGen: Style-Disentangled Flow-Based Generative Models for RGB-to-Thermal Image Translation

Low-Rank Head Avatar Personalization with Registers

OmniTry: Virtual Try-On Anything without Masks

High Dynamic Range Imaging with Time-Encoding Spike Camera

Inference-Time Text-to-Video Alignment with Diffusion Latent Beam Search

GeoVideo: Introducing Geometric Regularization into Video Generation Model

Towards Physical Understanding in Video Generation: A 3D Point Regularization Approach

SceneDecorator: Towards Scene-Oriented Story Generation with Scene Planning and Scene Consistency

🎧MOSPA: Human Motion Generation Driven by Spatial Audio

Faster Video Diffusion with Trainable Sparse Attention

Aligning Text to Image in Diffusion Models is Easier Than You Think

CPO: Condition Preference Optimization for Controllable Image Generation

Entropy Rectifying Guidance for Diffusion and Flow Models

Discovering Latent Graphs with GFlowNets for Diverse Conditional Image Generation

FlowMo: Variance-Based Flow Guidance for Coherent Motion in Video Generation

Image as a World: Generating Interactive World from Single Image via Panoramic Video Generation

Towards Better & Faster Autoregressive Image Generation: From the Perspective of Entropy

InfinityStar: Uniﬁed Spacetime AutoRegressive Modeling for Visual Generation

EverybodyDance: Bipartite Graph–Based Identity Correspondence for Multi-Character Animation

SceneSplat++: A Large Dataset and Comprehensive Benchmark for Language Gaussian Splatting

GeoCAD: Local Geometry-Controllable CAD Generation with Large Language Models

HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis

REArtGS: Reconstructing and Generating Articulated Objects via 3D Gaussian Splatting with Geometric and Motion Constraints

H3D-DGS: Exploring Heterogeneous 3D Motion Representation for Deformable 3D Gaussian Splatting

Optimize the Unseen - Fast NeRF Cleanup with Free Space Prior

NFL-BA: Near-Field Light Bundle Adjustment for SLAM in Dynamic Lighting

3DOT: Texture Transfer for 3DGS Objects from a Single Reference Image

Learning Efficient Fuse-and-Refine for Feed-Forward 3D Gaussian Splatting

Motion4D: Learning 3D-Consistent Motion and Semantics for 4D Scene Understanding

PPMStereo: Pick-and-Play Memory Construction for Consistent Dynamic Stereo Matching

GeneMAN: Generalizable Single-Image 3D Human Reconstruction from Multi-Source Human Data

Generative Perception of Shape and Material from Differential Motion

CAGE: Continuity-Aware edGE Network Unlocks Robust Floorplan Reconstruction

GLVD: Guided Learned Vertex Descent

MetaGS: A Meta-Learned Gaussian-Phong Model for Out-of-Distribution 3D Scene Relighting

Spike4DGS: Towards High-Speed Dynamic Scene Rendering with 4D Gaussian Splatting via a Spike Camera Array

Orientation Matters: Making 3D Generative Models Orientation-Aligned

ReCon-GS: Continuum-Preserved Guassian Streaming for Fast and Compact Reconstruction of Dynamic Scenes

V2X-Radar: A Multi-modal Dataset with 4D Radar for Cooperative Perception

TAPVid-360: Tracking Any Point in 360 from Narrow Field of View Video

VADB: A Large-Scale Video Aesthetic Database with Professional and Multi-Dimensional Annotations

A2Seek: Towards Reasoning-Centric Benchmark for Aerial Anomaly Understanding

EgoExOR: An Ego-Exo-Centric Operating Room Dataset for Surgical Activity Understanding

Knot So Simple: A Minimalistic Environment for Spatial Reasoning

Roboflow100-VL: A Multi-Domain Object Detection Benchmark for Vision-Language Models

MMLongBench: Benchmarking Long-Context Vision-Language Models Effectively and Thoroughly

FAVOR-Bench: A Comprehensive Benchmark for Fine-Grained Video Motion Understanding

Embodied Web Agents: Bridging Physical-Digital Realms for Integrated Agent Intelligence

MedSG-Bench: A Benchmark for Medical Image Sequences Grounding

GeRaF: Neural Geometry Reconstruction from Radio Frequency Signals

Fix False Transparency by Noise Guided Splatting

Motion Matters: Compact Gaussian Streaming for Free-Viewpoint Video Reconstruction

Event-based HDR Structured Light

Object-X: Learning to Reconstruct Multi-Modal 3D Object Representations

VoxDet: Rethinking 3D Semantic Scene Completion as Dense Object Detection

Track, Inpaint, Resplat: Subject-driven 3D and 4D Generation with Progressive Texture Infilling

Gaussian Herding across Pens: An Optimal Transport Perspective on Global Gaussian Reduction for 3DGS

High Resolution UDF Meshing via Iterative Networks

Seeking and Updating with Live Visual Knowledge

OST-Bench: Evaluating the Capabilities of MLLMs in Online Spatio-temporal Scene Understanding

Audio-Sync Video Generation with Multi-Stream Temporal Control

ForgerySleuth: Empowering Multimodal Large Language Models for Image Manipulation Detection

Unleashing Hour-Scale Video Training for Long Video-Language Understanding

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents

GRE Suite: Geo-localization Inference via Fine-Tuned Vision-Language Models and Enhanced Reasoning Chains

HoliTom: Holistic Token Merging for Fast Video Large Language Models

Enhancing Compositional Reasoning in CLIP via Reconstruction and Alignment of Text Descriptions

Aha! - Predicting What Matters Next: Online Highlight Detection Without Looking Ahead

MDReID: Modality-Decoupled Learning for Any-to-Any Multi-Modal Object Re-Identification

Mitigating Hallucination in VideoLLMs via Temporal-Aware Activation Engineering

MR. Video: MapReduce as an Effective Principle for Long Video Understanding

DecompNet: Enhancing Time Series Forecasting Models with Implicit Decomposition

SceneForge: Enhancing 3D-text alignment with Structured Scene Compositions

Q-Insight: Understanding Image Quality via Visual Reinforcement Learning

Perception-R1: Pioneering Perception Policy with Reinforcement Learning

StreamBridge: Turning Your Offline Video Large Language Model into a Proactive Streaming Assistant

ViSPLA: Visual Iterative Self-Prompting for Language-Guided 3D Affordance Learning

Promptable 3-D Object Localization with Latent Diffusion Models

Cross-modal Associations in Vision and Language Models: Revisiting the Bouba-Kiki Effect

Zooming from Context to Cue: Hierarchical Preference Optimization for Multi-Image MLLMs

Highlighting What Matters: Promptable Embeddings for Attribute-Focused Image Retrieval

Tracking and Understanding Object Transformations

Efficient RAW Image Deblurring with Adaptive Frequency Modulation

MANGO: Multimodal Attention-based Normalizing Flow Approach to Fusion Learning

MixSignGraph: A Sign Sequence is Worth Mixed Graphs of Nodes

GUI-Rise: Structured Reasoning and History Summarization for GUI Navigation

TC-Light: Temporally Coherent Generative Rendering for Realistic World Transfer

Scaling RL to Long Videos

VideoLucy: Deep Memory Backtracking for Long Video Understanding

GRIT: Teaching MLLMs to Think with Images

Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension

Hierarchical Information Aggregation for Incomplete Multimodal Alzheimer's Disease Diagnosis

Aligning by Misaligning: Boundary-aware Curriculum Learning for Multimodal Alignment

VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations on Synthetic Video Understanding

VR-Drive: Viewpoint-Robust End-to-End Driving with Feed-Forward 3D Gaussian Splatting

Understanding and Rectifying Safety Perception Distortion in VLMs

Intervene-All-Paths: Unified Mitigation of LVLM Hallucinations across Alignment Formats

VITRIX-CLIPIN: Enhancing Fine-Grained Visual Understanding in CLIP via Instruction-Editing Data and Long Captions

Toward Human Deictic Gesture Target Estimation

ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs

Continual Multimodal Contrastive Learning

A Unified Solution to Video Fusion: From Multi-Frame Learning to Benchmarking

Bisecle: Binding and Separation in Continual Learning for Video Language Understanding

Uni-MuMER: Unified Multi-Task Fine-Tuning of Vision-Language Model for Handwritten Mathematical Expression Recognition

Kinaema: a recurrent sequence model for memory and pose in motion

ADMN: A Layer-Wise Adaptive Multimodal Network for Dynamic Input Noise and Compute Resources

Language‑Bias‑Resilient Visual Question Answering via Adaptive Multi‑Margin Collaborative Debiasing

Physics-informed Neural Operator for Pansharpening

EvolvedGRPO: Unlocking Reasoning in LVLMs via Progressive Instruction Evolution

MMaDA: Multimodal Large Diffusion Language Models

Robust Cross-modal Alignment Learning for Cross-Scene Spatial Reasoning and Grounding

Multi-step Visual Reasoning with Visual Tokens Scaling and Verification

Enhancing Infrared Vision: Progressive Prompt Fusion Network and Benchmark

Learning Human-Object Interaction as Groups

GMM-based VAE model with Normalising Flow for effective stochastic segmentation

OPMapper: Enhancing Open-Vocabulary Semantic Segmentation with Multi-Guidance Information

Generalizable Hand-Object Modeling from Monocular RGB Images via 3D Gaussians

SANSA: Unleashing the Hidden Semantics in SAM2 for Few-Shot Segmentation

TRiCo: Triadic Game-Theoretic Co-Training for Robust Semi-Supervised Learning

CLIPTTA: Robust Contrastive Vision-Language Test-Time Adaptation

Breaking Latent Prior Bias in Detectors for Generalizable AIGC Image Detection

C$^2$Prompt: Class-aware Client Knowledge Interaction for Federated Continual Learning

Topology-Aware Learning of Tubular Manifolds via SE(3)-Equivariant Network on Ball B-Spline Curve

Exploring and Leveraging Class Vectors for Classifier Editing

DAA: Amplifying Unknown Discrepancy for Test-Time Discovery

ZigzagPointMamba: Spatial-Semantic Mamba for Point Cloud Understanding

DeltaFlow: An Efficient Multi-frame Scene Flow Estimation Method

BiggerGait: Unlocking Gait Recognition with Layer-wise Representations from Large Vision Models

Visual Diversity and Region-aware Prompt Learning for Zero-shot HOI Detection

Diffusion Classifiers Understand Compositionality, but Conditions Apply

OpenLex3D: A Tiered Benchmark for Open-Vocabulary 3D Scene Representations

CaMiT: A Time-Aware Car Model Dataset for Classification and Generation

EPFL-Smart-Kitchen: An Ego-Exo Multi-Modal Dataset for Challenging Action and Motion Understanding in Video-Language Models

Merlin L48 Spectrogram Dataset

BeyondMix: Leveraging Structural Priors and Long-Range Dependencies for Domain-Invariant LiDAR Segmentation

OVS Meets Continual Learning: Towards Sustainable Open-Vocabulary Segmentation

Leaving No OOD Instance Behind: Instance-Level OOD Fine-Tuning for Anomaly Segmentation

Credal Prediction based on Relative Likelihood

Delving into Cascaded Instability: A Lipschitz Continuity View on Image Restoration and Object Detection Synergy

NOVA: A Benchmark for Rare Anomaly Localization and Clinical Reasoning in Brain MRI

Mars-Bench: A Benchmark for Evaluating Foundation Models for Mars Science Tasks

BurstDeflicker: A Benchmark Dataset for Flicker Removal in Dynamic Scenes

BEDLAM2.0: Synthetic humans and cameras in motion

Týr-the-Pruner: Structural Pruning LLMs via Global Sparsity Distribution Optimization

HIDISC: A Hyperbolic Framework for Domain Generalization with Generalized Category Discovery

Efficient and Generalizable Mixed-Precision Quantization via Topological Entropy

Fuse2Match: Training-Free Fusion of Flow, Diffusion, and Contrastive Models for Zero-Shot Semantic Matching

DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling

Martingale Posterior Neural Networks for Fast Sequential Decision Making

MiniMax-Remover: Taming Bad Noise Helps Video Object Removal

MoRIC: A Modular Region-based Implicit Codec for Image Compression

4KAgent: Agentic Any Image to 4K Super-Resolution

SoPo: Text-to-Motion Generation Using Semi-Online Preference Optimization

Diffusion Feature Field for Text-based 3D Editing with Gaussian Splatting

Grids Often Outperform Implicit Neural Representation at Compressing Dense Signals

When No Paths Lead to Rome: Benchmarking Systematic Neural Relational Reasoning

Dataset Distillation of 3D Point Clouds via Distribution Matching

DeblurDiff: Real-Word Image Deblurring with Generative Diffusion Models

End-to-End Low-Light Enhancement for Object Detection with Learned Metadata from RAWs

Wasserstein Convergence of Critically Damped Langevin Diffusions

Certifying Deep Network Risks and Individual Predictions with PAC-Bayes Loss via Localized Priors

Statistical Analysis of the Sinkhorn Iterations for Two-Sample Schr\"{o}dinger Bridge Estimation

On the Hardness of Approximating Distributions with Tractable Probabilistic Models

Novel Exploration via Orthogonality

LaRes: Evolutionary Reinforcement Learning with LLM-based Adaptive Reward Search

The World Is Bigger: A Computationally-Embedded Perspective on the Big World Hypothesis

Videos are Sample-Efficient Supervisions: Behavior Cloning from Videos via Latent Representations

Structure Matters: Dynamic Policy Gradient

The Curse of Multi-Modalities: Evaluating Hallucinations of Large Multimodal Models across Language, Visual, and Audio

DQVis Dataset: Natural Language to Biomedical Visualization

LooGLE v2: Are LLMs Ready for Real World Long Dependency Challenges?

TalkCuts: A Large-Scale Dataset for Multi-Shot Human Speech Video Generation

InterMT: Multi-Turn Interleaved Preference Alignment with Human Feedback

PanTS: The Pancreatic Tumor Segmentation Dataset

SingRef6D: Monocular Novel Object Pose Estimation with a Single RGB Reference

SRSR: Enhancing Semantic Accuracy in Real-World Image Super-Resolution with Spatially Re-Focused Text-Conditioning

FAST: Foreground‑aware Diffusion with Accelerated Sampling Trajectory for Segmentation‑oriented Anomaly Synthesis

Towards Predicting Any Human Trajectory In Context

Pixel Reasoner: Incentivizing Pixel Space Reasoning via Curiosity-Driven Reinforcement Learning

SnapMoGen: Human Motion Generation from Expressive Texts

FIPER: Factorized Features for Robust Image Super-Resolution and Compression

Quantile Reward Policy Optimization: Alignment with Pointwise Regression and Exact Partition Functions

Offline Goal-conditioned Reinforcement Learning with Quasimetric Representations

How Far Are We from Optimal Reasoning Efficiency?

Predictive Preference Learning from Human Interventions

Can LLMs Outshine Conventional Recommenders? A Comparative Evaluation

MIR-Bench: Can Your LLM Recognize Complicated Patterns via Many-Shot In-Context Reasoning?

UniHG: A Large-scale Universal Heterogeneous Graph Dataset and Benchmark for Representation Learning and Cross-Domain Transferring

BLINK-Twice: You see, but do you observe? A Reasoning Benchmark on Visual Perception

Leader360V: A Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment

Towards Identifiability of Hierarchical Temporal Causal Representation Learning

See&Trek: Training-Free Spatial Prompting for Multimodal Large Language Model

Steering Information Utility in Key-Value Memory for Language Model Post-Training

Succeed or Learn Slowly: Sample Efficient Off-Policy Reinforcement Learning for Mobile App Control

GIST: Greedy Independent Set Thresholding for Max-Min Diversification with Submodular Utility

Real-World Adverse Weather Image Restoration via Dual-Level Reinforcement Learning with High-Quality Cold Start

NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints

Risk-aware Direct Preference Optimization under Nested Risk Measure

Learning to price with resource constraints: from full information to machine-learned prices

HYPERION: Fine-Grained Hypersphere Alignment for Robust Federated Graph Learning

MiCo: Multi-image Contrast for Reinforcement Visual Reasoning

Theoretical Investigation of Adafactor for Non-Convex Smooth Optimization

Continuous-time Riemannian SGD and SVRG Flows on Wasserstein Probabilistic Space

Seeing the Arrow of Time in Large Multimodal Models

HyperET: Efficient Training in Hyperbolic Space for Multi-modal Large Language Models

Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics

Inverse Methods for Missing Data Imputation

Asymmetric Dual-Lens Video Deblurring

MLLMs Need 3D-Aware Representation Supervision for Scene Understanding

FairDD: Fair Dataset Distillation

On Reasoning Strength Planning in Large Reasoning Models

State Size Independent Statistical Error Bound for Discrete Diffusion Models

Principled Fine-tuning of LLMs from User-Edits: A Medley of Preference, Supervision, and Reward

ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding

Momentum Multi-Marginal Schrödinger Bridge Matching

CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up

EvoLM: In Search of Lost Language Model Training Dynamics

Improved Representation Steering for Language Models

Domain-Specific Pruning of Large Mixture-of-Experts Models with Few-shot Demonstrations

CREA: A Collaborative Multi-Agent Framework for Creative Image Editing and Generation

Learning Intractable Multimodal Policies with Reparameterization and Diversity Regularization

Which Data Attributes Stimulate Math and Code Reasoning? An Investigation via Influence Functions

How Many Tokens Do 3D Point Cloud Transformer Architectures Really Need?

Image Super-Resolution with Guarantees via Conformalized Generative Models

Parallel Scaling Law for Language Models

OmniTalker: One-shot Real-time Text-Driven Talking Audio-Video Generation With Multimodal Style Mimicking

SD-KDE: Score-Debiased Kernel Density Estimation

Effective Policy Learning for Multi-Agent Online Coordination Beyond Submodular Objectives

Routing Mamba: Scaling State Space Models with Mixture-of-Experts Projection

NavBench: Probing Multimodal Large Language Models for Embodied Navigation

When Worse is Better: Navigating the Compression Generation Trade-off In Visual Tokenization

MEGADance: Mixture-of-Experts Architecture for Genre-Aware 3D Dance Generation

Efficient Speech Language Modeling via Energy Distance in Continuous Latent Space

ReDit: Reward Dithering for Improved LLM Policy Optimization

Conditioning Matters: Training Diffusion Policies is Faster Than You Think

Conformal Arbitrage: Risk-Controlled Balancing of Competing Objectives in Language Models

Kinetics: Rethinking Test-Time Scaling Law

LoRA vs Full Fine-tuning: An Illusion of Equivalence

Interactive Anomaly Detection for Articulated Objects via Motion Anticipation

Restricted Spectral Gap Decomposition for Simulated Tempering Targeting Mixture Distributions

Sim-LLM: Optimizing LLM Inference at the Edge through Inter-Task KV Reuse

AdvEDM: Fine-grained Adversarial Attack against VLM-based Embodied Agents

MARS: A Malignity-Aware Backdoor Defense in Federated Learning

Vanish into Thin Air: Cross-prompt Universal Adversarial Attacks for SAM2

SuperCLIP: CLIP with Simple Classification Supervision

Improving Model-Based Reinforcement Learning by Converging to Flatter Minima

Data Mixing Can Induce Phase Transitions in Knowledge Acquisition

Does Thinking More Always Help? Mirage of Test-Time Scaling in Reasoning Models

Breaking the Order Barrier: Off-Policy Evaluation for Confounded POMDPs

Adaptive and Multi-scale Affinity Alignment for Hierarchical Contrastive Learning

Adaptive Distraction: Probing LLM Contextual Robustness with Automated Tree Search

Spotlight Attention: Towards Efficient LLM Generation via Non-linear Hashing-based KV Cache Retrieval

Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers

PREAMBLE: Private and Efficient Aggregation via Block Sparse Vectors

Boosting Knowledge Utilization in Multimodal Large Language Models via Adaptive Logits Fusion and Attention Reallocation

Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods

Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need?

Transductive Conformal Inference for Full Ranking

Nearly Dimension-Independent Convergence of Mean-Field Black-Box Variational Inference

NeuralSurv: Deep Survival Analysis with Bayesian Uncertainty Quantification

Vicinal Label Supervision for Reliable Aleatoric and Epistemic Uncertainty Estimation

A Hierarchy of Graphical Models for Counterfactual Inferences

HoT-VI: Reparameterizable Variational Inference for Capturing Instance-Level High-Order Correlations

Stationary Kernels and Gaussian Processes on Lie Groups and their Homogeneous Spaces II: non-compact symmetric spaces

Optimal kernel regression bounds under energy-bounded noise

List-Level Distribution Coupling with Applications to Speculative Decoding and Lossy Compression

Energy-based generator matching: A neural sampler for general state space

Metropolis Adjusted Microcanonical Hamiltonian Monte Carlo

Test-Time Scaling of Diffusion Models via Noise Trajectory Search

Active Measurement: Efficient Estimation at Scale

$\Psi$-Sampler: Initial Particle Sampling for SMC-Based Inference-Time Reward Alignment in Score Models

Embeddings as Probabilistic Equivalence in Logic Programs

Scaling Laws for Gradient Descent and Sign Descent for Linear Bigram Models under Zipf’s Law

Logic.py: Bridging the Gap between LLMs and Constraint Solvers

Improved Approximation Algorithms for Chromatic and Pseudometric-Weighted Correlation Clustering

SVRPBench: A Realistic Benchmark for Stochastic Vehicle Routing Problem

On the Optimal Construction of Unbiased Gradient Estimators for Zeroth-Order Optimization

A Computationally Viable Numerical Gradient-based Technique for Optimal Covering Problems

A Unified Analysis of Stochastic Gradient Descent with Arbitrary Data Permutations and Beyond

Optimal Rates in Continual Linear Regression via Increasing Regularization

Unlocking Dataset Distillation with Diffusion Models

Conditional Gradient Methods with Standard LMO for Stochastic Simple Bilevel Optimization

Faster Algorithms for Structured John Ellipsoid Computation

TSENOR: Highly-Efficient Algorithm for Finding Transposable N:M Sparse Masks

Factor Decorrelation Enhanced Data Removal from Deep Predictive Models

Adaptive Riemannian ADMM for Nonsmooth Optimization: Optimal Complexity without Smoothing

Efficient Adaptive Federated Optimization

Finite-Time Analysis of Stochastic Nonconvex Nonsmooth Optimization on the Riemannian Manifolds

Perturbation Bounds for Low-Rank Inverse Approximations under Noise

Opinion Maximization in Social Networks by Modifying Internal Opinions

Non-monotone Submodular Optimization: $p$-Matchoid Constraints and Fully Dynamic Setting

On Inductive Biases That Enable Generalization in Diffusion Transformers

Robustifying Learning-Augmented Caching Efficiently without Compromising 1-Consistency

Fine-grained Analysis and Faster Algorithms for Iteratively Solving Linear Systems

PARALLELPROMPT: Extracting Parallelism from Large Language Model Queries

SpecEdge: Scalable Edge-Assisted Serving Framework for Interactive LLMs

FedWMSAM: Fast and Flat Federated Learning via Weighted Momentum and Sharpness-Aware Minimization

Towards Robust Parameter-Efficient Fine-Tuning for Federated Learning

Multiplayer Federated Learning: Reaching Equilibrium with Less Communication

Enhancing Optimizer Stability: Momentum Adaptation of The NGN Step-size

DynaPipe: Dynamic Layer Redistribution for Efficient Serving of LLMs with Pipeline Parallelism

Genesis: Multimodal Driving Scene Generation with Spatio-Temporal and Cross-Modal Consistency

FedFree: Breaking Knowledge-sharing Barriers through Layer-wise Alignment in Heterogeneous Federated Learning

Approximate Gradient Coding for Distributed Learning with Heterogeneous Stragglers

New Parallel and Streaming Algorithms for Directed Densest Subgraph

Distributed mediation analysis with communication efficiency

SuffixDecoding: Extreme Speculative Decoding for Emerging AI Applications

When majority rules, minority loses: bias amplification of gradient descent

Feature Unlearning: Theoretical Foundations and Practical Applications with Shuffling

Breaking the Frozen Subspace: Importance Sampling for Low-Rank Optimization in LLM Pretraining

Sparse MeZO: Less Parameters for Better Performance in Zeroth-Order LLM Fine-Tuning

TF-MAS: Training-free Mamba2 Architecture Search

Binary Quadratic Quantization: Beyond First-Order Quantization for Real-Valued Matrix Compression

Accelerating Model-Free Optimization via Averaging of Cost Samples

BayeSQP: Bayesian Optimization through Sequential Quadratic Programming

Distributional Adversarial Attacks and Training in Deep Hedging

Non-Clairvoyant Scheduling with Progress Bars

Semi-infinite Nonconvex Constrained Min-Max Optimization

Grammars of Formal Uncertainty: When to Trust LLMs in Automated Reasoning Tasks

Inverse Optimization Latent Variable Models for Learning Costs Applied to Route Problems

RCCDA: Adaptive Model Updates in the Presence of Concept Drift under a Constrained Resource Budget

R-KV: Redundancy-aware KV Cache Compression for Reasoning Models

Stochastic-Constrained Stochastic Optimization with Markovian Data

Online Estimation and Inference for Robust Policy Evaluation in Reinforcement Learning

(ends 2:00 PM)

1 p.m.

Break:

Hosted Lunch

(ends 2:30 PM)

2 p.m.

Award:

Sejnowski-Hinton Award

(ends 2:30 PM)

2:30 p.m.

San Diego Invited Talk:

Demystifying depth: Principles of learning in deep neural networks

Andrew Saxe

(ends 3:30 PM)

3:30 p.m.

Oral 6A Reinforcement/State-space 3 [3:30-4:30]

Orals 3:30-4:30

[3:30] A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning

[3:50] 1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities

[4:10] Learning long range dependencies through time reversal symmetry breaking

(ends 4:30 PM)

Oral 6B Multimodal 4 [3:30-4:30]

Orals 3:30-4:30

[3:30] KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction

[3:50] MokA: Multimodal Low-Rank Adaptation for MLLMs

[4:10] ElasticMM: Efficient Multimodal LLMs Serving with Elastic Multimodal Parallelism

(ends 4:30 PM)

Oral 6C Deep Learning 3 [3:30-4:30]

Orals 3:30-4:30

[3:30] Generalized Linear Mode Connectivity for Transformers

[3:50] On Linear Mode Connectivity of Mixture-of-Experts Architectures

[4:10] Learning (Approximately) Equivariant Networks via Constrained Optimization

(ends 4:30 PM)

Oral 6D Graph [3:30-4:30]

Orals 3:30-4:30

[3:30] GnnXemplar: Exemplars to Explanations - Natural Language Rules for Global GNN Interpretability

[3:50] RAG4GFM: Bridging Knowledge Gaps in Graph Foundation Models through Graph Retrieval Augmented Generation

[4:10] Discovering Opinion Intervals from Conflicts in Signed Graphs

(ends 4:30 PM)

Oral 6E Theory 4 [3:30-4:30]

Orals 3:30-4:30

[3:30] An Optimized Franz-Parisi Criterion and its Equivalence with SQ Lower Bounds

[3:50] Spectral Perturbation Bounds for Low-Rank Approximation with Applications to Privacy

[4:10] Improved Regret Bounds for Gaussian Process Upper Confidence Bound in Bayesian Optimization

(ends 4:30 PM)

4:30 p.m.

Break:

Coffee Break

(ends 5:30 PM)

San Diego Poster Session 6 [4:30-7:30]

Posters 4:30-7:30

Sheetpedia: A 300K-Spreadsheet Corpus for Spreadsheet Intelligence and LLM Fine-Tuning

RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models

An Ellipsoid Algorithm for Online Convex Optimization

Prohibiting Generative AI in any Form of Weapon Control

A Principled Approach to Randomized Selection under Uncertainty: Applications to Peer Review and Grant Funding

On Optimal Steering to Achieve Exact Fairness

Homogeneous Algorithms Can Reduce Competition in Personalized Pricing

GraSS: Scalable Data Attribution with Gradient Sparsification and Sparse Projection

The Rashomon Set Has It All: Analyzing Trustworthiness of Trees under Multiplicity

Parameterized Synthetic Text Generation with SimpleStories

How do Transformers Learn Implicit Reasoning?

Datasets, Documents, and Repetitions: The Practicalities of Unequal Data Quality

Emergence and Evolution of Interpretable Concepts in Diffusion Models

Better Language Model Inversion by Compactly Representing Next-Token Distributions

Minimizing False-Positive Attributions in Explanations of Non-Linear Models

Sample-efficient Learning of Concepts with Theoretical Guarantees: from Data to Concepts without Interventions

Revisiting LRP: Positional Attribution as the Missing Ingredient for Transformer Explainability

Tree Ensemble Explainability through the Hoeffding Functional Decomposition and TreeHFD Algorithm

Do different prompting methods yield a common task representation in language models?

TreeSynth: Synthesizing Diverse Data from Scratch via Tree-Guided Subspace Partitioning

MuSLR: Multimodal Symbolic Logical Reasoning

A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning

STRAP: Spatio-Temporal Pattern Retrieval for Out-of-Distribution Generalization

Rethinking Verification for LLM Code Generation: From Generation to Testing

Enhancing Training Data Attribution with Representational Optimization

Efficiently Verifiable Proofs of Data Attribution

ICPC-Eval: Probing the Frontiers of LLM Reasoning with Competitive Programming Contests

Diagnosing and Addressing Pitfalls in KG-RAG Datasets: Toward More Reliable Benchmarking

Boosting Adversarial Transferability with Spatial Adversarial Alignment

DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents

How Does Topology Bias Distort Message Passing in Graph Recommender? A Dirichlet Energy Perspective

Fairness under Competition

Understanding Fairness and Prediction Error through Subspace Decomposition and Influence Analysis

Distributive Fairness in Large Language Models: Evaluating Alignment with Human Values

AgentAuditor: Human-level Safety and Security Evaluation for LLM Agents

Trans-EnV: A Framework for Evaluating the Linguistic Robustness of LLMs Against English Varieties

A Multi-Task Benchmark for Abusive Language Detection in Low-Resource Settings

LLM Generated Persona is a Promise with a Catch

FedQS: Optimizing Gradient and Model Aggregation for Semi-Asynchronous Federated Learning

Comparison requires valid measurement: Rethinking attack success rate comparisons in AI red teaming

Pinpointing Attention-Causal Communication in Language Models

Explaining Similarity in Vision-Language Encoders with Weighted Banzhaf Interactions

Topology of Reasoning: Understanding Large Reasoning Models through Reasoning Graph Properties

The Narrow Gate: Localized Image-Text Communication in Native Multimodal Models

Causal Head Gating: A Framework for Interpreting Roles of Attention Heads in Transformers

Web-Scale Collection of Video Data for 4D Animal Reconstruction

MindGYM: What Matters in Question Synthesis for Thinking-Centric Fine-Tuning?

AGENTIF: Benchmarking Large Language Models Instruction Following Ability in Agentic Scenarios

PSBench: a large-scale benchmark for estimating the accuracy of protein complex structural models

From Flatland to Space: Teaching Vision-Language Models to Perceive and Reason in 3D

On Group Sufficiency Under Label Bias

Versatile differentially private learning for general loss functions

Don’t call it privacy-preserving or human-centric pose estimation if you don’t measure privacy

Struct-Bench: A Benchmark for Differentially Private Structured Text Generation

RUAGO: Effective and Practical Retain-Free Unlearning via Adversarial Attack and OOD Generator

When Data Can't Meet: Estimating Correlation Across Privacy Barriers

Spectral Perturbation Bounds for Low-Rank Approximation with Applications to Privacy

You Only Communicate Once: One-shot Federated Low-Rank Adaptation of MLLM

The Gaussian Mixing Mechanism: Renyi Differential Privacy via Gaussian Sketches

FedSVD: Adaptive Orthogonalization for Private Federated Learning with LoRA

An Iterative Algorithm for Differentially Private $k$-PCA with Adaptive Noise

DKDR: Dynamic Knowledge Distillation for Reliability in Federated Learning

OmniFC: Rethinking Federated Clustering via Lossless and Secure Distance Reconstruction

Rethinking Fair Federated Learning from Parameter and Client View

TokenSwap: A Lightweight Method to Disrupt Memorized Sequences in LLMs

Purifying Approximate Differential Privacy with Randomized Post-processing

Toward Efficient Inference Attacks: Shadow Model Sharing via Mixture-of-Experts

Virus Infection Attack on LLMs: Your Poisoning Can Spread "VIA" Synthetic Data

Learning to Steer: Input-dependent Steering for Multimodal LLMs

Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning

Predicting the Performance of Black-box Language Models with Follow-up Queries

SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations

LOMIA: Label-Only Membership Inference Attacks against Pre-trained Large Vision-Language Models

CoP: Agentic Red-teaming for Large Language Models using Composition of Principles

OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metrics

MARS-VFL: A Unified Benchmark for Vertical Federated Learning with Realistic Evaluation

Differentially Private High-dimensional Variable Selection via Integer Programming

Deep Learning with Plausible Deniability

Differential Privacy on Fully Dynamic Streams

FLUX: Efficient Descriptor-Driven Clustered Federated Learning under Arbitrary Distribution Shifts

MPCache: MPC-Friendly KV Cache Eviction for Efficient Private LLM Inference

Dynamical Properties of Tokens in Self-Attention and Effects of Positional Encoding

Adversarial Paraphrasing: A Universal Attack for Humanizing AI-Generated Text

Synthesize Privacy-Preserving High-Resolution Images via Private Textual Intermediaries

RULE: Reinforcement UnLEarning Achieves Forget-retain Pareto Optimality

Unlearning-Aware Minimization

Approximate Domain Unlearning for Vision-Language Models

Ridge Boosting is Both Robust and Efficient

C-SafeGen: Certified Safe LLM Generation with Claim-Based Streaming Guardrails

Don’t Forget the Enjoin: FocalLoRA for Instruction Hierarchical Alignment in Large Language Models

What Does It Take to Build a Performant Selective Classifier?

Attack via Overfitting: 10-shot Benign Fine-tuning to Jailbreak LLMs

Towards a General Attention Framework on Gyrovector Spaces for Matrix Manifolds

LC-Opt: Benchmarking Reinforcement Learning and Agentic AI for End-to-End Liquid Cooling Optimization in Data Centers

TEMPO: Temporal Multi-scale Autoregressive Generation of Protein Conformational Ensembles

NEED: Cross-Subject and Cross-Task Generalization for Video and Image Reconstruction from EEG Signals

MACS: Multi-Agent Reinforcement Learning for Optimization of Crystal Structures

Path Gradients after Flow Matching

Unlocking hidden biomolecular conformational landscapes in diffusion models at inference time

Atomic Diffusion Models for Small Molecule Structure Elucidation from NMR Spectra

Repurposing AlphaFold3-like Protein Folding Models for Antibody Sequence and Structure Co-design

Unified Scaling Laws for Compressed Representations

Accelerating 3D Molecule Generative Models with Trajectory Diagnosis

A Markov Decision Process for Variable Selection in Branch & Bound

Self-supervised Blending Structural Context of Visual Molecules for Robust Drug Interaction Prediction

Pareto-Optimal Energy Alignment for Designing Nature-Like Antibodies

Reinforced Active Learning for Large-Scale Virtual Screening with Learnable Policy Model

Retro-R1: LLM-based Agentic Retrosynthesis

EDBench: Large-Scale Electron Density Data for Molecular Modeling

KTAE: A Model-Free Algorithm to Key-Tokens Advantage Estimation in Mathematical Reasoning

MAPLE: Multi-scale Attribute-enhanced Prompt Learning for Few-shot Whole Slide Image Classification

Negative Feedback Really Matters: Signed Dual-Channel Graph Contrastive Learning Framework for Recommendation

TGA: True-to-Geometry Avatar Dynamic Reconstruction

TrajAgent: An LLM-Agent Framework for Trajectory Modeling via Large-and-Small Model Collaboration

ForceFM: Enhancing Protein-Ligand Predictions through Force-Guided Flow Matching

Automatic Auxiliary Task Selection and Adaptive Weighting Boost Molecular Property Prediction

Towards Unified and Lossless Latent Space for 3D Molecular Latent Diffusion Modeling

Consistent Sampling and Simulation: Molecular Dynamics with Energy-Based Diffusion Models

Progressive Inference-Time Annealing of Diffusion Models for Sampling from Boltzmann Densities

A Multimodal Benchmark for Framing of Oil & Gas Advertising and Potential Greenwashing Detection

AtmosSci-Bench: Evaluating the Recent Advance of Large Language Model for Atmospheric Science

Align-DA: Align Score-based Atmospheric Data Assimilation with Multiple Preferences

Cloud4D: Estimating Cloud Properties at a High Spatial and Temporal Resolution

PRING: Rethinking Protein-Protein Interaction Prediction from Pairs to Graphs

SpecMER: Fast Protein Generation with K-mer Guided Speculative Decoding

Modeling Microenvironment Trajectories on Spatial Transcriptomics with NicheFlow

Inferring stochastic dynamics with growth from cross-sectional data

scPilot: Large Language Model Reasoning Toward Automated Single-Cell Analysis and Discovery

Modeling Cell Dynamics and Interactions with Unbalanced Mean Field Schrödinger Bridge

Causality-Induced Positional Encoding for Transformer-Based Representation Learning of Non-Sequential Features

Multimodal 3D Genome Pre-training

A Diffusion Model for Regular Time Series Generation from Irregular Data with Completion and Masking

CoRe: Benchmarking LLMs’ Code Reasoning Capabilities through Static Analysis Tasks

CHASM: Unveiling Covert Advertisements on Chinese Social Media

WolBanking77: Wolof Banking Speech Intent Classification Dataset

Fast MRI for All: Bridging Access Gaps by Training without Raw Data

Uncertainty-Calibrated Prediction of Randomly-Timed Biomarker Trajectories with Conformal Bands

GEM: Empowering MLLM for Grounded ECG Understanding with Time Series and Images

MoPFormer: Motion-Primitive Transformer for Wearable-Sensor Activity Recognition

AOR: Anatomical Ontology-Guided Reasoning for Medical Large Multimodal Model in Chest X-Ray Interpretation

Cancer Survival Analysis via Zero-shot Tumor Microenvironment Segmentation on Low-resolution Whole Slide Pathology Images

AneuG-Flow: A Large-Scale Synthetic Dataset of Diverse Intracranial Aneurysm Geometries and Hemodynamics

Towards Evaluating Proactive Risk Awareness of Multimodal Language Models

GeoDynamics: A Geometric State‑Space Neural Network for Understanding Brain Dynamics on Riemannian Manifolds

Statistically Valid Post-Deployment Monitoring Should Be Standard for AI-Based Digital Health

Context-Aware Regularization with Markovian Integration for Attention-Based Nucleotide Analysis

Venus-MAXWELL: Efficient Learning of Protein-Mutation Stability Landscapes using Protein Language Models

Omni-DNA: A Genomic Model Supporting Sequence Understanding, Long-context, and Textual Annotation

MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix

A Simple Linear Patch Revives Layer-Pruned Large Language Models

SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning

AdaDetectGPT: Adaptive Detection of LLM-Generated Text with Statistical Guarantees

Enhancing LLM Planning for Robotics Manipulation through Hierarchical Procedural Knowledge Graphs

Consistently Simulating Human Personas with Multi-Turn Reinforcement Learning

ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation

SongBloom: Coherent Song Generation via Interleaved Autoregressive Sketching and Diffusion Refinement

dKV-Cache: The Cache for Diffusion Language Models

PolarQuant: Leveraging Polar Transformation for Key Cache Quantization and Decoding Acceleration

Don’t Let It Fade: Preserving Edits in Diffusion Language Models via Token Timestep Allocation

Conformal Linguistic Calibration: Trading-off between Factuality and Specificity

DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generation

LeVo: High-Quality Song Generation with Multi-Preference Alignment

Reasoning Planning for Language Models

Joint Design of Protein Surface and Backbone Using a Diffusion Bridge Model

A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning

NOBLE - Neural Operator with Biologically-informed Latent Embeddings to Capture Experimental Variability in Biological Neuron Models

Spike-RetinexFormer: Rethinking Low-light Image Enhancement with Spiking Neural Networks

Bounds on the computational complexity of neurons due to dendritic morphology

Inference of Whole Brain Electrophysiological Networks Through Multimodal Integration of Simultaneous Scalp and Intracranial EEG

Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference

PlanU: Large Language Model Reasoning through Planning under Uncertainty

Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning

Absolute Zero: Reinforced Self-play Reasoning with Zero Data

OSTAR: Optimized Statistical Text-classifier with Adversarial Resistance

Sparta Alignment: Collectively Aligning Multiple Language Models through Combat

SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based Agents

Know What You Don't Know: Uncertainty Calibration of Process Reward Models

Collaborative Reasoner: Self-Improving Social Agents with Synthetic Conversations

Less is More: Local Intrinsic Dimensions of Contextual Language Models

Are Large Reasoning Models Good Translation Evaluators? Analysis and Performance Boost

LIMOPro: Reasoning Refinement for Efficient and Effective Test-time Scaling

Audio Super-Resolution with Latent Bridge Models

NeuroH-TGL: Neuro-Heterogeneity Guided Temporal Graph Learning Strategy for Brain Disease Diagnosis

Measuring and Controlling Solution Degeneracy across Task-Trained Recurrent Neural Networks

From Pixels to Views: Learning Angular-Aware and Physics-Consistent Representations for Light Field Microscopy

Transformer brain encoders explain human high-level visual responses

Unfolding the Black Box of Recurrent Neural Networks for Path Integration

S$^2$M-Former: Spiking Symmetric Mixing Branchformer for Brain Auditory Attention Detection

POCO: Scalable Neural Forecasting through Population Conditioning

Inpainting the Neural Picture: Inferring Unrecorded Brain Area Dynamics from Multi-Animal Datasets

Bridging Critical Gaps in Convergent Learning: How Representational Alignment Evolves Across Layers, Training, and Distribution Shifts

Is Limited Participant Diversity Impeding EEG-based Machine Learning?

LTD-Bench: Evaluating Large Language Models by Letting Them Draw

Model–Behavior Alignment under Flexible Evaluation: When the Best-Fitting Model Isn’t the Right One

Mechanistic Interpretability of RNNs emulating Hidden Markov Models

Quantifying Uncertainty in Error Consistency: Towards Reliable Behavioral Comparison of Classifiers

What do you know? Bayesian knowledge inference for navigating agents

RobIA: Robust Instance-aware Continual Test-time Adaptation for Deep Stereo

DCA: Graph-Guided Deep Embedding Clustering for Brain Atlases

LithoSim: A Large, Holistic Lithography Simulation Benchmark for AI-Driven Semiconductor Manufacturing

PSI: A Benchmark for Human Interpretation and Response in Traffic Interactions

Conditional Distribution Compression via the Kernel Conditional Mean Embedding

Track3R: Joint Point Map and Trajectory Prior for Spatiotemporal 3D Understanding

Refining Norms: A Post-hoc Framework for OOD Detection in Graph Neural Networks

Pretraining a Shared Q-Network for Data-Efficient Offline Reinforcement Learning

Price of Parsimony: Complexity of Fourier Sparsity Testing

Finite-Time Bounds for Average-Reward Fitted Q-Iteration

Structural Information-based Hierarchical Diffusion for Offline Reinforcement Learning

Oryx: a Scalable Sequence Model for Many-Agent Coordination in Offline MARL

SutureBot: A Precision Framework & Benchmark For Autonomous End-to-End Suturing

Learning long range dependencies through time reversal symmetry breaking

AutoSciDACT: Automated Scientific Discovery through Contrastive Embedding and Hypothesis Testing

Energy Loss Functions for Physical Systems

Discovering Symbolic Partial Differential Equation by Abductive Learning

Sparse Diffusion Autoencoder for Test-time Adapting Prediction of Complex Systems

Neural Emulator Superiority: When Machine Learning for PDEs Surpasses its Training Data

HyPINO: Multi-Physics Neural Operators via HyperPINNs and the Method of Manufactured Solutions

MoE-Gyro: Self-Supervised Over-Range Reconstruction and Denoising for MEMS Gyroscopes

Graph-based Symbolic Regression with Invariance and Constraint Encoding

DAIL: Beyond Task Ambiguity for Language-Conditioned Reinforcement Learning

BoltzNCE: Learning likelihoods for Boltzmann Generation with Stochastic Interpolants and Noise Contrastive Estimation

Neuro-Spectral Architectures for Causal Physics-Informed Networks

Learning conformational ensembles of proteins based on backbone geometry

CALM-PDE: Continuous and Adaptive Convolutions for Latent Space Modeling of Time-dependent PDEs

TensorRL-QAS: Reinforcement learning with tensor networks for improved quantum architecture search

QCircuitBench: A Large-Scale Dataset for Benchmarking Quantum Algorithm Design

Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models

NAVIX: Scaling MiniGrid Environments with JAX

Learning to Think: Information-Theoretic Reinforcement Fine-Tuning for LLMs

Trajectory Bellman Residual Minimization: A Simple Value-Based Method for LLM Reasoning

Compute-Optimal Scaling for Value-Based Deep RL

Fully Autonomous Neuromorphic Navigation and Dynamic Obstacle Avoidance

ChatVLA-2: Vision-Language-Action Model with Open-World Reasoning

$\textit{HiMaCon:}$ Discovering Hierarchical Manipulation Concepts from Unlabeled Multi-Modal Data

ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning

Failure Prediction at Runtime for Generative Robot Policies

RLGF: Reinforcement Learning with Geometric Feedback for Autonomous Driving Video Generation

Toward Artificial Palpation: Representation Learning of Touch on Soft Bodies

GaussianFusion: Gaussian-Based Multi-Sensor Fusion for End-to-End Autonomous Driving

Flow Matching-Based Autonomous Driving Planning with Advanced Interactive Behavior Modeling

Neighbor-aware Contrastive Disambiguation for Cross-Modal Hashing with Redundant Annotations

Embodied Crowd Counting

Understanding while Exploring: Semantics-driven Active Mapping

Towards Reliable Code-as-Policies: A Neuro-Symbolic Framework for Embodied Task Planning

DiffE2E: Rethinking End-to-End Driving with a Hybrid Diffusion-Regression-Classification Policy

DexFlyWheel: A Scalable and Self-improving Data Generation Framework for Dexterous Manipulation

Universal Visuo-Tactile Video Understanding for Embodied Interaction

Many Minds, One Goal: Time Series Forecasting via Sub-task Specialization and Inter-agent Cooperation

SPOT-Trip: Dual-Preference Driven Out-of-Town Trip Recommendation

DBLoss: Decomposition-based Loss Function for Time Series Forecasting

True Zero-Shot Inference of Dynamical Systems Preserving Long-Term Statistics

Multi-Scale Finetuning for Encoder-based Time Series Foundation Models

Meta Guidance: Incorporating Inductive Biases into Deep Time Series Imputers

Abstain Mask Retain Core: Time Series Prediction by Adaptive Masking Loss with Representation Consistency

Enhancing the Maximum Effective Window for Long-Term Time Series Forecasting

OLinear: A Linear Model for Time Series Forecasting in Orthogonally Transformed Domain

WaLRUS: Wavelets for Long range Representation Using State Space Methods

This Time is Different: An Observability Perspective on Time Series Foundation Models

Temporal Representation Alignment: Successor Features Enable Emergent Compositionality in Robot Instruction Following

TP-MDDN: Task-Preferenced Multi-Demand-Driven Navigation with Autonomous Decision-Making

CoC-VLA: Delving into Adversarial Domain Transfer for Explainable Autonomous Driving via Chain-of-Causality Visual-Language-Action Model

InstructFlow: Adaptive Symbolic Constraint-Guided Code Generation for Long-Horizon Planning

3D Equivariant Visuomotor Policy Learning via Spherical Projection

Learning Spatial-Aware Manipulation Ordering

Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Better

Functional Virtual Adversarial Training for Semi-Supervised Time Series Classification

Adaptive Time Encoding for Irregular Multivariate Time-Series Classification

TimeEmb: A Lightweight Static-Dynamic Disentanglement Framework for Time Series Forecasting

MoFo: Empowering Long-term Time Series Forecasting with Periodic Pattern Modeling

TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning

Synthetic Series-Symbol Data Generation for Time Series Foundation Models

Towards Automated Petrography

IPSI: Enhancing Structural Inference with Automatically Learned Structural Priors

Functional Matching of Logic Subgraphs: Beyond Structural Isomorphism

UniTraj: Learning a Universal Trajectory Foundation Model from Billion-Scale Worldwide Traces

EnCompass: Enhancing Agent Programming with Search Over Program Execution Paths

Enhancing Time Series Forecasting through Selective Representation Spaces: A Patch Perspective

PLMTrajRec: A Scalable and Generalizable Trajectory Recovery Method with Pre-trained Language Models

Computational Algebra with Attention: Transformer Oracles for Border Basis Algorithms

High-Performance Arithmetic Circuit Optimization via Differentiable Architecture Search

VADTree: Explainable Training-Free Video Anomaly Detection via Hierarchical Granularity-Aware Tree

STRATUS: A Multi-agent System for Autonomous Reliability Engineering of Modern Clouds

CADMorph: Geometry‑Driven Parametric CAD Editing via a Plan–Generate–Verify Loop

Siegel Neural Networks

Interpreting Emergent Features in Deep Learning-based Side-channel Analysis

Tracing the Representation Geometry of Language Models from Pretraining to Post-training

Beyond Node-Centric Modeling: Sketching Signed Networks with Simplicial Complexes

Coloring Learning for Heterophilic Graph Representation

Mitigating Overthinking in Large Reasoning Models via Manifold Steering

On the Value of Cross-Modal Misalignment in Multimodal Representation Learning

UnCLe: Towards Scalable Dynamic Causal Discovery in Non-linear Temporal Systems

DeCaFlow: A deconfounding causal generative model

Counterfactual Identifiability via Dynamic Optimal Transport

Causal Discovery and Inference through Next-Token Prediction

A Counterfactual Semantics for Hybrid Dynamical Systems

Causal Sufficiency and Necessity Improves Chain-of-Thought Reasoning

When Causal Dynamics Matter: Adapting Causal Strategies through Meta-Aware Interventions

Resolution of Simpson's paradox via the common cause principle

ContextAgent: Context-Aware Proactive LLM Agents with Open-world Sensory Perceptions

SketchMind: A Multi-Agent Cognitive Framework for Assessing Student-Drawn Scientific Sketches

FACE: A General Framework for Mapping Collaborative Filtering Embeddings into LLM Tokens

Deep Edge Filter: Return of the Human-Crafted Layer in Deep Learning

Mitigating Spurious Features in Contrastive Learning with Spectral Regularization

LLM Interpretability with Identifiable Temporal-Instantaneous Representation

Causal Differentiating Concepts: Interpreting LM Behavior via Causal Representation Learning

Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights

LocDiff: Identifying Locations on Earth by Diffusing in the Hilbert Space

AdaTS: Learning Adaptive Time Series Representations via Dynamic Soft Contrasts

Self-Supervised Contrastive Learning is Approximately Supervised Contrastive Learning

TrajMamba: An Efficient and Semantic-rich Vehicle Trajectory Pre-training Model

CG-SSL: Concept-Guided Self-Supervised Learning

Token Bottleneck: One Token to Remember Dynamics

Robust Transfer Learning with Unreliable Source Data

Towards Minimizing Feature Drift in Model Merging: Layer-wise Task Vector Fusion for Adaptive Knowledge Integration

MINGLE: Mixture of Null-Space Gated Low-Rank Experts for Test-Time Continual Model Merging

Continual Optimization with Symmetry Teleportation for Multi-Task Learning

Encouraging metric-aware diversity in contrastive representation space

Treasure Hunt: Real-time Targeting of the Long Tail using Training-Time Markers

Co-Regularization Enhances Knowledge Transfer in High Dimensions

LLM Meeting Decision Trees on Tabular Data

TPP-SD: Accelerating Transformer Point Process Sampling with Speculative Decoding

Revisiting Logit Distributions for Reliable Out-of-Distribution Detection

Post Hoc Regression Refinement via Pairwise Rankings

Generalizable Reasoning through Compositional Energy Minimization

Towards a Pairwise Ranking Model with Orderliness and Monotonicity for Label Enhancement

Decentralized Dynamic Cooperation of Personalized Models for Federated Continual Learning

Towards a Geometric Understanding of Tensor Learning via the t-Product

Common Task Framework For a Critical Evaluation of Scientific Machine Learning Algorithms

Establishing Best Practices in Building Rigorous Agentic Benchmarks

ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research Code

Mint: A Simple Test-Time Adaptation of Vision-Language Models against Common Corruptions

Revisiting Semi-Supervised Learning in the Era of Foundation Models

Provably Efficient Multi-Task Meta Bandit Learning via Shared Representations

Gated Integration of Low-Rank Adaptation for Continual Learning of Large Language Models

Domain Adaptive Hashing Retrieval via VLM Assisted Pseudo-Labeling and Dual Space Adaptation

Optimal and Provable Calibration in High-Dimensional Binary Classification: Angular Calibration and Platt Scaling

Spectral Graph Coarsening Using Inner Product Preservation and the Grassmann Manifold

Weak-to-Strong Generalization under Distribution Shifts

Keep It on a Leash: Controllable Pseudo-label Generation Towards Realistic Long-Tailed Semi-Supervised Learning

AnaCP: Toward Upper-Bound Continual Learning via Analytic Contrastive Projection

A Bayesian Approach to Contextual Dynamic Pricing using the Proportional Hazards Model with Discrete Price Data

Preference-Based Dynamic Ranking Structure Recognition

Accelerated Evolving Set Processes for Local PageRank Computation

Environment Inference for Learning Generalizable Dynamical System

Large Language Models for Lossless Image Compression: Next-Pixel Prediction in Language Space is All You Need

OOD-Barrier: Build a Middle-Barrier for Open-Set Single-Image Test Time Adaptation via Vision Language Models

Quantifying Distributional Invariance in Causal Subgraph for IRM-Free Graph Generalization

Provable Meta-Learning with Low-Rank Adaptations

When Does Curriculum Learning Help? A Theoretical Perspective

Transfer Learning on Edge Connecting Probability Estimation Under Graphon Model

Principled Model Routing for Unknown Mixtures of Source Domains

Proper Hölder-Kullback Dirichlet Diffusion: A Framework for High Dimensional Generative Modeling

An Optimized Franz-Parisi Criterion and its Equivalence with SQ Lower Bounds

Transformers are almost optimal metalearners for linear classification

Infrequent Exploration in Linear Bandits

An Analytical Theory of Spectral Bias in the Learning Dynamics of Diffusion Models

Safely Learning Controlled Stochastic Dynamics

Information-theoretic Generalization Analysis for VQ-VAEs: A Role of Latent Variables

Agnostic Continuous-Time Online Learning

Dynamic Regret Reduces to Kernelized Static Regret

Improved Regret and Contextual Linear Extension for Pandora's Box and Prophet Inequality

Prediction with expert advice under additive noise

Refinement Methods for Distributed Distribution Estimation under $\ell^p$-Losses

No-Regret Online Autobidding Algorithms in First-price Auctions

Optimism Without Regularization: Constant Regret in Zero-Sum Games

Mechanism Design via the Interim Relaxation

Stackelberg Learning with Outcome-based Payment

Cooperative Bargaining Games Without Utilities: Mediated Solutions from Direction Oracles

Prior-Guided Diffusion Planning for Offline Reinforcement Learning

Incentive-Aware Dynamic Resource Allocation under Long-Term Cost Constraints

Transformers Provably Learn Chain-of-Thought Reasoning with Length Generalization

Generalization Bounds for Kolmogorov-Arnold Networks (KANs) and Enhanced KANs with Lower Lipschitz Complexity

Generalization Bounds for Model-based Algorithm Configuration

Learning from positive and unlabeled examples -Finite size sample bounds

Learning Theory for Kernel Bilevel Optimization

Stability and Sharper Risk Bounds with Convergence Rate $\tilde{O}(1/n^2)$

Robust Contextual Pricing

Hessian-guided Perturbed Wasserstein Gradient Flows for Escaping Saddle Points

On the Robustness of Transformers against Context Hijacking for Linear Classification

PeRL: Permutation-Enhanced Reinforcement Learning for Interleaved Vision-Language Reasoning

Geometry Meets Incentives: Sample-Efficient Incentivized Exploration with Linear Contexts

Online Learning of Neural Networks

Learning single index models via harmonic decomposition

A Tale of Two Symmetries: Exploring the Loss Landscape of Equivariant Models

Online Learning of Pure States is as Hard as Mixed States

Optimal Regret of Bandits under Differential Privacy

Nyström-Accelerated Primal LS-SVMs: Breaking the $O(an^3)$ Complexity Bottleneck for Scalable ODEs Learning

RLZero: Direct Policy Inference from Language Without In-Domain Supervision

SEEA-R1: Tree-Structured Reinforcement Fine-Tuning for Self-Evolving Embodied Agents

Shallow Flow Matching for Coarse-to-Fine Text-to-Speech Synthesis

SPiDR: A Simple Approach for Zero-Shot Safety in Sim-to-Real Transfer

BraVE: Offline Reinforcement Learning for Discrete Combinatorial Action Spaces

Actor-Free Continuous Control via Structurally Maximizable Q-Functions

One Subgoal at a Time: Zero-Shot Generalization to Arbitrary Linear Temporal Logic Requirements in Multi-Task Reinforcement Learning

Uncertainty-Based Smooth Policy Regularisation for Reinforcement Learning with Few Demonstrations

Angles Don’t Lie: Unlocking Training‑Efficient RL Through the Model’s Own Signals

Multi-Environment POMDPs: Discrete Model Uncertainty Under Partial Observability

Near-Optimal Sample Complexity for Online Constrained MDPs

Planning and Learning in Average Risk-aware MDPs

When Lower-Order Terms Dominate: Adaptive Expert Algorithms for Heavy-Tailed Losses

Constrained Linear Thompson Sampling

REINFORCE Converges to Optimal Policies with Any Learning Rate

Trajectory Graph Learning: Aligning with Long Trajectories in Reinforcement Learning Without Reward Design

Convergence Theorems for Entropy-Regularized and Distributional Reinforcement Learning

LexiCon: a Benchmark for Planning under Temporal Constraints in Natural Language

The ODE Method for Stochastic Approximation and Reinforcement Learning with Markovian Noise

Structured Reinforcement Learning for Combinatorial Decision-Making

Improved Regret Bounds for Linear Bandits with Heavy-Tailed Rewards

Normalizing Flows are Capable Models for Continuous Control

Adversarial Diffusion for Robust Reinforcement Learning

OpenHOI: Open-World Hand-Object Interaction Synthesis with Multimodal Large Language Model

Learning to Better Search with Language Models via Guided Reinforced Self-Training

Memo: Training Memory-Efficient Embodied Agents with Reinforcement Learning

Sparse Optimistic Information Directed Sampling

Regret Analysis of Average-Reward Unichain MDPs via an Actor-Critic Approach

FraPPE: Fast and Efficient Preference-Based Pure Exploration

$\varepsilon$-Optimally Solving Two-Player Zero-Sum POSGs

Backward Conformal Prediction

Generalized Linear Bandits: Almost Optimal Regret with One-Pass Update

Online Learning in the Repeated Mediated Newsvendor Problem

How Patterns Dictate Learnability in Sequential Data

Non-Asymptotic Analysis Of Data Augmentation For Precision Matrix Estimation

On the Emergence of Linear Analogies in Word Embeddings

Advancing Wasserstein Convergence Analysis of Score-Based Models: Insights from Discretization and Second-Order Acceleration

ACT as Human: Multimodal Large Language Model Data Annotation with Critical Thinking

PermLLM: Learnable Channel Permutation for N:M Sparse Large Language Models

HALO: Hadamard-Assisted Lower-Precision Optimization for LLMs

Revisiting Residual Connections: Orthogonal Updates for Stable and Efficient Deep Networks

Flexible Realignment of Language Models

Towards Multi-Table Learning: A Novel Paradigm for Complementarity Quantification and Integration

QBasicVSR: Temporal Awareness Adaptation Quantization for Video Super-Resolution

Masked Gated Linear Unit

Uncovering the Spectral Bias in Diagonal State Space Models

Token-Level Self-Play with Importance-Aware Guidance for Large Language Models

Deep Tree Tensor Networks

PaceLLM: Brain-Inspired Large Language Models for Long-Context Understanding

Adaptive Classifier-Free Guidance via Dynamic Low-Confidence Masking

The Automated LLM Speedrunning Benchmark: Reproducing NanoGPT Improvements

AlphaBeta is not as good as you think: a simple random games model for a better analysis of deterministic game-solving algorithms

Tight Asymptotics of Extreme Order Statistics

Improved Regret Bounds for Gaussian Process Upper Confidence Bound in Bayesian Optimization

Optimal community detection in dense bipartite graphs

Dynamic Diameter in High-Dimensions against Adaptive Adversary and Beyond

Self-Generated In-Context Examples Improve LLM Agents for Sequential Decision-Making Tasks

Collapsing Taylor Mode Automatic Differentiation

PINNs with Learnable Quadrature

STree: Speculative Tree Decoding for Hybrid State Space Models

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning

Projective Equivariant Networks via Second-order Fundamental Differential Invariants

Efficient Training-Free Online Routing for High-Volume Multi-LLM Serving

Enhanced Self-Distillation Framework for Efficient Spiking Neural Network Training

Curvature Tuning: Provable Training-free Model Steering From a Single Parameter

Ravan: Multi-Head Low-Rank Adaptation for Federated Fine-Tuning

Improving Bilinear RNN with Closed-loop Control

Q-Palette: Fractional-Bit Quantizers Toward Optimal Bit Allocation for Efficient LLM Deployment

Bridging Expressivity and Scalability with Adaptive Unitary SSMs

Structured Spectral Reasoning for Frequency-Adaptive Multimodal Recommendation

RAG4GFM: Bridging Knowledge Gaps in Graph Foundation Models through Graph Retrieval Augmented Generation

Causal Spatio-Temporal Prediction: An Effective and Efficient Multi-Modal Approach

Spectral Compressive Imaging via Chromaticity-Intensity Decomposition

Training the Untrainable: Introducing Inductive Bias via Representational Alignment

SmallKV: Small Model Assisted Compensation of KV Cache Compression for Efficient LLM Inference

Encoder-Decoder Diffusion Language Models for Efficient Training and Inference

Diffusion Models and the Manifold Hypothesis: Log-Domain Smoothing is Geometry Adaptive

Mind the Gap: Bridging Thought Leap for Improved Chain-of-Thought Tuning

When Thinking Fails: The Pitfalls of Reasoning for Instruction-Following in LLMs

Fast attention mechanisms: a tale of parallelism

Efficient Large Language Model Inference with Neural Block Linearization

On the Role of Hidden States of Modern Hopfield Network in Transformer

Homogeneous Keys, Heterogeneous Values: Exploiting Local KV Cache Asymmetry for Long-Context LLMs

Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation

Twilight: Adaptive Attention Sparsity with Hierarchical Top-$p$ Pruning

Attention on the Sphere

Dependency Parsing is More Parameter-Efficient with Normalization

MoBA: Mixture of Block Attention for Long-Context LLMs

KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction

Let Me Think! A Long Chain of Thought Can Be Worth Exponentially Many Short Ones

AttentionPredictor: Temporal Patterns Matter for KV Cache Compression

RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval

Towards Interpretable and Efficient Attention: Compressing All by Contracting a Few

Multipole Attention for Efficient Long Context Reasoning

Tropical Attention: Neural Algorithmic Reasoning for Combinatorial Algorithms

Iterative Foundation Model Fine-Tuning on Multiple Rewards

PhysVLM-AVR: Active Visual Reasoning for Multimodal Large Language Models in Physical Environments

Multimodal Tabular Reasoning with Privileged Structured Information

Lookahead Routing for Large Language Models

LinEAS: End-to-end Learning of Activation Steering with a Distributional Loss

Rao-Blackwell Gradient Estimators for Equivariant Denoising Diffusion

Adaptive Discretization for Consistency Models

Edit Flows: Variable Length Discrete Flow Matching with Sequence-Level Edit Operations

Ranking-based Preference Optimization for Diffusion Models from Implicit User Feedback

What Matters in Data for DPO?

rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Dataset

Flow Matching Neural Processes

Coupled Data and Measurement Space Dynamics for Enhanced Diffusion Posterior Sampling

Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models

Towards Understanding the Mechanisms of Classifier-Free Guidance

Pre-trained Large Language Models Learn to Predict Hidden Markov Models In-context

Deliberation on Priors: Trustworthy Reasoning of Large Language Models on Knowledge Graphs

Restoring Pruned Large Language Models via Lost Component Compensation

Optimize Any Topology: A Foundation Model for Shape- and Resolution-Free Structural Topology Optimization

SCAN: Self-Denoising Monte Carlo Annotation for Robust Process Reward Learning

On Universality Classes of Equivariant Networks

Learning (Approximately) Equivariant Networks via Constrained Optimization

On Vanishing Gradients, Over-Smoothing, and Over-Squashing in GNNs: Bridging Recurrent and Graph Learning

Unsupervised Learning for Optimal Transport plan prediction between unbalanced graphs

Over-squashing in Spatiotemporal Graph Neural Networks

Contextual Tokenization for Graph Inverted Indices

Towards Unsupervised Training of Matching-based Graph Edit Distance Solver via Preference-aware GAN

Spectral Graph Neural Networks are Incomplete on Graphs with a Simple Spectrum

CURE: Concept Unlearning via Orthogonal Representation Editing in Diffusion Models

CLAWS:Creativity detection for LLM-generated solutions using Attention Window of Sections

CURE: Co-Evolving Coders and Unit Testers via Reinforcement Learning

NeuroPath: Neurobiology-Inspired Path Tracking and Reflection for Semantically Coherent Retrieval

Any Large Language Model Can Be a Reliable Judge: Debiasing with a Reasoning-based Bias Detector

EVODiff: Entropy-aware Variance Optimized Diffusion Inference

Color Conditional Generation with Sliced Wasserstein Guidance

Beyond Masked and Unmasked: Discrete Diffusion Models via Partial Masking

AdmTree: Compressing Lengthy Context with Adaptive Semantic Trees

un$^2$CLIP: Improving CLIP's Visual Detail Capturing Ability via Inverting unCLIP

Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivization

Rethinking Fine-Tuning when Scaling Test-Time Compute: Limiting Confidence Improves Mathematical Reasoning

Bridging Theory and Practice in Link Representation with Graph Neural Networks

GnnXemplar: Exemplars to Explanations - Natural Language Rules for Global GNN Interpretability

Enhanced Expert Merging for Mixture-of-Experts in Graph Foundation Models

On Local Limits of Sparse Random Graphs: Color Convergence and the Refined Configuration Model

Higher-Order Learning with Graph Neural Networks via Hypergraph Encodings

Graph Persistence goes Spectral

REOBench: Benchmarking Robustness of Earth Observation Foundation Models

H-SPLID: HSIC-based Saliency Preserving Latent Information Decomposition

Learning Robust Vision-Language Models from Natural Latent Spaces

Pruning-Robust Mamba with Asymmetric Multi-Scale Scanning Paths

Preference Learning with Response Time: Robust Losses and Guarantees

Multi-Expert Distributionally Robust Optimization for Out-of-Distribution Generalization

Compositional Neural Network Verification via Assume-Guarantee Reasoning

ReservoirTTA: Prolonged Test-time Adaptation for Evolving and Recurring Domains

Vulnerable Data-Aware Adversarial Training

Analog Foundation Models

Dropout Regularization Versus l2-Penalization in the Linear Model

Understanding the Gain from Data Filtering in Multimodal Contrastive Learning

Embedding Principle of Homogeneous Neural Network for Classification Problem

The Computational Advantage of Depth in Learning High-Dimensional Hierarchical Targets

T2V-OptJail: Discrete Prompt Optimization for Text-to-Video Jailbreak Attacks

Hankel Singular Value Regularization for Highly Compressible State Space Models

Neural Hamiltonian Diffusions for Modeling Structured Geometric Dynamics

Hyperbolic Fine-Tuning for Large Language Models

Analyzing Fine-Grained Alignment and Enhancing Vision Understanding in Multimodal Language Models

Optimal Control for Transformer Architectures: Enhancing Generalization, Robustness and Efficiency

Scaling Up Liquid-Resistance Liquid-Capacitance Networks for Efficient Sequence Modeling

Better Training Data Attribution via Better Inverse Hessian-Vector Products

AuroRA: Breaking Low-Rank Bottleneck of LoRA with Nonlinear Mapping

Attention with Trained Embeddings Provably Selects Important Tokens

Approximation theory for 1-Lipschitz ResNets

A Theoretical Framework for Grokking: Interpolation followed by Riemannian Norm Minimisation

Metric Automata Theory: A Unifying Theory of RNNs

Beyond Benign Overfitting in Nadaraya-Watson Interpolators

Learning Orthogonal Multi-Index Models: A Fine-Grained Information Exponent Analysis

Shortcut Features as Top Eigenfunctions of NTK: A Linear Neural Network Case and More

On Linear Mode Connectivity of Mixture-of-Experts Architectures

Neural Thermodynamics: Entropic Forces in Deep and Universal Representation Learning

The Computational Complexity of Counting Linear Regions in ReLU Neural Networks

Generalized Linear Mode Connectivity for Transformers

Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models

Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViT

DISCO: Disentangled Communication Steering for Large Language Models

Gompertz Linear Units: Leveraging Asymmetry for Enhanced Learning Dynamics

Uni-LoRA: One Vector is All You Need

Value-Guided KV Compression for LLMs via Approximated CUR Decomposition

Robust Hyperbolic Learning with Curvature-Aware Optimization

Iterative Self-Incentivization Empowers Large Language Models as Agentic Searchers

LongMagpie: A Self-synthesis Method for Generating Large-scale Long-context Instructions

Learning to Focus: Causal Attention Distillation via Gradient‐Guided Token Pruning

DREAM: Drafting with Refined Target Features and Entropy-Adaptive Cross-Attention Fusion for Multimodal Speculative Decoding

Introducing FOReCAst: The Future Outcome Reasoning and Confidence Assessment Benchmark

UltraVideo: High-Quality UHD Video Dataset with Comprehensive Captions

LD-RoViS: Training-free Robust Video Steganography for Deterministic Latent Diffusion Model

One Stone with Two Birds: A Null-Text-Null Frequency-Aware Diffusion Models for Text-Guided Image Inpainting

ViewCraft3D: High-fidelity and View-Consistent 3D Vector Graphics Synthesis

Advanced Sign Language Video Generation with Compressed and Quantized Multi-Condition Tokenization

InvFusion: Bridging Supervised and Zero-shot Diffusion for Inverse Problems

RoPECraft: Training-Free Motion Transfer with Trajectory-Guided RoPE Optimization on Diffusion Transformers

OmniSync: Towards Universal Lip Synchronization via Diffusion Transformers

Latent Refinement via Flow Matching for Training-free Linear Inverse Problem Solving

Adaptive Stochastic Coefficients for Accelerating Diffusion Sampling

COGNAC: Cooperative Graph-based Networked Agent Challenges for Multi-Agent Reinforcement Learning

Adv-SSL: Adversarial Self-Supervised Representation Learning with Theoretical Guarantees

Solving Continuous Mean Field Games: Deep Reinforcement Learning for Non-Stationary Dynamics

Evaluating LLMs in Open-Source Games

Online Mixture of Experts: No-Regret Learning for Optimal Collective Decision-Making

Regret Lower Bounds for Decentralized Multi-Agent Stochastic Shortest Path Problems

Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving

Gymnasium: A Standard Interface for Reinforcement Learning Environments

MTRec: Learning to Align with User Preferences via Mental Reward Models

VORTA: Efficient Video Diffusion via Routing Sparse Attention

GoT: Unleashing Reasoning Capability of MLLM for Visual Generation and Editing

Free-Lunch Color-Texture Disentanglement for Stylized Image Generation

Learning Diffusion Models with Flexible Representation Guidance

Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation

FreeControl: Efficient, Training-Free Structural Control via One-Step Attention Extraction

Shallow Diffuse: Robust and Invisible Watermarking through Low-Dim Subspaces in Diffusion Models

X-Scene: Large-Scale Driving Scene Generation with High Fidelity and Flexible Controllability

Controllable Human-centric Keyframe Interpolation with Generative Prior

Luminance-Aware Statistical Quantization: Unsupervised Hierarchical Learning for Illumination Enhancement

A Finite Sample Analysis of Distributional TD Learning with Linear Function Approximation

WarpGAN: Warping-Guided 3D GAN Inversion with Style-Based Novel View Inpainting

Robust Label Proportions Learning

Automaton Constrained Q-Learning

STAR: Efficient Preference-based Reinforcement Learning via Dual Regularization

A Closed-Form Solution for Fast and Reliable Adaptive Testing

Reinforcement Learning for Reasoning in Large Language Models with One Training Example

Ground-Compose-Reinforce: Grounding Language in Agentic Behaviours using Limited Data

CAR-Flow: Condition-Aware Reparameterization Aligns Source and Target for Better Flow Matching

Degradation-Aware Dynamic Schrödinger Bridge for Unpaired Image Restoration

HairFree: Compositional 2D Head Prior for Text-Driven 360° Bald Texture Synthesis

DisMo: Disentangled Motion Representations for Open-World Motion Transfer

AR-RAG: Autoregressive Retrieval Augmentation for Image Generation

Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance

VTON-VLLM: Aligning Virtual Try-On Models with Human Preferences

Frame In-N-Out: Unbounded Controllable Image-to-Video Generation

Flow-GRPO: Training Flow Matching Models via Online RL

Safe-Sora: Safe Text-to-Video Generation via Graphical Watermarking

Speculative Jacobi-Denoising Decoding for Accelerating Autoregressive Text-to-image Generation

DreamLight: Towards Harmonious and Consistent Image Relighting

Gaussian-Augmented Physics Simulation and System Identification with Complex Colliders

U-CAN: Unsupervised Point Cloud Denoising with Consistency-Aware Noise2Noise Matching

Reconstruct, Inpaint, Test-Time Finetune: Dynamic Novel-view Synthesis from Monocular Videos

OptiScene: LLM-driven Indoor Scene Layout Generation via Scaled Human-aligned Data Synthesis and Multi-Stage Preference Optimization

1000+ FPS 4D Gaussian Splatting for Dynamic Scene Rendering

TAPIP3D: Tracking Any Point in Persistent 3D Geometry

Reframing Gaussian Splatting Densification with Complexity-Density Consistency of Primitives

Plenodium: Underwater 3D Scene Reconstruction with Plenoptic Medium Representation

Spiral: Semantic-Aware Progressive LiDAR Scene Generation and Understanding

4DGCPro: Efficient Hierarchical 4D Gaussian Compression for Progressive Volumetric Video Streaming

GuideFlow3D: Optimization-Guided Rectified Flow For Appearance Transfer

MaterialRefGS: Reflective Gaussian Splatting with Multi-view Consistent Material Inference

Optimized Minimal 3D Gaussian Splatting

GSRF: Complex-Valued 3D Gaussian Splatting for Efficient Radio-Frequency Data Synthesis

MVSMamba: Multi-View Stereo with State Space Model

EGGS: Exchangeable 2D/3D Gaussian Splatting for Geometry-Appearance Balanced Novel View Synthesis

MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details

NerfBaselines: Consistent and Reproducible Evaluation of Novel View Synthesis Methods

HouseLayout3D: A Benchmark and Training-free Baseline for 3D Layout Estimation in the Wild

InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts

SAP: Exact Sorting in Splatting via Screen-Aligned Primitives

ViDAR: Video Diffusion-Aware 4D Reconstruction From Monocular Inputs

Learning Temporal 3D Semantic Scene Completion via Optical Flow Guidance

Jamais Vu: Exposing the Generalization Gap in Supervised Semantic Correspondence

Point-MaDi: Masked Autoencoding with Diffusion for Point Cloud Pre-training

Mesh-RFT: Enhancing Mesh Generation via Fine-grained Reinforcement Fine-Tuning

Temporal Smoothness-Aware Rate-Distortion Optimized 4D Gaussian Splatting

PLD: A Choice-Theoretic List-Wise Knowledge Distillation

MLLM-ISU: The First-Ever Comprehensive Benchmark for Multimodal Large Language Models based Intrusion Scene Understanding

RGB-to-Polarization Estimation: A New Task and Benchmark Study

FlySearch: Exploring how vision-language models explore

Can Large Language Models Help Multimodal Language Analysis? MMLA: A Comprehensive Benchmark

RTV-Bench: Benchmarking MLLM Continuous Perception, Understanding and Reasoning through Real-Time Video

THUNDER: Tile-level Histopathology image UNDERstanding benchmark

Two Causally Related Needles in a Video Haystack

RSCC: A Large-Scale Remote Sensing Change Caption Dataset for Disaster Events

VimoRAG: Video-based Retrieval-augmented 3D Motion Generation for Motion Language Models

Grounded Reinforcement Learning for Visual Reasoning

DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO

FastVID: Dynamic Density Pruning for Fast Video Large Language Models

NormFit: A Lightweight Solution for Few-Shot Federated Learning with Non-IID Data

HMVLM:Human Motion-Vision-Language Model via MoE LoRA

Universal Video Temporal Grounding with Generative Multi-modal Large Language Models

Conditional Representation Learning for Customized Tasks

VLM-R³: Region Recognition, Reasoning, and Refinement for Enhanced Multimodal Chain-of-Thought

FedMGP: Personalized Federated Learning with Multi-Group Text-Visual Prompts

DOVTrack: Data-Efficient Open-Vocabulary Tracking

MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks

Mitigating Intra- and Inter-modal Forgetting in Continual Learning of Unified Multimodal Models

Neighborhood Self-Dissimilarity Attention for Medical Image Segmentation

BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent

Discovering Compositional Hallucinations in LVLMs

The Dual Nature of Plasticity Loss in Deep Continual Learning: Dissection and Mitigation

StreamForest: Efficient Online Video Understanding with Persistent Event Memory

Instance-Level Composed Image Retrieval

Vad-R1: Towards Video Anomaly Reasoning via Perception-to-Cognition Chain-of-Thought

Personalized Visual Content Generation in Conversational Systems

RESAnything: Attribute Prompting for Arbitrary Referring Segmentation

DP²O-SR: Direct Perceptual Preference Optimization for Real-World Image Super-Resolution

VLM in a flash: I/O-Efficient Sparsification of Vision-Language Model via Neuron Chunking

Seeing Sound, Hearing Sight: Uncovering Modality Bias and Conflict of AI models in Sound Localization

Rethinking Multimodal Learning from the Perspective of Mitigating Classification Ability Disproportion

Uncertainty-quantified Rollout Policy Adaptation for Unlabelled Cross-domain Video Temporal Grounding

Projection-Manifold Regularized Latent Diffusion for Robust General Image Fusion

Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning

CAT: Content-Adaptive Image Tokenization

$\Delta \mathrm{Energy}$: Optimizing Energy Change During Vision-Language Alignment Improves both OOD Detection and OOD Generalization

STAR: Spatial-Temporal Tracklet Matching for Multi-Object Tracking

Availability-aware Sensor Fusion via Unified Canonical Space

DGSolver: Diffusion Generalist Solver with Universal Posterior Sampling for Image Restoration

Training-free Online Video Step Grounding

Directed-Tokens: A Robust Multi-Modality Alignment Approach to Large Language-Vision Models

MokA: Multimodal Low-Rank Adaptation for MLLMs

Automated Model Discovery via Multi-modal & Multi-step Pipeline

REN: Fast and Efficient Region Encodings from Patch-Based Image Encoders

Too Late to Recall: Explaining the Two-Hop Problem in Multimodal Knowledge Retrieval

Struct2D: A Perception-Guided Framework for Spatial Reasoning in MLLMs

QSVD: Efficient Low-rank Approximation for Unified Query-Key-Value Weight Compression in Low-Precision Vision-Language Models

VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank

Hallucination at a Glance: Controlled Visual Edits and Fine-Grained Multimodal Learning

Long-Tailed Recognition via Information-Preservable Two-Stage Learning

State Space Prompting via Gathering and Spreading Spatio-Temporal Information for Video Understanding

Reading Recognition in the Wild

T-norm Selection for Object Detection in Autonomous Driving with Logical Constraints

LabelAny3D: Label Any Object 3D in the Wild

Consistent Supervised-Unsupervised Alignment for Generalized Category Discovery

Rising from Ashes: Generalized Federated Learning via Dynamic Parameter Reset

AdaVideoRAG: Omni-Contextual Adaptive Retrieval-Augmented Efficient Long Video Understanding

MLEP: Multi-granularity Local Entropy Patterns for Generalized AI-generated Image Detection

Visual Anagrams Reveal Hidden Differences in Holistic Shape Processing Across Vision Models

Is This Tracker On? A Benchmark Protocol for Dynamic Tracking

The Illusion of Progress? A Critical Look at Test-Time Adaptation for Vision-Language Models

FineRS: Fine-grained Reasoning and Segmentation of Small Objects with Reinforcement Learning

Cyclic Counterfactuals under Shift–Scale Interventions

Robust Ego-Exo Correspondence with Long-Term Memory

Gaze-VLM: Bridging Gaze and VLMs through Attention Regularization for Egocentric Understanding

Towards Robust Pseudo-Label Learning in Semantic Segmentation: An Encoding Perspective

ViSpec: Accelerating Vision-Language Models with Vision-Aware Speculative Decoding

EMLoC: Emulator-based Memory-efficient Fine-tuning with LoRA Correction

LangHOPS: Language Grounded Hierarchical Open-Vocabulary Part Segmentation

Gradient-Weight Alignment as a Train-Time Proxy for Generalization in Classification Tasks

CSPCL: Category Semantic Prior Contrastive Learning for Deformable DETR-Based Prohibited Item Detectors

A Generalized Label Shift Perspective for Cross-Domain Gaze Estimation

Weak-shot Keypoint Estimation via Keyness and Correspondence Transfer

An Effective Levelling Paradigm for Unlabeled Scenarios

Noise Matters: Optimizing Matching Noise for Diffusion Classifiers

Salient Concept-Aware Generative Data Augmentation

The Fragile Truth of Saliency: Improving LLM Input Attribution via Attention Bias Optimization

Señorita-2M: A High-Quality Instruction-based Dataset for General Video Editing by Video Specialists

Seeing the Wind from a Falling Leaf

Dynamic Semantic-Aware Correlation Modeling for UAV Tracking

RANK++LETR: Learn to Rank and Optimize Candidates for Line Segment Detection

Spatiotemporal Consensus with Scene Prior for Unsupervised Domain Adaptive Person Search

PoseCrafter: Extreme Pose Estimation with Hybrid Video Synthesis

FastJAM: a Fast Joint Alignment Model for Images

Rethinking Nighttime Image Deraining via Learnable Color Space Transformation

PointTruss: K-Truss for Point Cloud Registration

PandaPose: 3D Human Pose Lifting from a Single Image via Propagating 2D Pose Prior to 3D Anchor Space

ST$^2$360D: Spatial-to-Temporal Consistency for Training-free 360 Monocular Depth Estimation

Prompt-Guided Alignment with Information Bottleneck Makes Image Compression Also a Restorer

Styl3R: Instant 3D Stylized Reconstruction for Arbitrary Scenes and Styles

HoloScene: Simulation‑Ready Interactive 3D Worlds from a Single Video

More effort is needed to protect pedestrian privacy in the era of AI

A Circular Argument: Does RoPE need to be Equivariant for Vision?

Short-length Adversarial Training Helps LLMs Defend Long-length Jailbreak Attacks: Theoretical and Empirical Evidence

LILO: Learning to Reason at the Frontier of Learnability

Value Gradient Guidance for Flow Matching Alignment

Yggdrasil: Bridging Dynamic Speculation and Static Runtime for Latency-Optimal Tree-Based LLM Decoding

Improving Progressive Generation with Decomposable Flow Matching

Reinforcement Learning with Backtracking Feedback

Uncover Governing Law of Pathology Propagation Mechanism Through A Mean-Field Game

ClinicalLab: Aligning Agents for Multi-Departmental Clinical Diagnostics in the Real World

OMEGA: Can LLMs Reason Outside the Box in Math? Evaluating Exploratory, Compositional, and Transformative Generalization

Bag of Tricks for Inference-time Computation of LLM Reasoning

IR3D-Bench: Evaluating Vision-Language Model Scene Understanding as Agentic Inverse Rendering

Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition

Noise-Robustness Through Noise: A Framework combining Asymmetric LoRA with Poisoning MoE

Intermediate Domain Alignment and Morphology Analogy for Patent-Product Image Retrieval

Neural B-frame Video Compression with Bi-directional Reference Harmonization

WaveAR: Wavelet-Aware Continuous Autoregressive Diffusion for Accurate Human Motion Prediction

Variational Inference with Mixtures of Isotropic Gaussians

Vector Database Watermarking

Deciphering the Extremes: A Novel Approach for Pathological Long-tailed Recognition in Scientific Discovery

Adaptive Algorithms with Sharp Convergence Rates for Stochastic Hierarchical Optimization

Learning When to Think: Shaping Adaptive Reasoning in R1-Style Models via Multi-Stage RL

MLLM-For3D: Adapting Multimodal Large Language Model for 3D Reasoning Segmentation

OmniConsistency: Learning Style-Agnostic Consistency from Paired Stylization Data

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning

The Good, the Bad and the Ugly: Meta-Analysis of Watermarks, Transferable Attacks and Adversarial Defenses

The Cost of Compression: Tight Quadratic Black-Box Attacks on Sketches for $\ell_2$ Norm Estimation

LeMiCa: Lexicographic Minimax Path Caching for Efficient Diffusion-Based Video Generation

ItDPDM: Information-Theoretic Discrete Poisson Diffusion Model

RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing

FPSAttention: Training-Aware FP8 and Sparsity Co-Design for Fast Video Diffusion

Design-Based Bandits Under Network Interference: Trade-Off Between Regret and Statistical Inference

Neural-Driven Image Editing

VQToken: Neural Discrete Token Representation Learning for Extreme Token Reduction in Video Large Language Models

Explore In-Context Message Passing Operator for Graph Neural Networks in A Mean Field Game

Tri-MARF: A Tri-Modal Multi-Agent Responsive Framework for Comprehensive 3D Object Annotation

Stop DDoS Attacking the Research Community with AI-Generated Survey Papers

Sample-Conditional Coverage in Split-Conformal Prediction

UGG-ReID: Uncertainty-Guided Graph Model for Multi-Modal Object Re-Identification

Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and Inference

Direct Fisher Score Estimation for Likelihood Maximization

Curriculum Design for Trajectory-Constrained Agent: Compressing Chain-of-Thought Tokens in LLMs

Policy Compatible Skill Incremental Learning via Lazy Learning Interface

Learning to Reason under Off-Policy Guidance

Faithful Dynamic Imitation Learning from Human Intervention with Dynamic Regret Minimization

Critical Batch Size Revisited: A Simple Empirical Approach to Large-Batch Language Model Training

Behavior Injection: Preparing Language Models for Reinforcement Learning

On Evaluating Policies for Robust POMDPs

Gradient Descent as Loss Landscape Navigation: a Normative Framework for Deriving Learning Rules

Activity Pruning for Efficient Spiking Neural Networks

Adam Reduces a Unique Form of Sharpness: Theoretical Insights Near the Minimizer Manifold

U-REPA: Aligning Diffusion U-Nets to ViTs

Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles

Vision‑Language‑Vision Auto‑Encoder: Scalable Knowledge Distillation from Diffusion Models

An Information-theoretical Framework for Understanding Out-of-distribution Detection with Pretrained Vision-Language Models

Pause Tokens Strictly Increase the Expressivity of Constant-Depth Transformers

Functional Scaling Laws in Kernel Regression: Loss Dynamics and Learning Rate Schedules

Optimal Regret Bounds via Low-Rank Structured Variation in Non-Stationary Reinforcement Learning

DISC: Dynamic Decomposition Improves LLM Inference Scaling

Surface-Aware Feed-Forward Quadratic Gaussian for Frame Interpolation with Large Motion

Matchings Under Biased and Correlated Evaluations

DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning

KeeA*: Epistemic Exploratory A* Search via Knowledge Calibration

AREAL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Improving planning and MBRL with temporally-extended actions

VideoChat-R1.5: Visual Test-Time Scaling to Reinforce Multimodal Reasoning by Iterative Perception

MOF-BFN: Metal-Organic Frameworks Structure Prediction via Bayesian Flow Networks

Text-Aware Real-World Image Super-Resolution via Diffusion Model with Joint Segmentation Decoders

Outcome-Based Online Reinforcement Learning: Algorithms and Fundamental Limits

Leveraging semantic similarity for experimentation with AI-generated treatments

Proxy Target: Bridging the Gap Between Discrete Spiking Neural Networks and Continuous Control

Logic-in-Frames: Dynamic Keyframe Search via Visual Semantic-Logical Verification for Long Video Understanding

JailBound: Jailbreaking Internal Safety Boundaries of Vision-Language Models

Multi-Modal Interactive Agent Layer for Few-Shot Universal Cross-Domain Retrieval and Beyond

CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models

Auto-Connect: Connectivity-Preserving RigFormer with Direct Preference Optimization

ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understanding

DMWM: Dual-Mind World Model with Long-Term Imagination

Multimodal Bandits: Regret Lower Bounds and Optimal Algorithms

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts

SCOUT: Teaching Pre-trained Language Models to Enhance Reasoning via Flow Chain-of-Thought

Dual Alignment Framework for Few-shot Learning with Inter-Set and Intra-Set Shifts

Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons

Tree of Preferences for Diversified Recommendation

SHAP Meets Tensor Networks: Provably Tractable Explanations with Parallelism

Scaling Embedding Layers in Language Models

Disentangling Superpositions: Interpretable Brain Encoding Model with Sparse Concept Atoms

Structured Sparse Transition Matrices to Enable State Tracking in State-Space Models

Low Rank Gradients and Where to Find Them

MOSDT: Self-Distillation-Based Decision Transformer for Multi-Agent Offline Safe Reinforcement Learning

$\text{G}^2\text{M}$: A Generalized Gaussian Mirror Method to Boost Feature Selection Power

FNOPE: Simulation-based inference on function spaces with Fourier Neural Operators

DOTA: Distributional Test-time Adaptation of Vision-Language Models

Covariate-moderated Empirical Bayes Matrix Factorization

Uncertainty Quantification with the Empirical Neural Tangent Kernel

Recurrent Memory for Online Interdomain Gaussian Processes

Multi-View Oriented GPLVM: Expressiveness and Efficiency

Quantum speedup of non-linear Monte Carlo problems

Parallelizing MCMC Across the Sequence Length

Reasoning is Periodicity? Improving Large Language Models Through Effective Periodicity Modeling

Fast Computation and Optimization for Opinion-Based Quantities of Friedkin-Johnsen Model

Model Reconciliation via Cost-Optimal Explanations in Probabilistic Logic Programming

Estimating Hitting Times Locally at Scale

Solver-Informed RL: Grounding Large Language Models for Authentic Optimization Modeling

A Gradient Guided Diffusion Framework for Chance Constrained Programming

Set Smoothness Unlocks Clarke Hyper-stationarity in Bilevel Optimization

Structure-Aware Cooperative Ensemble Evolutionary Optimization on Combinatorial Problems with Multimodal Large Language Models

Discovering Opinion Intervals from Conflicts in Signed Graphs

Generalization Guarantees for Learning Score-Based Branch-and-Cut Policies in Integer Programming

How to Learn a Star: Binary Classification with Starshaped Polyhedral Sets

Coreset for Robust Geometric Median: Eliminating Size Dependency on Outliers

Geometric Algorithms for Neural Combinatorial Optimization with Constraints

Uniform Wrappers: Bridging Concave to Quadratizable Functions in Online Optimization

Nonlinearly Preconditioned Gradient Methods: Momentum and Stochastic Analysis

Controlling the Flow: Stability and Convergence for Stochastic Gradient Descent with Decaying Regularization

Sparse Polyak: an adaptive step size rule for high-dimensional M-estimation

Treatment Effect Estimation for Optimal Decision-Making

Fast Local Search Algorithms for Clustering with Adaptive Sampling and Bandit Strategies

Targeted Maximum Likelihood Learning: An Optimization Perspective

Revisiting Frank-Wolfe for Structured Nonconvex Optimization

Enforcing Hard Linear Constraints in Deep Learning Models with Decision Rules

Speculate Deep and Accurate: Lossless and Training-Free Acceleration for Offloaded LLMs via Substitute Speculative Decoding

Corporate Needs You to Find the Difference: Revisiting Submodular and Supermodular Ratio Optimization Problems

Unleashing the Power of One-Step Diffusion based Image Super-Resolution via a Large-Scale Diffusion Discriminator

Understanding outer learning rates in Local SGD

Hierachical Balance Packing: Towards Efficient Supervised Fine-tuning for Long-Context LLM

Predictability Enables Parallelization of Nonlinear State Space Models

FedRACE: A Hierarchical and Statistical Framework for Robust Federated Learning

Transforming Gaps into Gains: Bridging Model and Data Heterogeneity in Federated Learning via Knowledge Weak-Aware Zones

Towards Straggler-Resilient Split Federated Learning: An Unbalanced Update Approach

StarTrail: Concentric Ring Sequence Parallelism for Efficient Near-Infinite-Context Transformer Model Training

Second-Order Convergence in Private Stochastic Non-Convex Optimization

ElasticMM: Efficient Multimodal LLMs Serving with Elastic Multimodal Parallelism

First Attentions Last: Better Exploiting First Attentions for Efficient Parallel Training

Subspace Networks: Scaling Decentralized Training with Communication-Efficient Model Parallelism

DiEP: Adaptive Mixture-of-Experts Compression through Differentiable Expert Pruning

Scaling Epidemic Inference on Contact Networks: Theory and Algorithms

Revisiting Consensus Error: A Fine-grained Analysis of Local SGD under Second-order Data Heterogeneity

A Beyond-Worst-Case Analysis of Greedy k-means++

Stable Coresets via Posterior Sampling: Aligning Induced and Full Loss Landscapes

DSAS: A Universal Plug-and-Play Framework for Attention Optimization in Multi-Document Question Answering

Compress to Impress: Efficient LLM Adaptation Using a Single Gradient Step on 100 Samples

FRAM: Frobenius-Regularized Assignment Matching with Mixed-Precision Computing

Stepsize anything: A unified learning rate schedule for budgeted-iteration training

VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-Tuning

Irrational Complex Rotations Empower Low-bit Optimizers

A geometric framework for momentum-based optimizers for low-rank training

Through the River: Understanding the Benefit of Schedule-Free Methods for Language Model Training

HBLLM: Wavelet-Enhanced High-Fidelity 1-Bit Quantization for LLMs

REASONING COMPILER: LLM-Guided Optimizations for Efficient Model Serving

Exploring and Exploiting Model Uncertainty in Bayesian Optimization

Amortized Active Generation of Pareto Sets

Informed Initialization for Bayesian Optimization and Active Learning

Adaptive Kernel Design for Bayesian Optimization Is a Piece of CAKE with LLMs

Beyond $\tilde{O}(\sqrt{T})$ Constraint Violation for Online Convex Optimization with Adversarial Constraints

Adaptive Frontier Exploration on Graphs with Applications to Network-Based Disease Testing

Feasibility-Aware Decision-Focused Learning for Predicting Parameters in the Constraints

(ends 7:30 PM)

7 p.m.

Town Hall:

Town Hall

(ends 8:00 PM)

8 p.m.

Reception:

Closing Reception

(ends 9:30 PM)

SAT 6 DEC

7:30 a.m.

Registration Desk

(ends 4:00 PM)

8 a.m.

Workshop:

Imageomics: Discovering Biological Knowledge from Images Using AI

(ends 5:00 PM)

Workshop:

GenProCC: 1st Workshop on Generative and Protective AI for Content Creation

(ends 5:00 PM)

Workshop:

The Second Workshop on GenAI for Health: Potential, Trust, and Policy Compliance

(ends 5:00 PM)

Workshop:

Generative AI in Finance

(ends 5:00 PM)

Workshop:

Embodied World Models for Decision Making

(ends 5:00 PM)

Workshop:

Dynamics at the Frontiers of Optimization, Sampling, and Games

(ends 5:00 PM)

Workshop:

Differentiable Learning of Combinatorial Algorithms: From Theory To Practice

(ends 5:00 PM)

Workshop:

Deep Learning for Code in the Agentic Era

(ends 5:00 PM)

Workshop:

CauScien: Uncovering Causality in Science

(ends 5:00 PM)

Workshop:

Biosecurity Safeguards for Generative AI

(ends 5:00 PM)

Workshop:

Foundation Models for the Brain and Body Workshop

(ends 5:00 PM)

Workshop:

Second Workshop on Aligning Reinforcement Learning Experimentalists and Theorists (ARLET)

(ends 5:00 PM)

Workshop:

AI Virtual Cells and Instruments: A New Era in Drug Discovery and Development

(ends 5:00 PM)

Workshop:

AI4Mat-NeurIPS-2025: NeurIPS 2025 Workshop on AI for Accelerated Materials Design

(ends 5:00 PM)

Competition:

MyoChallenge 2025: Towards Human Athletic Intelligence

(ends 10:45 AM)

Competition:

The Competition of Fairness in AI Face Detection

(ends 10:45 AM)

Workshop:

ML x OR: Mathematical Foundations and Operational Integration of Machine Learning for Uncertainty-Aware Decision-Making

(ends 5:00 PM)

Workshop:

The First Workshop on Efficient Reasoning

(ends 5:00 PM)

Workshop:

Lock-LLM Workshop: Prevent Unauthorized Knowledge Use from Large Language Models - Deep Dive into Un-Distillate, Un-Finetunable, Un-Compressible, Un-Editable, and Un-Usable

(ends 5:00 PM)

Workshop:

Machine Learning and the Physical Sciences

(ends 5:00 PM)

Workshop:

ML for Systems

(ends 5:00 PM)

Workshop:

Workshop on Multi-Turn Interactions in Large Language Models

(ends 5:00 PM)

Workshop:

OPT 2025: Optimization for Machine Learning

(ends 5:00 PM)

Workshop:

Reliable ML from Unreliable Data

(ends 5:00 PM)

Workshop:

Structured Probabilistic Inference and Generative Modeling

(ends 5:00 PM)

Workshop:

UniReps: Unifying Representations in Neural Models

(ends 5:00 PM)

Workshop:

What Makes a Good Video: Next Practices in Video Generation and Evaluation

(ends 5:00 PM)

Workshop:

AI for non-human animal communication

(ends 5:00 PM)

Workshop:

MATH-AI: The 5th Workshop on Mathematical Reasoning and AI

(ends 5:00 PM)

Workshop:

Algorithmic Collective Action

(ends 5:00 PM)

Workshop:

AI and ML for Next-Generation Wireless Communications and Networking (AI4NextG @ NeurIPS’25)

(ends 5:00 PM)

9 a.m.

Break:

Coffee Break

(ends 9:45 AM)

11 a.m.

Competition:

EEG Foundation Challenge: From Cross-Task to Cross-Subject EEG Decoding

(ends 1:45 PM)

Competition:

DCVLR: Data Curation for Vision Language Reasoning

(ends 1:45 PM)

noon

Break:

Retail Lunch

(ends 1:30 PM)

2 p.m.

Competition:

Open Polymer Challenge: Leveraging Machine Learning for Polymer Informatics

(ends 4:45 PM)

Competition:

CURE-Bench: Competition on Reasoning Models for Drug Decision-Making in Precision Therapeutics

(ends 4:45 PM)

3 p.m.

Break:

Coffee Break

(ends 3:45 PM)

SUN 7 DEC

7:30 a.m.

Registration Desk

(ends 12:00 PM)

8 a.m.

Competition:

Early Training Scientific Knowledge and Reasoning Evaluation of Small Language Models

(ends 10:45 AM)

Competition:

Ariel Data Challenge 2025: Methods to Extract Planetary Signals for the Ariel Space Telescope

(ends 10:45 AM)

Workshop:

Learning from Time-Series for Health

(ends 5:00 PM)

Workshop:

Regulatable ML: Towards Bridging the Gaps between Machine Learning Research and Regulations

(ends 5:00 PM)

Workshop:

CogInterp: Interpreting Cognition in Deep Learning Models

(ends 5:00 PM)

Workshop:

AI That Keeps Up: Workshop on Continual and Compatible Foundation Model Updates (CCFM)

(ends 5:00 PM)

Workshop:

AI for Science: The Reach and Limits of AI for Scientific Discovery

(ends 5:00 PM)

Workshop:

Artificial Intelligence for Music: Where Creativity Meets Computation

(ends 5:00 PM)

Competition:

The PokéAgent Challenge: Competitive and Long-Context Learning at Scale

(ends 10:45 AM)

Workshop:

Multimodal Algorithmic Reasoning Workshop

(ends 5:00 PM)

Workshop:

2nd Workshop on Multi-modal Foundation Models and Large Language Models for Life Sciences

(ends 5:00 PM)

Workshop:

Evaluating the Evolving LLM Lifecycle: Benchmarks, Emergent Abilities, and Scaling

(ends 5:00 PM)

Competition:

The MindGames Challenge: Theory-of-Mind and Game Intelligence in LLM Agents

(ends 10:45 AM)

Workshop:

NeurIPS 2025 Workshop on Space in Vision, Language, and Embodied AI

(ends 5:00 PM)

Workshop:

Data on the Brain and Mind

(ends 5:00 PM)

Workshop:

Constrained Optimization for Machine Learning

(ends 5:00 PM)

Workshop:

Tackling Climate Change with Machine Learning

(ends 5:00 PM)

Workshop:

What Can('t) Transformers Do?

(ends 5:00 PM)

Workshop:

Workshop on Scaling Environments for Agents

(ends 5:00 PM)

Workshop:

GPU-Accelerated and Scalable Optimization (ScaleOpt)

(ends 5:00 PM)

Workshop:

UrbanAI: Harnessing Artificial Intelligence for Smart Cities

(ends 5:00 PM)

Workshop:

Learning to Sense (L2S)

(ends 5:00 PM)

Workshop:

Recent Advances in Time Series Foundation Models: Have We Reached the ‘BERT Moment’?

(ends 5:00 PM)

Workshop:

Frontiers in Probabilistic Inference: Learning meets Sampling

(ends 5:00 PM)

Workshop:

New Perspectives in Graph Machine Learning

(ends 5:00 PM)

Workshop:

Symmetry and Geometry in Neural Representations

(ends 5:00 PM)

Workshop:

Non-Euclidean Foundation Models and Geometric Learning: Advancing AI Beyond Euclidean Frameworks

(ends 5:00 PM)

Workshop:

Workshop on Mechanistic Interpretability

(ends 5:00 PM)

Workshop:

LAW 2025: Bridging Language, Agent, and World Models for Reasoning and Planning

(ends 5:00 PM)

Workshop:

Foundations of Reasoning in Language Models

(ends 5:00 PM)

9 a.m.

Break:

Coffee Break

(ends 9:45 AM)

11 a.m.

Competition:

Foundation Models for Embodied Agents

(ends 1:45 PM)

Competition:

Mouse vs. AI: A Neuroethological Benchmark for Visual Robustness

(ends 1:45 PM)

Competition:

SLC-PFM: Self-supervised Learning for Cancer Pathology Foundation Models

(ends 1:45 PM)

Competition:

FAIR Universe – handling uncertainties and distribution shifts for precision cosmology

(ends 1:45 PM)

noon

Break:

Retail Lunch

(ends 1:30 PM)

2 p.m.

Competition:

NeurIPS 2025 Competition: MMU-RAGent: Massive Multi-Modal User-Centric Retrieval Augmented Generation Benchmark

(ends 4:45 PM)

Competition:

The 2025 PNPL Competition: Speech Detection and Phoneme Classification in the LibriBrain Dataset

(ends 4:45 PM)

Competition:

The 2025 Google Code Golf Championship

(ends 4:45 PM)

Competition:

Weather4cast 2025 – Multi-task Challenges for Weather & Pollution Pattern Prediction on the Road to Hi-Res Foundation Models

(ends 4:45 PM)

3 p.m.

Break:

Coffee Break

(ends 3:45 PM)