Skip to yearly menu bar
Skip to main content
Main Navigation
NeurIPS
Help/FAQ
Contact NeurIPS
Code of Ethics
Code of Conduct
Create Profile
Journal To Conference Track
Diversity & Inclusion
Proceedings
Future Meetings
Press
Exhibitor Information
Privacy Policy
Downloads
My Stuff
Login
Select Year: (2024)
2024
2023
2022
2021
2020
2019
2018
2017
2016
2015
2014
2013
2012
2011
2010
2009
2008
2007
2006
Getting Started
Schedule
Tutorials
Main Conference
Invited Talks
Orals
Papers
Competitions
Datasets & Benchmarks
Journal Track
Creative AI Track
Outstanding Paper Awards
Affinity Workshops
Community
Bridging the Future
Socials
Careers
Mentoring (coming soon)
Workshops
Sponsors
Help
FAQ
Helpdesk in RocketChat
Organizers
Browse
mini
compact
topic
detail
Showing papers for
.
×
×
title
author
topic
session
shuffle
by
serendipity
bookmarked first
visited first
not visited first
bookmarked but not visited
Enable Javascript in your browser to see the papers page.
Upping the Game: How 2D U-Net Skip Connections Dominate 3D Segmentation
Adjust Pearson's $r$ to Measure Nonlinear Monotone Dependence
Dissecting Query-Key Interaction in Vision Transformers
AlphaMath Almost Zero: Process Supervision Without Process
UniFL: Improve Stable Diffusion via Unified Feedback Learning
Customized Subgraph Selection and Encoding for Drug-drug Interaction Prediction
Evaluate then Cooperate: Shapley-based View Cooperation Enhancement for Multi-view Clustering
Alleviate Anchor-Shift: Explore Blind Spots with Cross-View Reconstruction for Incomplete Multi-View Clustering
Clustering then Propagation: Select Better Anchors for Knowledge Graph Embedding
Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis
Automating Dataset Updates Towards Reliable and Timely Evaluation of Large Language Models
Learning Commonality, Divergence and Variety for Unsupervised Visible-Infrared Person Re-identification
Information Re-Organization Improves Reasoning in Large Language Models
Coupled Mamba: Enhanced Multimodal Fusion with Coupled State Space Model
MotionTTT: 2D Test-Time-Training Motion Estimation for 3D Motion Corrected MRI
Test-time Aggregation for Collaborative Filtering
Second-order forward-mode optimization of recurrent neural networks for neuroscience
Neural Krylov Iteration for Accelerating Linear System Solving
NeuralSteiner: Learning Steiner Tree for Overflow-avoiding Global Routing in Chip Design
LLM-ESR: Large Language Models Enhancement for Long-tailed Sequential Recommendation
GV-Rep: A Large-Scale Dataset for Genetic Variant Representation Learning
A probability contrastive learning framework for 3D molecular representation learning
Full-Atom Peptide Design with Geometric Latent Diffusion
MMSite: A Multi-modal Framework for the Identification of Active Sites in Proteins
Reprogramming Pretrained Target-Specific Diffusion Models for Dual-Target Drug Design
DRACO: A Denoising-Reconstruction Autoencoder for Cryo-EM
MutaPLM: Protein Language Modeling for Mutation Explanation and Engineering
3D Focusing-and-Matching Network for Multi-Instance Point Cloud Registration
LaSe-E2V: Towards Language-guided Semantic-Aware Event-to-Video Reconstruction
LION: Linear Group RNN for 3D Object Detection in Point Clouds
Lips Are Lying: Spotting the Temporal Inconsistency between Audio and Visual in Lip-Syncing DeepFakes
MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splatting
Lighting Every Darkness with 3DGS: Fast Training and Real-Time Rendering for HDR View Synthesis
Adaptive Visual Scene Understanding: Incremental Scene Graph Generation
Memorize What Matters: Emergent Scene Decomposition from Multitraverse
Robust Sleep Staging over Incomplete Multimodal Physiological Signals via Contrastive Imagination
Challenges of Generating Structurally Diverse Graphs
UMB: Understanding Model Behavior for Open-World Object Detection
Self-Supervised Adversarial Training via Diverse Augmented Queries and Self-Supervised Double Perturbation
Effective Rank Analysis and Regularization for Enhanced 3D Gaussian Splatting
NVRC: Neural Video Representation Compression
3D Gaussian Can Be Sparser Than You Thought: Efficient Rendering via Learned Fragment Pruning
Unveiling the Power of Diffusion Features For Personalized Segmentation and Retrieval
Estimating Ego-Body Pose from Doubly Sparse Egocentric Video Data
Equivariant spatio-hemispherical networks for diffusion MRI deconvolution
VeXKD: The Versatile Integration of Cross-Modal Fusion and Knowledge Distillation for 3D Perception
3D Gaussian Splatting as Markov Chain Monte Carlo
VQ-Map: Bird's-Eye-View Map Layout Estimation in Tokenized Discrete Space via Vector Quantization
Kermut: Composite kernel regression for protein variant effects
Transformer Doctor: Diagnosing and Treating Vision Transformers
Exploiting Descriptive Completeness Prior for Cross Modal Hashing with Incomplete Labels
Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detection
Dynamic Multi-Object 3D Grounding with Language Informed Spatial Attention
FreeSplat: Generalizable 3D Gaussian Splatting Towards Free View Synthesis of Indoor Scenes
GSDF: 3DGS Meets SDF for Improved Neural Rendering and Reconstruction
Beware of Road Markings: A New Adversarial Patch Attack to Monocular Depth Estimation
SeeClear: Semantic Distillation Enhances Pixel Condensation for Video Super-Resolution
Reproducibility study of “LICO: Explainable Models with Language-Image Consistency"
Improving Visual Prompt Tuning by Gaussian Neighborhood Minimization for Long-Tailed Visual Recognition
Plant-and-Steal: Truthful Fair Allocations via Predictions
Rethinking The Training And Evaluation of Rich-Context Layout-to-Image Generation
SHMT: Self-supervised Hierarchical Makeup Transfer via Latent Diffusion Models
DiMSUM: Diffusion Mamba - A Scalable and Unified Spatial-Frequency Method for Image Generation
IF-Font: Ideographic Description Sequence-Following Font Generation
FasterDiT: Towards Faster Diffusion Transformers Training without Architecture Modification
ReFIR: Grounding Large Restoration Models with Retrieval Augmentation
HairFastGAN: Realistic and Robust Hair Transfer with a Fast Encoder-Based Approach
Leveraging Hallucinations to Reduce Manual Prompt Dependency in Promptable Segmentation
OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding
One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos
LESS: Label-Efficient and Single-Stage Referring 3D Instance Segmentation
Towards Flexible Visual Relationship Segmentation
Learn more, but bother less: parameter efficient continual learning
A Surprisingly Simple Approach to Generalized Few-Shot Semantic Segmentation
XMask3D: Cross-modal Mask Reasoning for Open Vocabulary 3D Semantic Segmentation
ActAnywhere: Subject-Aware Video Background Generation
E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding
Towards Multi-Domain Learning for Generalizable Video Anomaly Detection
No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance
REDUCR: Robust Data Downsampling using Class Priority Reweighting
FreqMark: Invisible Image Watermarking via Frequency Based Optimization in Latent Space
DAVED: Data Acquisition via Experimental Design for Data Markets
TabEBM: A Tabular Data Augmentation Method with Class-Specific Energy-Based Models
Optimal and Approximate Adaptive Stochastic Quantization
Improving robustness to corruptions with multiplicative weight perturbations
Two-way Deconfounder for Off-policy Evaluation under Unmeasured Confounding
Beyond Redundancy: Information-aware Unsupervised Multiplex Graph Structure Learning
Credal Deep Ensembles for Uncertainty Quantification
Spectral Adapter: Fine-Tuning in Spectral Space
Building on Efficient Foundations: Effective Training of LLMs with Structured Feedforward Layers
Learning 3D Equivariant Implicit Function with Patch-Level Pose-Invariant Representation
A Layer-Wise Natural Gradient Optimizer for Training Deep Neural Networks
DropBP: Accelerating Fine-Tuning of Large Language Models by Dropping Backward Propagation
Single Image Reflection Separation via Interactive Dual-Stream Transformers
Understanding the differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks
FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision
Mobility-LLM: Learning Visiting Intentions and Travel Preference from Human Mobility Data with Large Language Models
Compositional Automata Embeddings for Goal-Conditioned Reinforcement Learning
Preventing Model Collapse in Deep Canonical Correlation Analysis by Noise Regularization
Algebraic Positional Encodings
VMamba: Visual State Space Model
Decoupled Kullback-Leibler Divergence Loss
A teacher-teacher framework for clinical language representation learning
Coded Computing: A Learning-Theoretic Framework
Benchmarking the Reasoning Robustness against Noisy Rationales in Chain-of-thought Prompting
Scalable Neural Network Verification with Branch-and-bound Inferred Cutting Planes
Adaptive Randomized Smoothing: Certifying Multi-Step Defences against Adversarial Examples
Transferable Adversarial Attacks on SAM and Its Downstream Models via Universal Meta Initialization and Gradient Robust Attacks
SAM-Guided Masked Token Prediction for 3D Scene Understanding
Warm-starting Push-Relabel
Understanding Transformer Reasoning Capabilities via Graph Algorithms
Task Confusion and Catastrophic Forgetting in Class-Incremental Learning: A Mathematical Framework for Discriminative and Generative Modelings
Provable Benefits of Complex Parameterizations for Structured State Space Models
Transformers are Minimax Optimal Nonparametric In-Context Learners
On the Saturation Effects of Spectral Algorithms in Large Dimensions
The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains
DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusion
What makes unlearning hard and what to do about it
Spiking Token Mixer: A event-driven friendly Former structure for spiking neural networks
The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof
Learning Infinitesimal Generators of Continuous Symmetries from Data
Stress-Testing Capability Elicitation With Password-Locked Models
Invariant Tokenization for Language Model Enabled Crystal Materials Generation
Categorical Flow Matching on Statistical Manifolds
A Trajectory-aware Spatio-temporal Graph for Video Salient Object Ranking
ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification
DreamScene: Layout-Guided 3D Scene Generation
Towards a Scalable Reference-Free Evaluation of Generative Models
Motion Generation based on Spatial-Temporal Joint Modeling
Fundamental Limits of Prompt Compression: A Rate-Distortion Framework for Black-Box Language Models
Overcoming Brittleness in Pareto-Optimal Learning Augmented Algorithms
A Decision-Language Model (DLM) for Dynamic Restless Multi-Armed Bandit Tasks in Public Health
Stability and Generalizability in SDE Diffusion Models with Measure-Preserving Dynamics
Absorb & Escape: Overcoming Single Model Limitations in Generating Heterogeneous Genomic Sequences
Synergistic Dual Spatial-aware Generation of Image-to-text and Text-to-image
DeepDRK: Deep Dependency Regularized Knockoff for Feature Selection
Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference
Local Curvature Smoothing with Stein's Identity for Efficient Score Matching
VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models
Learning Diffusion Priors from Observations by Expectation Maximization
Generative Fractional Diffusion Models
Model-based Diffusion for Trajectory Optimization
Diffusion of Thought: Chain-of-Thought Reasoning in Diffusion Language Models
Resfusion: Denoising Diffusion Probabilistic Models for Image Restoration Based on Prior Residual Noise
Warped Diffusion: Solving Video Inverse Problems with Image Diffusion Models
Taming Generative Diffusion Prior for Universal Blind Image Restoration
Hollowed Net for On-Device Personalization of Text-to-Image Diffusion Models
Attack-Resilient Image Watermarking Using Stable Diffusion
PrefPaint: Aligning Image Inpainting Diffusion Model with Human Preference
Where does In-context Learning \\ Happen in Large Language Models?
Automated Generation and Selection of Context-Aware Guidelines for Large Language Model Agents
Efficient Contextual LLM Cascades through Budget-Constrained Policy Learning
Certified Robustness for Deep Equilibrium Models via Serialized Random Smoothing
On the Identifiability of Hybrid Physics-Neural Models: Meta-Learning as a Solution
SemCoder: Training Code Language Models with Comprehensive Semantics
Advancing Tool-Augmented Large Language Models: Integrating Insights from Errors in Inference Trees
AutoCV: Empowering Reasoning with Automated Process Labeling via Confidence Variation
[Re] GNNInterpreter: A probabilistic generative model-level explanation for Graph Neural Networks
Graph Neural Networks and Arithmetic Circuits
EGonc : Energy-based Open-Set Node Classification with substitute Unknowns
Spectral Graph Pruning Against Over-Squashing and Over-Smoothing
Deep Homomorphism Networks
Graphcode: Learning from multiparameter persistent homology using graph neural networks
Are Graph Neural Networks Optimal Approximation Algorithms?
State Space Models on Temporal Graphs: A First-Principles Study
The Map Equation Goes Neural: Mapping Network Flows with Graph Neural Networks
Unitary Convolutions for Learning on Graphs and Groups
Graph Neural Networks Do Not Always Oversmooth
Generative Semi-supervised Graph Anomaly Detection
Unleash Region Understanding in Intermediate Layers for MLLM-based Referring Expression Generation
RG-SAN: Rule-Guided Spatial Awareness Network for End-to-End 3D Referring Expression Segmentation
Towards Human-AI Complementarity with Predictions Sets
DiReCT: Diagnostic Reasoning for Clinical Notes via Large Language Models
LLM Circuit Analyses Are Consistent Across Training and Scale
Conditional Density Estimation with Histogram Trees
Initialization is Critical to Whether Transformers Fit Composite Functions by Inference or Memorizing
Selective Explanations
Interpretable Image Classification with Adaptive Prototype-based Vision Transformers
Model Lego: Creating Models Like Disassembling and Assembling Building Blocks
Refusal in Language Models Is Mediated by a Single Direction
Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models
Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling
Evaluating and Eliciting Lateral Thinking of Large Language Models with Situation Puzzles
Semantics and Spatiality of Emergent Communication
Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies
LLM-Check: Investigating Detection of Hallucinations in Large Language Models
Aligning to Thousands of Varying Preferences via System Message Generalization
Text2NKG: Fine-Grained N-ary Relation Extraction for N-ary relational Knowledge Graph Construction
Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech Separation
LoRANN: Low-Rank Matrix Factorization for Approximate Nearest Neighbor Search
Revealing Distribution Discrepancy by Sampling Transfer in Unlabeled Data
Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices
Neuronal Competition Groups with Supervised STDP for Spike-Based Classification
Quantifying the Gain in Weak-to-Strong Generalization
Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging
Differentiable Structure Learning with Partial Orders
DASH: Warm-Starting Neural Network Training Without Loss of Plasticity Under Stationarity
Zero-Shot Transfer of Neural ODEs
Learning from Offline Foundation Features with Tensor Augmentations
(FL)${}^2$: Overcoming Few Labels in Federated Semi-Supervised Learning
A Practitioner's Guide to Real-World Continual Multimodal Pretraining
Probabilistic Conformal Distillation for Enhancing Missing Modality Robustness
Mitigating Object Hallucination via Concentric Causal Attention
Artemis: Towards Referential Understanding in Complex Videos
HEALNet: Multimodal Fusion for Heterogeneous Biomedical Data
Visual Perception by Large Language Model’s Weights
Accelerating Pre-training of Multimodal LLMs via Chain-of-Sight
Why are Visually-Grounded Language Models Bad at Image Classification?
Toward a Well-Calibrated Discrimination via Survival Outcome-Aware Contrastive Learning
Continual Audio-Visual Sound Separation
Generalization Beyond Data Imbalance: A Controlled Study on CLIP for Transferable Insights
MoMu-Diffusion: On Learning Long-Term Motion-Music Synchronization and Correspondence
Empowering Visible-Infrared Person Re-Identification with Large Foundation Models
Bridging 3D Scene and Large Language Models with Object Identifiers
HAWK: Learning to Understand Open-World Video Anomalies
Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image
Do CLIP Models Always Generalize Better than ImageNet Models?
EnsIR: An Ensemble Algorithm for Image Restoration via Gaussian Mixture Models
Automated Multi-level Preference for MLLMs
Unified Lexical Representation for Interpretable Visual-Language Alignment
Deep Correlated Prompting for Visual Recognition with Missing Modalities
Evaluating alignment between humans and neural network representations in image-based learning tasks
Neural networks with fast and bounded units learn flexible task abstractions
Inferring stochastic low-rank recurrent neural networks from neural data
Latent Learning Progress Drives Autonomous Goal Selection in Human Reinforcement Learning
LM-HT SNN: Enhancing the Performance of SNN to ANN Counterpart through Learnable Multi-hierarchical Threshold Model
Exploring the trade-off between deep-learning and explainable models for brain-machine interfaces
Latent Diffusion for Neural Spiking Data
Brain-JEPA: Brain Dynamics Foundation Model with Gradient Positioning and Spatiotemporal Masking
Flexible mapping of abstract domains by grid cells via self-supervised extraction and projection of generalized velocity signals
Exploring Behavior-Relevant and Disentangled Neural Dynamics with Generative Diffusion Models
Active design of two-photon holographic stimulation for identifying neural population dynamics
Multiple Physics Pretraining for Spatiotemporal Surrogate Models
Poseidon: Efficient Foundation Models for PDEs
A Recipe for Charge Density Prediction
Conjugate Bayesian Two-step Change Point Detection for Hawkes Process
Pre-trained Gaussian Processes for Bayesian Optimization
Nonstationary Sparse Spectral Permanental Process
Aligning LLM Agents by Learning Latent Preference from User Edits
Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot Learning
EASI: Evolutionary Adversarial Simulator Identification for Sim-to-Real Transfer
Reasoning Multi-Agent Behavioral Topology for Interactive Autonomous Driving
Variational Distillation of Diffusion Policies into Mixture of Experts
Scaling Law for Time Series Forecasting
TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables
Con4m: Context-aware Consistency Learning Framework for Segmented Time Series Classification
Improved Generation of Adversarial Examples Against Safety-aligned LLMs
The Best of Both Worlds: On the Dilemma of Out-of-distribution Detection
On the Identifiability of Poisson Branching Structural Causal Model Using Probability Generating Function
Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack
Improving Viewpoint-Independent Object-Centric Representations through Active Viewpoint Selection
ZeroMark: Towards Dataset Ownership Verification without Disclosing Dataset-specified Watermarks
Efficient Availability Attacks against Supervised and Contrastive Learning Simultaneously
Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models
Training for Stable Explanation for Free
Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models
Beyond Slow Signs in High-fidelity Model Extraction
RaVL: Discovering and Mitigating Spurious Correlations in Fine-Tuned Vision-Language Models
Estimating Fréchet bounds for validating programmatic weak supervision
Fine-Tuning Personalization in Federated Learning to Mitigate Adversarial Clients
When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback
Text-Guided Attention is All You Need for Zero-Shot Robustness in Vision-Language Models
Neural Model Checking
Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement
Reconstruct and Match: Out-of-Distribution Robustness via Topological Homogeneity
Be Confident in What You Know: Bayesian Parameter Efficient Fine-Tuning of Foundation Models
Bridging OOD Generalization and Detection: A Graph-Theoretic View
From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion Models
Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses
$\texttt{ConflictBank}$: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLMs
DiTFastAtten: Accelerate Diffusion Transformers Through Efficient Attention Computation
Stratified Prediction-Powered Inference for Effective Hybrid Evaluation of Language Models
ALOHA: from Attention to Likes – a unified mOdel for understanding HumAn responses to diverse visual content
Theoretical Investigations and Practical Enhancements on Tail Task Risk Minimization in Meta Learning
Learning Partitions from Context
QVAE-Mole: The Quantum VAE with Spherical Latent Variable Learning for 3-D Molecule Generation
State-free Reinforcement Learning
Satformer: Accurate and Robust Traffic Data Estimation for Satellite Networks
DisC-GS: Discontinuity-aware Gaussian Splatting
Towards General Conceptual Model Editing via Adversarial Representation Engineering
Tactile DreamFusion: Exploiting Tactile Sensing for 3D Generation
Gorilla: Teaching LLMs to Use Tools
SPRINQL: Sub-optimal Demonstrations driven Offline Imitation Learning
Fast Proxy Experiment Design for Causal Effect Identification
Likelihood-based differentiable structure learning
Sample Complexity of Interventional Causal Representation Learning
Drift-Resilient TabPFN: In-Context Learning Distribution Shifts on Tabular Data
Marginal Causal Flows for Validation and Inference
Benchmarking Counterfactual Image Generation
DTGB: A Comprehensive Benchmark for Dynamic Text-Attributed Graphs
Muharaf: Manuscripts of Handwritten Arabic Dataset for Cursive Text Recognition
A Large-Scale Human-Centric Benchmark for Referring Expression Comprehension in the LMM Era
UltraEdit: Instruction-based Fine-Grained Image Editing at Scale
WildPPG: A Real-World PPG Dataset of Long Continuous Recordings
Comprehensive Framework for Curating Speech Datasets and Evaluating ASR Systems: A Case Study for the Polish Language
Arctique: An artificial histopathological dataset unifying realism and controllability for uncertainty quantification
SolarCube: An Integrative Benchmark Dataset Harnessing Satellite and In-situ Observations for Large-scale Solar Energy Forecasting
Evaluating Large Vision-and-Language Models on Children's Mathematical Olympiads
VERIFIED: A Video Corpus Moment Retrieval Benchmark for Fine-Grained Video Understanding
DivSafe: Evaluating the Generalization of LLM Safety Training Across Diverse Tasks and Prompt Types
CableInspect-AD: An Expert-Annotated Anomaly Detection Dataset
Advancing Video Anomaly Detection: A Concise Review and a New Dataset
CryoBench: Datasets and Benchmarks for Heterogeneous Cryo-EM Reconstruction
Multi-Chain Graphs of Graphs: A New Paradigm in Blockchain Dataset
DrivingDojo Dataset: Advancing Interactive and Knowledge-Enriched Driving World Model
Einsum Benchmark: Enabling the Development of Next-Generation Tensor Execution Engines
HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language Models
Animal-Bench: Benchmarking Multimodal Video Models for Animal-centric Video Understanding
Reproducibility study of FairAC
Mitigating Spurious Correlations via Disagreement Probability
Monoculture in Matching Markets
Decision-Making Behavior Evaluation Framework for LLMs under Uncertain Context
AnonFair: A Flexible Toolkit for Algorithmic Fairness
Active Classification with Few Queries under Misspecification
Statistical-Computational Trade-offs for Density Estimation
A two-scale Complexity Measure for Deep Learning Models
Active Learning of General Halfspaces: Label Queries vs Membership Queries
On the Impacts of the Random Initialization in the Neural Tangent Kernel Theory
Distributed Least Squares in Small Space via Sketching and Bias Reduction
Optimal Parallelization of Boosting
Exploring the Precise Dynamics of Single-Layer GAN Models: Leveraging Multi-Feature Discriminators for High-Dimensional Subspace Learning
Information-theoretic Generalization Analysis for Expected Calibration Error
Taming Heavy-Tailed Losses in Adversarial Bandits and the Best-of-Both-Worlds Setting
On the Minimax Regret for Contextual Linear Bandits and Multi-Armed Bandits with Expert Advice
PRODuctive bandits: Importance Weighting No More
The Road Less Scheduled
Towards Exact Gradient-based Training on Analog In-memory Computing
SequentialAttention++ for Block Sparsification: Differentiable Pruning Meets Combinatorial Optimization
Non-asymptotic Analysis of Biased Adaptive Stochastic Approximation
BPQP: A Differentiable Convex Optimization Framework for Efficient End-to-End Learning
Exact, Tractable Gauss-Newton Optimization in Deep Reversible Architectures Reveal Poor Generalization
Near-Optimal Methods for Convex Simple Bilevel Problems
Interpretable Lightweight Transformer via Unrolling of Learned Graph Smoothness Priors
Promoting Fairness Among Dynamic Agents in Online-Matching Markets under Known Stationary Arrival Distributions
Accelerating Inference with Fast and Expressive Sketch Structured Transform
$M^3$GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and Generation
A Combinatorial Algorithm for the Semi-Discrete Optimal Transport Problem
Freya PAGE: First Optimal Time Complexity for Large-Scale Nonconvex Finite-Sum Optimization with Heterogeneous Asynchronous Computations
LSH-MoE: Communication-efficient MoE Training via Locality-Sensitive Hashing
IPM-LSTM: A Learning-Based Interior Point Method for Solving Nonlinear Programs
Learning to Handle Complex Constraints for Vehicle Routing Problems
Learning high-dimensional targets by two-parameter models and gradient flow
The Collusion of Memory and Nonlinearity in Stochastic Approximation With Constant Stepsize
Guided Trajectory Generation with Diffusion Models for Offline Model-based Optimization
Multi-Stage Predict+Optimize for (Mixed Integer) Linear Programs
Fishers and Hessians of Continuous Relaxations
Logical characterizations of recurrent graph neural networks with reals and floats
Differentially Private Set Representations
Entropy-regularized Diffusion Policy with Q-Ensembles for Offline Reinforcement Learning
A Simulation Benchmark for Autonomous Racing with Large-Scale Human Data
Dual Critic Reinforcement Learning under Partial Observability
The Surprising Ineffectiveness of Pre-Trained Visual Representations for Model-Based Reinforcement Learning
SSDiff: Spatial-spectral Integrated Diffusion Model for Remote Sensing Pansharpening
Time-Constrained Robust MDPs
No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO
Resolving Partial Observability in Decision Processes via the Lambda Discrepancy
Autoregressive Image Diffusion: Generating Image Sequence and Application in MRI
Disentangled Unsupervised Skill Discovery for Efficient Hierarchical Reinforcement Learning
Autoregressive Policy Optimization for Constrained Allocation Tasks
BenchMARL: Benchmarking Multi-Agent Reinforcement Learning
A Consistency-Aware Spot-Guided Transformer for Versatile and Hierarchical Point Cloud Registration
ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot Coordination
SustainDC: Benchmarking for Sustainable Data Center Control
Melting Pot Contest: Charting the Future of Generalized Cooperative Intelligence
Opponent Modeling based on Subgoal Inference
MADiff: Offline Multi-agent Learning with Diffusion Models
Measuring Mutual Policy Divergence for Multi-Agent Sequential Exploration
Towards Effective Planning Strategies for Dynamic Opinion Networks
Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing
Latent Plan Transformer: Planning as Latent Variable Inference
Understanding Preference Learning Through the Lens of Coverage
LLM-based Skill Diffusion for Zero-shot Policy Adaptation
Stepwise Alignment for Constrained Language Model Policy Optimization
Beyond Optimism: Exploration With Partially Observable Rewards
Is Score Matching Suitable for Estimating Point Processes?
POCA: Partially Observable Cost-Aware Active-Learning
Clustering with Non-adaptive Subset Queries
Preference Learning of Latent Decision Utilities with a Human-like Model of Preferential Choice
Sketchy Moment Matching: Toward Fast and Provable Data Selection for Finetuning
Continuous Temporal Domain Generalization
Cross-Device Collaborative Test-Time Adaptation
Quantum algorithm for large-scale market equilibrium computation
Conformalized Credal Set Predictors
Sub-optimal Experts mitigate Ambiguity in Inverse Reinforcement Learning
Bisimulation Metrics are Optimal Transport Distances, and Can be Computed Efficiently
Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning
Towards Robust \emph{De Novo} Peptide Sequencing in Proteomics against Data Biases
Instance-adaptive Zero-shot Chain-of-Thought Prompting
Motion Graph Unleashed: A Novel Approach to Video Prediction
Efficient Minimum Bayes Risk Decoding using Low-Rank Matrix Completion Algorithms
Large Language Models-guided Dynamic Adaptation for Temporal Knowledge Graph Reasoning
ROIDICE: Offline Return on Investment Maximization for Efficient Decision Making
TAPTRv2: Tracking Any Point with Transformers as Detection
SpGesture: Source-Free Domain-adaptive sEMG-based Gesture Recognition with Jaccard Attentive Spiking Neural Network
LCM: Locally Constrained Compact Point Cloud Model for Masked Point Modeling
Connecting Joint-Embedding Predictive Architecture with Contrastive Self-supervised Learning
Reparameterized Multi-Resolution Convolutions for Long Sequence Modelling
Variational Flow Matching for Graph Generation
Derivative-enhanced Deep Operator Network
ShowMaker: Creating High-Fidelity 2D Human Video via Fine-Grained Diffusion Modeling
Generalization Error Bounds for Two-stage Recommender Systems with Tree Structure
Wings: Learning Multimodal LLMs without Text-only Forgetting
Iterative Methods via Locally Evolving Set Process
IMPACT: A Large-scale Integrated Multimodal Patent Analysis and Creation Dataset for Design Patents
Evidential Stochastic Differential Equations for Time-Aware Sequential Recommendation
Pin-Tuning: Parameter-Efficient In-Context Tuning for Few-shot Molecular Property Prediction
Relationship Prompt Learning is Enough for Open-Vocabulary Semantic Segmentation
LLMDFA: Analyzing Dataflow in Code with Large Language Models
CoSW: Conditional Sample Weighting for Smoke Segmentation with Label Noise
SplitNeRF: Split Sum Approximation Neural Field for Joint Geometry, Illumination, and Material Estimation
P$^2$C$^2$Net: PDE-Preserved Coarse Correction Network for efficient prediction of spatiotemporal dynamics
On Softmax Direct Preference Optimization for Recommendation
AsEP: Benchmarking Deep Learning Methods for Antibody-specific Epitope Prediction
Reactzyme: A Benchmark for Enzyme-Reaction Prediction
ProSST: Protein Language Modeling with Quantized Structure and Disentangled Attention
Association Pattern-aware Fusion for Biological Entity Relationship Prediction
Multi-Scale Representation Learning for Protein Fitness Prediction
S-MolSearch: 3D Semi-supervised Contrastive Learning for Bioactive Molecule Search
Lexicon3D: Probing Visual Encoding Models for Complex 3D Scene Understanding
Is Your LiDAR Placement Optimized for 3D Scene Understanding?
InterDreamer: Less Supervision for More Generalizable Text-Driven 3D Human-Object Interaction Synthesis
Multi-hypotheses Conditioned Point Cloud Diffusion for 3D Human Reconstruction from Occluded Images
SemFlow: Binding Semantic Segmentation and Image Synthesis via Rectified Flow
Training an Open-Vocabulary Monocular 3D Detection Model without 3D Data
Event-3DGS: Event-based 3D Reconstruction Using 3D Gaussian Splatting
StreamFlow: Streamlined Multi-Frame Optical Flow Estimation for Video Sequences
CLIP in Mirror: Disentangling text from visual images through reflection
LiveScene: Language Embedding Interactive Radiance Fields for Physical Scene Control and Rendering
TopoFR: A Closer Look at Topology Alignment on Face Recognition
TopoLogic: An Interpretable Pipeline for Lane Topology Reasoning on Driving Scenes
Parameter-Inverted Image Pyramid Networks
On the Power of Small-size Graph Neural Networks for Linear Programming
WildGaussians: 3D Gaussian Splatting In the Wild
LoD-Loc: Aerial Visual Localization using LoD 3D Map with Neural Wireframe Alignment
MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks
PPLNs: Parametric Piecewise Linear Networks for Event-Based Temporal Modeling and Beyond
Multi-times Monte Carlo Rendering for Inter-reflection Reconstruction
GenRec: Unifying Video Generation and Recognition with Diffusion Models
VCR-GauS: View Consistent Depth-Normal Regularizer for Gaussian Surface Reconstruction
Splatter a Video: Video Gaussian Representation for Versatile Processing
DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators
Rethinking Imbalance in Image Super-Resolution for Efficient Inference
GOMAA-Geo: GOal Modality Agnostic Active Geo-localization
Efficient Temporal Action Segmentation via Boundary-aware Query Voting
MambaLLIE: Implicit Retinex-Aware Low Light Enhancement with Global-then-Local State Space
DeBaRA: Denoising-Based 3D Room Arrangement Generation
ResAD: A Simple Framework for Class Generalizable Anomaly Detection
Advancing Open-Set Domain Generalization Using Evidential Bi-Level Hardest Domain Scheduler
Continual Learning in the Frequency Domain
Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model
Exploring Low-Dimensional Subspace in Diffusion Models for Controllable Image Editing
Stable-Pose: Leveraging Transformers for Pose-Guided Text-to-Image Generation
Conditional Controllable Image Fusion
AsCAN: Asymmetric Convolution-Attention Networks for Efficient Recognition and Generation
CemiFace: Center-based Semi-hard Synthetic Face Generation for Face Recognition
Steganalysis on Digital Watermarking: Is Your Robustness a Maginot Line?
Unleashing the Potential of the Diffusion Model in Few-shot Semantic Segmentation
SpelsNet: Surface Primitive Elements Segmentation by B-Rep Graph Structure Supervision
Federated Black-Box Adaptation for Semantic Segmentation
Infinite-Dimensional Feature Interaction
Weakly Supervised Referring Image Segmentation via Progressive Comprehension
SafeWorld: Geo-Diverse Safety Alignment
Semantic and Spatial Adaptive Pixel-level Classifier for Semantic Segmentation
Uncertainty-aware Fine-tuning of Segmentation Foundation Models
Zero-Shot Event-Intensity Asymmetric Stereo via Visual Prompting from Image Domain
3DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priors
Non-parametric classification via expand-and-sparsify representation
VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time
Motion Consistency Model: Accelerating Video Diffusion with Disentangled Motion-Appearance Distillation
VideoTetris: Towards Compositional Text-to-Video Generation
ChatTracker: Enhancing Visual Tracking Performance via Chatting with Multimodal Large Language Model
Extending Video Masked Autoencoders to 128 frames
Video Token Merging for Long Video Understanding
Data Distribution Valuation
$\texttt{dattri}$: A Library for Efficient Data Attribution
Image Textualization: An Automatic Framework for Generating Rich and Detailed Image Descriptions
CSPG: Crossing Sparse Proximity Graphs for Approximate Nearest Neighbor Search
Deep linear networks for regression are implicitly regularized towards flat minima
DeltaDock: A Unified Framework for Accurate, Efficient, and Physically Reliable Molecular Docking
Improving Neural ODE Training with Temporal Adaptive Batch Normalization
A robust inlier identification algorithm for point cloud registration via $\mathbf{\ell_0}$-minimization
Are nuclear masks all you need for improved out-of-domain generalization? A closer look at cancer classification in histopathology.
CondTSF: One-line Plugin of Dataset Condensation for Time Series Forecasting
LLMs as Zero-shot Graph Learners: Alignment of GNN Represetantions with LLM Token Embeddings
Enhancing Protein Mutation Effect Prediction through a Retrieval-Augmented Framework
Normalization Layer Per-Example Gradients are Sufficient to Predict Gradient Noise Scale in Transformers
Efficient Leverage Score Sampling for Tensor Train Decomposition
BLAST: Block-Level Adaptive Structured Matrices for Efficient Deep Neural Network Inference
Demystify Mamba in Vision: A Linear Attention Perspective
Federated Graph Learning for Cross-Domain Recommendation
Collaborative Cognitive Diagnosis with Disentangled Representation Learning
Bayesian Domain Adaptation with Gaussian Mixture Domain-Indexing
MC-DiT: Contextual Enhancement via Clean-to-Clean Reconstruction for Masked Diffusion Models
An effective framework for estimating individualized treatment rule with multi-category treatments
Computerized Adaptive Testing via Collaborative Ranking
QT-ViT: Improving Linear Attention in ViT with Quadratic Taylor Expansion
Unveiling the Hidden Structure of Self-Attention via Kernel Principal Component Analysis
Graph Convolutions Enrich the Self-Attention in Transformers!
Robustly overfitting latents for flexible neural image compression
Semi-Open 3D Object Retrieval via Hypergraph-Based Hierarchical Equilibrium Representation
Dual-Perspective Activation: Efficient Channel Denoising via Joint Forward-Backward Criterion for Artificial Neural Networks
DRIP: Unleashing Diffusion Priors for Joint Foreground and Alpha Prediction in Image Matting
In Pursuit of Causal Label Correlations for Multi-label Image Recognition
Learning Structure-Aware Representations of Dependent Types
D2R2: Diffusion-based Representation with Random Distance Matching for Tabular Few-shot Learning
Chimera: Effectively Modeling Multivariate Time Series with 2-Dimensional State Space Models
Learning Structured Representations with Hyperbolic Embeddings
Catastrophic Goodhart: regularizing RLHF with KL divergence does not mitigate heavy-tailed reward misspecification
DiffHammer: Rethinking the Robustness of Diffusion-Based Adversarial Purification
Robust Graph Neural Networks via Unbiased Aggregation
You Don't Need Data-Augmentations in Self-Supervised Learning
Self-supervised Transformation Learning for Equivariant Representations
LoCo: Learning 3D Location-Consistent Image Features with a Memory-Efficient Ranking Loss
Cross-video Identity Correlating for Person Re-identification Pre-training
Symmetries In-Context: Universal Self-Supervised Learning through Contextual World Models
Your contrastive learning problem is secretly a distribution alignment problem
Variation Spaces for Multi-Output Neural Networks: Insights on Multi-Task Learning and Network Compression
Reparameterization invariance in approximate Bayesian inference
The Implicit Bias of Gradient Descent on Separable Multiclass Data
Provable Tempered Overfitting of Minimal Nets and Typical Nets
Surge Phenomenon in Optimal Learning Rate and Batch Size Scaling
Implicit Bias of Mirror Flow on Separable Data
How does Architecture Influence the Base Capabilities of Pre-trained Language Models? A Case Study Based on FFN-Wider and MoE Transformers
FuseFL: One-Shot Federated Learning through the Lens of Causality with Progressive Model Fusion
Mixture of Nested Experts: Adaptive Processing of Visual Tokens
SDP4Bit: Toward 4-bit Communication Quantization in Sharded Data Parallelism for LLM Training
Layer-Adaptive $\mathcal{H}_\infty$ State Pruning for Deep Diagonal State Space Model Compression
NoiseGPT: Label Noise Detection and Rectification through Probability Curvature
Toward Efficient Inference for Mixtures of Experts
Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text
SMART: Scalable Multi-agent Real-time Motion Generation via Next-token Prediction
Atlas3D: Physically Constrained Self-Supporting Text-to-3D for Simulation and Fabrication
Doob's Lagrangian: A Sample-Efficient Variational Approach to Transition Path Sampling
GaussianCube: A Structured and Explicit Radiance Representation for 3D Generative Modeling
GAVEL: Generating Games via Evolution and Language Models
SCube: Instant Large-Scale Scene Reconstruction using VoxSplats
Scene Graph Disentanglement and Composition for Generalizable Complex Image Generation
Utilizing Image Transforms and Diffusion Models for Generative Modeling of Short and Long Time Series
Unleashing the Denoising Capability of Diffusion Prior for Solving Inverse Problems
ReplaceAnything3D: Text-Guided Object Replacement in 3D Scenes with Compositional Scene Representations
On improved Conditioning Mechanisms and Pre-training Strategies for Diffusion Models
Improved Bayes Regret Bounds for Multi-Task Hierarchical Bayesian Bandit Algorithms
Consistency Diffusion Bridge Models
EDT: An Efficient Diffusion Transformer Framework Inspired by Human-like Sketching
Your Diffusion Model is Secretly a Noise Classifier and Benefits from Contrastive Training
RealCompo: Balancing Realism and Compositionality Improves Text-to-Image Diffusion Models
Diffusion Tuning: Transferring Diffusion Models via Chain of Forgetting
Diffusing Differentiable Representations
Gradient Guidance for Diffusion Models: An Optimization Perspective
What matters when building vision-language models?
Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models
Video Diffusion Models are Training-free Motion Interpreter and Controller
Understanding Hallucinations in Diffusion Models through Mode Interpolation
An Expectation-Maximization Algorithm for Training Clean Diffusion Models from Corrupted Observations
Towards Safe Concept Transfer of Multi-Modal Diffusion via Causal Representation Editing
EM Distillation for One-step Diffusion Models
ControlSynth Neural ODEs: Modeling Dynamical Systems with Guaranteed Convergence
Towards Global Optimal Visual In-Context Learning Prompt Selection
In-Context Learning State Vector with Inner and Momentum Optimization
UDKAG: Augmenting Large Vision-Language Models with Up-to-Date Knowledge
Base of RoPE Bounds Context Length
Elo Uncovered: Robustness and Best Practices in Language Model Evaluation
INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulness
Language Models as Hierarchy Encoders
Risk-Averse Finetuning of Large Language Models
ACES: Generating a Diversity of Challenging Programming Puzzles with Autotelic Generative Models
DenseFormer: Enhancing Information Flow in Transformers via Depth Weighted Averaging
Mr.Bean: A Comprehensive Meta-Reasoning Benchmark for Analyzing Large Language Models
Can Graph Learning Improve Task Planning?
OccamLLM: Fast and Exact Language Model Arithmetic in a Single Step
TGB 2.0: A Benchmark for Learning on Temporal Knowledge Graphs and Heterogeneous Graphs
IntraMix: Intra-Class Mixup Generation for Accurate Labels and Neighbors
Improving Neural Network Surface Processing with Principal Curvatures
Schur Nets: exploiting local structure for equivariance in higher order graph neural networks
FedSSP: Federated Graph Learning with Spectral Knowledge and Personalized Preference
Probabilistic Graph Rewiring via Virtual Nodes
Are Your Models Still Fair? Fairness Attacks on Graph Neural Networks via Node Injections
HGDL: Heterogeneous Graph Label Distribution Learning
Prompt-Based Knowledge Graph Foundation Model for Universal In-Context Reasoning
Causal Inference in the Closed-Loop: Marginal Structural Models for Sequential Excursion Effects
SpeAr: A Spectral Approach for Zero-Shot Node Classification
A Canonization Perspective on Invariant and Equivariant Learning
UniGAD: Unifying Multi-level Graph Anomaly Detection
Beyond Single Stationary Policies: Meta-Task Players as Naturally Superior Collaborators
Posture-Informed Muscular Force Learning for Robust Hand Pressure Estimation
Expectation Alignment: Handling Reward Misspecification in the Presence of Expectation Mismatch
[Re] On the Reproducibility of Post-Hoc Concept Bottleneck Models
shapiq: Shapley Interactions for Machine Learning
Vision Mamba Mender
Model Reconstruction Using Counterfactual Explanations: A Perspective From Polytope Theory
I Bet You Did Not Mean That: Semantic Importance of Any Classifier via Betting
What Makes Safety Fine-tuning Methods Safe? A Mechanistic Study
A Concept-Based Explainability Framework for Large Multimodal Models
Iteration Head: A Mechanistic Study of Chain-of-Thought
Coarse-to-Fine Concept Bottleneck Models
Towards Accurate and Fair Cognitive Diagnosis via Monotonic Data Augmentation
Interpretable Concept-Based Memory Reasoning
Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents
OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI
Block Transformer: Global-to-Local Language Modeling for Fast Inference
AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment
LoFiT: Localized Fine-tuning on LLM Representations
Reward Learning from Human Demonstration Improves Supervised Fine-tuning for LLM Alignment
Enhancing LLM’s Cognition via Structurization
FLAME : Factuality-Aware Alignment for Large Language Models
Decoding-Time Language Model Alignment with Multiple Objectives
Mixture of Scales: Memory-Efficient Token-Adaptive Binarization for Large Language Models
DiffNorm: Self-Supervised Normalization for Non-autoregressive Speech-to-speech Translation
SILENCE: Protecting privacy in offloaded speech understanding on wimpy devices
Gradients of Functions of Large Matrices
The Selective $G$-Bispectrum and its Inversion: Applications to $G$-Invariant Networks
Learning to Embed Distributions via Maximum Kernel Entropy
The Minimax Rate of HSIC Estimation for Translation-Invariant Kernels
Soft Tensor Product Representations for Fully Continuous, Compositional Visual Representations
Model Sensitivity Aware Continual Learning
On the Stability and Generalization of Meta-Learning
Mind the Gap Between Prototypes and Images in Cross-domain Few-shot Classification
DA-Ada: Learning Domain-Aware Adapter for Domain Adaptive Object Detection
EMR-Merging: Tuning-Free High-Performance Model Merging
RankUp: Boosting Semi-Supervised Regression with an Auxiliary Ranking Classifier
Fast Graph Sharpness-Aware Minimization for Enhancing and Accelerating Few-Shot Node Classification
CONTRAST: Continual Multi-source Adaptation to Dynamic Distributions
KFNN: K-Free Nearest Neighbor For Crowdsourcing
Visual Riddles: a Commonsense and World Knowledge Challenge for Large Vision and Language Models
Facilitating Multimodal Classification via Dynamically Learning Modality Gap
What Factors Affect Multi-modal In-Context Learning? An In-Depth Exploration
DDR: Exploiting Deep Degradation Response as Flexible Image Descriptor
Model Fusion through Bayesian Optimization in Language Model Fine-Tuning
TripletCLIP: Improving Compositional Reasoning of CLIP via Vision-Language Negatives
CODE: Contrasting Self-generated Description to Combat Hallucination in Large Multi-modal Models
CigTime: Corrective Instruction Generation Through Inverse Motion Editing
Dual Prototype Evolving for Test-Time Generalization of Vision-Language Models
InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD
Feature-Level Adversarial Attacks and Ranking Disruption for Visible-Infrared Person Re-identification
Membership Inference Attacks against Large Vision-Language Models
A Rank-Based Metric for Evaluating Large Language Models
UDPM: Upsampling Diffusion Probabilistic Models
Efficient Sketches for Training Data Attribution and Studying the Loss Landscape
Provably Optimal Memory Capacity for Modern Hopfield Models
Divergences between Language Models and Human Brains
Doing Experiments and Revising Rules with Natural Language and Probabilistic Reasoning
Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem
The motion planning neural circuit in goal-directed navigation as Lie group operator search
Probabilistic Decomposed Linear Dynamical Systems for Robust Discovery of Latent Neural Dynamics
Advancing Spiking Neural Networks for Sequential Modeling through Central Pattern Generators
Advancing Training Efficiency of Deep Spiking Neural Networks through Rate-based Backpropagation
Physics-Constrained Comprehensive Optical Neural Networks
Towards Universal Mesh Movement Networks
DEL: Discrete Element Learner for Learning 3D Dynamics from 2D Observations
MG-Net: Automatically Customize QAOA with Quantum Hardware Constraints for Enhanced Performance
The Challenges of the Nonlinear Regime for Physics-Informed Neural Netowrks
DiffusionPDE: Generative PDE-Solving under Partial Observation
HyperDDPM: Estimating Epistemic and Aleatoric Uncertainty with a Single Model
Small coresets via negative dependence: DPPs, linear statistics, and concentration
Block Sparse Bayesian Learning: A Diversified Scheme
Generating Origin-Destination Matrices in Neural Spatial Interaction Models
Sample-efficient Simulation-based Inference for Urban Travel Demand Calibration
Cost-aware Bayesian optimization via the Pandora's box Gittins index
Closed-Loop Visuomotor Control with Generative Expectation for Robotic Manipulation
BricksRL: A Platform for Democratizing Robotics and Reinforcement Learning Research and Education with LEGO
BehaviorGPT: Smart Agent Simulation for Autonomous Driving with Next-Patch Prediction
QueST: Self-Supervised Skill Abstractions for Learning Continuous Control
Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution
Learning Neural Contracting Dynamics: Extended Linearization and Global Guarantees
DG-SLAM: Robust Dynamic Gaussian Splatting SLAM with Hybrid Pose Optimization
Pearls from Pebbles: Improved Confidence Functions for Auto-labeling
Private Algorithms for Stochastic Saddle Points and Variational Inequalities: Beyond Euclidean Geometry
Can Large Language Model Agents Simulate Human Trust Behavior?
Unlocking the Potential of Global Human Expertise
Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Series
Rethinking Fourier Transform for Long-term Time Series Forecasting: A Basis Functions Perspective
Addressing Spatial-Temporal Heterogeneity: General Mixed Time Series Analysis via Latent Continuity Recovery and Alignment
AutoTimes: Autoregressive Time Series Forecasters via Large Language Models
Frequency Adaptive Normalization For Non-stationary Time Series Forecasting
PGN: The RNN's New Successor is Effective for Long-Range Time Series Forecasting
Evaluating Copyright Takedown Methods for Language Models
Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights
Automating Data Annotation under Strategic Human Agents: Risks and Potential Solutions
Kernel PCA for Out-of-Distribution Detection
Heterogeneity-Guided Client Sampling: Towards Fast and Efficient Non-IID Federated Learning
Neuc-MDS: Non-Euclidean Multidimensional Scaling Through Bilinear Forms
What Makes Partial-Label Learning Algorithms Effective?
How Far Can Transformers Reason? The Locality Barrier and Inductive Scratchpad
Typicalness-Aware Learning for Failure Detection
A Textbook Remedy for Domain Shifts: Knowledge Priors for Medical Image Analysis
Unified Insights: Harnessing Multi-modal Data for Phenotype Imputation via View Decoupling
Uncovering Safety Risks of Large Language Models through Concept Activation Vector
Test-Time Adaptation Induces Stronger Accuracy and Agreement-on-the-Line
Selective Generation for Language Models
Certified Adversarial Robustness via Randomized $\alpha$-Smoothing for Regression Models
RFLPA: A Robust Federated Learning Framework against Poisoning Attacks with Secure Aggregation
Understanding and Improving Adversarial Collaborative Filtering for Robust Recommendation
Learning the Latent Causal Structure for Modeling Label Noise
SEEV: Synthesis with Efficient Exact Verification for ReLU Neural Barrier Functions
Revive Re-weighting in Imbalanced Learning by Density Ratio Estimation
Visual Anchors Are Strong Information Aggregators For Multimodal Large Language Model
Expressive Gaussian Human Avatars from Monocular RGB Video
The Edge-of-Reach Problem in Offline Model-Based Reinforcement Learning
Inevitable Trade-off between Watermark Strength and Speculative Sampling Efficiency for Language Models
A Boosting-Type Convergence Result for AdaBoost.MH with Factorized Multi-Class Classifiers
Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models
ARC: A Generalist Graph Anomaly Detector with In-Context Learning
A Local Method for Satisfying Interventional Fairness with Partially Known Causal Graphs
Unveiling The Matthew Effect Across Channels: Assessing Layer Width Sufficiency via Weight Norm Variance
Analytically Computing Partial Information Decomposition
Improving Environment Novelty Quantification for Effective Unsupervised Environment Design
Federated Learning under Periodic Client Participation and Heterogeneous Data: A New Communication-Efficient Algorithm and Analysis
FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attention
Discrete Modeling via Boundary Conditional Diffusion Processes
Normalization and effective learning rates in reinforcement learning
Truthful High Dimensional Sparse Linear Regression
TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy
Approximately Equivariant Neural Processes
Advantage-Aware Policy Optimization for Offline Reinforcement Learning
Sequential Harmful Shift Detection Without Labels
End-to-End Video Semantic Segmentation in Adverse Weather using Fusion Blocks and Temporal-Spatial Teacher-Student Learning
MiniCache: KV Cache Compression in Depth Dimension for Large Language Models
Graph Neural Flows for Unveiling Systemic Interactions Among Irregularly Sampled Time Series
ElasTST: Towards Robust Varied-Horizon Forecasting with Elastic Time-Series Transformer
Causal-learn: Causal Discovery in Python
Higher-Order Causal Message Passing for Experimentation Under Unknown Interference
Proximal Causal Inference With Text Data
Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision Processes
Identifiability Guarantees for Causal Disentanglement from Purely Observational Data
Marrying Causal Representation Learning with Dynamical Systems for Science
Natural Counterfactuals With Necessary Backtracking
Ordering-Based Causal Discovery for Linear and Nonlinear Relations
Sample Efficient Bayesian Learning of Causal Graphs from Interventions
Causal discovery in the presence of endogenous context variables
FindingEmo: An Image Dataset for Emotion Recognition in the Wild
VastTrack: Vast Category Visual Object Tracking
Neural Cover Selection for Image Steganography
Through the Looking-Glass: Tracing Shifts in AI Data Consent across the Web
ActionAtlas: A VideoQA Benchmark for Fine-grained Action Recognition
StreamBench: Towards Benchmarking Continuous Improvement of Language Agents
The Multimodal Universe: Enabling Large-Scale Machine Learning with 70TBs of Astronomical Scientific Data
BeanCounter: A low-toxicity, large-scale, and open dataset of business-oriented text
RAGChecker: A Fine-grained Framework for Diagnosing Retrieval-Augmented Generation
SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation
Noisy Ostracods: A Fine-Grained, Imbalanced Real-World Dataset for Benchmarking Robust Machine Learning and Label Correction Methods
WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks
NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples
MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding
SeTAR: Out-of-Distribution Detection with Selective Low-Rank Approximation
NovoBench: Benchmarking Deep Learning-based \emph{De Novo} Sequencing Methods in Proteomics
Evaluating Numerical Reasoning in Text-to-Image Models
DECO-Bench: Unified Benchmark for Decoupled Task-Agnostic Synthetic Data Release
RoleAgent: Building, Interacting, and Benchmarking High-quality Role-Playing Agents from Scripts
MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models
Unlocking Tokens as Data Points for Generalization Bounds on Larger Language Models
Nuclear Fusion Diamond Polishing Dataset
Outlier-Robust Distributionally Robust Optimization via Unbalanced Optimal Transport
MMLONGBENCH-DOC: Benchmarking Long-context Document Understanding with Visualizations
RealMAN: A Real-Recorded and Annotated Microphone Array Dataset for Dynamic Speech Enhancement and Localization
SS3DM: Benchmarking Street-View Surface Reconstruction with a Synthetic 3D Mesh Dataset
Towards Open Respiratory Acoustic Foundation Models: Pretraining and Benchmarking
SE(3)-bi-equivariant Transformers for Point Cloud Assembly
Reproducibility study of "Robust Fair Clustering: A Novel Fairness Attack and Defense Framework"
Proportional Fairness in Non-Centroid Clustering
Geometry Cloak: Preventing TGS-based 3D Reconstruction from Copyrighted Images
Fairness-Aware Estimation of Graphical Models
Improving Logits-based Detector without Logits from Black-box LLMs
On the Computational Landscape of Replicable Learning
Provable Benefit of Cutout and CutMix for Feature Learning
Oracle-Efficient Differentially Private Learning with Public Data
Realizable $H$-Consistent and Bayes-Consistent Loss Functions for Learning to Defer
On the Complexity of Learning Sparse Functions with Statistical and Gradient Queries
Robust Mixture Learning when Outliers Overwhelm Small Groups
4+3 Phases of Compute-Optimal Neural Scaling Laws
A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning
Entropy testing and its application to testing Bayesian networks
Semi-Supervised Sparse Gaussian Classification: Provable Benefits of Unlabeled Data
The Price of Implicit Bias in Adversarially Robust Generalization
Metric Transforms and Low Rank Representations of Kernels
Solving Sparse \& High-Dimensional-Output Regression via Compression
Online Estimation via Offline Estimation: An Information-Theoretic Framework
Saliency-driven Experience Replay for Continual Learning
Online Non-convex Learning in Dynamic Environments
Online Control with Adversarial Disturbance for Continuous-time Linear Systems
Online Composite Optimization Between Stochastic and Adversarial Environments
Towards Efficient and Optimal Covariance-Adaptive Algorithms for Combinatorial Semi-Bandits
Almost Minimax Optimal Best Arm Identification in Piecewise Stationary Linear Bandits
Piecewise-Stationary Bandits with Knapsacks
The High Line: Exact Risk and Learning Rate Curves of Stochastic Adaptive Learning Rate Algorithms
Pseudo-Private Data Guided Model Inversion Attacks
An Improved Empirical Fisher Approximation for Natural Gradient Descent
SkipPredict: When to Invest in Predictions for Scheduling
Exploring Jacobian Inexactness in Second-Order Methods for Variational Inequalities: Lower Bounds, Optimal Algorithms and Quasi-Newton Approximations
CoBo: Collaborative Learning via Bilevel Optimization
BitDelta: Your Fine-Tune May Only Be Worth One Bit
Code Agents are State of the Art Software Testers
Collaboration! Towards Robust Neural Methods for Routing Problems
Generalization Bound and Learning Methods for Data-Driven Projections in Linear Programming
Learning to Solve Quadratic Unconstrained Binary Optimization in a Classification Way
A Novel Approach to Loss Landscape Characterization without Over-Parametrization
Nonconvex Federated Learning on Compact Smooth Submanifolds With Heterogeneous Data
Conformal Inverse Optimization
Treeffuser: probabilistic prediction via conditional diffusions with gradient-boosted trees
Localized Adaptive Risk Control
Minimizing UCB: a Better Local Search Strategy in Local Bayesian Optimization
Stepping Forward on the Last Mile
Privacy without Noisy Gradients: Slicing Mechanism for Generative Model Training
Differentially Private Optimization with Sparse Gradients
Disentangled Style Domain for Implicit $z$-Watermark Towards Copyright Protection
Sample-Efficient Private Learning of Mixtures of Gaussians
Nearly Tight Black-Box Auditing of Differentially Private Machine Learning
On Differentially Private U Statistics
Constrained Latent Action Policies for Model-Based Offline Reinforcement Learning
Off-Policy Selection for Initiating Human-Centric Experimental Design
Neural Combinatorial Optimization for Robust Routing Problem with Uncertain Travel Times
Enhancing Robustness in Deep Reinforcement Learning: A Lyapunov Exponent Approach
Federated Ensemble-Directed Offline Reinforcement Learning
Minimax Optimal and Computationally Efficient Algorithms for Distributionally Robust Offline Reinforcement Learning
JaxMARL: Multi-Agent RL Environments and Algorithms in JAX
Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning
Learning to Cooperate with Humans using Generative Agents
A Generative Approach to Control Complex Physical Systems
Inference via Interpolation: Contrastive Representations Provably Enable Planning and Inference
SkiLD: Unsupervised Skill Discovery Guided by Local Dependencies
Last-Iterate Global Convergence of Policy Gradients for Constrained Reinforcement Learning
Exploring the Edges of Latent State Clusters for Goal-Conditioned Reinforcement Learning
Exploratory Retrieval-Augmented Planning For Continual Embodied Instruction Following
Rethinking Inverse Reinforcement Learning: from Data Alignment to Task Alignment
Learning World Models for Unconstrained Goal Navigation
Speculative Monte-Carlo Tree Search
Classifier Clustering and Feature Alignment for Federated Learning under Distributed Concept Drift
Learn Incrementally from An Ongoing Trajectory: A Provable In-Trajectory Inverse Reinforcement Learning Framework
Boosted Conformal Prediction Intervals
Worst-Case Offline Reinforcement Learning with Arbitrary Data Support
Initializing Services in Interactive ML Systems for Diverse Users
Adaptive Sampling for Efficient Softmax Approximation
Safe Time-Varying Optimization based on Gaussian Processes with Spatio-Temporal Kernel
DiffuPac: Contextual Mimicry in Adversarial Packets Generation via Diffusion Model
CLIPCEIL: Boosting Domain Generalization for CLIP by Channel rEfinement and Image-text aLignment
Nimbus: Secure and Efficient Two-Party Inference for Transformers
Cloud Object Detector Adaptation by Integrating Different Source Knowledge
TALoS: Enhancing Semantic Scene Completion via Test-time Adaptation on the Line of Sight
Maximizing utility in multi-agent environments by anticipating the behavior of other learners
Aggregating Quantitative Relative Judgments: From Social Choice to Ranking Prediction
Efficiency of the First-Price Auction in the Autobidding World
Contracting with a Learning Agent
Is Knowledge Power? Dissecting Information Asymmetry In Repeated Games
Putting Gale & Shapley to Work: Guaranteeing Stability Through Learning
Mechanism design augmented with output advice
OT4P: Unlocking Effective Orthogonal Group Path for Permutation Relaxation
Autobidder's Dilemma: Why More Sophisticated Autobidders Lead to Worse Auction Efficiency
Externally Valid Policy Evaluation from Randomized Trials Using Additional Observational Data
Meta-Exploiting Frequency Prior for Cross-Domain Few-Shot Learning
Policy Aggregation
Balancing Context Length and Mixing Times for Reinforcement Learning at Scale
Enhancing Large Language Models through Adaptive Tokenizers
Reinforcement Learning with Lookahead Information
Corruption-Robust Linear Bandits: Minimax Optimality and Gap-Dependent Misspecification
Aligning Embeddings and Geometric Random Graphs: Informational Results and Computational Approaches for the Procrustes-Wasserstein Problem
Progressive Entropic Optimal Transport Solvers
Off-policy estimation with adaptively collected data: the power of online learning
The Space Complexity of Approximating Logistic Loss
MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark
Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations
Multi-Reward Best Policy Identification
FineStyle: Fine-grained Controllable Style Personalization for Text-to-image Models
B-ary Tree Push-Pull Method is Provably Efficient for Distributed Learning on Heterogeneous Data
MILP-StuDio: MILP Instance Generation via Block Structure Decomposition
Transformers Represent Belief State Geometry in their Residual Stream
OW-VISCapTor: Abstractors for Open-World Video Instance Segmentation and Captioning
Distributional regression: CRPS-error bounds for model fitting, model selection and convex aggregation
Globally Q-linear Gaussian-Newton Method for Overparameterized Non-convex Matrix Sensing
Wasserstein Distance Rivals Kullback-Leibler Divergence for Knowledge Distillation
Nonparametric Classification on Low Dimensional Manifolds using Overparameterized Convolutional Residual Networks
Sparsity-Agnostic Linear Bandits with Adaptive Adversaries
CAT: Coordinating Anatomical-Textual Prompts for Multi-Organ and Tumor Segmentation
Learning to Discuss Strategically: A Case Study on One Night Ultimate Werewolf
Entity Alignment with Noisy Annotations from Large Language Models
Unified Generative and Discriminative Training for Multi-modal Large Language Models
Stochastic Optimal Control Matching
End-to-End Ontology Learning with Large Language Models
PhoCoLens: Photorealistic and Consistent Reconstruction in Lensless Imaging
Detecting Bugs with Substantial Monetary Consequences by LLM and Rule-based Reasoning
MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution
GTA: Generative Trajectory Augmentation with Guidance for Offline Reinforcement Learning
PROSPECT PTMs: Rich Labeled Tandem Mass Spectrometry Dataset of Modified Peptides for Machine Learning in Proteomics
xMIL: Insightful Explanations for Multiple Instance Learning in Histopathology
MSAGPT: Neural Prompting Protein Structure Prediction via MSA Generative Pre-Training
Harmony4D: A Video Dataset for In-The-Wild Close Human Interactions
A Benchmark Dataset for Event-Guided Human Pose Estimation and Tracking in Extreme Conditions
ScaleKD: Strong Vision Transformers Could Be Excellent Teachers
Cooperate or Collapse: Emergence of Sustainability in a Society of LLM Agents
Not Just Object, But State: Compositional Incremental Learning without Forgetting
BetterDepth: Plug-and-Play Diffusion Refiner for Zero-Shot Monocular Depth Estimation
Learning to Decouple the Lights for 3D Face Texture Modeling
D-MiSo: Editing Dynamic 3D Scenes using Multi-Gaussians Soup
LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS
Optimal Transport-based Labor-free Text Prompt Modeling for Sketch Re-identification
Learning Transferable Features for Implicit Neural Representations
Causal Context Adjustment Loss for Learned Image Compression
DiChaViT: Diverse Representations Boosts Channel-Adaptive Vision Transformers
Constrained Diffusion Models via Dual Training
CRT-Fusion: Camera, Radar, Temporal Fusion Using Motion Information for Bird's Eye View Object Detection
Animate3D: Animating Any 3D Model with Multi-view Video Diffusion
1-bit quanta video reconstruction via self-supervised photon prediction
DiPEx: Dispersing Prompt Expansion for Class-Agnostic Object Detection
When does perceptual alignment benefit vision representations?
Neural Localization Fields for Continuous 3D Human Pose and Shape Estimation
SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object Detection
SuperVLAD: Compact and Robust Image Descriptors for Visual Place Recognition
Multistable Shape from Shading Emerges from Patch Diffusion
A Unified Framework for 3D Scene Understanding
GeoLRM: Geometry-Aware Large Reconstruction Model for High-Quality 3D Gaussian Generation
Text-Infused Attention and Foreground-Aware Modeling for Zero-Shot Temporal Action Detection
FewViewGS: Gaussian Splatting with Few View Matching and Multi-stage Training
Rad-NeRF: Ray-decoupled Training of Neural Radiance Field
DiffSF: Diffusion Models for Scene Flow Estimation
LookHere: Vision Transformers with Directed Attention Generalize and Extrapolate
Learning to Merge Tokens via Decoupled Embedding for Efficient Vision Transformers
Toward Approaches to Scalability in 3D Human Pose Estimation
Unsupervised Homography Estimation on Multimodal Image Pair via Alternating Optimization
Factorized Diffusion Architectures for Unsupervised Image Generation and Segmentation
ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization
Prompt-Agnostic Adversarial Perturbation for Customized Diffusion Models
PromptFix: You Prompt and We Fix the Photo
Leveraging Catastrophic Forgetting to Develop Safe Diffusion Models against Malicious Finetuning
LG-VQ: Language-Guided Codebook Learning
Towards Understanding the Working Mechanism of Text-to-Image Diffusion Model
MVSDet: Multi-View Indoor 3D Object Detection via Efficient Plane Sweeps
Geometric Exploitation for Indoor Panoramic Semantic Segmentation
A Simple Image Segmentation Framework via In-Context Examples
Hierarchical Object-Aware Dual-Level Contrastive Learning for Domain Generalized Stereo Matching
Tetrahedron Splatting for 3D Generation
Variational Multi-scale Representation for Estimating Uncertainty in 3D Gaussian Splatting
Single Forward Video Generation Model
Adversarial Moment-Matching Distillation of Large Language Models
Measuring Dejavu Memorization Efficiently
Diffusion4D: Fast Spatial-temporal Consistent 4D generation via Video Diffusion Models
Fast and Memory-Efficient Video Diffusion Using Streamlined Inference
ReVideo: Remake a Video with Motion and Content Control
TAPVid-3D: A Benchmark for Tracking Any Point in 3D
Croissant: A Metadata Format for ML-Ready Datasets
SyncTweedies: A General Generative Framework Based on Synchronized Diffusions
EEVR: A Virtual Reality-Based Emotion Dataset Featuring Paired Physiological Signals and Textual Descriptions
Offline Behavior Distillation
Just Add $100 More: Augmenting Pseudo-LiDAR Point Cloud for Resolving Class-imbalance Problem
Right this way: Can VLMs Guide Us to See More to Answer Questions?
MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language Annotations
Turning Indirect Knowledge into Direct Demonstrations for Computer Agents at Scale
Intrinsic Self-Supervision for Data Quality Audits
On the Inductive Bias of Stacking Towards Improving Reasoning
B$\oplus$LD: Boolean Logic Deep Learning
Simulation-Free Training of Neural ODEs on Paired Data
Multi-Agent Coordination via Multi-Level Communication
Adaptive Depth Networks with Skippable Sub-Paths
Alias-Free Mamba Neural Operator
Learn To be Efficient: Build Structured Sparsity in Large Language Models
DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs
Convergence Analysis of Split Federated Learning on Heterogeneous Data
Incorporating Test-Time Optimization into Training with Dual Networks for Human Mesh Recovery
Scaling White-Box Transformers for Vision
KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
AudioMarkBench: Benchmarking Robustness of Audio Watermarking
SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention
Rough Transformers: Lightweight Continuous-Time Sequence Modelling with Path Signatures
Learning Low-Rank Feature for Thorax Disease Classification
Discrete Dictionary-based Decomposition Layer for Structured Representation Learning
The Benefits of Balance: From Information Projections to Variance Reduction
Reproducibility Study on Adversarial Attacks Against Robust Transformer Trackers
Compositional Estimation of Lipschitz Constants for Deep Neural Networks
HYDRA-FL: Hybrid Knowledge Distillation for Robust and Accurate Federated Learning
DeSparsify: Adversarial Attack Against Token Sparsification Mechanisms
On the Scalability of Certified Adversarial Robustness with Generated Data
Strategic Littlestone Dimension: Improved Bounds on Online Strategic Classification
ProTransformer: Robustify Transformers via Plug-and-Play Paradigm
A Simple Remedy for Dataset Bias via Self-Influence: A Mislabeled Sample Perspective
Wormhole Loss for Partial Shape Matching
NeuralFuse: Learning to Recover the Accuracy of Access-Limited Neural Network Inference in Low-Voltage Regimes
PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models
FUNGI: Features From Unsupervised Gradients
How Sparse Can We Prune A Deep Network: A Fundamental Limit Perspective
Learning and Transferring Sparse Contextual Bigrams with Linear Transformers
The Prevalence of Neural Collapse in Neural Multivariate Regression
Cross-model Control: Improving Multiple Large Language Models in One-time Training
AllClear: A Comprehensive Dataset and Benchmark for Cloud Removal in Satellite Imagery
LRM-Zero: Training Large Reconstruction Models with Synthesized Data
Rethinking Deep Thinking
Sparse High Rank Adapters
Instruction Tuning With Loss Over Instructions
Image Reconstruction Via Autoencoding Sequential Deep Image Prior
Adversarial Schrödinger Bridge Matching
Transcendence: Generative Models Can Outperform The Experts That Train Them
Metric Flow Matching for Smooth Interpolations on the Data Manifold
Harmonizing Visual Text Comprehension and Generation
Are More LLM Calls All You Need? Towards the Scaling Properties of Compound AI Systems
Zero-to-Hero: Enhancing Zero-Shot Novel View Synthesis via Attention Map Filtering
Equivariant Neural Diffusion for Molecule Generation
Graph Diffusion Policy Optimization
Optimistic Verifiable Training by Controlling Hardware Nondeterminism
Interpreting the Weight Space of Customized Diffusion Models
Simple and Effective Masked Diffusion Language Models
TFG: Unified Training-Free Guidance for Diffusion Models
CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching
DreamSteerer: Enhancing Source Image Conditioned Editability using Personalized Diffusion Models
MoLE: Enhancing Human-centric Text-to-image Diffusion via Mixture of Low-rank Experts
Discrete-state Continuous-time Diffusion for Graph Generation
Training-Free Adaptive Diffusion with Bounded Difference Approximation Strategy
RedPajama: an Open Dataset for Training Large Language Models
The Convergence of Variance Exploding Diffusion Models under the Manifold Hypothesis
Immiscible Diffusion: Accelerating Diffusion Training with Noise Assignment
Permutation-Invariant Autoregressive Diffusion for Graph Generation
On the Noise Robustness of In-Context Learning for Text Generation
BERTs are Generative In-Context Learners
Generate Universal Adversarial Perturbations for Few-Shot Learning
Procedure-Aware Surgical Video-language Pretraining with Hierarchical Knowledge Augmentation
Enhancing In-Context Learning Performance with just SVD-Based Weight Pruning: A Theoretical Perspective
MixEval: Fast and Dynamic Human Preference Approximation with LLM Benchmark Mixtures
Physically Compatible 3D Object Modeling from a Single Image
Generative Forests
Multi-Head Mixture-of-Experts
TACT: Advancing Complex Aggregative Reasoning with Information Extraction Tools
BenchX: A Unified Benchmark Framework for Medical Vision-Language Pretraining on Chest X-Rays
TableRAG: Million-Token Tabular Reasoning with Large Language Models
Iterative Reasoning Preference Optimization
Recursive Introspection: Teaching Foundation Model Agents How to Self-Improve
Chain of Agents: Large Language Models Collaborating on Long-Context Tasks
Solving Intricate Problems with Human-like Decomposition and Rethinking
Learning Better Representations From Less Data For Propositional Satisfiability
Unlocking the Boundaries of Thought: A Reasoning Granularity Framework to Quantify and Optimize Chain-of-Thought
Cluster-wise Graph Transformer with Dual-granularity Kernelized Attention
Towards Dynamic Message Passing on Graphs
Energy-based Epistemic Uncertainty for Graph Neural Networks
WenMind: A Comprehensive Benchmark for Evaluating Large Language Models in Chinese Classical Literature and Language Arts
What Is Missing For Graph Homophily? Disentangling Graph Homophily For Graph Neural Networks
Deep Equilibrium Algorithmic Reasoning
Boosting Graph Pooling with Persistent Homology
Pure Message Passing Can Estimate Common Neighbor for Link Prediction
HC-GAE: The Hierarchical Cluster-based Graph Auto-Encoder for Graph Representation Learning
Deep Graph Mating
Near-Optimal Approximation of Matrix Functions by the Lanczos Method
Intruding with Words: Towards Understanding Graph Injection Attacks at the Text Level
GRANOLA: Adaptive Normalization for Graph Neural Networks
Supra-Laplacian Encoding for Transformer on Dynamic Graphs
Fine-grained Image-to-LiDAR Contrastive Distillation with Visual Foundation Models
VideoGUI: A Benchmark for GUI Automation from Instructional Videos
Confidence Regulation Neurons in Language Models
Provable Guarantees for Model Performance via Mechanistic Intepretability
CoSy: Evaluating Textual Explanations of Neurons
B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable
Causal Dependence Plots
FFAM: Feature Factorization Activation Map for Explanation of 3D Detectors
Interpretable Machine Learning for Datasets with Missing Values
Analysing the Generalisation and Reliability of Steering Vectors
Learning diverse causally emergent representations from time series data
ChronoEpilogi: Scalable Time Series Selection with Multiple Solutions
LLM Evaluators Recognize and Favor Their Own Generations
Guiding Neural Collapse: Optimising Towards the Nearest Simplex Equiangular Tight Frame
HLM-Cite: Hybrid Language Model Workflow for Text-based Scientific Citation Prediction
PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression
How do Large Language Models Handle Multilingualism?
The Factorization Curse: Which Tokens You Predict Underlie the Reversal Curse and More
IQA-EVAL: Automatic Evaluation of Human-Model Interactive Question Answering
WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipedia
Spectral Editing of Activations for Large Language Model Alignment
Unchosen Experts Can Contribute Too: Unleashing MoE Models’ Power by Self-Contrast
Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformers
Personalized Federated Learning with Mixture of Models for Adaptive Prediction and Model Fine-Tuning
Superposed Decoding: Multiple Generations from a Single Autoregressive Inference Pass
Discovering Preference Optimization Algorithms with and for Large Language Models
CorDA: Context-Oriented Decomposition Adaptation of Large Language Models
Knowledge Graph Completion by Intermediate Variables Regularization
HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models
Agent Planning with World Knowledge Model
SLIM: Style-Linguistics Mismatch Model for Generalized Audio Deepfake Detection
An Autoencoder-Like Nonnegative Matrix Co-Factorization for Improved Student Cognitive Modeling
AGILE: A Novel Framework of LLM Agent
Reciprocal Learning
MmCows: A Multimodal Dataset for Dairy Cattle Monitoring
Target-Guided Adversarial Point Cloud Transformer Towards Recognition Against Real-world Corruptions
Implicit Regularization Paths of Weighted Neural Representations
V-PETL Bench: A Unified Visual Parameter-Efficient Transfer Learning Benchmark
A benchmark for prediction of transcriptomic responses to chemical perturbations across cell types
Meta-Learning Universal Priors Using Non-Injective Change of Variables
Knowledge Composition using Task Vectors with Learned Anisotropic Scaling
TPR: Topology-Preserving Reservoirs for Generalized Zero-Shot Learning
Unsupervised Anomaly Detection Algorithms on Real-world Data: How Many Do We Need?
MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection
Protected Test-Time Domain Adaptation via Online Entropy Matching
OwMatch: Conditional Self-Labeling with Consistency for Open-world Semi-Supervised Learning
MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens
WildVision: Evaluating Vision-Language Models in the Wild with Human Preferences
Test-Time Dynamic Image Fusion
Hierarchical Visual Feature Aggregation for OCR-Free Document Understanding
Exogenous Matching: Learning Good Proposals for Tractable Counterfactual Estimation
Unveiling Encoder-Free Vision-Language Models
Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning
MoME: Mixture of Multimodal Experts for Generalist Multimodal Large Language Models
Advancing Cross-domain Discriminability in Continual Learning of Vison-Language Models
Molecule Design by Latent Prompt Transformer
Are We on the Right Way for Evaluating Large Vision-Language Models?
Towards Unified Multimodal Editing with Enhanced Knowledge Collaboration
FRIEREN: Efficient Video-to-Audio Generation with Rectified Flow Matching
Unveiling the Tapestry of Consistency in Large Vision-Language Models
LOVA3: Learning to Visual Question Answering, Asking and Assessment
Linking In-context Learning in Transformers to Human Episodic Memory
Text-DiFuse: An Interactive Multi-Modal Image Fusion Framework based on Text-modulated Diffusion Model
$\textit{NeuroPath}$: A Neural Pathway Transformer for Joining the Dots of Human Connectomes
Cascade of phase transitions in the training of energy-based models
Spike-based Neuromorphic Model for Sound Source Localization
The Bayesian sampling in a canonical recurrent circuit with a diversity of inhibitory interneurons
Encrypted Data Pruning for Confidential Training of Deep Neural Networks
Back to the Continuous Attractors
Medformer: A Multi-Granularity Patching Transformer for Medical Time-Series Classification
Crafting Interpretable Embeddings by Asking LLMs Questions
Towards a "Universal Translator" for Neural Dynamics at Single-Cell, Single-Spike Resolution
RTify: Aligning Deep Neural Networks with Human Behavioral Decisions
Learning Macroscopic Dynamics from Partial Microscopic Observations
Universal Physics Transformers: A Framework For Efficiently Scaling Neural Operators
Newswire: A Large-Scale Structured Database of a Century of Historical News
PACE: Pacing Operator Learning to Accurate Optical Field Simulation for Complicated Photonic Devices
Probablistic Emulation of a Global Climate Model with Spherical DYffusion
Precipitation Downscaling with Spatiotemporal Video Diffusion
Lorentz-Equivariant Geometric Algebra Transformers for High-Energy Physics
Space-Time Continuous PDE Forecasting using Equivariant Neural Fields
Abductive Reasoning in Logical Credal Networks
CLAVE: An Adaptive Framework for Evaluating Values of LLM Generated Responses
Annealed Multiple Choice Learning: Overcoming limitations of Winner-takes-all with annealing
Interaction-Force Transport Gradient Flows
FasMe: Fast and Sample-efficient Meta Estimator for Precision Matrix Learning in Small Sample Settings
TuneTables: Context Optimization for Scalable Prior-Data Fitted Networks
BLoB: Bayesian Low-Rank Adaptation by Backpropagation for Large Language Models
Principled Bayesian Optimization in Collaboration with Human Experts
Computation-Aware Gaussian Processes: Model Selection And Linear-Time Inference
Fast Channel Simulation via Error-Correcting Codes
Structural Inference of Dynamical Systems with Conjoined State Space Models
Dual-Diffusion for Binocular 3D Human Pose Estimation
A Neural Network Approach for Efficiently Answering Most Probable Explanation Queries in Probabilistic Models
VISA: Variational Inference with Sequential Sample-Average Approximations
Sharing Key Semantics in Transformer Makes Efficient Image Restoration
Entrywise error bounds for low-rank approximations of kernel matrices
Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions
SurgicAI: A Fine-grained Platform for Data Collection and Benchmarking in Surgical Policy Learning
RadarOcc: Robust 3D Occupancy Prediction with 4D Imaging Radar
RoboMamba: Multimodal State Space Model for Efficient Robot Reasoning and Manipulation
MO-DDN: A Coarse-to-Fine Attribute-based Exploration Agent for Multi-Object Demand-driven Navigation
Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformers
HumanVLA: Towards Vision-Language Directed Object Rearrangement by Physical Humanoid
Prediction with Action: Visual Policy Learning via Joint Denoising Process
Biomedical Visual Instruction Tuning with Clinician Preference Alignment
BAKU: An Efficient Transformer for Multi-Task Policy Learning
Vision-Language Navigation with Energy-Based Policy
Apathetic or Empathetic? Evaluating LLMs' Emotional Alignments with Humans
Causal Deciphering and Inpainting in Spatio-Temporal Dynamics via Diffusion Model
Ada-MSHyper: Adaptive Multi-Scale Hypergraph Transformer for Time Series Forecasting
Introducing Spectral Attention for Long-Range Dependency in Time Series Forecasting
Task-oriented Time Series Imputation Evaluation via Generalized Representers
UNITS: A Unified Multi-Task Time Series Model
The Art of Saying No: Contextual Noncompliance in Language Models
DeNetDM: Debiasing by Network Depth Modulation
A Swiss Army Knife for Heterogeneous Federated Learning: Flexible Coupling via Trace Norm
Linear Causal Representation Learning from Unknown Multi-node Interventions
Achieving Tractable Minimax Optimal Regret in Average Reward MDPs
Goal Conditioned Reinforcement Learning for Photo Finishing Tuning
Real-Time Selection Under General Constraints via Predictive Inference
Large Language Model Unlearning
ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users
Neural Experts: Mixture of Experts for Implicit Neural Representations
Noisy Label Learning with Instance-Dependent Outliers: Identifiability via Crowd Wisdom
BiScope: AI-generated Text Detection by Checking Memorization of Preceding Tokens
Arboretum: A Large Multimodal Dataset Enabling AI for Biodiversity
Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
Learning Scene-specific Descriptions via Adaptive Renormalization for Open-vocabulary Scene Graph Generation
Are Uncertainty Quantification Capabilities of Evidential Deep Learning a Mirage?
Rethinking Misalignment in Vision-Language Model Adaptation from a Causal Perspective
Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning
Exploring Adversarial Robustness of Deep State Space Models
Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
Dispelling the Mirage of Progress in Offline MARL through Standardised Baselines and Evaluation
DAT: Improving Adversarial Robustness via Generative Amplitude Mix-up in Frequency Domain
What If the Input is Expanded in OOD Detection?
Enhancing Multiple Dimensions of Trustworthiness in LLMs via Sparse Activation Control
Fast yet Safe: Early-Exiting with Risk Control
Nonlocal Attention Operator: Materializing Hidden Knowledge Towards Interpretable Physics Discovery
Towards Evaluation of Adversarial Robustness and Privacy on Label Mapping Visual Prompting Models
Trajectory Volatility for Out-of-Distribution Detection in Mathematical Reasoning
USCILab3D: A Large-scale, Long-term, Semantically Annotated Outdoor Dataset
Post-Robustness of Backdoor Purification
SRFUND: A Multi-Granularity Hierarchical Structure Reconstruction Benchmark in Form Understanding
Protecting Your LLMs with Information Bottleneck
Self-Calibrated Tuning of Vision-Language Models for Out-of-Distribution Detection
FedGMark: Certifiably Robust Watermarking for Federated Graph Learning
Aligning Large Language Models with Representation Editing: A Control Perspective
More PAC-Bayes bounds: From bounded losses, to losses with general tail behaviors, to anytime validity
LibMOON: A Gradient-based MultiObjective OptimizatioN Library in PyTorch
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
MemoryFormer : Minimize Transformer Computation by Removing Fully-Connected Layers
Not All Tokens Are What You Need for Pretraining
T2V-Turbo: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward Feedback
Efficient Adversarial Training in LLMs with Continuous Attacks
Make Continual Learning Stronger via C-Flat
Learning in Markov Games with Adaptive Adversaries: Policy Regret, Fundamental Barriers, and Efficient Algorithms
Data-Efficient Operator Learning via Unsupervised Pretraining and In-Context Learning
VideoLLM-MoD: Efficient Video-Language Streaming with Mixture-of-Depths Vision Computation
Alleviating Hallucinations in Large Vision-Language Models through Hallucination-Induced Optimization
Universal Rates for Active Learning
Generalized Protein Pocket Generation with Prior-Informed Flow Matching
Why Transformers Need Adam: A Hessian Perspective
BAN: Detecting Backdoors Activated by Neuron Noise
Relation-Driven Diffusion for Human-Object Interaction Detection
Identify Then Recommend: Towards Unsupervised Group Recommendation
Synthesize, Partition, then Adapt: Eliciting Diverse Samples from Foundation Models
Communication-Efficient Federated Group Distributionally Robust Optimization
Complete Graphical Criterion for Sequential Covariate Adjustment in Causal Inference
Efficiently Learning Significant Fourier Feature Pairs for Statistical Independence Testing
Smoke and Mirrors in Causal Downstream Tasks
Covariate Shift Corrected Conditional Randomization Test
Qualitative Mechanism Independence
Causal Contrastive Learning for Counterfactual Regression Over Time
Instruction Embedding: Latent Representations of Instructions Towards Task Identification
Learning Discrete Concepts in Latent Hierarchical Models
Is the MMI Criterion Necessary for Explanation? Degenerating Non-causal Features to Plain Noise
End-To-End Causal Effect Estimation from Unstructured Text Data
Identifying General Mechanism Shifts in Linear Causal Representations
Unveiling the Potential of Robustness in Selecting Conditional Average Treatment Effect Estimators
From Causal to Concept-Based Representation Learning
Disentangled Representation Learning in Non-Markovian Causal Systems
Conditional Generative Models are Sufficient to Sample from Any Causal Effect Estimand
The Well: a Large-Scale Collection of Diverse Physics Simulations for Machine Learning
The Scandinavian Embedding Benchmarks: Comprehensive Assessment of Multilingual and Monolingual Text Embedding
Benchmarking Estimators for Natural Experiments: A Novel Dataset and a Doubly Robust Algorithm
Constrained Human-AI Cooperation: An Inclusive Embodied Social Intelligence Challenge
OpenDebateEvidence: A Massive-Scale Argument Mining and Summarization Dataset
ReXTime: A Benchmark Suite for Reasoning-Across-Time in Videos
SciCode: A Research Coding Benchmark Curated by Scientists
Sim2Real-Fire: A Multi-modal Simulation Dataset for Forecast and Backtracking of Real-world Forest Fire
Infer Induced Sentiment of Comment Response to Video: A New Task, Dataset and Baseline
Muscles in Time: Learning to Understand Human Motion In-Depth by Simulating Muscle Activations
Few-shot Algorithms for Consistent Neural Decoding (FALCON) Benchmark
OAM-TCD: A globally diverse dataset of high-resolution tree cover maps
Off to new Shores: A Dataset & Benchmark for (near-)coastal Flood Inundation Forecasting
$\texttt{pfl-research}$: simulation framework for accelerating research in Private Federated Learning
Evidential Mixture Machines: Deciphering Multi-Label Correlations for Active Learning Sensitivity
AMBROSIA: A Benchmark for Parsing Ambiguous Questions into Database Queries
When LLMs Meet Cunning Texts: A Fallacy Understanding Benchmark for Large Language Models
AFBench: A Large-scale Benchmark for Airfoil Design
DACO: Towards Application-Driven and Comprehensive Data Analysis via Code Generation
SM3-Text-to-Query: Synthetic Multi-Model Medical Text-to-Query Benchmark
Archaeoscape: Bringing Aerial Laser Scanning Archaeology to the Deep Learning Era
Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?
Implicit Zoo: A Large-Scale Dataset of Neural Implicit Functions for 2D Images and 3D Scenes
TaskBench: Benchmarking Large Language Models for Task Automation
μBench: A Microscopy Benchmark for Vision-Language Understanding
ViLCo-Bench: VIdeo Language COntinual learning Benchmark
APEBench: A Benchmark for Autoregressive Neural Emulators of PDEs
OpenCDA-Loop: A Closed-loop Benchmarking Platform for End-to-end Evaluation of Cooperative Perception
MARPLE: A Benchmark for Long-Horizon Inference
Mercury: A Code Efficiency Benchmark for Code Large Language Models
Multivariate Stochastic Dominance via Optimal Transport and Applications to Models Benchmarking
Cracking the Code of Juxtaposition: Can AI Models Understand the Humorous Contradictions
Reproducibility Study: Equal Improvability: A New Fairness Notion Considering the Long-Term Impact
Reproducibility Study of "ITI-GEN: Inclusive Text-to-Image Generation"
Multi-Group Proportional Representation
Fair GLASSO: Estimating Fair Graphical Models with Unbiased Statistical Behavior
Interpolating Item and User Fairness in Multi-Sided Recommendations
GaussianMarker: Uncertainty-Aware Copyright Protection of 3D Gaussian Splatting
Tight Bounds for Learning RUMs from Small Slates
Topological Generalization Bounds for Discrete-Time Stochastic Optimization Algorithms
Fast Rates for Bandit PAC Multiclass Classification
Error Analysis of Spherically Constrained Least Squares Reformulation in Solving the Stackelberg Prediction Game
Dimension-free deterministic equivalents for random feature regression
Tolerant Algorithms for Learning with Arbitrary Covariate Shift
Cardinality-Aware Set Prediction and Top-$k$ Classification
Analytic Nonlinear Dynamical System Identification with Non-asymptotic Guarantees
Optimal Algorithms for Augmented Testing of Discrete Distributions
Sample-Efficient Agnostic Boosting
Adversarially Robust Multi-task Representation Learning
Task-recency bias strikes back: Adapting covariances in Exemplar-Free Class Incremental Learning
Gradient Methods for Online DR-Submodular Maximization with Stochastic Long Term Constraints
Optimal Algorithms for Online Convex Optimization with Adversarial Constraints
Optimal Top-Two Method for Best Arm Identification and Fluid Analysis
Regret Minimization in Stackelberg Games with Side Information
Fast Iterative Hard Thresholding Methods with Pruning Gradient Computations
Generalizing Weather Forecast to Fine-grained Temporal Scales via Physics-AI Hybrid Modeling
Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Models
Mirror and Preconditioned Gradient Descent in Wasserstein Space
Weight decay induces low-rank attention layers
Penalty-based Methods for Simple Bilevel Optimization under Hölderian Error Bounds
Unveiling LoRA Intrinsic Ranks via Salience Analysis
Mean-Field Langevin Dynamics for Signed Measures via a Bilevel Approach
Functional Bilevel Optimization for Machine Learning
Approximately Pareto-optimal Solutions for Bi-Objective k-Clustering
HardCore Generation: Generating Hard UNSAT Problems for Data Augmentation
Sketching for Distributed Deep Learning: A Sharper Analysis
Randomized Minor-Value Rectification: A Novel Matrix Sparsification Algorithm for Solving Constrained Optimizations in Cancer Radiation Therapy
Implicit Regularization of Decentralized Gradient Descent for Sparse Regression
Shadowheart SGD: Distributed Asynchronous SGD with Optimal Time Complexity Under Arbitrary Computation and Communication Heterogeneity
Resource-Aware Federated Self-Supervised Learning with Global Class Representations
Dual Lagrangian Learning for Conic Optimization
FERERO: A Flexible Framework for Preference-Guided Multi-Objective Learning
Provable Acceleration of Nesterov's Accelerated Gradient for Asymmetric Matrix Factorization and Linear Neural Networks
On Convergence of Adam for Stochastic Optimization under Relaxed Assumptions
Decentralized Noncooperative Games with Coupled Decision-Dependent Distributions
Random Function Descent
Improved Regret of Linear Ensemble Sampling
This Too Shall Pass: Removing Stale Observations in Dynamic Bayesian Optimization
A Synthetic Dataset for Personal Attribute Inference
PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action
Statistical Estimation in the Spiked Tensor Model via the Quantum Approximate Optimization Algorithm
Higher-Rank Irreducible Cartesian Tensors for Equivariant Message Passing
Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning
Noise-Aware Differentially Private Regression via Meta-Learning
On provable privacy vulnerabilities of graph representations
Continual Counting with Gradual Privacy Expiration
Efficient and Private Marginal Reconstruction with Local Non-Negativity
How to Solve Contextual Goal-Oriented Problems with Offline Datasets?
Deterministic Uncertainty Propagation for Improved Model-Based Offline Reinforcement Learning
Offline Reinforcement Learning with OOD State Correction and OOD Action Suppression
Explaining RL Decisions with Trajectories': A Reproducibility Study
Efficient Multi-task Reinforcement Learning with Cross-Task Policy Guidance
Reinforcement Learning Gradients as Vitamin for Online Finetuning Decision Transformers
Diffusion Imitation from Observation
Spectral-Risk Safe Reinforcement Learning with Convergence Guarantees
Bayesian Optimisation with Unknown Hyperparameters: Regret Bounds Logarithmically Closer to Optimal
Reinforcing Language Agents via Policy Optimization with Action Decomposition
Pick up the PACE: A Parameter-Free Optimizer for Lifelong Reinforcement Learning
Subwords as Skills: Tokenization for Sparse-Reward Reinforcement Learning
Can Learned Optimization Make Reinforcement Learning Less Difficult?
Discovering Creative Behaviours through DUPLEX: Diverse Universal Features for Policy Exploration
Learning from Noisy Labels via Conditional Distributionally Robust Optimization
Optimizing Automatic Differentiation with Deep Reinforcement Learning
QGFN: Controllable Greediness with Action Values
Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow
Recurrent Reinforcement Learning with Memoroids
Learning Multimodal Behaviors from Scratch with Diffusion Policy Gradient
Stochastic contextual bandits with graph feedback: from independence number to MAS number
Achieving Constant Regret in Linear Markov Decision Processes
Learning to Assist Humans without Inferring Rewards
ICAL: Continual Learning of Multimodal Agents by Transforming Trajectories into Actionable Insights
RegExplainer: Generating Explanations for Graph Neural Networks in Regression Tasks
Focus On What Matters: Separated Models For Visual-Based RL Generalization
AutoManual: Generating Instruction Manuals by LLM Agents via Interactive Environmental Learning
Predicting Future Actions of Reinforcement Learning Agents
Thought of Search: Planning with Language Models Through The Lens of Efficiency
NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking
Using Unity to Help Solve Reinforcement Learning
DynaMITE-RL: A Dynamic Model for Improved Temporal Meta-Reinforcement Learning
Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs
Constructing Semantics-Aware Adversarial Examples with Probabilistic Perspective
Towards Understanding How Transformers Learn In-context Through a Representation Learning Lens
Self-Consuming Generative Models with Curated Data Provably Optimize Human Preferences
Knowledgeable Agents by Offline Reinforcement Learning from Large Language Model Rollouts
Online Weighted Paging with Unknown Weights
Beyond task diversity: provable representation transfer for sequential multitask linear bandits
Extensive-Form Game Solving via Blackwell Approachability on Treeplexes
ReGS: Reference-based Controllable Scene Stylization with Gaussian Splatting
Intrinsic Robustness of Prophet Inequality to Strategic Reward Signaling
Honor Among Bandits: No-Regret Learning for Online Fair Division
Efficient $\Phi$-Regret Minimization with Low-Degree Swap Deviations in Extensive-Form Games
Accelerating Nash Equilibrium Convergence in Monte Carlo Settings Through Counterfactual Value Based Fictitious Play
Diffusion Models are Certifiably Robust Classifiers
Accelerating Relative Entropy Coding with Space Partitioning
Warm-up Free Policy Optimization: Improved Regret in Linear Markov Decision Processes
Beating Adversarial Low-Rank MDPs with Unknown Transition and Bandit Feedback
Periodic agent-state based Q-learning for POMDPs
Risk-sensitive control as inference with Rényi divergence
Reinforcement Learning with LTL and $\omega$-Regular Objectives via Optimality-Preserving Translation to Average Rewards
On the Curses of Future and History in Future-dependent Value Functions for Off-policy Evaluation
NaRCan: Natural Refined Canonical Image with Integration of Diffusion Prior for Video Editing
Statistical Inference for Fairness Auditing
A Unified Confidence Sequence for Generalized Linear Models, with Applications to Bandits
Community Detection Guarantees using Embeddings Learned by Node2Vec
Beyond Assouad, Fano, and Le Cam: Toward Unified Lower Bounds for Statistical Estimation and Interactive Decision Making
Navigable Graphs for High-Dimensional Nearest Neighbor Search: Constructions and Limits
Aligning Model Properties via Conformal Risk Control
Bias in Motion: Theoretical Insights into the Dynamics of Bias in SGD Training
DISP-LLM: Dimension-Independent Structural Pruning for Large Language Models
ODRL: A Benchmark for Off-Dynamics Reinforcement Learning
Can Models Learn Skill Composition from Examples?
User-item fairness tradeoffs in recommendations
Theoretical Foundations of Deep Selective State-Space Models
Error Correction Output Codes for Robust Neural Networks against Weight-errors: A Neural Tangent Kernel Point of View
RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Models
Ensemble Learning for Heterogeneous Large Language Models with Deep Parallel Collaboration
Scaling transformer neural networks for skillful and reliable medium-range weather forecasting
Multi-Agent Domain Calibration with a Handful of Offline Data
3D Structure Prediction of Atomic Systems with Flow-based Direct Preference Optimization
FACT or Fiction: Can Truthful Mechanisms Eliminate Federated Free Riding?
Cross-Modality Perturbation Synergy Attack for Person Re-identification
You Only Look Around: Learning Illumination-Invariant Feature for Low-light Object Detection
AvaTaR: Optimizing LLM Agents for Tool-Assisted Knowledge Retrieval
Data Augmentation with Diffusion for Open-Set Semi-Supervised Learning
Energy-Based Modelling for Discrete and Mixed Data via Heat Equations on Structured Spaces
Improved Sample Complexity Bounds for Diffusion Model Training
Diffusion-Inspired Truncated Sampler for Text-Video Retrieval
Targeted Sequential Indirect Experiment Design
Single Image Unlearning: Efficient Machine Unlearning in Multimodal Large Language Models
MemVLT: Vision-Language Tracking with Adaptive Memory-based Prompts
Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attribution
ChatQA: Surpassing GPT-4 on Conversational QA and RAG
Causal language modeling can elicit search and reasoning capabilities on sudoku puzzles
Time-Reversal Provides Unsupervised Feedback to LLMs
Cost-efficient Knowledge-based Question Answering with Large Language Models
DDK: Distilling Domain Knowledge for Efficient Large Language Models
Fine Tuning Out-of-Vocabulary Item Recommendation with User Sequence Imagination
Bandits with Abstention under Expert Advice
Double-Ended Synthesis Planning with Goal-Constrained Bidirectional Search
Gaussian-Informed Continuum for Physical Property Identification and Simulation
MACM: Utilizing a Multi-Agent System for Condition Mining in Solving Complex Mathematical Problems
Long-Tailed Out-of-Distribution Detection via Normalized Outlier Distribution Adaptation
The Value of Reward Lookahead in Reinforcement Learning
A Closer Look at the CLS Token for Cross-Domain Few-Shot Learning
Rethinking Transformer for Long Contextual Histopathology Whole Slide Image Analysis
Lyapunov functions: a long-standing open problem in mathematics, with symbolic transformers
Understanding the expressivity and trainability of Fourier Neural Operator
Confidence Calibration of Classifiers with Many Classes
Addressing Asynchronicity in Clinical Multimodal Fusion via Individualized Chest X-ray Generation
Practical Guide for Designing Cell-Type-Specific Promoter Sequences Using Conservative Model-Based Optimization
Antigen-Specific Antibody Design via Direct Energy-based Preference Optimization
Ordered Momentum for Asynchronous SGD
Ultrafast classical phylogenetic method beats large protein language models on variant effect prediction
Generating Highly Designable Proteins with Geometric Algebra Flow Matching
Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba
Large Pre-trained time series models for cross-domain Time series analysis tasks
PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly Detection
Toward Reliable, Reproducible, and Practical Human Evaluation Protocol for Text-to-Video Models
HOPE: Shape Matching Via Aligning Different K-hop Neighbourhoods
Toward Semantic Gaze Target Detection
Progressive Cross-Scale Self-Supervised Blind Image Deconvolution via Implicit Neural Representation
LuSh-NeRF: Lighting up and Sharpening NeRFs for Low-light Scenes
Trade-Offs of Diagonal Fisher Information Matrix Estimators
Tensor-Based Synchronization and the Low-Rankness of the Block Trifocal Tensor
SimGen: Simulator-conditioned Driving Scene Generation
PointMamba: A Simple State Space Model for Point Cloud Analysis
Learning 1D Causal Visual Representation with De-focus Attention Networks
DenoiseReID: Denoising Model for Representation Learning of Person Re-Identification
Virtual Scanning: Unsupervised Non-line-of-sight Imaging from Irregularly Undersampled Transients
Depth Anywhere: Enhancing 360 Monocular Depth Estimation via Perspective Distillation and Unlabeled Data Augmentation
Training-Free Open-Ended Object Detection and Segmentation via Attention as Prompts
Norms for Managing Datasets: A Systematic Review of NeurIPS Datasets
Reconstructing the Image Stitching Pipeline: Integrating Fusion and Rectangling into a Unified Inpainting Model
Vivid-ZOO: Multi-View Video Generation with Diffusion Model
Fast Encoder-Based 3D from Casual Videos via Point Track Processing
Towards Unsupervised Model Selection for Domain Adaptive Object Detection
Crafting Hierarchical Strand-based Hair Geometry with Frequency-decomposed Representative Guide Curves
MV2Cyl: Reconstructing 3D Extrusion Cylinders from Multi-View Images
3D Equivariant Pose Regression via Direct Wigner-D Harmonics Prediction
CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition
OctreeOcc: Efficient and Multi-Granularity Occupancy Prediction Using Octree Queries
One-to-Normal: Anomaly Personalization for Few-shot Anomaly Detection
YOLOv10: Real-Time End-to-End Object Detection
Template-free Articulated Gaussian Splatting for Real-time Reposable Dynamic View Synthesis
RCDN: Towards Robust Camera-Insensitivity Collaborative Perception via Dynamic Feature-based 3D Neural Modeling
SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflection
Expanding Sparse Tuning for Low Memory Usage
Samba: Severity-aware Recurrent Modeling for Cross-domain Medical Image Grading
Optimization Efficient Open-World Visual Region Recognition
Multimodal Large Language Models Make Text-to-Image Generative Models Align Better
Advancing Fine-Grained Classification by Structure and Subject Preserving Augmentation
TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Control
SegVol: Universal and Interactive Volumetric Medical Image Segmentation
Replay-and-Forget-Free Graph Class-Incremental Learning: A Task Profiling and Prompting Approach
TARSS-Net: Temporal-Aware Radar Semantic Segmentation Network
Unsupervised Hierarchy-Agnostic Segmentation: Parsing Semantic Image Structure
Generated and Pseudo Content guided Prototype Refinement for Few-shot Point Cloud Segmentation
Bridge the Points: Graph-based Few-shot Segment Anything Semantically
Binocular-Guided 3D Gaussian Splatting with View Consistency for Sparse View Synthesis
Memory-Efficient LLM Training with Online Subspace Descent
Alleviating Attention Bias for Visual-Informed Text Generation
ChronoMagic: A Benchmark for Metamorphic Evaluation of Time-lapse Text-to-Video Generation
CAT3D: Create Anything in 3D with Multi-View Diffusion Models
SlowFocus: Enhancing Fine-grained Temporal Understanding in Video LLM
Depth Anything V2
ST$_k$: A Scalable Module for Solving Top-k problems
The Unmet Promise of Synthetic Training Images: Using Retrieved Real Images Performs Better
PURE: Prompt Evolution with Graph ODE for Out-of-distribution Fluid Dynamics Modeling
ImageNet++: A Large-Scale Benchmark of Data Curation Strategies
On scalable oversight with weak LLMs judging strong LLMs
No-Regret M${}^{\natural}$-Concave Function Maximization: Stochastic Bandit Algorithms and NP-Hardness of Adversarial Full-Information Setting
Are Large-scale Soft Labels Necessary for Large-scale Dataset Distillation?
SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain
Inverse M-Kernels for Linear Universal Approximators of Non-Negative Functions
Data Mixture Inference Attack: BPE Tokenizers Reveal Training Data Compositions
Fetch and Forge: Efficient Dataset Condensation for Object Detection
Group and Shuffle: Efficient Structured Orthogonal Parametrization
Initializing Variable-sized Vision Transformers from Learngene with Learnable Transformations
Bridging The Gap between Low-rank and Orthogonal Adaptation via Householder Reflection Adaptation
A Single-Step, Sharpness-Aware Minimization is All You Need to Achieve Efficient and Accurate Sparse Training
Generalizing Consistency Policy to Visual RL with Prioritized Proximal Experience Regularization
DEPrune: Depth-wise Separable Convolution Pruning for Maximizing GPU Parallelism
Open-Book Neural Algorithmic Reasoning
MUVERA: Multi-Vector Retrieval via Fixed Dimensional Encoding
CoMERA: Computing- and Memory-Efficient Training via Rank-Adaptive Tensor Optimization
Implicit Regularization of Sharpness-Aware Minimization for Scale-Invariant Problems
Learning to Reason Iteratively and Parallelly for Complex Visual Reasoning Scenarios
Transformers need glasses! Information over-squashing in language tasks
A Comprehensive Investigation of Sparse Rate Reduction in Transformer-like Models
Robot Policy Learning with Temporal Optiaml Transport Reward
Selective Attention: Enhancing Transformer through Principled Context Control
On the Role of Attention Masks and LayerNorm in Transformers
APDDv2: Aesthetics of Paintings and Drawings Dataset with Artist Labeled Scores and Comments
Hierarchical and Density-based Causal Clustering
Vector Quantization Prompting for Continual Learning
GUIDE: Real-Time Human-Shaped Agents
Addressing Hidden Confounding with Heterogeneous Observational Datasets for Recommendation
ProxyFusion: Face Feature Aggregation Through Sparse Experts
Pre-trained Text-to-Image Diffusion Models Are Versatile Representation Learners for Control
Repurposing Language Models into Embedding Models: Finding the Compute-Optimal Recipe
Speaking Your Language: Spatial Relationships in Interpretable Emergent Communication
A StrongREJECT for Empty Jailbreaks
Ask, Attend, Attack: A Effective Decision-Based Black-Box Targeted Attack for Image-to-Text Models
Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space
Full-Distance Evasion of Pedestrian Detectors in the Physical World
Curriculum Fine-tuning of Vision Foundation Model for Medical Image Classification Under Label Noise
Preventing Dimensional Collapse in Self-Supervised Learning via Orthogonality Regularization
PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders
Approximation Rate of the Transformer Architecture for Sequence Modeling
The Expressive Capacity of State Space Models: A Formal Language Perspective
Mixture of Tokens: Continuous MoE through Cross-Example Aggregation
FM-Delta: Lossless Compression for Storing Massive Fine-tuned Foundation Models
SHED: Shapley-Based Automated Dataset Refinement for Instruction Fine-Tuning
MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization
QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
Any2Graph: Deep End-To-End Supervised Graph Prediction With An Optimal Transport Loss
CIFD: Controlled Information Flow to Enhance Knowledge Distillation
Stylus: Automatic Adapter Selection for Diffusion Models
Open LLMs are Necessary for Private Adaptations and Outperform their Closed Alternatives
Non-asymptotic Approximation Error Bounds of Parameterized Quantum Circuits
Exploring & Improving Multi-token Prediction (Block Draft) in Language Modeling
Nearest Neighbor Speculative Decoding for LLM Generation and Attribution
The GAN is dead; long live the GAN! A Modern GAN Baseline
Dual Encoder GAN Inversion for High-Fidelity 3D Head Reconstruction from Single Images
Evaluating the World Model Implicit in a Generative Model
Light Unbalanced Optimal Transport
Hallo3D: Multi-Modal Hallucination Detection and Mitigation for Consistent 3D Content Generation
Mesa-Extrapolation: A Weave Position Encoding Method for Enhanced Extrapolation in LLMs
CLIPAway: Harmonizing focused embeddings for removing objects via diffusion models
Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features
Few-Shot Diffusion Models Escape the Curse of Dimensionality
Generating compositional scenes via Text-to-image RGBA Instance Generation
ID-to-3D: Expressive ID-guided 3D Heads via Score Distillation Sampling
DomainGallery: Few-shot Domain-driven Image Generation by Attribute-centric Finetuning
Guiding a Diffusion Model with a Bad Version of Itself
BELM: Bidirectional Explicit Linear Multi-step Sampler for Exact Inversion in Diffusion Models
Constrained Diffusion with Trust Sampling
Exploring DCN-like architecture for fast image generation with arbitrary resolution
L-TTA: Lightweight Test-Time Adaptation Using a Versatile Stem Layer
Conditional Synthesis of 3D Molecules with Time Correction Sampler
On conditional diffusion models for PDE simulations
Identifying and Solving Conditional Image Leakage in Image-to-Video Generation
PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator
Out-of-Distribution Detection with a Single Unconditional Diffusion Model
Real-world Image Dehazing with Coherence-based Pseudo Labeling and Cooperative Unfolding Network
Motif-oriented influence maximization for viral marketing in large-scale social networks
Automatic Outlier Rectification via Optimal Transport
Stabilized Proximal Point Methods for Federated Optimization
FineCLIP: Self-distilled Region-based CLIP for Better Fine-Grained Understanding
BonBon Alignment for Large Language Models: on the Sweetness of Best-of-n Sampling
Synthetic Programming Elicitation and Repair for Text-to-Code in Very Low-Resource Programming Languages
HYDRA: Model Factorization Framework for Black-Box LLM Personalization
Discovering Sparsity Allocation for Layer-wise Pruning of Large Language Models
OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset
A Hitchhikers Guide to Fine-Grained Face Forgery Detection Using Common Sense Reasoning
Diffusion-based Layer-wise Semantic Reconstruction for Unsupervised Out-of-Distribution Detection
Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?
DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph
Temporally Consistent Atmospheric Turbulence Mitigation with Neural Representations
GLBench: A Comprehensive Benchmark for Graph with Large Language Models
Differentiable Task Graph Learning: Procedural Activity Representation and Online Mistake Detection from Egocentric Videos
Revisiting, Benchmarking and Understanding Unsupervised Graph Domain Adaptation
Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification
Temporal Graph Neural Tangent Kernel with Graphon-Guaranteed
Faster Local Solvers for Graph Diffusion Equations
Using Time-Aware Graph Neural Networks to Predict Temporal Centralities in Dynamic Graphs
Lambda: Learning Matchable Prior For Entity Alignment with Unlabeled Dangling Cases
Are High-Degree Representations Really Unnecessary in Equivariant Graph Neural Networks?
Enhancing Graph Transformers with Hierarchical Distance Structural Encoding
FOOGD: Federated Collaboration for Both Out-of-distribution Generalization and Detection
Spiking Graph Neural Network on Riemannian Manifolds
Sequential Signal Mixing Aggregation for Message Passing Graph Neural Networks
Bayesian Nonparametrics Meets Data-Driven Distributionally Robust Optimization
Extracting Training Data from Molecular Pre-trained Models
Long-range Brain Graph Transformer
Testing Calibration in Nearly-Linear Time
Hypothesis Testing the Circuit Hypothesis in LLMs
Evidence of Learned Look-Ahead in a Chess-Playing Neural Network
Relational Concept Bottleneck Models
Jointly Modeling Inter- & Intra-Modality Dependencies for Multi-modal Learning
VLMimic: Vision Language Models are Visual Imitation Learner for Fine-grained Actions
Learning Interaction-aware 3D Gaussian Splatting for One-shot Hand Avatars
Transcoders find interpretable LLM feature circuits
Talking Heads: Understanding Inter-Layer Communication in Transformer Language Models
MeLLoC: Lossless Compression with High-order Mechanism Learning
Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP
A Functional Extension of Semi-Structured Networks
InversionView: A General-Purpose Method for Reading Information from Neural Activations
Who’s asking? User personas and the mechanics of latent misalignment
AROMA: Preserving Spatial Structure for Latent PDE Modeling with Local Neural Fields
Pretrained Large Language Models Use Fourier Features to Compute Addition
AR-Pro: Anomaly Explanation and Repair with Formal Properties
Hyperbolic Embeddings of Supervised Models
Understanding Information Storage and Transfer in Multi-Modal Large Language Models
Reasons and solutions for the decline in model performance after editing
RGFN: Synthesizable Molecular Generation Using GFlowNets
2DQuant: Low-bit Post-Training Quantization for Image Super-Resolution
Toxicity Detection for Free
Articulate your NeRF: Unsupervised articulated object modeling via conditional view synthesis
Fast samplers for Inverse Problems in Iterative Refinement models
Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback
LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding
Zero-Shot Tokenizer Transfer
WizardArena: Post-training Large Language Models via Simulated Offline Chatbot Arena
Train-Attention: Meta-Learning Where to Focus in Continual Knowledge Learning
Stress-Testing Long-Context Language Models with Lifelong ICL and Task Haystack
Contrasting with Symile: Simple Model-Agnostic Representation Learning for Unlimited Modalities
Faster Neighborhood Attention: Reducing the O(n^2) Cost of Self Attention at the Threadblock Level
Limits of Transformer Language Models on Learning to Compose Algorithms
StreamingDialogue: Prolonged Dialogue Learning via Long Context Compression with Minimal Losses
Long-form factuality in large language models
HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection
Revisiting Ensembling in One-Shot Federated Learning
ReMoDetect: Reward Models Recognize Aligned LLM's Generations
GlotCC: An Open Broad-Coverage CommonCrawl Corpus and Pipeline for Minority Languages
Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization
Derandomizing Multi-Distribution Learning
D-LLM: A Token Adaptive Computing Resource Allocation Strategy for Large Language Models
$\beta$-DPO: Direct Preference Optimization with Dynamic $\beta$
QUEST: Quality-Aware Metropolis-Hastings Sampling for Machine Translation
DistillNeRF: Perceiving 3D Scenes from Single-Glance Images by Distilling Neural Fields and Foundation Model Features
Doubly Mild Generalization for Offline Reinforcement Learning
COLD: Causal reasOning in cLosed Daily activities
Local Superior Soups: A Catalyst for Model Merging in Cross-Silo Federated Learning
UrbanKGent: A Unified Large Language Model Agent Framework for Urban Knowledge Graph Construction
Knowledge Circuit in Transformers
Robust Neural Contextual Bandit against Adversarial Corruptions
Should We Really Edit Language Models? On the Evaluation of Edited Language Models
SongCreator: Lyrics-based Universal Song Generation
Detecting Brittle Decisions for Free: Leveraging Margin Consistency in Deep Robust Classifiers
SSDM: Scalable Speech Dysfluency Modeling
Large Language Model-Driven Audio Codec is a Few-Shot Audio Task Learner
Unified Speech Recognition: A Single Model for Auditory, Visual, and Audiovisual Inputs
FedLPA: One-shot Federated Learning with Layer-Wise Posterior Aggregation
ESPACE: Dimensionality Reduction of Activations for Model Compression
Multi-Instance Partial-Label Learning with Margin Adjustment
Hierarchical Hybrid Sliced Wasserstein: A Scalable Metric for Heterogeneous Joint Distributions
Efficient Convex Algorithms for Universal Kernel Learning
Wasserstein convergence of Cech persistence diagrams for samplings of submanifolds
Enriching Disentanglement: From Logical Definitions to Quantitative Metrics
RAMP: Boosting Adversarial Robustness Against Multiple $l_p$ Perturbations
Better by default: Strong pre-tuned MLPs and boosted trees on tabular data
Test-time Adaptation in Non-stationary Environments via Adaptive Representation Alignment
Transferable Reinforcement Learning via Generalized Occupancy Models
SAFE: Slow and Fast Parameter-Efficient Tuning for Continual Learning with Pre-Trained Models
Federated Learning over Connected Modes
Transforming Vision Transformer: Towards Efficient Multi-Task Asynchronous Learner
Large Scale Transfer Learning for Tabular Data via Language Modeling
TinyTTA: Efficient Test-time Adaptation via Early-exit Ensembles on Edge Devices
Learning De-Biased Representations for Remote-Sensing Imagery
Dynamic Neural Regeneration: Enhancing Deep Learning Generalization on Small Datasets
Span-Based Optimal Sample Complexity for Weakly Communicating and General Average Reward MDPs
Amortized Eigendecomposition for Neural Networks
SEA: State-Exchange Attention for High-Fidelity Physics-Based Transformers
Semantic Feature Learning for Universal Unsupervised Cross-Domain Retrieval
Generic Unsupervised Optimization for a Latent Variable Model With Exponential Family Observables
Efficient Centroid-Linkage Clustering
Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognition
Retrieval & Fine-Tuning for In-Context Tabular Models
Parameterized Approximation Schemes for Fair-Range Clustering
IWBVT: Instance Weighting-based Bias-Variance Trade-off for Crowdsourcing
Boosting Vision-Language Models with Transduction
Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs
Happy: A Debiased Learning Framework for Continual Generalized Category Discovery
When Is Inductive Inference Possible?
VLKEB: A Large Vision-Language Model Knowledge Editing Benchmark
Dendritic Integration Inspired Artificial Neural Networks Enhance Data Correlation
Bridge the Modality and Capacity Gaps in Vision-Language Model Selection
AV-GS: Learning Material and Geometry Aware Priors for Novel View Acoustic Synthesis
TFGDA: Exploring Topology and Feature Alignment in Semi-supervised Graph Domain Adaptation through Robust Clustering
LLaNA: Large Language and NeRF Assistant
Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment
DeTikZify: Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ
Learning-Augmented Priority Queues
CountGD: Multi-Modal Open-World Counting
Towards Croppable Implicit Neural Representations
Accelerating Matroid Optimization through Fast Imprecise Oracles
Improving Deep Reinforcement Learning by Reducing the Chain Effect of Value and Policy Churn
Towards Visual Text Design Transfer Across Languages
COVE: Unleashing the Diffusion Feature Correspondence for Consistent Video Editing
Q-VLM: Post-training Quantization for Large Vision-Language Models
LocCa: Visual Pretraining with Location-aware Captioners
Black-Box Forgetting
Lumen: Unleashing Versatile Vision-Centric Capabilities of Large Multimodal Models
Flexible Context-Driven Sensory Processing in Dynamical Vision Models
Temporal-Difference Learning Using Distributed Error Signals
Humor in AI: Massive Scale Crowd-Sourced Preferences and Benchmarks for Cartoon Captioning
QKFormer: Hierarchical Spiking Transformer using Q-K Attention
Neural Embedding Ranks: Aligning 3D latent dynamics with movement for long-term and cross-area decoding
Game-Traversal-Benchmark: Evaluating Planning Abilities Of Large Language Models Via Traversing 2D Game Maps
Geometry of naturalistic object representations in recurrent neural network models of working memory
FEEL-SNN: Robust Spiking Neural Networks with Frequency Encoding and Evolutionary Leak Factor
Recurrent Complex-Weighted Autoencoders for Unsupervised Object Discovery
MMM-RS: A Multi-modal, Multi-GSD, Multi-scene Remote Sensing Dataset and Benchmark for Text-to-Image Generation
Benchmarking Generative Models on Computational Thinking Tests in Elementary Visual Programming
Recurrent neural network dynamical systems for biological vision
A scalable generative model for dynamical system reconstruction from neuroimaging data
A Polar Coordinate System Explicitly Represents Syntax in Language Models
Fourier Amplitude and Correlation Loss: Beyond Using L2 loss for Skillful Precipitation Nowcasting
Amortized Fourier Neural Operators
Towards training digitally-tied analog blocks via hybrid gradient computation
Graph-based Uncertainty Metrics for Long-form Language Model Generations
Dual Cone Gradient Descent for Training Physics-Informed Neural Networks
Quadratic Quantum Variational Monte Carlo
Regularized Adaptive Momentum Dual Averaging with an Efficient Inexact Subproblem Solver for Training Structured Neural Network
DeepLag: Discovering Deep Lagrangian Dynamics for Intuitive Fluid Prediction
Low Degree Hardness for Broadcasting on Trees
HYSYNTH: Context-Free LLM Approximation for Guiding Program Synthesis
Inflationary Flows: Calibrated Bayesian Inference with Diffusion-Based Models
Hyper-opinion Evidential Deep Learning for Out-of-Distribution Detection
An End-To-End Graph Attention Network Hash for Cross-Modal Retrieval
Hierarchical Uncertainty Exploration via Feedforward Posterior Trees
SubjECTive-QA: A dataset for the subjective evaluation of answers in Earnings Call Transcripts (ECTs)
Foundation Inference Models for Markov Jump Processes
Identifiable Object-Centric Representation Learning via Probabilistic Slot Attention
Diffusion Model-based Numerical Tabular Data Imputation: A Wasserstein Gradient Flow Perspective
FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep Learning
eXponential FAmily Dynamical Systems (XFADS): Large-scale nonlinear Gaussian state-space modeling
WikiDBs: A Large-Scale Corpus Of Relational Databases From Wikidata
Improving Linear System Solvers for Hyperparameter Optimisation in Iterative Gaussian Processes
Reverse Transition Kernel: A Flexible Framework to Accelerate Diffusion Inference
Efficient Streaming Algorithms for Graphlet Sampling
Constrained Sampling with Primal-Dual Langevin Monte Carlo
Mutual Information Estimation via Normalizing Flows
Unscrambling disease progression at scale: fast inference of event permutations with optimal transport
Map It Anywhere: Empowering BEV Map Prediction using Large-scale Public Datasets
MeMo: Meaningful, Modular Controllers via Noise Injection
Hierarchical data visualization via PCA trees
GAMap: Zero-Shot Object Goal Navigation with Multi-Scale Geometric-Affordance Guidance
Grasp as You Say: Language-guided Dexterous Grasp Generation
Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environments
Learning Cooperative Trajectory Representations for Motion Forecasting
CausalStock: Deep End-to-end Causal Discovery for News-driven Multi-stock Movement Prediction
Shape analysis for time series
ReMAP: Neural Model Reprogramming with Network Inversion and Retrieval-Augmented Mapping for Adaptive Motion Forecasting
Are Self-Attentions Effective for Time Series Forecasting?
SHDocs: A dataset, benchmark, and method to efficiently generate high-quality, real-world specular highlight data with near-perfect alignment
RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models
Personalized Adapter for Large Meteorology Model on Devices: Towards Weather Foundation Models
CALANet: Cheap All-Layer Aggregation for Human Activity Recognition
Hints-In-Browser: Benchmarking Language Models for Programming Feedback Generation
Abstracted Shapes as Tokens - A Generalizable and Interpretable Model for Time-series Classification
PertEval: Unveiling Real Knowledge Capacity of LLMs with Knowledge-Invariant Perturbations
Stylebreeder: Exploring and Democratizing Artistic Styles through Text-to-Image Models
WildGuard: Open One-stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
Self-Calibrating Conformal Prediction
When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Search
Pre-training Differentially Private Models with Limited Public Data
Counterfactual Fairness by Combining Factual and Counterfactual Predictions
Cross-Care: Assessing the Healthcare Implications of Pre-training Data on Language Model Bias
Latent Intrinsics Emerge from Training to Relight
Provably Safe Neural Network Controllers via Differential Dynamic Logic
WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models
PureGen: Universal Data Purification for Train-Time Poison Defense via Generative Model Dynamics
Context-aware testing: A new paradigm for tabular model testing
Leveraging Tumor Heterogeneity: Heterogeneous Graph Representation Learning for Cancer Survival Prediction in Whole Slide Images
The Group Robustness is in the Details: Revisiting Finetuning under Spurious Correlations
Representation noising effectively prevents harmful fine-tuning on LLMs
Transductive Active Learning: Theory and Applications
Improving Adversarial Robust Fairness via Anti-Bias Soft Label Distillation
MaNo: Exploiting Matrix Norm for Unsupervised Accuracy Estimation Under Distribution Shifts
Inference on the Change Point under a High Dimensional Covariance Shift
Fight Back Against Jailbreaking via Prompt Adversarial Tuning
Enhancing Efficiency of Safe Reinforcement Learning via Sample Manipulation
Seeing is NOT Always Believing! Unveiling the True Symmetric Moral Consistency of Large Language Models
Unveiling the Hidden: Online Vectorized HD Map Construction with Clip-Level Token Interaction and Propagation
ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficulty
Improving Equivariant Model Training via Constraint Relaxation
Benchmarking Complex Instruction-Following with Multiple Constraints Composition
MAGNET: Improving the Multilingual Fairness of Language Models with Adaptive Gradient-Based Tokenization
E2E-MFD: Towards End-to-End Synchronous Multimodal Fusion Detection
SMART: Towards Pre-trained Missing-Aware Model for Patient Health Status Prediction
SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusion
Learning Identifiable Factorized Causal Representations of Cellular Responses
SELF-DISCOVER: Large Language Models Self-Compose Reasoning Structures
Diffusion-DICE: In-Sample Diffusion Guidance for Offline Reinforcement Learning
Rethinking Out-of-Distribution Detection on Imbalanced Data Distribution
DoFIT: Domain-aware Federated Instruction Tuning with Alleviated Catastrophic Forgetting
L4GM: Large 4D Gaussian Reconstruction Model
KnowGPT: Knowledge Graph based Prompting for Large Language Models
Adapting to Unknown Low-Dimensional Structures in Score-Based Diffusion Models
Beyond Euclidean: Dual-Space Representation Learning for Weakly Supervised Video Violence Detection
Slight Corruption in Pre-training Data Makes Better Diffusion Models
Tracing Hyperparameter Dependencies for Model Parsing via Learnable Graph Pooling Network
realSEUDO for real-time calcium imaging analysis
InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory
Revisiting motion information for RGB-Event tracking with MOT philosophy
OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents
EGSST: Event-based Graph Spatiotemporal Sensitive Transformer for Object Detection
LLMs Can Evolve Continually on Modality for $\mathbb{X}$-Modal Reasoning
Set-based Neural Network Encoding Without Weight Tying
Towards Neuron Attributions in Multi-Modal Large Language Models
On the Power of Decision Trees in Auto-Regressive Language Modeling
Image Understanding Makes for A Good Tokenizer for Image Generation
UPS: Unified Projection Sharing for Lightweight Single-Image Super-resolution and Beyond
DisCEdit: Model Editing by Identifying Discriminative Components
MoVA: Adapting Mixture of Vision Experts to Multimodal Context
Loss Symmetry and Noise Equilibrium of Stochastic Gradient Descent
On the Necessity of Collaboration for Online Model Selection with Decentralized Data
Flaws can be Applause: Unleashing Potential of Segmenting Ambiguous Objects in SAM
$\text{ID}^3$: Identity-Preserving-yet-Diversified Diffusion Models for Synthetic Face Recognition
Optimization-based Causal Estimation from Heterogeneous Environments
Learning Discrete Latent Variable Structures with Tensor Rank Conditions
Causal Imitation for Markov Decision Processes: a Partial Identification Approach
Who’s Gaming the System? A Causally-Motivated Approach for Detecting Strategic Adaptation
Interventionally Consistent Surrogates for Complex Simulation Models
Interventional Causal Discovery in a Mixture of DAGs
Discovery of the Hidden World with Large Language Models
Kuro Siwo: 33 billion $m^2$ under the water. A global multi-temporal satellite dataset for rapid flood mapping
Unsupervised Modality Adaptation with Text-to-Image Diffusion Models for Semantic Segmentation
CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark
HourVideo: 1-Hour Video-Language Understanding
WikiDO: Evaluating Out-of-Distribution Generalization of Vision-Language Models in Cross-Modal Retrieval
GeoLife: Spacial Plant Species Prediction Dataset
SciFIBench: Benchmarking Large Multimodal Models for Scientific Figure Interpretation
GMAI-MMBench: A Comprehensive Multimodal Evaluation Benchmark Towards General Medical AI
LogiCity: Advancing Neuro-Symbolic AI with Abstract Urban Simulation
SCRREAM : SCan, Register, REnder And Map: A Framework for Annotating Accurate and Dense 3D Indoor Scenes with a Benchmark
HelpSteer 2: Open-source dataset for training top-performing reward models
A survey and benchmark of high-dimensional Bayesian optimization of discrete sequences
VLM4Bio: A Benchmark Dataset to Evaluate Pretrained Vision-Language Models for Trait Discovery from Biological Images
MAN TruckScenes: A multimodal dataset for autonomous trucking in diverse conditions
MultiOrg: A Multi-rater Organoid-detection Dataset
EHRNoteQA: An LLM Benchmark for Real-World Clinical Practice Using Discharge Summaries
Quantifying the Bitter Lesson: How Safety Benchmarks Measure Capabilities Instead of Safety
EyeGraph: Modularity-aware Spatio Temporal Graph Clustering for Continuous Event-based Eye Tracking
Stronger Than You Think: Benchmarking Weak Supervision on Realistic Tasks
LINGOLY: A Benchmark of Olympiad-Level Linguistic Reasoning Puzzles in Low Resource and Extinct Languages
IMDL-BenCo: A Comprehensive Benchmark and Codebase for Image Manipulation Detection & Localization
FedLLM-Bench: Realistic Benchmarks for Federated Learning of Large Language Models
SynRS3D: A Synthetic Dataset for Global 3D Semantic Understanding from Monocular Remote Sensing Imagery
ConceptFactory: Facilitate 3D Object Knowledge Annotation with Object Conceptualization
CTIBench: A Benchmark for Evaluating LLMs in Cyber Threat Intelligence
Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization
NYU CTF Dataset: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security
Benchmarking Structural Inference Methods for Interacting Dynamical Systems with Synthetic Data
Preferential Normalizing Flows
VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding
AgentGym: A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents
Learning Human-like Representations to Enable Learning Human Values
Learning on Large Graphs using Intersecting Communities
RedCode: Multi-dimensional Safety Benchmark for Code Agents
Minimizing Hyperspherical Energy for Diverse Deep Ensembling
UltraMedical: Building Specialized Generalists in Biomedicine
Towards Heterogeneous Long-tailed Learning: Benchmarking, Metrics, and Toolbox
Topic-Conversation Relevance (TCR) Dataset and Benchmarks
PowerGraph: A power grid benchmark dataset for graph neural networks
WhodunitBench: Evaluating Large Multimodal Agents via Murder Mystery Games
Do Multimodal Foundation Models Understand Enterprise Workflows? A Benchmark for Business Process Management Tasks
Benchmarking Out-of-Distribution Generalization and Adaptation for Electromyography
MEQA: A Benchmark for Multi-hop Event-centric Question Answering with Explanations
kGym: A Platform and Dataset to Benchmark Large Language Models on Linux Kernel Crash Resolution
GTBench: Uncovering the Strategic Reasoning Capabilities of LLMs via Game-Theoretic Evaluations
FairWire: Fair Graph Generation
Mind the Gap: A Causal Perspective on Bias Amplification in Prediction & Decision-Making
Wasserstein Distributionally Robust Optimization through the Lens of Structural Causal Models and Individual Fairness
How Does Black-Box Impact the Learning Guarantee of Stochastic Compositional Optimization?
Overfitting Behaviour of Gaussian Kernel Ridge Regression: Varying Bandwidth or Dimensionality
Credal Learning Theory
Contextual Decision-Making with Knapsacks beyond the Worst Case
On Mesa-Optimization in Autoregressively Trained Transformers: Emergence and Capability
Data subsampling for Poisson regression
Language Generation in the Limit
The Reliability of OKRidge Method in Solving Sparse Ridge Regression Problems
Only Strict Saddles in the Energy Landscape of Predictive Coding Networks?
Stochastic Zeroth-Order Optimization under Strongly Convexity and Lipschitz Hessian: Minimax Sample Complexity
Transformation-Invariant Learning and Theoretical Guarantees for OOD Generalization
Accelerating ERM for data-driven algorithm design using output-sensitive techniques
Predicting Ground State Properties: Constant Sample Complexity and Deep Learning Algorithms
Efficient Graph Matching for Correlated Stochastic Block Models
Toward Global Convergence of Gradient EM for Over-Paramterized Gaussian Mixture Models
Queueing Matching Bandits with Preference Feedback
WATT: Weight Average Test Time Adaptation of CLIP
Bandit-Feedback Online Multiclass Classification: Variants and Tradeoffs
Barely Random Algorithms for Metrical Task Systems
Online Adaptation of Language Models with a Memory of Amortized Contexts
Color-Oriented Redundancy Reduction in Dataset Distillation
Improved Regret for Bandit Convex Optimization with Delayed Feedback
Mixture of Experts Meets Prompt-Based Continual Learning
Adaptive Passive-Aggressive Framework for Online Regression with Side Information
Universal Online Convex Optimization with $1$ Projection per Round
Accelerating Non-Maximum Suppression: A Graph Theory Perspective
Unsupervised Object Detection with Theoretical Guarantees
Linear Time Approximation Algorithm for Column Subset Selection with Local Search
Efficient Multi-task LLM Quantization and Serving for Multiple LoRA Adapters
Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models
MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence
Semi-Discrete Optimal Transport: Nearly Minimax Estimation With Stochastic Gradient Descent and Adaptive Entropic Regularization
Provably Faster Algorithms for Bilevel Optimization via Without-Replacement Sampling
A Framework for Bilevel Optimization on Riemannian Manifolds
Safe and Sparse Newton Method for Entropic-Regularized Optimal Transport
Universality of AdaGrad Stepsizes for Stochastic Optimization: Inexact Oracle, Acceleration and Variance Reduction
Large Language Models as Hyper-Heuristics for Combinatorial Optimization
Learning Cut Generating Functions for Integer Programming
Discretely beyond $1/e$: Guided Combinatorial Algortihms for Submodular Maximization
Efficient Combinatorial Optimization via Heat Diffusion
Rethinking Memory and Communication Costs for Efficient Large Language Model Training
Achieving Linear Convergence with Parameter-Free Algorithms in Decentralized Optimization
LoQT: Low Rank Adapters for Quantized Training
Efficient Pipeline Parallelism with Controllable Memory
Improving the Worst-Case Bidirectional Communication Complexity for Nonconvex Distributed Optimization under Function Similarity
OptEx: Expediting First-Order Optimization with Approximately Parallelized Iterations
Understanding Representation of Deep Equilibrium Models from Neural Collapse Perspective
ADOPT: Modified Adam Can Converge with Any $\beta_2$ with the Optimal Rate
Generative Adversarial Bayesian Optimization for Surrogate Objectives
Contextual Linear Optimization with Bandit Feedback
How to Boost Any Loss Function
Incorporating Surrogate Gradient Norm to Improve Offline Optimization Techniques
ReLIZO: Sample Reusable Linear Interpolation-based Zeroth-order Optimization
Scalable DP-SGD: Shuffling vs. Poisson Subsampling
Banded Square Root Matrix Factorization for Differentially Private Model Training
Towards More Efficient Property Inference Attacks on Graph Neural Networks
On the Computational Complexity of Private High-dimensional Model Selection
Faster Differentially Private Top-$k$ Selection: A Joint Exponential Mechanism with Pruning
Certified Machine Unlearning via Noisy Stochastic Gradient Descent
Q-Distribution guided Q-learning for offline reinforcement learning: Uncertainty penalized Q-value via consistency model
Abstract Reward Processes: Leveraging State Abstraction for Consistent Off-Policy Evaluation
Is Value Function Learning Really the Main Bottleneck of Offline RL?
A Simple Framework for Generalization in Visual RL under Dynamic Scene Perturbations
No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design Choices
iVideoGPT: Interactive VideoGPTs are Scalable World Models
First-Explore, then Exploit: Meta-Learning to Solve Hard Exploration-Exploitation Trade-Offs
Distributional Reinforcement Learning with Regularized Wasserstein Loss
Skill-aware Mutual Information Optimisation for Zero-shot Generalisation in Reinforcement Learning
State Chrono Representation for Enhancing Generalization in Reinforcement Learning
Diffusion-based Reinforcement Learning via Q-weighted Variational Policy Optimization
Adversarial Robust Decision Transformer: Enhancing RvS Robustness via Minimax Returns
Diffusion Actor-Critic with Entropy Regulator
Diversity Is Not All You Need: Training A Robust Cooperative Agent Needs Specialist Partners
Randomized Exploration in Cooperative Multi-Agent Reinforcement Learning
Learning Distinguishable Trajectory Representation with Contrastive Loss
Few-Shot Task Learning Through Inverse Generative Modeling
Imitating Language via Scalable Inverse Reinforcement Learning
Uniform Last-Iterate Guarantee for Bandits and Reinforcement Learning
Oracle-Efficient Reinforcement Learning for Max Value Ensembles
Reinforcement Learning with Adaptive Control Regularization for Safe Control of Critical Systems
Simplifying Constraint Inference with Inverse Reinforcement Learning
NeoRL: Efficient Exploration for Nonepisodic RL
Opponent Modeling with In-context Search
Sequential Decision Making with Expert Demonstrations under Unobserved Heterogeneity
Off-Dynamics Reinforcement Learning via Domain Adaptation and Reward Augmented Imitation
Text-Aware Diffusion for Policy Learning
Gated Inference Network: Inferencing and Learning State-Space Models
Empowering Active Learning for 3D Molecular Graphs with Geometric Graph Isomorphism
Universality in Transfer Learning for Linear Models
Persistent Test-time Adaptation in Recurring Testing Scenarios
Efficient Discrepancy Testing for Learning with Distribution Shift
On Tractable $\Phi$-Equilibria in Non-Concave Games
The Secretary Problem with Predicted Additive Gap
Paths to Equilibrium in Games
Gaussian Approximation and Multiplier Bootstrap for Polyak-Ruppert Averaged Linear Stochastic Approximation with Applications to TD Learning
Constrained Binary Decision Making
Diversity-Driven Synthesis: Enhancing Dataset Distillation through Directed Weight Adjustment
A Unified Principle of Pessimism for Offline Reinforcement Learning under Model Mismatch
Operator World Models for Reinforcement Learning
Diffusion-based Curriculum Reinforcement Learning
SeeA*: Efficient Exploration-Enhanced A* Search by Selective Sampling
Fixed points of nonnegative neural networks
EffiBench: Benchmarking the Efficiency of Automatically Generated Code
Score-Optimal Diffusion Schedules
CausalDiff: Causality-Inspired Disentanglement via Diffusion Model for Adversarial Defense
Mixtures of Experts for Audio-Visual Learning
Euclidean distance compression via deep random features
IPO: Interpretable Prompt Optimization for Vision-Language Models
VeLoRA: Memory Efficient Training using Rank-1 Sub-Token Projections
Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization
Training LLMs to Better Self-Debug and Explain Code
MaVEn: An Effective Multi-granularity Hybrid Visual Encoding Framework for Multimodal Large Language Model
Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning
Amortizing intractable inference in diffusion models for vision, language, and control
In-Context Learning with Representations: Contextual Generalization of Trained Transformers
Replicable Uniformity Testing
Integrating GNN and Neural ODEs for Estimating Two-Body Interactions in Mixed-Species Collective Motion
Taming "data-hungry" reinforcement learning? Stability in continuous state-action spaces
Over-parameterized Student Model via Tensor Decomposition Boosted Knowledge Distillation
Persistence Homology Distillation for Semi-supervised Continual Learning
CLIPLoss and Norm-Based Data Selection Methods for Multimodal Contrastive Learning
Enhancing vision-language models for medical imaging: bridging the 3D gap with innovative slice selection
Self-Guiding Exploration for Combinatorial Problems
Newton Informed Neural Operator for Computing Multiple Solutions of Nonlinear Partials Differential Equations
Hybrid Generative AI for De Novo Design of Co-Crystals with Enhanced Tabletability
Learning to compute Gröbner bases
Trajectory Flow Matching with Applications to Clinical Time Series Modelling
Differentiable Modal Synthesis for Physical Modeling of Planar String Sound and Motion Simulation
Pruning neural network models for gene regulatory dynamics using data and domain knowledge
Training Compute-Optimal Protein Language Models
Multiview Scene Graph
Improving Ab-Initio Cryo-EM Reconstruction with Semi-Amortized Pose Inference
Key-Grid: Unsupervised 3D Keypoints Detection using Grid Heatmap Features
DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation
Reimagining Mutual Information for Enhanced Defense against Data Leakage in Collaborative Inference
AlphaTablets: A Generic Plane Representation for 3D Planar Reconstruction from Monocular Videos
ContactField: Implicit Field Representation for Multi-Person Interaction Geometry
Approaching Human-Level Forecasting with Language Models
All-in-One Image Coding for Joint Human-Machine Vision with Multi-Path Aggregation
Make-it-Real: Unleashing Large Multimodal Model for Painting 3D Objects with Realistic Materials
einspace: Searching for Neural Architectures from Fundamental Operations
Context and Geometry Aware Voxel Transformer for Semantic Scene Completion
UV-free Texture Generation with Denoising and Heat Diffusion
ODGS: 3D Scene Reconstruction from Omnidirectional Images with 3D Gaussian Splattings
Metric from Human: Zero-shot Monocular Metric Depth Estimation via Test-time Adaptation
Inferring Neural Signed Distance Functions by Overfitting on Single Noisy Point Clouds through Finetuning Data-Driven based Priors
OpenDlign: Enhancing Open-World 3D Learning with Depth-Aligned Images
Diffusion Priors for Variational Image Denoising
Accelerating Transformers with Spectrum-Preserving Token Merging
Assemblage: Automatic Binary Dataset Construction for Machine Learning
DN-4DGS: Denoised Deformable Network with Temporal-Spatial Aggregation for Dynamic Scene Rendering
ImOV3D: Learning Open Vocabulary Point Clouds 3D Object Detection from Only 2D Images
An Analytical Study of Utility Functions in Multi-Objective Reinforcement Learning
Optimal-state Dynamics Estimation for Physics-based Human Motion Capture from Videos
Wild-GS: Real-Time Novel View Synthesis from Unconstrained Photo Collections
QuadMamba: Learning Quadtree-based Selective Scan for Visual State Space Model
MambaSCI: Efficient Mamba-UNet for Quad-Bayer Patterned Video Snapshot Compressive Imaging
Web-Scale Visual Entity Recognition: An LLM-Driven Data Approach
MVInpainter: Learning Multi-View Consistent Inpainting to Bridge 2D and 3D Editing
Improved Analysis for Bandit Learning in Matching Markets
A Simple yet Universal Framework for Depth Completion
What do Graph Neural Networks learn? Insights from Tropical Geometry
Generalizable Implicit Motion Modeling for Video Frame Interpolation
OPS: Occupancy Prediction as A Sparse Set
Active Perception for Grasp Detection via Neural Graspness Field
Learning Truncated Causal History Model for Video Restoration
Adaptive Domain Learning for Cross-domain Image Denoising
IllumiNeRF: 3D Relighting without Inverse Rendering
A Novel Unified Architecture for Low-Shot Counting by Detection and Segmentation
Visual Fourier Prompt Tuning
DI-MaskDINO: A Joint Object Detection and Instance Segmentation Model
Learning the Optimal Policy for Balancing Multiple Short-Term and Long-Term Rewards
Revisiting the Integration of Convolution and Attention for Vision Backbone
Skinned Motion Retargeting with Dense Geometric Interaction Perception
On-Road Object Importance Estimation: A New Dataset and A Model with Multi-Fold Top-Down Guidance
Can We Leave Deepfake Data Behind in Training Deepfake Detector?
Aligning Vision Models with Human Aesthetics in Retrieval: Benchmarks and Algorithms
Learning Plaintext-Ciphertext Cryptographic Problems via ANF-based SAT Instance Representation
Binarized Diffusion Model for Image Super-Resolution
A Prompt Learning based Regulation Framework for Generalizable Point Cloud Analysis
Vision-Language Models are Strong Noisy Label Detectors
To Err like Human: Affective Bias-Inspired Measures for Visual Emotion Recognition Evaluation
Recovering Complete Actions for Cross-dataset Skeleton Action Recognition
Prompting LLMs for Social Relation Reasoning via Greedy Segment Optimization
ACFun: Abstract-Concrete Fusion Facial Stylization
Is One GPU Enough? Pushing Image Generation at Higher-Resolutions with Foundation Models.
Smoothed Energy Guidance: Guiding Diffusion Models by Attenuating Energy Curvature of Attention
FIDE: Frequency-Inflated Conditional Diffusion Model for Extreme-Aware Time Series Generation
ENAT: Rethinking Spatial-temporal Interactions in Token-based Image Synthesis
Transferring disentangled representations: bridging the gap between synthetic and real images
Scaling the Codebook Size of VQ-GAN to 100,000 with a Utilization Rate of 99%
Kaleido Diffusion: Improving Conditional Diffusion Models with Autoregressive Latent Modeling
An Image is Worth 32 Tokens for Reconstruction and Generation
E2ENet: Dynamic Sparse Feature Fusion for Accurate and Efficient 3D Medical Image Segmentation
Learning Frequency-aware Vision Foundation Model for Domain Generalized Semantic Segmentation
DeiSAM: Segment Anything with Deictic Prompting
AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation
GraphMorph: Tubular Structure Extraction by Morphing Predicted Graphs
Toward Real Ultra Image Segmentation: Leveraging Surrounding Context to Cultivate General Segmentation Model
Temporal Sentence Grounding with Relevance Feedback in Videos
SyncVIS: Synchronized Video Instance Segmentation
General Detection-based Text Line Recognition
MVSplat360: Benchmarking 360$\textdegree$ Generalizable 3D Novel View Synthesis from Sparse Views
A Versatile Diffusion Transformer with Mixture of Noise Levels for Audiovisual Generation
Enhancing Motion in Text-to-Video Generation with Decomposed Encoding and Conditioning
GoMatching: A Simple Baseline for Video Text Spotting via Long and Short Term Matching
MECD: Unlocking Multi-Event Causal Discovery in Video Reasoning
TrackIME: Enhanced Video Point Tracking via Instance Motion Estimation
Boundary Matters: A Bi-Level Active Finetuning Method
Beyond Efficiency: Molecular Data Pruning for Enhanced Generalization
Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning
Provable and Efficient Dataset Distillation for Kernel Ridge Regression
Distilling Costly Set Functions to Parametric Families
Data Selection for Task-Specific Model Finetuning
[Re] CUDA: Curriculum of Data Augmentation for Long‐tailed Recognition
FedAvP: Augment Local Data via Shared Policy in Federated Learning
HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning
Make the Most of Your Data: Changing the Training Data Distribution to Improve Generalization
DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving
Compact Language Models via Pruning and Knowledge Distillation
4-bit Shampoo for Memory-Efficient Network Training
ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization
DHA: Learning Decoupled-Head Attention from Transformer Checkpoints via Adaptive Heads Fusion
DiffGS: Functional Gaussian Splatting Diffusion
Zero-Shot Scene Reconstruction from Single Images with Deep Prior Assembly
On Sampling Strategies for Spectral Model Sharding
Diversify, Contextualize, and Adapt: Efficient Entropy Modeling for Neural Image Codec
Improving Deep Learning Performance through Constrained Parameter Regularization
Perceiving Longer Sequences With Bi-Directional Cross-Attention Transformers
Cluster-Learngene: Inheriting Adaptive Clusters for Vision Transformers
Reducing Transformer Key-Value Cache Size with Cross-Layer Attention
Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding
Real-time Core-Periphery Guided ViT with Smart Data Layout Selection on Mobile Devices
Activating Self-Attention for Multi-Scene Absolute Pose Regression
Efficient Attention using Low-Dimensional Keys
Gradient-free Decoder Inversion in Latent Diffusion Models
Embedding Dimension of Contrastive Learning and $k$-Nearest Neighbors
Classification Done Right for Vision-Language Pre-Training
Interactive Deep Clustering via Value Mining
Latent functional maps
What Variables Affect Out-Of-Distribution Generalization in Pretrained Models?
Critically Assessing the State of the Art in Neural Network Verification
Is Your HD Map Constructor Reliable under Sensor Corruptions?
Expecting The Unexpected: Towards Broad Out-Of-Distribution Detection
Learnability Matters: Active Learning for Video Captionin
WaveAttack: Asymmetric Frequency Obfuscation-based Backdoor Attacks Against Deep Neural Networks
The Implicit Bias of Gradient Descent toward Collaboration between Layers: A Dynamic Analysis of Multilayer Perceptions
Adaptive Labeling for Efficient Out-of-distribution Model Evaluation
GREAT Score: Global Robustness Evaluation of Adversarial Perturbation using Generative Models
SUGARCREPE++ Dataset: Vision-Language Model Sensitivity to Semantic and Lexical Alterations
Harnessing small projectors and multiple views for efficient vision pretraining
How does PDE order affect the convergence of PINNs?
A New Neural Kernel Regime: The Inductive Bias of Multi-Task Training
Principled Probabilistic Imaging using Diffusion Models as Plug-and-Play Priors
Polyhedral Complex Derivation from Piecewise Trilinear Networks
Debiasing Synthetic Data Generated by Deep Generative Models
An exactly solvable model for emergence and scaling laws
Hardness of Learning Neural Networks under the Manifold Hypothesis
Nature-Inspired Local Propagation
Near-Optimal Distributed Minimax Optimization under the Second-Order Similarity
MINI-SEQUENCE TRANSFORMER: Optimizing Intermediate Memory for Long Sequences Training
Convolutional Differentiable Logic Gate Networks
Towards Next-Level Post-Training Quantization of Hyper-Scale Transformers
Where Do Large Learning Rates Lead Us?
MatrixNet: Learning over symmetry groups using learned group representations
$\textit{Read-ME}$: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design
Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning
A Critical Evaluation of AI Feedback for Aligning Large Language Models
Pessimistic Backward Policy for GFlowNets
Structured Multi-Track Accompaniment Arrangement via Style Prior Modelling
Group Robust Preference Optimization in Reward-free RLHF
Grounded Answers for Multi-agent Decision-making Problem through Generative World Model
Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models
Optimal Flow Matching: Learning Straight Trajectories in Just One Step
Search for Efficient Large Language Models
SnapKV: LLM Knows What You are Looking for Before Generation
Data Attribution for Text-to-Image Models by Unlearning Synthesized Images
Adversarial Generation of Hierarchical Gaussians for 3D Generative Model
Efficient LLM Scheduling by Learning to Rank
Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers
Fisher Flow Matching for Discrete Data
Simple and Fast Distillation of Diffusion Models
Multistep Distillation of Diffusion Models via Moment Matching
Med-Real2Sim: Non-Invasive Medical Digital Twins using Physics-Informed Self-Supervised Learning
Understanding and Improving Training-free Loss-based Diffusion Guidance
Unified Guidance for Geometry-Conditioned Molecular Generation
HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priors
DP-SGD with Fixed-Size Minibatches: Tighter Guarantees with or without Replacement
BrainBits: How Much of the Brain are Generative Reconstruction Methods Using?
KOALA: Empirical Lessons Toward Memory-Efficient and Fast Diffusion Models for Text-to-Image Synthesis
Algorithmic Capabilities of Random Transformers
AID: Attention Interpolation of Text-to-Image Diffusion
How to Continually Adapt Text-to-Image Diffusion Models for Flexible Customization?
Optical Diffusion Models for Image Generation
Images that Sound: Composing Images and Sounds on a Single Canvas
UniDSeg: Unified Cross-Domain 3D Semantic Segmentation via Visual Foundation Models Prior
Diffusion Twigs with Loop Guidance for Conditional Graph Generation
Phased Consistency Model
A Geometric View of Data Complexity: Efficient Local Intrinsic Dimension Estimation with Diffusion Models
Taming Diffusion Prior for Image Super-Resolution with Domain Shift SDEs
Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning
SocraticLM: Exploring Socratic Personalized Teaching with Large Language Models
Trajectory Diffusion for ObjectGoal Navigation
Prompt Optimization with EASE? Efficient Ordering-aware Automated Selection of Exemplars
Localized Zeroth-Order Prompt Optimization
Fine-grained Analysis of In-context Linear Estimation
UniBias: Unveiling and Mitigating LLM Bias through Internal Attention and FFN Manipulation
Concentrate Attention: Towards Domain-Generalizable Prompt Optimization for Language Models
Are Large Language Models Good Statisticians?
Introspective Planning: Aligning Robots' Uncertainty with Inherent Task Ambiguity
Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphs
On Giant's Shoulders: Effortless Weak to Strong by Dynamic Logits Fusion
Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer
NoisyGL: A Comprehensive Benchmark for Graph Neural Networks under Label Noise
Uncovering the Redundancy in Graph Self-supervised Learning Models
Scale Equivariant Graph Meta Networks
Weisfeiler and Leman Go Loopy: A New Hierarchy for Graph Representational Learning
NN4SysBench: Characterizing Neural Network Verification for Computer Systems
Revisiting Self-Supervised Heterogeneous Graph Learning from Spectral Clustering Perspective
Analysis of Corrected Graph Convolutions
Learning rigid-body simulators over implicit shapes for large-scale scenes and vision
The Intelligible and Effective Graph Neural Additive Network
Deep Graph Neural Networks via Posteriori-Sampling-based Node-Adaptative Residual Module
Generalizing CNNs to graphs with learnable neighborhood quantization
YouDream: Generating Anatomically Controllable Consistent Text-to-3D Animals
Combining Statistical Depth and Fermat Distance for Uncertainty Quantification
Graph Neural Networks Need Cluster-Normalize-Activate Modules
Long-range Meta-path Search on Large-scale Heterogeneous Graphs
On the Scalability of GNNs for Molecular Graphs
MAC Advice for facility location mechanism design
DisenGCD: A Meta Multigraph-assisted Disentangled Graph Learning Framework for Cognitive Diagnosis
If You Want to Be Robust, Be Wary of Initialization
Enhancing Robustness of Graph Neural Networks on Social Media with Explainable Inverse Reinforcement Learning
Autonomous Agent for Collaborative Task under Information Asymmetry
SEL-BALD: Deep Bayesian Active Learning for Selective Labeling with Instance Rejection
Towards Multi-dimensional Explanation Alignment for Medical Classification
Beyond Concept Bottleneck Models: How to Make Black Boxes Intervenable?
Transformers Learn Higher-Order Optimization Methods for In-Context Learning: A Study with Linear Models
STL: Still Tricky Logic (for System Validation, Even When Showing Your Work)
Using Noise to Infer Aspects of Simplicity Without Learning
Listenable Maps for Zero-Shot Audio Classifiers
Analysing CLIP's Zero-Shot Image Classification via Mutual Knowledge
A hierarchical decomposition for explaining ML performance discrepancies
Understanding Emergent Abilities of Language Models from the Loss Perspective
Improving Context-Aware Preference Modeling for Language Models
ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search
Bias Amplification in Language Model Evolution: An Iterated Learning Perspective
Self-Retrieval: End-to-End Information Retrieval with One Large Language Model
CiteME: Can Language Models Accurately Cite Scientific Claims?
ANAH-v2: Scaling Analytical Hallucination Annotation of Large Language Models
Self-Evolution Decoding for Improving Factuality in Large Language Models
A Modular Conditional Diffusion Framework for Image Reconstruction
Scalable DBSCAN with Random Projections
SCOREQ: Speech Quality Assessment with Contrastive Regression
ProgressGym: Alignment with a Millennium of Moral Progress
SimPO: Simple Preference Optimization with a Reference-Free Reward
ConStat: Performance-Based Contamination Detection in Large Language Models
Bridging Gaps: Federated Multi-View Clustering in Heterogeneous Hybrid Views
Improving Generalization in Federated Learning with Model-Data Mutual Information Regularization: A Posterior Inference Approach
Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models
IRCAN: Mitigating Knowledge Conflicts in LLM Generation via Identifying and Reweighting Context-Aware Neurons
Evaluate calibration of language models with folktexts
Meaningful Learning: Enhancing Abstract Reasoning in Large Language Models via Generic Fact Guidance
MKGL: Mastery of a Three-Word Language
Source Code Foundation Models are Transferable Binary Analysis Knowledge Bases
Language Grounded Multi-Agent Communication for Ad-hoc Teamwork
FINALLY: fast and universal speech enhancement with studio-like quality
CoVoMix: Advancing Zero-Shot Speech Generation for Human-like Multi-talker Conversations
CA-SSLR: Condition-Aware Self-Supervised Learning Representation for Generalized Speech Processing
Stochastic Taylor Derivative Estimator: Efficient amortization for arbitrary differential operators
SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers
KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization
Multi-Label Open Set Recognition
Dense Associative Memory Through the Lens of Random Features
Graph-enhanced Optimizers for Structure-aware Recommendation Embedding Evolution
Collaborative Refining for Learning from Inaccurate Labels
Implicit regularization of multi-task learning and finetuning: multiple regimes of feature reuse
DPIC: Decoupling Prompt and Intrinsic Characteristics for LLM Generated Text Detection
Reinforcement Learning-Guided Semi-Supervised Learning
Grounding Multimodal Large Language Models in Actions
Scaling Sign Language Translation
An eye for an ear: zero-shot audio description leveraging an image captioner with audio-visual token distribution matching
Renovating Names in Open-Vocabulary Segmentation Benchmarks
Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs
GrootVL: Tree Topology is All You Need in State Space Model
Unity by Diversity: Improved Representation Learning for Multimodal VAEs
UMFC: Unsupervised Multi-Domain Feature Calibration for Vision-Language Models
Voila-A: Aligning Vision-Language Models with User's Gaze Attention
Frustratingly Easy Test-Time Adaptation of Vision-Language Models
Adaptive Image Quality Assessment via Teaching Large Multimodal Models to Compare
Neural Assets: 3D-Aware Multi-Object Scene Synthesis with Image Diffusion Models
CLAP4CLIP: Continual Learning with Probabilistic Finetuning for Vision-Language Models
Scalable Constrained Policy Optimization for Safe Multi-agent Reinforcement Learning
Look, Listen, and Answer: Overcoming Biases for Audio-Visual Question Answering
Customized Multiple Clustering via Multi-Modal Subspace Proxy Learning
SpaFL: Communication-Efficient Federated Learning With Sparse Models And Low Computational Overhead
Benchmarking Out-of-Distribution Generalization Capabilities of DNN-based Encoding Models for the Ventral Visual Cortex.
Aggregate-and-Adapt Natural Language Prompts for Downstream Generalization of CLIP
Bridging semantics and pragmatics in information-theoretic emergent communication
Rethinking the Dynamics of Spiking Neural Networks
NeuMA: Neural Material Adaptor for Visual Grounding of Intrinsic Dynamics
Spectral Learning of Shared Dynamics Between Generalized-Linear Processes
Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration
Visual Decoding and Reconstruction via EEG Embeddings with Guided Diffusion
fMRI predictors based on language models of increasing complexity recover brain left lateralization
Flow Snapshot Neurons in Action: Deep Neural Networks Generalize to Biological Motion Perception
Long-Range Feedback Spiking Network Captures Dynamic and Static Representations of the Visual Cortex under Movie Stimuli
SpikedAttention: Training-Free and Fully Spike-Driven Transformer-to-SNN Conversion with Winner-Oriented Spike Shift for Softmax Operation
Du-IN: Discrete units-guided mask modeling for decoding speech from Intracranial Neural signals
Combining Observational Data and Language for Species Range Estimation
FNP: Fourier Neural Processes for Arbitrary-Resolution Data Assimilation
DrivAerNet++: A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarks
Symbolic Regression with a Learned Concept Library
Construction and Application of Materials Knowledge Graph in Multidisciplinary Materials Science via Large Language Model
Boosting Generalization in Parametric PDE Neural Solvers through Adaptive Conditioning
The Importance of Being Scalable: Efficient Architectures for Neural Network Potentials
NeuralClothSim: Neural Deformation Fields Meet the Thin Shell Theory
Expected Probabilistic Hierarchies
Avoiding Undesired Future with Minimal Cost in Non-Stationary Environments
Neural Conditional Probability for Inference
Sourcerer: Sample-based Maximum Entropy Source Distribution Estimation
Deep Bayesian Active Learning for Preference Modeling in Large Language Models
BMRS: Bayesian Model Reduction for Structured Pruning
Practical Bayesian Algorithm Execution via Posterior Sampling
Amortized Bayesian Experimental Design for Decision-Making
Globally Convergent Variational Inference
Asymptotics of Alpha-Divergence Variational Inference Algorithms with Exponential Families
ClevrSkills: Compositional Language And Visual Understanding in Robotics
Simulated Humanoid Grasping on Diverse Objects
GarmentLab: A Unified Simulation and Benchmark for Garment Manipulation
DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control
Continuously Learning, Adapting, and Improving: A Dual-Process Approach to Autonomous Driving
The Effectiveness of Surprisingly Popular Voting with Partial Preferences
Mechanism Design Through Exploration Control: Optimizing the Trade-Off Between User and Creator Engagement
Peri-midFormer: Periodic Pyramid Transformer for Time Series Analysis
Rethinking the Power of Timestamps for Robust Time Series Forecasting: A Global-Local Fusion Perspective
SLowcalSGD : Slow Query Points Improve Local-SGD for Stochastic Convex Optimization
One-Step Effective Diffusion Network for Real-World Image Super-Resolution
Time-FFM: Towards LM-Empowered Federated Foundation Model for Time Series Forecasting
Faster Accelerated First-order Methods for Convex Optimization with Strongly Convex Function Constraints
From News to Forecast: Integrating Event Analysis in LLM-Based Time Series Forecasting with Reflection
Get Rid of Isolation: A Continuous Multi-task Spatio-Temporal Learning Framework
Parsimony or Capability? Decomposition Delivers Both in Long-term Time Series Forecasting
Benchmarking Trustworthiness of Multimodal Large Language Models: A Comprehensive Study
Achieving Near-Optimal Convergence for Distributed Minimax Optimization with Adaptive Stepsizes
An Efficient Memory Module for Graph Few-Shot Class-Incremental Learning
Implicit Multimodal Alignment: On the Generalization of Frozen LLMs to Multimodal Inputs
PrivAuditor: Benchmarking Data Protection Vulnerabilities in LLM Adaptation Techniques
On the Adversarial Robustness of Benjamini Hochberg
VHELM: A Holistic Evaluation of Vision Language Models
The Best of Both Worlds: Toward an Honest and Helpful Large Language Model
Transferability Bound Theory: Exploring Relationship between Adversarial Transferability and Flatness
IDGen: Item Discrimination Induced Prompt Generation for LLM Evaluation
From Dictionary to Tensor: A Scalable Multi-View Subspace Clustering Framework with Triple Information Enhancement
Towards Calibrated Robust Fine-Tuning of Vision-Language Models
Safe LoRA: The Silver Lining of Reducing Safety Risks when Finetuning Large Language Models
ALI-Agent: Assessing LLMs' Alignment with Human Values via Agent-based Evaluation
Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization
Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness
MoGU: A Framework for Enhancing Safety of Open-Sourced LLMs While Preserving Their Usability
Federated Online Prediction from Experts with Differential Privacy: Separations and Regret Speed-ups
Test Where Decisions Matter: Importance-driven Testing for Deep Reinforcement Learning
Robust Contrastive Multi-view Clustering against Dual Noisy Correspondence
Faster Repeated Evasion Attacks in Tree Ensembles
Designs for Enabling Collaboration in Human-Machine Teaming via Interactive and Explainable Systems
Unelicitable Backdoors via Cryptographic Transformer Circuits
Parameter Disparities Dissection for Backdoor Defense in Heterogeneous Federated Learning
HyperLogic: Enhancing Diversity and Accuracy in Rule Learning with HyperNets
Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities
Query-Based Adversarial Prompt Generation
DFA-GNN: Forward Learning of Graph Neural Networks by Direct Feedback Alignment
Enhancing Zero-Shot Vision Models by Label-Free Prompt Distribution Learning and Bias Correcting
RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable Guarantees
GeSS: Benchmarking Geometric Deep Learning under Scientific Applications with Distribution Shifts
DiffusionFake: Enhancing Generalization in Deepfake Detection via Guided Stable Diffusion
General Articulated Objects Manipulation in Real Images via Part-Aware Diffusion Process
WFCRL: A Multi-Agent Reinforcement Learning Benchmark for Wind Farm Control
Terra: A Multimodal Spatio-Temporal Dataset Spanning the Earth
UniTox: Leveraging LLMs to Curate a Unified Dataset of Drug-Induced Toxicity from FDA Labels
LibAMM: Empirical Insights into Approximate Computing for Accelerating Matrix Multiplication
DECRL: A Deep Evolutionary Clustering Jointed Temporal Knowledge Graph Representation Learning Approach
Learning Superconductivity from Ordered and Disordered Material Structures
FlowTurbo: Towards Real-time Flow-Based Image Generation with Velocity Refiner
IMAGPose: A Unified Conditional Framework for Pose-Guided Person Generation
Invisible Image Watermarks Are Provably Removable Using Generative AI
Spatio-Spectral Graph Neural Networks
Enhancing Large Vision Language Models with Self-Training on Image Comprehension
OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation
Towards General Loop Invariant Generation: A Benchmark of Programs with Memory Manipulation
SpecExec: Massively Parallel Speculative Decoding For Interactive LLM Inference on Consumer Devices
Multivariate Probabilistic Time Series Forecasting with Correlated Errors
Architect: Generating Vivid and Interactive 3D Scenes with Hierarchical 2D Inpainting
SOAP: Enhancing Efficiency of generated Code via Self-Optimization
Noise Contrastive Alignment of Language Models with Explicit Rewards
Observational Scaling Laws and the Predictability of Langauge Model Performance
Continuous Spatiotemporal Events Decoupling through Spike-based Bayesian Computation
GraphMETRO: Mitigating Complex Graph Distribution Shifts via Mixture of Aligned Experts
U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers
Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior Models
LiT: Unifying LiDAR "Languages" with LiDAR Translator
Universal Neural Functionals
A Gradient Accumulation Method for Dense Retriever under Memory Constraint
FUSE: Fast Unified Simulation and Estimation for PDEs
MOTE-NAS: Multi-Objective Training-based Estimate for Efficient Neural Architecture Search
Domain Adaptation for Large-Vocabulary Object Detectors
Noether's Razor: Learning Conserved Quantities
DataStealing: Steal Data from Diffusion Models in Federated Learning with Multiple Trojans
Generalization Analysis for Label-Specific Representation Learning
Exploring Token Pruning in Vision State Space Models
AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models
Convergence of $\log(1/\epsilon)$ for Gradient-Based Algorithms in Zero-Sum Games without the Condition Number: A Smoothed Analysis
Direct Preference-Based Evolutionary Multi-Objective Optimization with Dueling Bandits
Octopus: A Multi-modal LLM with Parallel Recognition and Sequential Understanding
Do Finetti: On Causal Effects for Exchangeable Data
QWO: Speeding Up Permutation-Based Causal Discovery in LiGAMs
Identification and Estimation of the Bi-Directional MR with Some Invalid Instruments
Detecting and Measuring Confounding Using Causal Mechanism Shifts
On Causal Discovery in the Presence of Deterministic Relations
FastDrag: Manipulate Anything in One Step
Towards Estimating Bounds on the Effect of Policies under Unobserved Confounding
StackEval: Benchmarking LLMs in Coding Assistance
Building Timeseries Dataset: Empowering Large-Scale Building Analytics
IaC-Eval: A code generation benchmark for Infrastructure-as-Code programs
Lightweight Frequency Masker for Cross-Domain Few-Shot Semantic Segmentation
ReMI: A Dataset for Reasoning with Multiple Images
HairDiffusion: Vivid Multi-Colored Hair Editing via Latent Diffusion
ShopBench: A Massive Multi-Task Online Shopping Benchmark for Large Language Models
PersonalSum: A User-Subjective Guided Personalized Summarization Dataset for Large Language Models
Team-Fictitious Play for Reaching Team-Nash Equilibrium in Multi-team Games
emg2qwerty: A Large Dataset with Baselines for Touch Typing using Surface Electromyography
AverNet: All-in-one Video Restoration for Time-varying Unknown Degradations
Is Function Similarity Over-Engineered? Building a Benchmark
Rethinking No-reference Image Exposure Assessment from Holism to Pixel: Models, Datasets and Benchmarks
SETBENCH: Assessing the Analytical and Semantic Robustness of Language Models
Multi-modal Situated Reasoning in 3D Scenes
Optimistic Critic Reconstruction and Constrained Fine-Tuning for General Offline-to-Online RL
CARE: a Benchmark Suite for the Classification and Retrieval of Enzymes
RashomonGB: Analyzing the Rashomon Effect and Mitigating Predictive Multiplicity in Gradient Boosting
DreamCatcher: A Wearer-aware Multi-modal Sleep Event Dataset Based on Earables in Non-restrictive Environments
BertaQA: How Much Do Language Models Know About Local Culture?
OpenSatMap: A Fine-grained High-resolution Satellite Dataset for Large-scale Map Construction
WelQrate: Defining the Gold Standard in Small Molecule Drug Discovery Benchmarking
DF40: Toward Next-Generation Deepfake Detection
BiVLC: Extending Vision-Language Compositionality Evaluation with Text-to-Image Retrieval
Copycats: the many lives of a publicly available medical imaging dataset
$\texttt{dopanim}$: A Dataset of Doppelganger Animals with Noisy Annotations from Multiple Humans
CaptainCook4D: A Dataset for Understanding Errors in Procedural Activities
GTA: A Benchmark for General Tool Agents
emg2pose: A Large and Diverse Benchmark for Surface Electromyographic Hand Pose Estimation
DiscoveryWorld: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents
FVEL: Interactive Formal Verification Environment with Large Language Models via Theorem Proving
EpiCare: A Reinforcement Learning Benchmark for Dynamic Treatment Regimes
BLURD: Benchmarking and Learning using a Unified Rendering and Diffusion Model
Indoor Air Quality Dataset with Activities of Daily Living in Low to Middle-income Communities
FT-AED: Benchmark Dataset for Early Freeway Traffic Anomalous Event Detection
STimage-1K4M: A histopathology image-gene expression dataset for spatial transcriptomics
RClicks: Realistic Click Simulation for Benchmarking Interactive Segmentation
Mixture of Adversarial LoRAs: Boosting Robust Generalization in Meta-tuning
Towards Reliable Model Selection for Unsupervised Domain Adaptation: An Empirical Study and A Certified Baseline
Cherry on Top: Parameter Heterogeneity and Quantization in Large Language Models
Vocal Call Locator Benchmark (VCL'24) for localizing rodent vocalizations from multi-channel audio
Beyond Prompts: Dynamic Conversational Benchmarking of Large Language Models
ERBench: An Entity-Relationship based Automatically Verifiable Hallucination Benchmark for Large Language Models
Fit for our purpose, not yours: Benchmark for a low-resource, Indigenous language
Seshat Global History Databank Text Dataset and Benchmark of Large Language Models' History Knowledge
SeafloorGenAI: A Large-scale Vision-Language Dataset for Seafloor Geological Survey
Amnesia as a Catalyst for Enhancing Black Box Pixel Attacks in Image Classification and Object Detection
The Fairness-Quality Tradeoff in Clustering
Fair Bilevel Neural Network (FairBiNN): On Balancing fairness and accuracy via Stackelberg Equilibrium
CultureLLM: Incorporating Cultural Differences into Large Language Models
Improving Subgroup Robustness via Data Selection
Wide Two-Layer Networks can Learn from Adversarial Perturbations
On the Efficiency of ERM in Feature Learning
Fair Online Bilateral Trade
Recursive PAC-Bayes: A Frequentist Approach to Sequential Prior Updates with No Information Loss
Learning a Single Neuron Robustly to Distributional Shifts and Adversarial Label Noise
CooHOI: Learning Cooperative Human-Object Interaction with Manipulated Object Dynamics
Stability and Generalization of Asynchronous SGD: Sharper Bounds Beyond Lipschitz and Smoothness
Online Consistency of the Nearest Neighbor Rule
OptCM: The Optimization Consistency Models for Solving Combinatorial Problems in Few Shots
Boosting Transferability and Discriminability for Time Series Domain Adaptation
CoMix: A Comprehensive Benchmark for Multi-Task Comic Understanding
Understanding the Gains from Repeated Self-Distillation
Learning from higher-order correlations, efficiently: hypothesis tests, random features, and neural networks
Differential Privacy in Scalable General Kernel Learning via $K$-means Nystr{\"o}m Random Features
Sharpness-diversity tradeoff: improving flat ensembles with SharpBalance
Exploration, Exploitation, and Engagement in Multi-Armed Bandits with Abandonment
BEACON: Benchmark for Comprehensive RNA Tasks and Language Models
Online Learning with Sublinear Best-Action Queries
Dynamic Service Fee Pricing under Strategic Behavior: Actions as Instruments and Phase Transition
Nearly Minimax Optimal Submodular Maximization with Bandit Feedback
Symmetric Linear Bandits with Hidden Symmetry
Learning Goal-Conditioned Representations in Reward Models for Aligning Language Models
FiVA: Fine-grained Visual Attribute Dataset for Text-to-Image Diffusion Models
Truthfulness of Calibration Measures
Policy Optimization for Robust Average Reward MDPs
Online Convex Optimisation: The Optimal Switching Regret for all Segmentations Simultaneously
The Minimax Regret of Sequential Probability Assignment, Contextual Shtarkov Sums, and Contextual Normalized Maximum Likelihood
Optimization Algorithm Design via Electric Circuits
Sparse maximal update parameterization: A holistic approach to sparse training dynamics
Sample-Efficient Geometry Reconstruction from Euclidean Distances using Non-Convex Optimization
Tighter Convergence Bounds for Shuffled SGD via Primal-Dual Perspective
Mind's Eye of LLMs: Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models
SPARKLE: A Unified Single-Loop Primal-Dual Framework for Decentralized Bilevel Optimization
A Primal-Dual-Assisted Penalty Approach to Bilevel Optimization with Coupled Constraints
Learning with Fitzpatrick Losses
The Power of Extrapolation in Federated Learning
Scalable Kernel Inverse Optimization
A Bayesian Approach to Data Point Selection
Don't Compress Gradients in Random Reshuffling: Compress Gradient Differences
Quantitative Convergences of Lie Group Momentum Optimizers
Sample-efficient Bayesian Optimisation Using Known Invariances
Query-Efficient Correlation Clustering with Noisy Oracle
Transition Constrained Bayesian Optimization via Markov Decision Processes
Active Set Ordering
Private Attribute Inference from Images with Vision-Language Models
PANORAMIA: Efficient Privacy Auditing of Machine Learning Models without Retraining
Semi-supervised Multi-label Learning with Balanced Binary Angular Margin Loss
Dual Defense: Enhancing Privacy and Mitigating Poisoning Attacks in Federated Learning
Trap-MID: Trapdoor-based Defense against Model Inversion Attacks
Membership Inference Attacks against Large Language Models via Self-prompt Calibration
Private Online Learning via Lazy Algorithms
Differentially Private Equivalence Testing for Continuous Distributions and Application
DMC-VB: A Benchmark for Representation Learning for Control with Visual Distractors
Exclusively Penalized Q-learning for Offline Reinforcement Learning
Adaptive $Q$-Aid for Conditional Supervised Learning in Offline Reinforcement Learning
Drones Help Drones: A Collaborative Framework for Multi-Drone Object Trajectory Prediction and Beyond
Multi-Task Prompt Decision Transformer for Efficient Unseen Task Generalization
VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks
Bootstrapping Top-down Information for Self-modulating Slot Attention
Boosting the Potential of Large Language Models with an Intelligent Information Assistant
OPERA: Automatic Offline Policy Evaluation with Re-weighted Aggregates of Multiple Estimators
Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning
Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning?
MultiPull: Detailing Signed Distance Functions by Pulling Multi-Level Queries at Multi-Step
R$^2$-Gaussian: Rectifying Radiative Gaussian Splatting for Tomographic Reconstruction
Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learning
The Ladder in Chaos: Improving Policy Learning by Harnessing the Parameter Evolving Path in A Low-dimensional Space
Do's and Don'ts: Learning Desirable Skills with Instruction Videos
Effective Exploration Based on the Structural Information Principles
Deep Policy Gradient Without Batch Updates or a Replay Buffer
Diffusion for World Modeling: Visual Details Matter in Atari
Sample-Efficient Constrained Reinforcement Learning with General Parameterization
Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers
Exploiting the Replay Memory Before Exploring the Environment: Enhancing Reinforcement Learning Through Empirical MDP Iteration
Structured Unrestricted-Rank Matrices for Parameter Efficient Finetuning
C-GAIL: Stabilizing Generative Adversarial Imitation Learning with Control Theory
Regularized Q-Learning
The Power of Resets in Online Reinforcement Learning
Fast Tree-Field Integrators: From Low Displacement Rank to Topological Transformers
Efficient Algorithm and Improved Regret for RL with Multinomial Logit Function Approximation
N-agent Ad Hoc Teamwork
Inverse Factorized Soft Q-Learning for Cooperative Multi-agent Imitation Learning
Flipping-based Policy for Chance-Constrained Markov Decision Processes
Adversarially Trained Weighted Actor-Critic for Safe Offline Reinforcement Learning
Robust Reinforcement Learning with General Utility
Action Gaps and Advantages in Continuous-Time Distributional Reinforcement Learning
The surprising efficiency of temporal difference learning for rare event prediction
WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environment
Tight Rates for Bandit Control Beyond Quadratics
How to Scale Inverse RL to Large State Spaces? A Provably Efficient Approach
Strategic Linear Contextual Bandits
A Robust Mixed-Effects Bandit Algorithm for Assessing Mobile Health Interventions
Fixed Confidence Best Arm Identification in the Bayesian Setting
START: A Generalized State Space Model with Saliency-Driven Token-Aware Transformation
Bayesian Adaptive Calibration and Optimal Design
Meta-Reinforcement Learning with Universal Policy Adaptation: Provable Near-Optimality under All-task Optimum Comparator
Contrastive dimension reduction: when and how?
Task-Agnostic Machine Learning-Assisted Inference
Robust group and simultaneous inferences for high-dimensional single index model
Do LLMs Build World Representations? Probing Through the Lens of State Abstraction
Unified Domain Generalization and Adaptation for Multi-View 3D Object Detection
Conditional Outcome Equivalence: A Quantile Alternative to CATE
Active preference learning for ordering items in- and out-of-sample
Near-Equivalence Between Bounded Regret and Delay Robustness in Interactive Decision Making
FedGTST: Boosting Global Transferability of Federated Models via Statistics Tuning
PACE: marrying the generalization of PArameter-efficient fine-tuning with Consistency rEgularization
Label Noise: Ignorance Is Bliss
Fine-Grained Dynamic Framework for Bias-Variance Joint Optimization on Data Missing Not at Random
Cascade Speculative Drafting for Even Faster LLM Inference
Optimal Aggregation of Prediction Intervals under Unsupervised Domain Shift
Fast Last-Iterate Convergence of Learning in Games Requires Forgetful Algorithms
Incentivizing Quality Text Generation via Statistical Contracts
PaCE: Parsimonious Concept Engineering for Large Language Models
CoIN: A Benchmark of Continual Instruction Tuning for Multimodel Large Language Models
Mutual Information Estimation via $f$-Divergence and Data Derangements
InterpBench: Semi-Synthetic Transformers for Evaluating Mechanistic Interpretability Techniques
Group-wise oracle-efficient algorithms for online multi-group learning
A generalized neural tangent kernel for surrogate gradient learning
How Does Variance Shape the Regret in Contextual Bandits?
Model-free Low-Rank Reinforcement Learning via Leveraged Entry-wise Matrix Estimation
Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies
Structured Learning of Compositional Sequential Interventions
Excluding the Irrelevant: Focusing Reinforcement Learning through Continuous Action Masking
UQ-Guided Hyperparameter Optimization for Iterative Learners
Nonparametric Evaluation of Noisy ICA Solutions
Almost Free: Self-concordance in Natural Exponential Families and an Application to Bandits
In-and-Out: Algorithmic Diffusion for Sampling Convex Bodies
On the Ability of Developers' Training Data Preservation of Learnware
Optimal Algorithms for Learning Partitions with Faulty Oracles
LT-Defense: Searching-free Backdoor Defense via Exploiting Long-Tailed Effect
Retrospective for the Dynamic Sensorium Competition for predicting large-scale mouse primary visual cortex activity from videos
Learning to Shape In-distribution Feature Space for Out-of-distribution Detection
Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models
Face2QR: A Unified Framework for Aesthetic, Face-Preserving, and Scannable QR Code Generation
Dynamic Subgroup Identification in Covariate-adjusted Response-adaptive Randomization Experiments
SIRIUS : Contexual Sparisty with Correction for Efficient LLMs
Diffusion Policies creating a Trust Region for Offline Reinforcement Learning
Optimizing the coalition gain in Online Auctions with Greedy Structured Bandits
Diffusion Representation for Reinforcement Learning
Online Feature Updates Improve Online (Generalized) Label Shift Adaptation
Understanding Visual Feature Reliance through the Lens of Complexity
A Theoretical Understanding of Self-Correction through In-context Alignment
Rethinking Exploration in Reinforcement Learning with Effective Metric-Based Exploration Bonus
SubgDiff: A Subgraph Diffusion Model to Improve Molecular Representation Learning
Exploitation of a Latent Mechanism in Graph Contrastive Learning: Representation Scattering
On Feature Learning in Structured State Space Models
How to Use Diffusion Priors under Sparse Views?
Symmetry-Informed Governing Equation Discovery
UDC: A Unified Neural Divide-and-Conquer Framework for Large-Scale Combinatorial Optimization Problems
What Rotary Position Embedding Can Tell Us: Identifying Query and Key Weights Corresponding to Basic Syntactic or High-level Semantic Information
Score-based 3D molecule generation with neural fields
Scalable and Stable Parallelization of Nonlinear RNNs
DiffusionBlend: Learning 3D Image Prior through Position-aware Diffusion Score Blending for 3D Computed Tomography Reconstruction
ReFT: Representation Finetuning for Language Models
Segment, Shuffle, and Stitch: A Simple Mechanism for Improving Time-Series Representations
Flex-MoE: Addressing Missing Modalities in Alzheimer’s Disease with Flexible Mixture-of-Experts
Learning Bregman Divergences with Application to Robustness
Toward a Stable, Fair, and Comprehensive Evaluation of Object Hallucination in Large Vision-Language Models
Optimal Multi-Fidelity Best-Arm Identification
Interpreting Learned Feedback Patterns in Large Language Models
TrAct: Making First-layer Pre-Activations Trainable
Decision-Focused Learning with Directional Gradients
GraphTrail: Translating GNN Predictions into Human-Interpretable Logical Rules
CRAYM: Neural Field Optimization via Camera RAY Matching
Learning predictable and robust neural representations by straightening image sequences
Lower Bounds of Uniform Stability in Gradient-Based Bilevel Algorithms for Hyperparameter Optimization
Towards Editing Time Series
Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs
FlexPlanner: Flexible 3D Floorplanning via Deep Reinforcement Learning in Hybrid Action Space with Multi-Modality Representation
Sequence-Augmented SE(3)-Flow Matching For Conditional Protein Generation
A Locally Optimal Portfolio for m-Sparse Sharpe Ratio Maximization
Soft ascent-descent as a stable and flexible alternative to flooding
S$^{2}$FT: Efficient, Scalable and Generalizable LLM Fine-tuning by Structured Sparsity
Transfer Learning for Latent Variable Network Models
Scanning Trojaned Models Using Out-of-Distribution Samples
Label Delay in Online Continual Learning
LotCLIP: Improving Language-Image Pre-training for Long Text Understanding
Accelerated Regularized Learning in Finite N-Person Games
Learning from Highly Sparse Spatio-temporal Data
Leveraging Contrastive Learning for Enhanced Node Representations in Tokenized Graph Transformers
Everyday Object Meets Vision-and-Language Navigation Agent via Backdoor
Large Scene Model: Real-time Unposed Images to Semantic 3D
HydraViT: Stacking Heads for a Scalable ViT
Improved Distribution Matching Distillation for Fast Image Synthesis
Predictive Attractor Models
FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion
Proving Olympiad Algebraic Inequalities without Human Demonstrations
$\nabla^2$DFT: A Universal Quantum Chemistry Dataset of Drug-Like Molecules and a Benchmark for Neural Network Potentials
Scalable and Effective Arithmetic Tree Generation for RL-Driven Adder and Multiplier Designs
Implicit Precursor Extraction with Expert Retriever for Inorganic Retrosynthesis
MDAgents: An Adaptive Collaboration of LLMs for Medical Decision Making
Soft Superpixel Neighborhood Attention
AutoSurvey: Large Language Models Can Automatically Write Surveys
AdjointDEIS: Efficient Gradients for Diffusion Models
Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning
PSL: Rethinking and Improving Softmax Loss from Pairwise Perspective for Recommendation
Idiographic Personality Gaussian Process for Psychological Assessment
FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making
Textual Training for the Hassle-Free Removal of Unwanted Visual Data
$\text{Di}^2\text{Pose}$: Discrete Diffusion Model for Occluded 3D Human Pose Estimation
Pretraining Codomain Attention Neural Operators for Solving Multiphysics PDEs
Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models
Exploring Structured Semantic Priors Underlying Diffusion Score for Test-time Adaptation
Estimating Heterogeneous Treatment Effects by Combining Weak Instruments and Observational Data
Learning to Edit Visual Programs with Self-Supervision
Low Precision Local Training is Enough for Federated Learning
NanoBaseLib: A Multi-Task Benchmark Dataset for Nanopore Sequencing
Progressive Exploration-Conformal Learning for Sparsely Annotated Object Detection in Aerial Images
Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length
Direct Consistency Optimization for Robust Customization of Text-to-Image Diffusion models
A SARS-CoV-2 Interaction Dataset and VHH Sequence Corpus for Antibody Language Models
Demographic parity fair regression in unaware setting
Transferable Boltzmann Generators
Gradual Domain Adaptation via Manifold-Constrained Distributionally Robust Optimization
Distribution-Aware Data Expansion with Diffusion Models
DiffAug: A Diffuse-and-Denoise Augmentation for Training Robust Classifiers
Revisiting K-mer Profile for Effective and Scalable Genome Representation Learning
Mixture of neural fields for heterogeneous reconstruction in cryo-EM
Zero-shot Generalizable Incremental Learning for Vision-Language Object Detection
Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language Models
Linear Uncertainty Quantification of Graphical Model Inference
Spatio-Temporal Interactive Learning for Efficient Image Reconstruction of Spiking Cameras
Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models
Computing the Bias of Constant-step Stochastic Approximation with Markovian Noise
Protein-Nucleic Acid Complex Modeling with Frame Averaging Transformer
Bridging the Divide: Reconsidering Softmax and Linear Attention
MaskFactory: Towards High-quality Synthetic Data Generation For Dichotomous Image Segmentation
Make Fashion Real: Texture-preserving Rendered-to-Real Translation with Diffusion Models
CryoGEM: Physics-Informed Generative Cryo-Electron Microscopy
On the Worst Prompt Performance of Large Language Models
Human-level shape inferences: A benchmark for evaluating the 3D understanding of vision models
Matrix Denoising with Doubly Heteroscedastic Noise: Fundamental Limits and Optimal Spectral Methods
Style Adaptation and Uncertainty Estimation for Multi-source Blended-Target Domain Adaptation
D-CPT Law: Domain-specific Continual Pre-Training Scaling Law for Large Language Models
AED: Adaptable Error Detection for Few-shot Imitation Policy
Hybrid Mamba: An Promising In-Context RL for Long-Term Decision
A General Protocol to Probe Large Vision Models for 3D Physical Understanding
Improving the Learning Capability of Small-size Image Restoration Network by Deep Fourier Shifting Operator over Resource-limited Scene
Constrained Synthesis with Projected Diffusion Models
Analysing Multi-Task Regression via Random Matrix Theory with Application to Time Series Forecasting
PuLID: Pure and Lightning ID Customization via Contrastive Alignment
On the Benefits of Public Representations for Private Transfer Learning under Distribution Shift
Optimal Rates for Vector-Valued Spectral Regularization Learning Algorithms
Fourier-enhanced Implicit Neural Fusion Network for Multispectral and Hyperspectral Image Fusion
From Instance Training to Instruction Learning: Task Adapters Generation from Instructions
AdanCA: Neural Cellular Automata As Adaptors For More Robust Vision Transformer
Conformal Alignment: Knowing When to Trust Foundation Models with Guarantees
On Learning Multi-Modal Forgery Representation for Diffusion Generated Video Detection
GO4Align: Group Optimization for Multi-Task Alignment
Harnessing Multiple Correlated Networks for Exact Community Recovery
An Efficient High-dimensional Gradient Estimator for Stochastic Differential Equations
Exploring Molecular Pretraining Model at Scale
Gradient-based Discrete Sampling with Automatic Cyclical Scheduling
Nonparametric Instrumental Variable Regression through Stochastic Approximate Gradients
Expectile Regularization for Fast and Accurate Training of Neural Optimal Transport
Score Distillation via Reparametrized DDIM
Efficient Adaptation of Pre-trained Vision Transformer via Householder Transformation
ZOPP: A Framework of Zero-shot Offboard Panoptic Perception for Autonomous Driving
Accelerating Best-of-N via Speculative Rejection
Gaussian Graph Network: Learning Efficient and Generalizable Gaussian Representations from Multi-view Images
Multi-language Diversity Benefits Autoformalization
Does Egalitarian Fairness Lead to Instability? The Fairness Bounds in Stable Federated Learning Under Altruistic Behaviors
An Adaptive Approach for Infinitely Many-armed Bandits under Generalized Rotting Constraints
SPEAR: Exact Gradient Inversion of Batches in Federated Learning
Learning Successor Features the Simple Way
UAV3D: A Large-scale 3D Perception Benchmark for Unmanned Aerial Vehicles
Can Large Language Models Analyze Graphs like Professionals? A Benchmark and Dataset
QUEEN: QUantized Efficient ENcoding for Streaming Free-viewpoint Videos
EAGLE: Efficient Adaptive Geometry-based Learning in Cross-view Understanding
Segment Any Change
DAGER: Exact Gradient Inversion for Large Language Models
Knowledge Graph Fine-Tuning Upon Open-World Knowledge from Large Language Models
Vision Foundation Model Enables Generalizable Object Pose Estimation
DoGaussian: Distributed-Oriented Gaussian Splatting for Large-Scale 3D Reconstruction Via Gaussian Consensus
EHRCon: Dataset for Checking Consistency between Unstructured Notes and Structured Tables in Electronic Health Records
Beyond Aesthetics: Cultural Competence in Text-to-Image Models
Beyond Accuracy: Tracking more like Human via Visual Search
Breaking Semantic Artifacts for Generalized AI-generated Image Detection
RLE: A Unified Perspective of Data Augmentation for Cross-Spectral Re-Identification
UniSDF: Unifying Neural Representations for High-Fidelity 3D Reconstruction of Complex Scenes with Reflections
Historical Test-time Prompt Tuning for Vision Foundation Models
FedGMKD: An Efficient Prototype Federated Learning Framework through Knowledge Distillation and Differential Aggregation
Directional Smoothness and Gradient Methods: Convergence and Adaptivity
High-Resolution Image Harmonization with Adaptive-Interval Color Transformation
Free Lunch in Pathology Foundation Model: Task-specific Model Adaptation with Concept-Guided Feature Enhancement
Adaptive Important Region Selection with Reinforced Hierarchical Search for Dense Object Detection
MeshFormer : High-Quality Mesh Generation with 3D-Guided Reconstruction Model
Don't Just String Tokens, Stack Them! Improving Multimodal Transformers with Layer Stack
NeuRodin: A Two-stage Framework for High-Fidelity Neural Surface Reconstruction
DC-Gaussian: Improving 3D Gaussian Splatting for Reflective Dash Cam Videos
Pedestrian-Centric 3D Pre-collision Pose and Shape Estimation from Dashcam Perspective
ECMamba: Consolidating Selective State Space Model with Retinex Guidance for Efficient Multiple Exposure Correction
InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling
MGF: Mixed Gaussian Flow for Diverse Trajectory Prediction
Dissecting the Failure of Invariant Learning on Graphs
Referencing Where to Focus: Improving Visual Grounding with Referential Query
Future Motion Estimation via Event Sequence Diffusion
Neural Signed Distance Function Inference through Splatting 3D Gaussians Pulled on Zero-Level Set
Towards Unified One-tower Expression Grounding and Segmentation with Mask Referring Modeling
TransAgent: Transfer Vision-Language Foundation Models with Heterogeneous Agent Collaboration
Parallelizing Model-based Reinforcement Learning Over the Sequence Length
Would I Lie To You? Inference Time Alignment of Language Models using Direct Preference Heads
GeoNLF: Geometry guided Pose-Free Neural LiDAR Fields
Dynamic 3D Gaussian Fields for Urban Areas
$SE(3)$ Equivariant Ray Embeddings for Implicit Multi-View Depth Estimation
Towards Flexible 3D Perception: Object-Centric Occupancy Completion Augments 3D Object Detection in Long Sequence
Prototypical Hash Encoding for On-the-Fly Fine-Grained Category Discovery
Hypergraph-Based Fuzzy Assembled Representation for Open-Set 3D Object Retrieval
Scala: Scalable Representation Learning for Vision Transformer
OneActor: Consistent Subject Generation via Cluster-Conditioned Guidance
SpaceByte: Towards Deleting Tokenization from Large Language Modeling
AP-Adapter: Improving Generalization of Automatic Prompts on Unseen Text-to-Image Diffusion Models
Magnet: We Never Know How Text-to-Image Diffusion Models Work, Until We Learn How Vision-Language Models Function
Pre-Trained Multi-Goal Transformers with Prompt Optimization for Efficient Online Adaptation
Training Dynamics of Transformers to Recognize Word Co-occurrence via Gradient Flow Analysis
Novel Object Synthesis via Adaptive Text-Image Harmony
Parameter Efficient Adaptation for Image Restoration with Heterogeneous Mixture-of-Experts
FuseAnyPart: Diffusion-Driven Facial Parts Swapping via Multiple Reference Images
ParallelEdits: Efficient Multi-Aspect Text-Driven Image Editing with Attention Grouping
FouRA: Fourier Low-Rank Adaptation
Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis
UltraPixel: Advancing Ultra High-Resolution Image Synthesis to New Peaks
DOFEN: Deep Oblivious Forest ENsemble
SA3DIP: Segment Any 3D Instance with Potential 3D Priors
Accelerating Diffusion Models with Parallel Sampling: Inference at Sub-Linear Time Complexity
Suitable is the Best: Task-oriented Knowledge Fusion in Vulnerability Detection
Spherical Frustum Sparse Convolution Network for LiDAR Point Cloud Semantic Segmentation
Zero-Shot Image Segmentation via Recursive Normalized Cut on Diffusion Features
HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splatting
Structure Consistent Gaussian Splatting with Matching Prior for Few-shot Novel View Synthesis
Multi-scale Consistency for Robust 3D Registration via Hierarchical Sinkhorn Tree
A Cat Is A Cat (Not A Dog!): Unraveling Information Mix-ups in Text-to-Image Encoders through Causal Analysis and Embedding Optimization
LVD-2M: A Long-take Video Dataset with Temporally Dense Captions
ActFusion: a Unified Diffusion Model for Action Segmentation and Anticipation
CYCLO: Cyclic Graph Transformer Approach to Multi-Object Relationship Modeling in Aerial Videos
DINTR: Tracking via Diffusion-based Interpolation
Expert-level protocol translation for self-driving labs
MoTE: Reconciling Generalization with Specialization for Visual-Language to Video Knowledge Transfer
SAND: Smooth imputation of sparse and noisy functional data with Transformer networks
Visual Data Diagnosis and Debiasing with Concept Graphs
MATES: Model-Aware Data Selection for Efficient Pretraining with Data Influence Models
SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models
Understanding Bias in Visual Datasets
UQE: A Query Engine for Unstructured Databases
Bayesian-Guided Label Mapping for Visual Reprogramming
Why Go Full? Elevating Federated Learning Through Partial Network Updates
Visual Prompt Tuning in Null Space for Continual Learning
Learning from Teaching Regularization: Generalizable Correlations Should be Easy to Imitate
Towards Understanding Evolving Patterns in Sequential Data
DARNet: Dual Attention Refinement Network with Spatiotemporal Construction for Auditory Attention Detection
RGMDT: Return-Gap-Minimizing Decision Tree Extraction in Non-Euclidean Metric Space
Building Network Architectures for Continual Reinforcement Learning with Parseval Regularization
ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction
A Walsh Hadamard Derived Linear Vector Symbolic Architecture
TinyLUT: Tiny Look-Up Table for Efficient Image Restoration at the Edge
NoMAD-Attention: Efficient LLM Inference on CPUs Through Multiply-add-free Attention
Unsupervised Discovery of Formulas for Mathematical Constants
AttnDreamBooth: Towards Text-Aligned Personalized Text-to-Image Generation
FactorizePhys: Effective Spatial-Temporal Attention in Remote Photo-plethysmography through Factorization of Voxel Embeddings
Efficient multi-prompt evaluation of LLMs
Parallelizing Linear Transformers with the Delta Rule over Sequence Length
Towards Understanding Extrapolation: a Causal Lens
Position Coupling: Leveraging Task Structure for Improved Length Generalization of Transformers
B'MOJO: Realizations of Hybrid State Space Models with Eidetic and Fading Memory
Learning Group Actions on Latent Representations
Random Representations Outperform Online Continually Learned Representations
When is an Embedding Model More Promising than Another?
SampDetox: Black-box Backdoor Defense via Perturbation-based Sample Detoxification
$\textit{Bifr\"ost}$: 3D-Aware Image Composing with Language Instructions
LinNet: Linear Network for Efficient Point Cloud Representation Learning
Road Network Representation Learning with the Third Law of Geography
Learning to Balance Altruism and Self-interest Based on Empathy in Mixed-Motive Games
Unconditional stability of a recurrent neural circuit implementing divisive normalization
$C^2M^3$: Cycle-Consistent Multi-Model Merging
Non-Euclidean Mixture Model for Social Network Embedding
Few-Shot Adversarial Prompt Learning on Vision-Language Models
Policy Improvement using Language Feedback Models
Attack-Aware Noise Calibration for Differential Privacy
The Mamba in the Llama: Distilling and Accelerating Hybrid Models
Stability and Generalization of Adversarial Training for Shallow Neural Networks with Smooth Activation
MALT Powers Up Adversarial Attacks
Can LLMs Solve Molecule Puzzles? A Multimodal Benchmark for Molecular Structure Elucidation
Many-shot Jailbreaking
On the Limitations of Fractal Dimension as a Measure of Generalization
Understanding the Role of Equivariance in Self-supervised Learning
Episodic Future Thinking Reinforcement Learning for Social Decision-making
Neural collapse vs. low-rank bias: Is deep neural collapse really optimal?
Relating Hopfield Networks to Episodic Control
A simplicity bias in the learning dynamics of transformers
StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem Solving
A Comprehensive Analysis on the Learning Curve in Kernel Ridge Regression
Predicting Scaling Laws with Statistical and Approximation Theory for Transformer Neural Networks on Intrinsically Low-dimensional Data
LLM Processes: Numerical Predictive Distributions Conditioned on Natural Language
AutoMix: Automatically Mixing Language Models
Bayes-optimal learning of an extensive-width neural network from quadratically many samples
Erasing Undesirable Concepts in Diffusion Models with Adversarial Preservation
Scalable Optimization in the Modular Norm
SGD vs GD: Rank Deficiency in Linear Networks
Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment
Are Multiple Instance Learning Algorithms Learnable for Instances?
Theoretical Characterisation of the Gauss Newton Conditioning in Neural Networks
HEST-1k: A Dataset For Spatial Transcriptomics and Histology Image Analysis
The Feature Speed Formula: a flexible approach to scale hyper-parameters of deep neural networks
G3: An Effective and Adaptive Framework for Worldwide Geolocalization Using Large Multi-Modality Models
Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion
Exploring and Exploiting the Asymmetric Valley of Deep Neural Networks
HORSE: Hierarchical Representation for Large-Scale Neural Subset Selection
Activation Map Compression through Tensor Decomposition for Deep Learning
FLoRA: Federated Fine-Tuning Large Language Models with Heterogeneous Low-Rank Adaptations
MoEUT: Mixture-of-Experts Universal Transformers
Benign overfitting in leaky ReLU networks with moderate input dimension
Amortized Planning with Large-Scale Transformers: A Case Study on Chess
Watermarking Makes Language Models Radioactive
Neural decoding from stereotactic EEG: accounting for electrode variability across subjects
MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models
Towards Diverse Device Heterogeneous Federated Learning via Task Arithmetic Knowledge Integration
Swift Sampler: Efficient Learning of Sampler by 10 parameters
Global Distortions from Local Rewards: Neural Coding Strategies in Path-Integrating Neural Systems
FlowLLM: Flow Matching for Material Generation with Learned Base Distributions
Provable Partially Observable Reinforcement Learning with Privileged Information
Flow Priors for Linear Inverse Problems via Iterative Corrupted Trajectory Matching
MVGamba: Unify 3D Content Generation as State Space Sequence Modeling
Hamiltonian Score Matching and Generative Flows
MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map
Fine-grained Control of Generative Data Augmentation in IoT Sensing
MInference: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention
Compositional 3D-aware Video Generation with LLM Director
Zero-shot Image Editing with Reference Imitation
Fully Transparent Self-Alignment for Code Generation
Schrodinger Bridge Flow for Unpaired Data Translation
Long-tailed Object Detection Pretraining: Dynamic Rebalancing Contrastive Learning with Dual Reconstruction
Rethinking Score Distillation as a Bridge Between Image Distributions
Global Convergence in Training Large-Scale Transformers
ReF-LDM: A Latent Diffusion Model for Reference-based Face Image Restoration
Suppress Content Shift: Better Diffusion Features via Off-the-Shelf Generation Techniques
Language-Driven Interactive Traffic Trajectory Generation
GrounDiT: Grounding Diffusion Transformers via Noisy Image Patch Transplantation
Graph Diffusion Transformer for Multi-Conditional Molecular Generation
Sharpness-Aware Minimization Activated Interactive Teaching Understanding and Optimization
Image Copy Detection for Diffusion Models
ProgressEditor: Simple Progression is All You Need for High-Quality 3D Scene Editing
Lumina-Next : Making Lumina-T2X Stronger and Faster with Next-DiT
COSMIC: Compress Satellite Image Efficiently via Diffusion Compensation
Diffusion Models With Learned Adaptive Noise
BiDM: Pushing the Limit of Quantization for Diffusion Models
DiP-GO: A Diffusion Pruner via Few-step Gradient Optimization
SELMA: Learning and Merging Skill-Specific Text-to-Image Experts with Auto-Generated Data
Improved off-policy training of diffusion samplers
DETAIL: Task DEmonsTration Attribution for Interpretable In-context Learning
Many-Shot In-Context Learning
Rule Extrapolation in Language Modeling: A Study of Compositional Generalization on OOD Prompts
Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration
Bias Detection via Signaling
Thinking Forward: Memory-Efficient Federated Finetuning of Language Models
Transformers as Game Players: Provable In-context Game-playing Capabilities of Pre-trained Models
Grammar-Aligned Decoding
LAM3D: Large Image-Point Clouds Alignment Model for 3D Reconstruction from Single Image
Trace is the New AutoDiff: Unlocking Efficient Optimization of Computational Workflows
Prospective Representation Learning for Non-Exemplar Class-Incremental Learning
Conformalized Time Series with Semantic Features
Mars: Situated Inductive Reasoning in an Open-World Environment
Learning Social Welfare Functions
Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset
Chain-of-Thought Reasoning Without Prompting
Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data
Addressing Spectral Bias of Deep Neural Networks by Multi-Grade Deep Learning
InstructG2I: Synthesizing Images from Multimodal Attributed Graphs
EAI: Emotional Decision-Making of LLMs in Strategic Games and Ethical Dilemmas
Does Reasoning Emerge? Examining the Probabilities of Causation in Large Language Models
Enhancing Large Language Models via Additional Pre-Training on Principled Synthetic Logic Corpus
TEG-DB: A Comprehensive Dataset and Benchmark of Textual-Edge Graphs
Training GNNs in Balance by Dynamic Rescaling
Towards Principled Graph Transformers
FUG: Feature-Universal Graph Contrastive Pre-training for Graphs with Diverse Node Features
A Topology-aware Graph Coarsening Framework for Continual Graph Learning
Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models
One-to-Multiple: A Progressive Style Transfer Unsupervised Domain-Adaptive Framework for Kidney Tumor Segmentation
Generalized Linear Bandits with Limited Adaptivity
GOUDA: A General Graph Contrastive Learning Framework via Augmentation Unification
UGC: Universal Graph Coarsening
Predictor-Corrector Enhanced Transformers with Exponential Moving Average Coefficient Learning
What Matters in Graph Class Incremental Learning? An Information Preservation Perspective
Graph Edit Distance with General Costs Using Neural Set Divergence
MambaTalk: Co-Speech Gesture Generation with Selective State Space Models
Harmonizing Stochasticity and Determinism: Scene-responsive Diverse Human Motion Prediction
On Sparse Canonical Correlation Analysis
Shared Autonomy with IDA: Interventional Diffusion Assistance
Towards Explainable Evaluation Metrics for Machine Translation
Benchmarking the Attribution Quality of Vision Models
Truth is Universal: Robust Detection of Lies in LLMs
Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)
Improving Decision Sparsity
How Do Transformers Fill in the Blanks? A Case Study on Matrix Completion
Goal-Conditioned On-Policy Reinforcement Learning
Interpretable Mesomorphic Networks for Tabular Data
FastSurvival: Hidden Computational Blessings in Training Cox Proportional Hazards Models
Zipper: Addressing Degeneracy in Algorithm-Agnostic Inference
GAIA: Rethinking Action Quality Assessment for AI-Generated Videos
Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization
Measuring Goal-Directedness
Optimal ablation for model internals
Fair and Welfare-Efficient Constrained Multi-Matchings under Uncertainty
Rule Based Rewards for Fine-Grained Safety Behavior in LLMs
A Full-duplex Speech Dialogue Scheme Based On Large Language Model
Divide-and-Conquer Posterior Sampling for Denoising Diffusion priors
DeTeCtive: Detecting AI-generated Text via Multi-Level Contrastive Learning
Achieving Efficient Alignment through Learned Correction
Multi-LLM Debate: Framework, Principals, and Interventions
Quantifying and Optimizing Global Faithfulness in Persona-driven Role-playing
xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token
MetaAligner: Towards Generalizable Multi-Objective Alignment of Language Models
Weak-to-Strong Search: Align Large Language Models via Searching over Small Language Models
Predicting Label Distribution from Ternary Labels
Subject-driven Text-to-Image Generation via Preference-based Reinforcement Learning
Mitigating Reward Overoptimization via Lightweight Uncertainty Estimation
Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exiting
Counterfactual PPO Enhanced Shared Reflector for LLM-based Multi-agent Collaboration
Bidirectional Recurrence for Cardiac Motion Tracking with Gaussian Process Latent Coding
I Don't Know: Explicit Modeling of Uncertainty with an [IDK] Token
Integrating Paralinguistics in Speech-Empowered Large Language Models for Natural Conversation
SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words
Unleashing Multispectral Video's Potential in Semantic Segmentation: A Semi-supervised Viewpoint and New UAV-View Benchmark
TransVIP: Speech to Speech Translation System with Voice and Isochrony Preservation
DDGS-CT: Direction-Disentangled Gaussian Splatting for Realistic Volume Rendering
Aligning Target-Aware Molecule Diffusion Models with Exact Energy Optimization
Aligner Encoders: Self-Attention Transformers Can Be Self-Transducers
Approximating the Top Eigenvector in Random Order Streams
A Pairwise Pseudo-likelihood Approach for Matrix Completion with Informative Missingness
Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation
Dissect Black Box: Interpreting for Rule-Based Explanations in Unsupervised Anomaly Detection
A Kernel Perspective on Distillation-based Collaborative Learning
Statistical and Geometrical properties of the Kernel Kullback-Leibler divergence
Fundamental Convergence Analysis of Sharpness-Aware Minimization
Learnable In-Context Vector for Visual Question Answering
Metric Space Magnitude for Evaluating the Diversity of Latent Representations
Identifiable Shared Component Analysis of Unpaired Multimodal Mixtures
One-shot Federated Learning via Synthetic Distiller-Distillate Communication
AdaNeg: Adaptive Negative Proxy Guided OOD Detection with Vision-Language Models
Understanding the Transferability of Representations via Task-Relatedness
QuanTA: Efficient High-Rank Fine-Tuning of LLMs with Quantum-Informed Tensor Adaptation
Unsupervised Anomaly Detection in The Presence of Missing Values
Geometric Analysis of Nonlinear Manifold Clustering
Enhancing Semi-Supervised Learning via Representative and Diverse Sample Selection
Revisiting Few-Shot Object Detection with Vision-Language Models
Needle In A Multimodal Haystack
Automated Label Unification for Multi-Dataset Semantic Segmentation with GNNs
Evaluation of Text-to-Video Generation Models: A Dynamics Perspective
Binary Search Tree with Distributional Predictions
Text2CAD: Generating Sequential CAD Designs from Beginner-to-Expert Level Text Prompts
Interpret Your Decision: Logical Reasoning Regularization for Generalization in Visual Classification
Extending Multi-modal Contrastive Representations
A PID Controller Approach for Adaptive Probability-dependent Gradient Decay in Model Calibration
SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priors
MQT-LLaVA: Matryoshka Query Transformer for Large Vision-Language Models
Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models
Uni-Med: A Unified Medical Generalist Foundation Model For Multi-Task Learning Via Connector-MoE
Homology Consistency Constrained Efficient Tuning for Vision-Language Models
Learning Spatially-Aware Language and Audio Embeddings
Spiking Neural Network as Adaptive Event Stream Slicer
Time Makes Space: Emergence of Place Fields in Networks Encoding Temporally Continuous Sensory Experiences
ColJailBreak: Collaborative Generation and Editing for Jailbreaking Text-to-Image Deep Generation
Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy
Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning
SLTrain: a sparse plus low rank approach for parameter and memory efficient pretraining
Improving optimal control and estimation methods adapted to the noise characteristics of the sensorimotor system
Discovering plasticity rules that organize and maintain neural circuits
Shaping the distribution of neural responses with interneurons in a recurrent circuit model
Geodesic Optimization for Predictive Shift Adaptation on EEG data
NeuroBOLT: Resting-state EEG-to-fMRI Synthesis with Multi-dimensional Feature Mapping
Decoupling Semantic Similarity from Spatial Alignment for Neural Networks.
RandNet-Parareal: a time-parallel PDE solver using Random Neural Networks
Advection Augmented Convolutional Neural Networks
Neural Pfaffians: Solving Many Many-Electron Schrödinger Equations
SfPUEL: Shape from Polarization under Unknown Environment Light
Neural Fluidic System Design and Control with Differentiable Simulation
The Implicit Bias of Heterogeneity towards Invariance: A Study of Multi-Environment Matrix Sensing
Dynamic Non-Line-of-Sight Imaging with Mamba Enforced Temporal Consistency
Physics-Informed Regularization for Domain-Agnostic Dynamical System Modeling
Learning 3D Garment Animation from Trajectories of A Piece of Cloth
A Fast Convoluted Story: Scaling Probabilistic Inference for Integer Arithmetics
Deep Learning for Computing Convergence Rates of Markov Chains
An Information Theoretic Perspective on Conformal Prediction
On the Expressive Power of Tree-Structured Probabilistic Circuits
MotionBooth: Motion-Aware Customized Text-to-Video Generation
Sketched Lanczos uncertainty score: a low-memory summary of the Fisher information
Quasi-Bayes meets Vines
Scalable Bayesian Optimization via Focalized Sparse Gaussian Processes
A Separation in Heavy-Tailed Sampling: Gaussian vs. Stable Oracles for Proximal Samplers
Scaling Continuous Latent Variable Models as Probabilistic Integral Circuits
CNCA: Toward Customizable and Natural Generation of Adversarial Camouflage for Vehicle Detectors
EigenVI: score-based variational inference with orthogonal function expansions
Microstructures and Accuracy of Graph Recall by Large Language Models
Motion Forecasting in Continuous Driving
SCaR: Refining Skill Chaining for Long-Horizon Robotic Manipulation via Dual Regularization
VidMan: Exploiting Intrinsic Dynamics from Video Diffusion Model for Effective Robot Manipulation
DeMo: Decoupling Motion Forecasting into Directional Intentions and Dynamic States
CulturePark: Boosting Cross-cultural Understanding in Large Language Models
The Elephant in the Room: Towards A Reliable Time-Series Anomaly Detection Benchmark
BoostAdapter: Improving Test-Time Adaptation via regional boostraping
Time-MMD: A New Multi-Domain Multimodal Dataset for Time Series Analysis
Are Language Models Actually Useful for Time Series Forecasting?
Structured Matrix Basis for Multivariate Time Series Forecasting with Interpretable Dynamics
Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspective
FilterNet: Harnessing Frequency Filters for Time Series Forecasting
CURE4Rec: A Benchmark for Recommendation Unlearning with Deeper Influence
A Unified Debiasing Approach for Vision-Language Models across Modalities and Tasks
Dense Connector for MLLMs
Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characters
Fairness without Harm: An Influence-Guided Active Sampling Approach
Public-data Assisted Private Stochastic Optimization: Power and Limitations
Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancy
Offline Multitask Representation Learning for Reinforcement Learning
UKnow: A Unified Knowledge Protocol with Multimodal Knowledge Graph Datasets for Reasoning and Vision-Language Pre-Training
Distributionally Robust Performative Prediction
GenWarp: Single Image to Novel Views with Semantic-Preserving Generative Warping
Physics-informed Neural Networks for Functional Differential Equations: Cylindrical Approximation and Its Convergence Guarantees
CausalChaos! Dataset for Comprehensive Causal Action Question Answering Over Longer Causal Chains Grounded in Dynamic Visual Scenes
Improving Alignment and Robustness with Short Circuiting
Perplexity-aware Correction for Robust Alignment with Noisy Preferences
Non-Asymptotic Uncertainty Quantification in High-Dimensional Learning
Diffusion Unlearning Optimization for Robust and Safe Text-to-Image Models
The State of Data Curation at NeurIPS: An Assessment of Dataset Development Practices in the Datasets and Benchmarks Track
Curvature Clues: Decoding Deep Learning Privacy with Input Loss Curvature
Self-Healing Machine Learning: A Framework for Autonomous Adaptation in Real-World Environments
Robust Conformal Prediction Using Privileged Information
WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models
FreqBlender: Enhancing DeepFake Detection by Blending Frequency Knowledge
Learning-Augmented Algorithms for the Bahncard Problem
Identifiability Analysis of Linear ODE Systems with Hidden Confounders
MOTI$\mathcal{V}\mathcal{E}$: A Drug-Target Interaction Graph For Inductive Link Prediction
Induced Model Matching: Restricted Models Help Train Full-Featured Models
MedJourney: Benchmark and Evaluation of Large Language Models over Patient Clinical Journey
Rethinking 3D Convolution in $\ell_p$-norm Space
JourneyBench: A Challenging One-Stop Vision-Language Understanding Benchmark of Generated Images
I2EBench: A Comprehensive Benchmark for Instruction-based Image Editing
FactorSim: Generative Simulation via Factorized Representation
Generative Retrieval Meets Multi-Graded Relevance
Vript: A Video Is Worth Thousands of Words
Intervention and Conditioning in Causal Bayesian Networks
DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning
Spec-Gaussian: Anisotropic View-Dependent Appearance for 3D Gaussian Splatting
CAPE: Context-Adaptive Positional Encoding for Length Extrapolation
LCGen: Mining in Low-Certainty Generation for View-consistent Text-to-3D
GVKF: Gaussian Voxel Kernel Functions for Highly Efficient Surface Reconstruction in Open Scenes
Real-time Stereo-based 3D Object Detection for Streaming Perception
Unravelling in Collaborative Learning
Multi-Object Hallucination in Vision Language Models
Noisy Dual Mirror Descent: A Near Optimal Algorithm for Jointly-DP Convex Resource Allocation
LG-CAV: Train Any Concept Activation Vector with Language Guidance
Reinforcement Learning with Euclidean Data Augmentation for State-Based Continuous Control
Iteratively Refined Behavior Regularization for Offline Reinforcement Learning
Robust Fine-tuning of Zero-shot Models via Variance Reduction
UNIT: Unifying Image and Text Recognition in One Vision Encoder
Neural Collapse Inspired Feature Alignment for Out-of-Distribution Generalization
EGODE: An Event-attended Graph ODE Framework for Modeling Rigid Dynamics
Localize, Understand, Collaborate: Semantic-Aware Dragging via Intention Reasoner
Attention Temperature Matters in ViT-Based Cross-Domain Few-Shot Learning
An Accelerated Algorithm for Stochastic Bilevel Optimization under Unbounded Smoothness
Provable Posterior Sampling with Denoising Oracles Through Tilted Transport
Trading off Consistency and Dimensionality of Convex Surrogates for Multiclass Classification
EvolveDirector: Approaching Advanced Text-to-Image Generation with Large Vision-Language Models
Automated Efficient Estimation using Monte Carlo Efficient Influence Functions
Consistency of Neural Causal Partial Identification
On the Complexity of Identification in Linear Structural Causal Models
A Simple yet Scalable Granger Causal Structural Learning from Topological Event Sequences
A Benchmark Suite for Systematically Evaluating Reasoning Shortcuts
UrbanDataLayer: A Unified Data Pipeline for Urban Science
MassSpecGym: A benchmark for the discovery and identification of molecules
DataComp-LM: In search of the next generation of training sets for language models
TorchSpatial: A Location Encoding Framework and Benchmark for Spatial Representation Learning
A Siamese Transformer with Hierarchical Refinement for Lane Detection
Instruction Tuning Large Language Models to Understand Electronic Health Records
CriticEval: Evaluating Large-scale Language Model as Critic
3DCoMPaT200: Language Grounded Large-Scale 3D Vision Dataset for Compositional Recognition
FIRE: A Dataset for Feedback Integration and Refinement Evaluation of Multimodal Models
NewTerm: Benchmarking Real-Time New Terms for Large Language Models with Annual Updates
CRAG - Comprehensive RAG Benchmark
MathPile: A Billion-Token-Scale Pretraining Corpus for Math
Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs
Lean Workbook: A large-scale Lean problem set formalized from natural language math problems
Mining and Transferring Feature-Geometry Coherence for Unsupervised Point Cloud Registration
Communication Bounds for the Distributed Experts Problem
Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models
RelBench: A Benchmark for Deep Learning on Relational Databases
WindsorML - High-Fidelity Computational Fluid Dynamics Dataset For Automotive Aerodynamics
SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset
Benchmark Repositories for Better Benchmarking
WebUOT-1M: Advancing Deep Underwater Object Tracking with A Million-Scale Benchmark
UnSeg: One Universal Unlearnable Example Generator is Enough against All Image Segmentation
Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attention
PEACE: A Dataset of Pharmaceutical Care for Cancer Pain Analgesia Evaluation and Medication Decision
Federated Learning from Vision-Language Foundation Models: Theoretical Analysis and Method
EgoSim: An Egocentric Multi-view Simulator for Body-worn Cameras during Human Motion
Algorithmic progress in language models
Leveraging Visual Tokens for Extended Text Contexts in Multi-Modal Learning
Re-assembling the past: The RePAIR dataset and benchmark for real world 2D and 3D puzzle solving
UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling
F-OAL: Foward-only Online Analytic Learning with Fast Training and Low Memory Footprint in Class Incremental Learning
HARMONIC: Harnessing LLMs for Tabular Data Synthesis and Privacy Protection
LucidAction: A Hierarchical and Multi-model Dataset for Comprehensive Action Quality Assessment
A New Multi-Source Light Detection Benchmark and Semi-Supervised Focal Light Detection
EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations
Rethinking the Evaluation of Out-of-Distribution Detection: A Sorites Paradox
The Many Faces of Optimal Weak-to-Strong Learning
ChaosBench: A Multi-Channel, Physics-Based Benchmark for Subseasonal-to-Seasonal Climate Prediction
MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs
Personalized Instance-based Navigation Toward User-Specific Objects in Realistic Environments
LLMCBench: Benchmarking Large Language Model Compression for Efficient Deployment
On the Effects of Data Scale on Computer Control Agents
Paloma: A Benchmark for Evaluating Language Model Fit
Efficient Lifelong Model Evaluation in an Era of Rapid Progress
Fair Kernel K-Means: from Single Kernel towards Multiple Kernel
A Closer Look at AUROC and AUPRC under Class Imbalance
ConvBench: A Multi-Turn Conversation Evaluation Benchmark with Hierarchical Ablation Capability for Large Vision-Language Models
Fairness in Social Influence Maximization via Optimal Transport
Fair Wasserstein Coresets
Scale-invariant Optimal Sampling for Rare-events Data and Sparse Models
OnlineTAS: An Online Baseline for Temporal Action Segmentation
PAC-Bayes-Chernoff bounds for unbounded losses
Nearly Minimax Optimal Regret for Multinomial Logistic Bandit
Compositional PAC-Bayes: Generalization of GNNs with persistence and beyond
On the Sparsity of the Strong Lottery Ticket Hypothesis
Controlling Multiple Errors Simultaneously with a PAC-Bayes Bound
Achieving $\tilde{O}(1/\epsilon)$ Sample Complexity for Constrained Markov Decision Process
A provable control of sensitivity of neural networks through a direct parameterization of the overall bi-Lipschitzness
Global Rewards in Restless Multi-Armed Bandits
Neural Residual Diffusion Models for Deep Scalable Vision Generation
A Theory of Optimistically Universal Online Learnability for General Concept Classes
G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering
Stabilizing Linear Passive-Aggressive Online Learning with Weighted Reservoir Sampling
Learning to Price Homogeneous Data
A Best-of-both-worlds Algorithm for Bandits with Delayed Feedback with Robustness to Excessive Delays
GACL: Exemplar-Free Generalized Analytic Continual Learning
Contextual Active Model Selection
A Continuous-time Stochastic Gradient Descent Method for Continuous Data
Emergence of heavy tails in homogenized stochastic gradient descent
SCAFFLSA: Taming Heterogeneity in Federated Linear Stochastic Approximation and TD Learning
Revisiting Adversarial Patches for Designing Camera-Agnostic Attacks against Person Detection
LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning
Adaptive and Optimal Second-order Optimistic Methods for Minimax Optimization
Geometry-aware training of factorized layers in tensor Tucker format
Optimizing over Multiple Distributions under Generalized Quasar-Convexity Condition
GLinSAT: The General Linear Satisfiability Neural Network Layer By Accelerated Gradient Descent
The Iterative Optimal Brain Surgeon: Faster Sparse Recovery by Leveraging Second-Order Information
TSGM: A Flexible Framework for Generative Modeling of Synthetic Time Series
Prejudice and Volatility: A Statistical Framework for Measuring Social Discrimination in Large Language Models
TorchOpt: An Efficient Library for Differentiable Optimization
ALPS: Improved Optimization for Highly Sparse One-Shot Pruning for Large Language Models
Decision Mamba: A Multi-Grained State Space Model with Self-Evolution Regularization for Offline RL
RefDrop: Controllable Consistency in Image or Video Generation via Reference Feature Guidance
Practical $0.385$-Approximation for Submodular Maximization Subject to a Cardinality Constraint
Marginalized Hamiltonian Monte Carlo for Linear Mixed-Effects Models
Byzantine Robustness and Partial Participation Can Be Achieved at Once: Just Clip Gradient Differences
On the Optimal Time Complexities in Decentralized Stochastic Asynchronous Optimization
Hierarchical Federated Learning with Multi-Timescale Gradient Correction
Weight for Robustness: A Comprehensive Approach towards Optimal Fault-Tolerant Asynchronous ML
Safe and Efficient: A Primal-Dual Method for Offline Convex CMDPs under Partial Data Coverage
Communication Efficient Distributed Training with Distributed Lion
Separation and Bias of Deep Equilibrium Models on Expressivity and Learning Dynamics
Unlocking the Capabilities of Masked Generative Models for Image Synthesis via Self-Guidance
HyperPrism: An Adaptive Non-linear Aggregation Framework for Distributed Machine Learning over Non-IID Data and Time-varying Communication Links
Performative Control for Linear Dynamical Systems
Free-Rider and Conflict Aware Collaboration Formation for Cross-Silo Federated Learning
Boosting Semi-Supervised Scene Text Recognition via Viewing and Summarizing
DistrictNet: Decision-aware learning for geographical districting
Delving into the Reversal Curse: How Far Can Large Language Models Generalize?
Non-geodesically-convex optimization in the Wasserstein space
Adaptive Variance Reduction for Stochastic Optimization under Weaker Assumptions
Drago: Primal-Dual Coupled Variance Reduction for Faster Distributionally Robust Optimization
Federated Behavioural Planes: Explaining the Evolution of Client Behaviour in Federated Learning
Auditing Privacy Mechanisms via Label Inference Attacks
The Limits of Differential Privacy in Online Learning
Human-Readable Fingerprint for Large Language Models
Differentially Private Graph Diffusion with Applications in Personalized PageRanks
Faster Algorithms for User-Level Private Stochastic Convex Optimization
RAGraph: A General Retrieval-Augmented Graph Learning Framework
Dimension-free Private Mean Estimation for Anisotropic Distributions
Tri-Level Navigator: LLM-Empowered Tri-Level Learning for Time Series OOD Generalization
In-N-Out: Lifting 2D Diffusion Prior for 3D Object Removal via Tuning-Free Latents Alignment
Zero-Shot Reinforcement Learning from Low Quality Data
Adversarial Environment Design via Regret-Guided Diffusion Models
Boundary Decomposition for Nadir Objective Vector Estimation
Solving Minimum-Cost Reach Avoid using Reinforcement Learning
Near-Optimal Dynamic Regret for Adversarial Linear Mixture MDPs
AdaSociety: An Adaptive Environment with Social Structures for Multi-Agent Decision-Making
Aligning Individual and Collective Objectives in Multi-Agent Cooperation
Perception of Knowledge Boundary for Large Language Models through Semi-open-ended Question Answering
The Dormant Neuron Phenomenon in Multi-Agent Reinforcement Learning Value Factorization
Understanding Generalizability of Diffusion Models Requires Rethinking the Hidden Gaussian Structure
Feint Behaviors and Strategies: Formalization, Implementation and Evaluation
Value-Based Deep Multi-Agent Reinforcement Learning with Dynamic Sparse Training
Boosting Sample Efficiency and Generalization in Multi-agent Reinforcement Learning via Equivariance
Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement Learning
Multi-Agent Imitation Learning: Value is Easy, Regret is Hard
What type of inference is planning?
Goal Reduction with Loop-Removal Accelerates RL and Models Human Brain Activity in Goal-Directed Learning
Identifying Latent State-Transition Processes for Individualized Reinforcement Learning
Seek Commonality but Preserve Differences: Dissected Dynamics Modeling for Multi-modal Visual RL
FinBen: An Holistic Financial Benchmark for Large Language Models
SDformer: Similarity-driven Discrete Transformer For Time Series Generation
Incremental Learning of Retrievable Skills For Efficient Continual Task Adaptation
DePLM: Denoising Protein Language Models for Property Optimization
Infusing Self-Consistency into Quantum Hamiltonian Prediction via Deep Equilibrium Models
UDA: A Benchmark Suite for Retrieval Augmented Generation in Real-World Document Analysis
Mixture of In-Context Experts Enhance LLMs' Long Context Awareness
Generalizablity of Memorization Neural Network
Accurate and Steady Inertial Pose Estimation through Sequence Structure Learning and Modulation
Constant Acceleration Flow
Slack-Free Spiking Neural Network Formulation for Hypergraph Minimum Vertex Cover
Exploring Context Window of Large Language Models via Decomposed Positional Vectors
DCDepth: Progressive Monocular Depth Estimation in Discrete Cosine Domain
REBEL: Reinforcement Learning via Regressing Relative Rewards
Nonparametric Regression for 3D Point Cloud Learning
Conformal Classification with Equalized Coverage for Adaptively Selected Groups
Verifiably Robust Conformal Prediction
Attention boosted Individualized Regression
Multi-view Masked Contrastive Representation Learning for Endoscopic Video Analysis
MediQ: Question-Asking LLMs for Adaptive and Reliable Medical Reasoning
Using Surrogates in Covariate-adjusted Response-adaptive Randomization Experiments with Delayed Outcomes
Generalized Tensor Decomposition for Understanding Multi-Output Regression under Combinatorial Shifts
Generalize or Detect? Towards Robust Semantic Segmentation Under Multiple Distribution Shifts
DapperFL: Domain Adaptive Federated Learning with Model Fusion Pruning for Edge Devices
LFME: A Simple Framework for Learning from Multiple Experts in Domain Generalization
LaSCal: Label-Shift Calibration without target labels
Swap Regret, Symmetry, and Nash Convergence in Games
Learning Versatile Skills with Curriculum Masking
ChatCam: Empowering Camera Control through Conversational AI
Bayesian Strategic Classification
Learning the Expected Core of Strictly Convex Stochastic Cooperative Games
Carrot and Stick: Eliciting Comparison Data and Beyond
Learning to Mitigate Externalities: the Coase Theorem with Hindsight Rationality
Symmetries in Overparametrized Neural Networks: A Mean Field View
SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Models
Learning General Parameterized Policies for Infinite Horizon Average Reward Constrained MDPs via Primal-Dual Policy Gradient Algorithm
Randomized Exploration for Reinforcement Learning with Multinomial Logistic Function Approximation
Offline Oracle-Efficient Learning for Contextual MDPs via Layerwise Exploration-Exploitation Tradeoff
Truncated Variance Reduced Value Iteration
Preference-based Pure Exploration
Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling Paradox
Hybrid Reinforcement Learning Breaks Sample Size Barriers In Linear MDPs
Dissecting the Interplay of Attention Paths in a Statistical Mechanics Theory of Transformers
NeuralPlane: An Efficiently Parallelizable Platform for Fixed-wing Aircraft Control with Reinforcement Learning
A Novel Benchmark for Decision-Making in Uncertain and Competitive Games
There is No Silver Bullet: Benchmarking Methods in Predictive Combinatorial Optimization
DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception
ProbTS: Benchmarking Point and Distributional Forecasting across Diverse Prediction Horizons
Consistency Models for Scalable and Fast Simulation-Based Inference
Mimicking To Dominate: Imitation Learning Strategies for Success in Multiagent Games
Can LLMs Learn by Teaching? A Preliminary Study
Weight Diffusion for Future: Learn to Generalize in Non-Stationary Environments
BAdam: A Memory Efficient Full Parameter Optimization Method for Large Language Models
A Global Depth-Range-Free Multi-View Stereo Transformer Network with Pose Embedding
ETO:Efficient Transformer-based Local Feature Matching by Organizing Multiple Homography Hypotheses
FlexSBDD: Structure-Based Drug Design with Flexible Protein Modeling
Handling Learnwares from Heterogeneous Feature Spaces with Explicit Label Exploitation
Epipolar-Free 3D Gaussian Splatting for Generalizable Novel View Synthesis
Provably and Practically Efficient Adversarial Imitation Learning with General Function Approximation
On the Parameter Identifiability of Partially Observed Linear Causal Models
SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation
Injecting Undetectable Backdoors in Deep Learning and Language Models
Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs
From Text to Trajectory: Exploring Unified Complex Constraint Representation and Decomposition in Safe Reinforcement Learning
GraphCroc: Cross-Correlation Autoencoder for Graph Structural Reconstruction
AUC Maximization under Positive Distribution Shift
HiCoM: Hierarchical Coherent Motion for Dynamic Streamable Scenes with 3D Gaussian Splatting
Enhancing LLM Reasoning via Vision-Augmented Prompting
Decomposable Transformer Point Processes
Visual Pinwheel Center Act as Geometric Saliency Detector
Connectivity-Driven Pseudo-Labeling Makes Stronger Cross-Domain Segmenters
PageRank Bandits for Link Prediction
ALPINE: Unveiling The Planning Capability of Autoregressive Learning in Language Models
Hybrid Mamba for Few-Shot Segmentation
Neural Persistence Dynamics
X-Ray: A Sequential 3D Representation For Generation
Gliding over the Pareto Front with Uniform Designs
AdaPKC: PeakConv with Adaptive Peak Receptive Field for Radar Semantic Segmentation
GITA: Graph to Visual and Textual Integration for Vision-Language Graph Reasoning
Non-asymptotic Global Convergence Analysis of BFGS with the Armijo-Wolfe Line Search
Neural Flow Diffusion Models: Learnable Forward Process for Improved Diffusion Modelling
Learning-Augmented Approximation Algorithms for Maximization Problems
EEGPT: Pretrained Transformer for Universal and Reliable Representation of EEG Signals
TurboHopp: Accelerated Molecule Scaffold Hopping with Consistency Models
DeTrack: In-model Latent Denoising Learning for Visual Object Tracking
Large Language Models Play StarCraft II:Benchmarks and A Chain of Summarization Approach
S-SOS: Stochastic Sum-Of-Squares for Parametric Polynomial Optimization
Similarity-Navigated Conformal Prediction for Graph Neural Networks
Unlock the Intermittent Control Ability of Model Free Reinforcement Learning
PIVOT-R: Primitive-Driven Waypoint-Aware World Model for Robotic Manipulation
MimicTalk: Mimicking a personalized and expressive 3D talking face in minutes
KptLLM: Unveiling the Power of Large Language Model for Keypoint Comprehension
On the Target-kernel Alignment: a Unified Analysis with Kernel Complexity
Frozen-DETR: Enhancing DETR with Image Understanding from Frozen Foundation Models
A Bayesian Approach for Personalized Federated Learning in Heterogeneous Settings
Language Without Borders: A Dataset and Benchmark for Code-Switching Lip Reading
Credit Attribution and Stable Compression
QUEST: Quadruple Multimodal Contrastive Learning with Constraints and Self-Penalization
Shuffling Gradient-Based Methods for Nonconvex-Concave Minimax Optimization
Cooperative Hardware-Prompt Learning for Snapshot Compressive Imaging
Minimum Entropy Coupling with Bottleneck
Cronos: Enhancing Deep Learning with Scalable GPU Accelerated Convex Neural Networks
Density-based User Representation using Gaussian Process Regression for Multi-interest Personalized Retrieval
Validating Climate Models with Spherical Convolutional Wasserstein Distance
Online Budgeted Matching with General Bids
Trajectory Data Suffices for Statistically Efficient Learning in Offline RL with Linear $q^\pi$-Realizability and Concentrability
High-dimensional (Group) Adversarial Training in Linear Regression
4Diffusion: Multi-view Video Diffusion Model for 4D Generation
Controlling Counterfactual Harm in Decision Support Systems Based on Prediction Sets
Scaling Laws in Linear Regression: Compute, Parameters, and Data
Identifying Causal Effects Under Functional Dependencies
Counter-Current Learning: A Biologically Plausible Dual Network Approach for Deep Learning
A structure-aware framework for learning device placements on computation graphs
SR-CACO-2: A Dataset for Confocal Fluorescence Microscopy Image Super-Resolution
GS-Hider: Hiding Messages into 3D Gaussian Splatting
Sample Complexity of Posted Pricing for a Single Item
A Flexible, Equivariant Framework for Subgraph GNNs via Graph Products and Graph Coarsening
Conformalized Multiple Testing after Data-dependent Selection
Separations in the Representational Capabilities of Transformers and Recurrent Architectures
Eye-gaze Guided Multi-modal Alignment for Medical Representation Learning
Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks
The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale
CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models
GC-Bench: An Open and Unified Benchmark for Graph Condensation
STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases
Locating What You Need: Towards Adapting Diffusion Models to OOD Concepts In-the-Wild
Causal Bandits for Linear Structural Equation Models
OpenGaussian: Towards Point-Level 3D Gaussian-based Open Vocabulary Understanding
Neural P$^3$M: A Long-Range Interaction Modeling Enhancer for Geometric GNNs
GENOT: A Neural Optimal Transport Framework for Single Cell Genomics
Almost-Linear RNNs Yield Highly Interpretable Symbolic Codes in Dynamical Systems Reconstruction
Voxel Proposal Network via Multi-Frame Knowledge Distillation for Semantic Scene Completion
The Representation Landscape of Few-Shot Learning and Fine-Tuning in Large Language Models
RSA: Resolving Scale Ambiguities in Monocular Depth Estimators through Language Descriptions
CE-NAS: An End-to-End Carbon-Efficient Neural Architecture Search Framework
Iteratively Refined Early Interaction Alignment for Subgraph Matching based Graph Retrieval
Verified Code Transpilation with LLMs
AdaptiveISP: Learning an Adaptive Image Signal Processor for Object Detection
Statistical Multicriteria Benchmarking via the GSD-Front
Panacea: Pareto Alignment via Preference Adaptation for LLMs
Breaking the curse of dimensionality in structured density estimation
Large Stepsize Gradient Descent for Non-Homogeneous Two-Layer Networks: Margin Improvement and Fast Optimization
SpeechForensics: Audio-Visual Speech Representation Learning for Face Forgery Detection
Deterministic Policies for Constrained Reinforcement Learning in Polynomial-Time
Monte Carlo Tree Search based Space Transfer for Black Box Optimization
Prompt Tuning Strikes Back: Customizing Foundation Models with Low-Rank Prompt Adaptation
No Free Lunch Theorem and Black-Box Complexity Analysis for Adversarial Optimisation
Partial observation can induce mechanistic mismatches in data-constrained models of neural dynamics
Mitigating Biases in Blackbox Feature Extractors for Image Classification Tasks
Neural Network Reparametrization for Accelerated Optimization in Molecular Simulations
Federated Natural Policy Gradient and Actor Critic Methods for Multi-task Reinforcement Learning
Stabilizing Zero-Shot Prediction: A Novel Antidote to Forgetting in Continual Vision-Language Tasks
FAST: A Dual-tier Few-Shot Learning Paradigm for Whole Slide Image Classification
Molecule Generation with Fragment Retrieval Augmentation
GTSinger: A Global Multi-Technique Singing Corpus with Realistic Music Scores for All Singing Tasks
II-Bench: An Image Implication Understanding Benchmark for Multimodal Large Language Models
Job-SDF: A Multi-Granularity Dataset for Job Skill Demand Forecasting and Benchmarking
Benchmarking LLMs via Uncertainty Quantification
ShareGPT4Video: Improving Video Understanding and Generation with Better Captions
RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Content
An Analysis of Robustness of Non-Lipschitz Networks
Controlling Continuous Relaxation for Combinatorial Optimization
Robust and Faster Zeroth-order Minimax Optimization: Complexity and Applications
Graph Classification via Reference Distribution Learning: Theory and Practice
Reranking Laws for Language Generation: A Communication-Theoretic Perspective
Scribbles for All: Benchmarking Scribble Supervised Segmentation Across Datasets
Ferrari: Federated Feature Unlearning via Optimizing Feature Sensitivity
Derivatives of Stochastic Gradient Descent
Segmenting Watermarked Texts From Language Models
WeiPer: OOD Detection using Weight Perturbations of Class Projections
Enhancing Preference-based Linear Bandits via Human Response Time
Ctrl-X: Controlling Structure and Appearance for Text-To-Image Generation Without Guidance
Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making
Resolving Discrepancies in Compute-Optimal Scaling of Language Models
Association of Objects May Engender Stereotypes: Mitigating Association-Engendered Stereotypes in Text-to-Image Generation
BECAUSE: Bilinear Causal Representation for Generalizable Offline Model-based Reinforcement Learning
OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning
DiffLight: A Partial Rewards Conditioned Diffusion Model for Traffic Signal Control with Missing Data
ODGEN: Domain-specific Object Detection Data Generation with Diffusion Models
No Filter: Towards Cultural and Socioeconomic Diversity in Multimodal Systems
Fractal Patterns May Illuminate the Success of Next-Token Prediction
DiffuLT: Diffusion for Long-tail Recognition Without External Knowledge
DDN: Dual-domain Dynamic Normalization for Non-stationary Time Series Forecasting
An Any-to-Any Vision Model for Tens of Tasks and Modalities
Continuous Partitioning for Graph-Based Semi-Supervised Learning
Energy-efficient Reinforcement Learning by Discovering Neural Pathways
Achievable Fairness on Your Data With Utility Guarantees
Multi-turn Reinforcement Learning with Preference Human Feedback
Boosting the Transferability of Adversarial Attack on Vision Transformer with Adaptive Token Tuning
Enhancing Domain Adaptation through Prompt Gradient Alignment
SLICE-100K: A Multimodal Dataset for Extrusion-based 3D Printing
Achievable distributional robustness when the robust risk is only partially identified
A Generative Model of Symmetry Transformations
Unified Mechanism-Specific Amplification by Subsampling and Group Privacy Amplification
$\textit{Trans-LoRA}$: towards data-free Transferable Parameter Efficient Finetuning
xLSTM: Extended Long Short-Term Memory
Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum
Label Alignment Regularization for Distribution Shift
Identifying spatio-temporal relations between anomalies and extreme events
"Studying How to Efficiently and Effectively Guide Models with Explanations" - A Reproducibility Study
T2Vs Meet VLMs: A Scalable Multimodal Dataset for Visual Harmfulness Recognition
On the Implicit Bias of Predicting in Latent Space in Self Supervised Learning
Confident Natural Policy Gradient for Local Planning in $q_\pi$-realizable Constrained MDPs
Model Based Inference of Synaptic Plasticity Rules
StepbaQ: Stepping backward as Correction for Quantized Diffusion Models
e-COP : Episodic Constrained Optimization of Policies
User-Creator Feature Dynamics in Recommender Systems with Dual Influence
How Control Information Influences Multilingual Text Image Generation and Editing?
InterControl: Zero-shot Human Interaction Generation by Controlling Every Joint
HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation
Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability
Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes
Model Decides How to Tokenize: Adaptive DNA Sequence Tokenization with MxDNA
ActSort: An active-learning accelerated cell sorting algorithm for large-scale calcium imaging datasets
Streaming Detection of Queried Event Start
The iNaturalist Sounds Dataset
Towards Harmless Rawlsian Fairness Regardless of Demographic Prior
What can Foundation Models’ Embeddings do?
Yo'LLaVA: Your Personalized Language and Vision Assistant
One-Shot Safety Alignment for Large Language Models via Optimal Dualization
How does Gradient Descent Learn Features --- A Local Analysis for Regularized Two-Layer Neural Networks
Diffusion PID: Interpreting Diffusion via Partial Information Decomposition
A Non-parametric Direct Learning Approach to Heterogeneous Treatment Effect Estimation under Unmeasured Confounding
Exploration by Learning Diverse Skills through Successor State Measures
A Cross-Domain Benchmark for Active Learning
The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models
TabularBench: Benchmarking Adversarial Robustness for Tabular Deep Learning in Real-world Use-cases
Pedestrian Trajectory Prediction with Missing Data: Datasets, Imputation, and Benchmarking
Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation?
PINNacle: A Comprehensive Benchmark of Physics-Informed Neural Networks for Solving PDEs
MedSafetyBench: Evaluating and Improving the Medical Safety of Large Language Models
Text-space Graph Foundation Models: Comprehensive Benchmarks and New Insights
Value Imprint: A Technique for Auditing the Human Values Embedded in RLHF Datasets
BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices
PutnamBench: Evaluating Neural Theorem-Provers on the Putnam Mathematical Competition
Brain Treebank: Large-scale intracranial recordings from naturalistic language stimuli
What to Say and When to Say it: Live Fitness Coaching as a Testbed for Situated Interaction
FlexMol: A Flexible Toolkit for Benchmarking Molecular Relational Learning
MARVEL: Multidimensional Abstraction and Reasoning through Visual Evaluation and Learning
ProG: A Graph Prompt Learning Benchmark
A Benchmark Suite for Evaluating Neural Mutual Information Estimators on Unstructured Datasets
Unraveling Molecular Structure: A Multimodal Spectroscopic Dataset for Chemistry
Reliable Learning of Halfspaces under Gaussian Marginals
Computation Tree: A Transferable Pattern Towards Graph Foundation Models
Regularized Conditional Diffusion Model for Multi-Task Preference Alignment
ANT: Adaptive Noise Schedule for Time Series Diffusion Models
CompBench: A Comparative Reasoning Benchmark for Multimodal LLMs
You Only Cache Once: Decoder-Decoder Architectures for Language Models
M3LEO: A Multi-Modal, Multi-Label Earth Observation Dataset Integrating Interferometric SAR and RGB Data
ProtGO: Function-Guided Protein Modeling for Unified Representation Learning
Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer
Exploring Fixed Point in Image Editing: Theoretical Support and Convergence Optimization
Optimal Scalarizations for Sublinear Hypervolume Regret
BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack
Geometry Awakening: Cross-Geometry Learning Exhibits Superiority over Individual Structures
Geometric-Averaged Preference Optimization for Soft Preference Labels
On the Impact of Feature Heterophily on Link Prediction with Graph Neural Networks
BIOSCAN-5M: A Multimodal Dataset for Insect Biodiversity
GenAI Arena: An Open Evaluation Platform for Generative Models
Private Edge Density Estimation for Random Graphs: Optimal, Efficient and Robust
A Near-optimal Algorithm for Learning Margin Halfspaces with Massart Noise
On Learning Physical Neural Representations of Dynamical Data
Continual Learning with Global Alignment
APIGen: Automated PIpeline for Generating Verifiable and Diverse Function-Calling Datasets
Learning Complete Protein Representation by Dynamically Coupling of Sequence and Structure
Efficient Multi-modal Models via Stage-wise Visual Context Compression
The Fragility of Fairness: Causal Sensitivity Analysis for Fair Machine Learning
Transfer Learning for Diffusion Models
Semi-Truths: A Large-Scale Dataset for Testing Robustness of AI-Generated Image Detectors
Slot-VLM: Object-Event Slots for Video-Language Modeling
CALVIN: Improved Contextual Video Captioning via Instruction Tuning
Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizes
Prediction-Powered Ranking of Large Language Models
Human 3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion Models
Utilizing Human Behavior Modeling to Manipulate Explanations in AI-Assisted Decision Making: The Good, the Bad, and the Ugly
Asynchronous Perception Machine for Test Time Training
Optimal Multiclass U-Calibration Error and Beyond
Exploring the Role of Large Language Models in Prompt Encoding for Diffusion Models
Untrained Neural Nets for Snapshot Compressive Imaging: Theory and Algorithms
DeltaDEQ: Exploiting Heterogeneous Convergence for Accelerating Deep Equilibrium Iterations
Graph neural networks and non-commuting operators
Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
Multiclass Transductive Online Learning
Beyond the Doors of Perception: Vision Transformers Represent Relations Between Objects
Replicability in Learning: Geometric Partitions and KKM-Sperner Lemma
Evaluating the design space of diffusion-based generative models
Knowledge-Empowered Dynamic Graph Network for Irregularly Sampled Medical Time Series
When to Sense and Control? A Time-adaptive Approach for Continuous-Time RL
Disentangling Interpretable Factors of Variations with Supervised Independent Subspace Principal Component Analysis
4D Gaussian Splatting in the Wild with Uncertainty-Aware Regularization
Stochastic Optimization Algorithms for Instrumental Variable Regression with Streaming Data
Contrastive-Equivariant Self-Supervised Learning Improves Alignment with Primate Visual Area IT
On the cohesion and separability of average-link for hierarchical agglomerative clustering
BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts
Reproducibility Study of "Learning Perturbations to Explain Time Series Predictions"
Locally Private and Robust Multi-Armed Bandits
A Unifying Normative Framework of Decision Confidence
Reward Machines for Deep RL in Noisy and Uncertain Environments
Universal Exact Compression of Differentially Private Mechanisms
Enhancing Robustness of Last Layer Two-Stage Fair Model Corrections
Bayesian Online Natural Gradient (BONG)
Preference Alignment with Flow Matching
DeepITE: Designing Variational Graph Autoencoders for Intervention Target Estimation
Reproducibility Study of "Robust Fair Clustering: A Novel Fairness Attack and Defense Framework"
Masked Hard-Attention Transformers Recognize Exactly the Star-Free Languages
Efficient Prompt Optimization Through the Lens of Best Arm Identification
A Method for Evaluating Hyperparameter Sensitivity in Reinforcement Learning
GL-NeRF: Gauss-Laguerre Quadrature Enables Training-Free NeRF Acceleration
On the Convergence of Loss and Uncertainty-based Active Learning Algorithms
Discrete Flow Matching
FRHOzen: Loss-Based Data Selection for Targeted Language Model Pre-training
Continuous Heatmap Regression for Pose Estimation via Implicit Neural Representation
Scientific Consistency Improves upon Multi-Task Learning in Molecular Science
Compressive Sensing with Sparsity Inducing Conditionally Gaussian Generative Models
Learning the Infinitesimal Generator of Stochastic Diffusion Processes
Learning Image Priors Through Patch-Based Diffusion Models for Solving Inverse Problems
Approximating mutual information of high-dimensional variables using learned representations
Theoretical Analysis of Weak-to-Strong Generalization
Finding good policies in average-reward Markov Decision Processes without prior knowledge
Blind Image Restoration via Fast Diffusion Inversion
Tackling Uncertain Correspondences for Multi-Modal Entity Alignment
Learning via Surrogate PAC-Bayes
Sigmoid Gating is More Sample Efficient than Softmax Gating in Mixture of Experts
Provable Editing of Deep Neural Networks using Parametric Linear Relaxation
SAMPa: Sharpness-aware Minimization Parallelized
Piecewise deterministic generative models
Exploiting LLM Quantization
Lower Bounds and Optimal Algorithms for Non-Smooth Convex Decentralized Optimization over Time-Varying Networks
Teach Better or Show Smarter? On Instructions and Exemplars in Automatic Prompt Optimization
DMesh: A Differentiable Mesh Representation
NeuralThink: Learning Algorithms For Consistent and Efficient Extrapolation Across General Tasks
A Foundation Model for Zero-shot Logical Query Reasoning
Sim-to-Real Transfer Can Make Naive Exploration Efficient in Reinforcement Learning
Semantic Routing via Autoregressive Modeling
Even Sparser Graph Transformers
Score-based generative models are provably robust: an uncertainty quantification perspective
Learning Representations for Hierarchies with Minimal Support
RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance
On Neural Networks as Infinite Tree-Structured Probabilistic Graphical Models
Towards Fast Exact Conformalization of Generalized Parametric Estimation
Model-Based Transfer Learning for Contextual Reinforcement Learning
Fast Sampling via Discrete Non-Markov Diffusion Models
Fearless Stochasticity in Expectation Propagation
BackTime: Backdoor Attacks on Multivariate Time Series Forecasting
Data-Driven Discovery of Dynamical Systems in Pharmacology using Large Language Models
Proportional Fairness in Clustering: A Social Choice Perspective
Rethinking LLM Memorization through the Lens of Adversarial Compression
QBB: Quantization with Binary Bases for LLMs
ProvNeRF: Modeling per Point Provenance in NeRFs as a Stochastic Process
Why the Metric Backbone Preserves Community Structure
Rejection via Learning Density Ratios
Bayesian Optimization of Functions over Node Subsets in Graphs
ALS: Adaptive Layer Sparsity for Large Language Models via Activation Correlation Assessment
VLG-CBM: Training Concept Bottleneck Models with Vision-Language Guidance
Distribution Guidance Network for Weakly Supervised Point Cloud Semantic Segmentation
EfficientCAPER: An End-to-End Framework for Fast and Robust Category-Level Articulated Object Pose Estimation
Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models
RL-GPT: Integrating Reinforcement Learning and Code-as-policy
Near-Minimax-Optimal Distributional Reinforcement Learning with a Generative Model
Seeing Beyond the Crop: Using Language Priors for Out-of-Bounding Box Keypoint Prediction
Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models
RA-PbRL: Provably Efficient Risk-Aware Preference-Based Reinforcement Learning
NeuroGauss4D-PCI: 4D Neural Fields and Gaussian Deformation Fields for Point Cloud Interpolation
Semantic Density: Uncertainty Quantification in Semantic Space for Large Language Models
SpatialRGPT: Grounded Spatial Reasoning in Vision-Language Models
PowerPM: Foundation Model for Power Systems
Mind the Graph When Balancing Data for Fairness or Robustness
Explicit Eigenvalue Reguralization Improves Sharpness-Aware Minimization
Modeling Latent Neural Dynamics with Gaussian Process Switching Linear Dynamical Systems
Large language model validity via enhanced conformal prediction methods
Dealing with Synthetic Data Contamination in Online Continual Learning
Causal Temporal Representation Learning with Nonstationary Sparse Transition
DiffuBox: Refining 3D Object Detection with Point Diffusion
Training-Free Visual Prompt Learning for Multimodal Large Language Models
Variance estimation for compound decisions
SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents
WaterMax: breaking the LLM watermark detectability-robustness-quality trade-off
PEAC: Unsupervised Pre-training for Cross-Embodiment Reinforcement Learning
ReLU Characteristic Activation Analysis
Estimating the Hallucination Rate of Generative AI
Perceptual Fairness in Image Restoration
Emu3D: Text-to-Mesh Generation with High-Quality Geometry, Texture, and PBR Materials
Meta-Controller: Few-Shot Imitation of Unseen Embodiments and Tasks in Continuous Control
Structured flexibility in recurrent neural networks via neuromodulation
Building a stable classifier with the inflated argmax
No-regret Learning in Harmonic Games: Extrapolation in the Face of Conflicting Interests
Online Classification with Predictions
Local and Adaptive Mirror Descents in Extensive-Form Games
From Similarity to Superiority: Channel Clustering for Time Series Forecasting
Robust Offline Active Learning on Graphs
Memory-Efficient Gradient Unrolling for Large-Scale Bi-level Optimization
RETR: Multi-View Radar Detection Transformer for Indoor Perception
PhyloGen: Language Model-Enhanced Phylogenetic Inference via Graph Structure Generation
Probing Social Bias in Labor Market Text Generation by ChatGPT: A Masked Language Model Approach
Adversarially Robust Dense-Sparse Tradeoffs via Heavy-Hitters
Humanoid Locomotion as Next Token Prediction
Universal In-Context Approximation By Prompting Fully Recurrent Models
Learning Disentangled Representations for Perceptual Point Cloud Quality Assessment via Mutual Information Minimization
Aligning Diffusion Models by Optimizing Human Utility
Adaptive Preference Scaling for Reinforcement Learning with Human Feedback
Ex Uno Pluria: Insights on Ensembling in Low Precision Number Systems
HOI-Swap: Swapping Objects in Videos with Hand-Object Interaction Awareness
MeshXL: Neural Coordinate Field for Generative 3D Foundation Models
MiSO: Optimizing brain stimulation to create neural activity states
Sample Selection via Contrastive Fragmentation for Noisy Label Regression
Differentiable Quantum Computing for Large-scale Linear Control
Confusion-Resistant Federated Learning via Diffusion-Based Data Harmonization on Non-IID Data
DiffTOP: Differentiable Trajectory Optimization for Deep Reinforcement and Imitation Learning
SlimGPT: Layer-wise Structured Pruning for Large Language Models
Linguistic Collapse: Neural Collapse in (Large) Language Models
Improving Gloss-free Sign Language Translation by Reducing Representation Density
Federated Transformer: Scalable Vertical Federated Learning on Practical Fuzzily Linked Data
Hierarchical Programmatic Option Framework for Solving Long and Repetitive Tasks
The Power of Hard Attention Transformers on Data Sequences: A formal language theoretic perspective
Probing the Decision Boundaries of In-context Learning in Large Language Models
Integrating Suboptimal Human Knowledge with Hierarchical Reinforcement Learning for Large-Scale Multiagent Systems
Stacking Your Transformers: A Closer Look at Model Growth for Efficient LLM Pre-Training
PTQ4DiT: Post-training Quantization for Diffusion Transformers
Conditioning non-linear and infinite-dimensional diffusion processes
Smoothed Online Classification can be Harder than Batch Classification
On Affine Homotopy between Language Encoders
Meta-Diffu$B$: A Contextualized Sequence-to-Sequence Text Diffusion Model with Meta-Exploration
GuardT2I: Defending Text-to-Image Models from Adversarial Prompts
Why Warmup the Learning Rate? Underlying Mechanisms and Improvements
Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization
Towards a theory of how the structure of language is acquired by deep neural networks
Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts
Non-asymptotic Convergence of Training Transformers for Next-token Prediction
Single-loop Stochastic Algorithms for Difference of Max-Structured Weakly Convex Functions
A Closer Look at Deep Learning Phenomena Through A Telescoping Lens
Provably Efficient Interactive-Grounded Learning with Personalized Reward
Leveraging an ECG Beat Diffusion Model for Morphological Reconstruction from Indirect Signals
Elliptical Attention
Occupancy-based Policy Gradient: Estimation, Convergence, and Optimality
GaussianCut: Interactive segmentation via graph cut for 3D Gaussian Splatting
Remove that Square Root: A New Efficient Scale-Invariant Version of AdaGrad
Matching the Statistical Query Lower Bound for $k$-Sparse Parity Problems with Stochastic Gradient Descent
Pseudo-Siamese Directional Transformers for Self-Supervised Real-World Denoising
GDeR: Safeguarding Efficiency, Balancing, and Robustness via Prototypical Graph Pruning
On Socially Fair Low-Rank Approximation and Column Subset Selection
Learning Noisy Halfspaces with a Margin: Massart is No Harder than Random
Towards Stable Representations for Protein Interface Prediction
Stochastic Extragradient with Flip-Flop Shuffling & Anchoring: Provable Improvements
When is Multicalibration Post-Processing Necessary?
Parallel Backpropagation for Shared-Feature Visualization
Enhancing Data Quality via Training Dynamics from Private Domains for Collaborative Fine-Tuning of Large Language Models
MonkeySee: Space-time-resolved reconstructions of natural images from macaque multi-unit activity
Local to Global: Learning Dynamics and Effect of Initialization for Transformers
Geometric Trajectory Diffusion Models
Clustering in Causal Attention Masking
Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs
GPT as Visual Explainer
Questioning the Survey Responses of Large Language Models
Exactly Minimax-Optimal Locally Differentially Private Sampling
Leveraging Separated World Model for Exploration in Visually Distracted Environments
Almost Surely Asymptotically Constant Graph Neural Networks
Improved Guarantees for Fully Dynamic $k$-Center Clustering with Outliers in General Metric Spaces
Understanding, Rehearsing, and Introspecting: Learn a Policy from Textual Tutorial Books in Football Games
Pretraining with Random Noise for Fast and Robust Learning without Weight Transport
Linear Causal Bandits: Unknown Graph and Soft Interventions
Variational Delayed Policy Optimization
Rethinking Decoders for Transformer-based Semantic Segmentation: Compression is All You Need
The Impact of Geometric Complexity on Neural Collapse in Transfer Learning
Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving
MSA Generation with Seqs2Seqs Pretraining: Advancing Protein Structure Predictions
Simplifying Latent Dynamics with Softly State-Invariant World Models
Efficient Policy Evaluation Across Multiple Different Experimental Datasets
Compute-efficient LLM Training via Online Batch Selection
A Metalearned Neural Circuit for Nonparametric Bayesian Inference
Coherence-free Entrywise Estimation of Eigenvectors in Low-rank Signal-plus-noise Matrix Models
OccFusion: Rendering Occluded Humans with Generative Diffusion Priors
Quantum Deep Equilibrium Models
Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in LLMs
Object segmentation from common fate: Motion energy processing enables human-like zero-shot generalization to random dot stimuli
Optimal Private and Communication Constraint Distributed Goodness-of-Fit Testing for Discrete Distributions in the Large Sample Regime
From Transparent to Opaque: Rethinking Neural Implicit Surfaces with $\alpha$-NeuS
Neuro-Symbolic Data Generation for Math Reasoning
Generative Hierarchical Materials Search
DropEdge not Foolproof: Effective Augmentation Method for Signed Graph Neural Networks
Reshuffling Resampling Splits Can Improve Generalization of Hyperparameter Optimization
Flipped Classroom: Aligning Teacher Attention with Student in Generalized Category Discovery
Learning an Actionable Discrete Diffusion Policy via Large-Scale Actionless Video Pre-Training
Fully Unconstrained Online Learning
An Offline Adaptation Framework for Constrained Multi-Objective Reinforcement Learning
Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization Problem
Leveraging partial stragglers within gradient coding
Tangent Space Causal Inference: Leveraging Vector Fields for Causal Discovery in Dynamical Systems
Addressing bias in online selection with limited budget of comparisons
Local Linearity: the Key for No-regret Reinforcement Learning in Continuous MDPs
Towards an Information Theoretic Framework of Context-Based Offline Meta-Reinforcement Learning
A Phase Transition between Positional and Semantic Learning in a Solvable Model of Dot-Product Attention
Accuracy is Not All You Need
Genetic-guided GFlowNets for Sample Efficient Molecular Optimization
Data-Efficient Learning with Neural Programs
DeformableTST: Transformer for Time Series Forecasting without Over-reliance on Patching
Safe Exploitative Play in Stochastic Bayesian Games with Untrusted Type Beliefs
Learning Distributions on Manifolds with Free-Form Flows
STONE: A Submodular Optimization Framework for Active 3D Object Detection
End-to-end Learnable Clustering for Intent Learning in Recommendation
Equivariant Blurring Diffusion for Hierarchical Molecular Conformer Generation
What does guidance do? A fine-grained analysis in a simple setting
Towards a Theoretical Understanding of the 'Reversal Curse' via Training Dynamics
PhyRecon: Physically Plausible Neural Scene Reconstruction
One Sample Fits All: Approximating All Probabilistic Values Simultaneously and Efficiently
Optimal Batched Best Arm Identification
Hybrid Global Causal Discovery with Local Search
Persistent Homology for High-dimensional Data Based on Spectral Methods
Large Language Models Must Be Taught to Know What They Don’t Know
Efficient Zero-Shot HOI Detection: Enhancing VLM Adaptation with Innovative Prompt Learning
MTGS: A Novel Framework for Multi-Person Temporal Gaze Following and Social Gaze Prediction
Understanding Model Selection for Learning in Strategic Environments
DEFT: Efficient Finetuning of Conditional Diffusion Models by Learning the Generalised $h$-transform
Ensuring Right Prediction With Right Rationale
MultiOOD: Scaling Out-of-Distribution Detection for Multiple Modalities
Quantifying Aleatoric Uncertainty of the Treatment Effect: A Novel Orthogonal Learner
Generative Modelling of Structurally Constrained Graphs
Trading Place for Space: Increasing Location Resolution Reduces Contextual Capacity in Hippocampal Codes
Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes
Disentangling the Roles of Distinct Cell Classes with Cell-Type Dynamical Systems
Connectivity Shapes Implicit Regularization in Matrix Factorization Models for Matrix Completion
Improving Generalization of Dynamic Graph Learning via Environment Prompt
Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning
Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search
MSPE: Multi-Scale Patch Embedding Prompts Vision Transformers to Any Resolution
Sample Complexity Reduction through Policy Difference Estimation in RL
Learning Conjunctive Representations
EEG2Video: Towards Decoding Dynamic Visual Perception from EEG Signals
SpikeReveal: Unlocking Temporal Sequences from Real Blurry Inputs with Spike Streams
Computational Aspects of Bayesian Persuasion under Approximate Best Response
LACIE: Listener-Aware Finetuning for Calibration in Large Language Models
Enhancing Chess Reinforcement Learning with Graph Representation
Boosting Alignment for Post-Unlearning Text-to-Image Generative Models
OTTER: Effortless Label Distribution Adaptation of Zero-shot Models
UNION: Unsupervised 3D Object Detection using Object Appearance-based Pseudo-Classes
SymILO: A Symmetry-Aware Learning Framework for Integer Linear Optimization
ROBIN: Robust and Invisible Watermarks for Diffusion Models with Adversarial Optimization
Shaving Weights with Occam's Razor: Bayesian Sparsification for Neural Networks using the Marginal Likelihood
CV-VAE: A Compatible Video VAE for Latent Generative Video Models
NeuroClips: Towards High-fidelity and Smooth fMRI-to-Video Reconstruction
RankRAG: Unifying Retrieval-Augmented Generation and Context Ranking in LLMs
Who Evaluates the Evaluations? Objectively Scoring Text-to-Image Prompt Coherence Metrics with T2IScoreScore (TS2)
Finding Transformer Circuits With Edge Pruning
A versatile informative diffusion model for single-cell ATAC-seq data generation and analysis
Autoformalize Mathematical Statements by Symbolic Equivalence and Semantic Consistency
AlchemistCoder: Harmonizing and Eliciting Code Capability by Hindsight Tuning on Multi-source Data
General bounds on the quality of Bayesian coresets
Stepping on the Edge: Curvature Aware Learning Rate Tuners
ContextCite: Attributing Model Generation to Context
Pricing and Competition for Generative AI
The Closeness of In-Context Learning and Weight Shifting for Softmax Regression
Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning
Near-Optimal Streaming Heavy-Tailed Statistical Estimation with Clipped SGD
SpeechAlign: Speech Language Models Can Self-Improve via Preference Optimization
Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction
On the Expressivity and Sample Complexity of Node-Individualized Graph Neural Networks
4Real: Towards Photorealistic 4D Scene Generation via Video Diffusion Models
Ensemble sampling for linear bandits: small ensembles suffice
Learning from Pattern Completion: Self-supervised Controllable Generation
DMPlug: A Plug-in Method for Solving Inverse Problems with Diffusion Models
Self-Guided Masked Autoencoder
Online Posterior Sampling with a Diffusion Prior
HENASY: Learning to Assemble Scene-Entities for Interpretable Egocentric Video-Language Model
FUGAL: Feature-fortified Unrestricted Graph Alignment
Class-wise Transformation Is All You Need
FASTopic: A Fast, Adaptive, Stable, and Transferable Topic Modeling Paradigm
QTIP: Quantization with Trellises and Incoherence Processing
Inexact Augmented Lagrangian Methods for Conic Optimization: Quadratic Growth and Linear Convergence
Optimal Hypothesis Selection in (Almost) Linear Time
Amortized Active Causal Induction with Deep Reinforcement Learning
EnOF: Training Accurate Spiking Neural Networks via Enhancing the Output Feature Representation
Improved Particle Approximation Error for Mean Field Neural Networks
PCoTTA: Continual Test-Time Adaptation for Multi-Task Point Cloud Understanding
Diffusion Model with Cross Attention as an Inductive Bias for Disentanglement
Differentially Private Reinforcement Learning with Self-Play
Consensus Learning with Deep Sets for Essential Matrix Estimation
The AlCHEmist: Automated Labeling 500x CHEaper than LLM Data Annotators
Conformal Prediction for Class-wise Coverage via Augmented Label Rank Calibration
HHD-GP: Incorporating Helmholtz-Hodge Decomposition into Gaussian Processes for Learning Dynamical Systems
DreamMesh4D: Video-to-4D Generation with Sparse-Controlled Gaussian-Mesh Hybrid Representation
The Sample-Communication Complexity Trade-off in Federated Q-Learning
Lever LM: Configuring In-Context Sequence to Lever Large Vision Language Models
From Biased to Unbiased Dynamics: An Infinitesimal Generator Approach
Taming Cross-Domain Representation Variance in Federated Prototype Learning with Heterogeneous Data Domains
On the Optimality of Dilated Entropy and Lower Bounds for Online Learning in Extensive-Form Games
Language Hierarchical Self-training for Detecting Twenty-thousand Classes using Image-level Supervision
MetaCURL: Non-stationary Concave Utility Reinforcement Learning
How Do Large Language Models Acquire Factual Knowledge During Pretraining?
Federated Model Heterogeneous Matryoshka Representation Learning
Transformers on Markov data: Constant depth suffices
In-Context Learning of a Linear Transformer Block: Benefits of the MLP Component and One-Step GD Initialization
Speeding up non-parametric regression via distribution compression
Subsurface Scattering for Gaussian Splatting
Inversion-based Latent Bayesian Optimization
Testably Learning Polynomial Threshold Functions
Randomized Truthful Auctions with Learning Agents
Deep Support Vectors
A Huber Loss Minimization Approach to Mean Estimation under User-level Differential Privacy
Transfer Q-star : Principled Decoding for LLM Alignment
Online Iterative Reinforcement Learning from Human Feedback with General Preference Model
Boosting Text-to-Video Generative Model with MLLMs Feedback
Do causal predictors generalize better to new domains?
Robust Gaussian Processes via Relevance Pursuit
Who Needs Features? On the Surprising Effectiveness of Attention Transfer for Vision Transformers
Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model Disentanglement
Adaptable Logical Control for Large Language Models
Calibrated Preference Optimization for Direct Language Model Alignment
Frequency-aware Generative Models for Multivariate Time-series Imputation
Exocentric-to-Egocentric Video Generation
Gaussian Process Bandits for Top-k Recommendations
Improved learning rates in multi-unit uniform price auctions
Rethinking Weight Decay for Robust Fine-Tuning of Foundation Models
TFS-NeRF: Template-Free NeRF for Semantic 3D Reconstruction of Dynamic Scene
MetaUAS: Universal Anomaly Segmentation with One-Prompt Meta-Learning
Cryptographic Hardness of Score Estimation
Gradient-Free Methods for Nonconvex Nonsmooth Stochastic Compositional Optimization
What is my quantum computer good for? Quantum capability learning with physics-aware neural networks
Real-Time Recurrent Learning using Trace Units in Reinforcement Learning
Improving Adaptivity via Over-Parameterization in Sequence Models
On Complexity of Teaching a Family of Linear Behavior Cloning Learners
Cross-modal Representation Flattening for Multi-modal Domain Generalization
Ad Auctions for LLMs via Retrieval Augmented Generation
GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editing
Human-Assisted Out-of-Distribution Generalization and Detection
Self-Supervised Alignment with Mutual Information: Learning to Follow Principles without Preference Labels
AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising
Recurrent neural networks: vanishing and exploding gradients are not the end of the story
Maximum Entropy Inverse Reinforcement Learning of Diffusion Models with Energy-Based Models
Learning symmetries via weight-sharing with doubly stochastic tensors
REBORN: Reinforcement-Learned Boundary Segmentation with Iterative Training for Unsupervised ASR
Stochastic Newton Proximal Extragradient Method
CodeRosetta: Pushing the Boundaries of Unsupervised Code Translation for Parallel Programming
Revisiting Differentially Private ReLU Regression
EMVP: Embracing Visual Foundation Model for Visual Place Recognition with Centroid-Free Probing
A theoretical case-study of Scalable Oversight in Hierarchical Reinforcement Learning
StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation
Learning Where to Edit Vision Transformers
Topological obstruction to the training of shallow ReLU neural networks
WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models
Energy-based Hopfield Boosting for Out-of-Distribution Detection
Can Transformers Smell Like Humans?
Latent Neural Operator for Solving Forward and Inverse PDE Problems
Towards Combating Frequency Simplicity-biased Learning for Domain Generalization
Autoregressive Image Generation without Vector Quantization
PrivCirNet: Efficient Private Inference via Block Circulant Transformation
Post-Hoc Reversal: Are We Selecting Models Prematurely?
Randomized algorithms and PAC bounds for inverse reinforcement learning in continuous spaces
FairQueue: Rethinking Prompt Learning for Fair Text-to-Image Generation
Reproducibility of predictive networks for mouse visual cortex
Multidimensional Fractional Programming for Normalized Cuts
LoRA-GA: Low-Rank Adaptation with Gradient Approximation
LLM-AutoDA: Large Language Model-Driven Automatic Data Augmentation for Long-tailed Problems
Adaptive Experimentation When You Can't Experiment
SGLang: Efficient Execution of Structured Language Model Programs
IR-CM: The Fast and Universal Image Restoration Method Based on Consistency Model
Kernel-Based Function Approximation for Average Reward Reinforcement Learning: An Optimist No-Regret Algorithm
Learning Generalized Linear Programming Value Functions
Partial Transportability for Domain Generalization
Overcoming Common Flaws in the Evaluation of Selective Classification Systems
Distributional Preference Alignment of LLMs via Optimal Transport
ContextGS : Compact 3D Gaussian Splatting with Anchor Level Context Model
Bilevel Optimization with Lower-Level Contextual MDPs
Precise Relational DNN Verification With Cross Executional Branching
Understanding Transformers via N-Gram Statistics
One-Layer Transformer Provably Learns One-Nearest Neighbor In Context
Theoretical and Empirical Insights into the Origins of Degree Bias in Graph Neural Networks
Towards Understanding the Mechanisms of Associative Memory in Transformers
Large Language Models as Urban Residents: An LLM Agent Framework for Personal Mobility Generation
Exploiting Representation Curvature for Boundary Detection in Time Series
Multilingual Diversity Improves Vision-Language Representations
Embedding-Aligned Language Models
Disentangling Linear Quadratic Control with Untrusted ML Predictions
Diffusion Policy Attacker: Crafting Adversarial Attacks for Diffusion-based Policies
Spiking Transformer with Experts Mixture
Aligning Diffusion Behaviors with Q-functions for Efficient Continuous Control
Accelerating Self-supervised Learning Pretraining
Personalized Federated Learning via Feature Distribution Adaptation
No-Regret Learning for Fair Multi-Agent Social Welfare Optimization
Breaking Long-Tailed Learning Bottlenecks: A Controllable Paradigm with Hypernetwork-Generated Diverse Experts
Strategic Multi-Armed Bandit Problems Under Debt-Free Reporting
PediatricsGPT: Large Language Models as Chinese Medical Assistants for Pediatric Applications
DarkSAM: Fooling Segment Anything Model to Segment Nothing
Learning Heuristics for Numeric Planning
Stochastic Optimal Control for Diffusion Bridges in Function Spaces
Understanding the Expressive Power and Mechanisms of Transformer for Sequence Modeling
BitsFusion: 1.99 bits Weight Quantization of Diffusion Model
Invariant subspaces and PCA in nearly matrix multiplication time
Near-Optimal Distributionally Robust RL with General $L_p$ Norms
Zeroth-Order Sampling Methods for Non-Log-Concave Distributions: Alleviating Metastability by Denoising Diffusion
Mixture of Link Predictors on Graphs
Generalization of Hamiltonian algorithms
Learning-Augmented Algorithms with Explicit Predictors
Prospective Learning: Learning for a Dynamic Future
Self-Refining Diffusion Samplers: Enabling Parallelization via Parareal Iterations
Log-concave Sampling from a Convex Body with a Barrier: a Robust and Unified Dikin Walk
SPO: Sequential Monte Carlo Policy Optimisation
High-probability complexity bounds for stochastic non-convex minimax optimization
Online Bayesian Persuasion Without a Clue
Fine-Tuning is Fine, if Calibrated
Continuous Product Graph Neural Networks
Human-AI Alignment in Chess with Skill-Aware Attention
Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks
DevBench: A multimodal developmental benchmark for language learning
No Free Delivery Service: Epistemic limits of passive data collection in complex social systems
XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX
Semi-Random Matrix Completion via Flow-Based Adaptive Reweighting
$E^3$: Exploring Embodied Emotion Through A Large-Scale Egocentric Video Dataset
Toward Robust Incomplete Multimodal Sentiment Analysis via Representation Factorization and Alignment
Random Cycle Coding: Lossless Compression of Cluster Assignments via Bits-Back Coding
Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs
Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Driving
A Simple and Adaptive Learning Rate for FTRL in Online Learning with Minimax Regret of $\Theta(T^{2/3})$ and its Application to Best-of-Both-Worlds
Data curation via joint example selection further accelerates multimodal learning
CALE: Continuous Arcade Learning Environment
Unraveling the Gradient Descent Dynamics of Transformers
ComBack: A Versatile Dataset for Enhancing Compiler Backend Development Efficiency
JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
TAIA: Large Language Models are Out-of-Distribution Data Learners
Scaling Laws and Compute-Optimal Training without Fixed Training Duration
MM-WLAuslan: Multi-View Multi-Modal Word-Level Australian Sign Language Recognition Dataset
QGym: Scalable Simulation and Benchmarking of Queuing Network Controllers
UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models
Learning Action and Reasoning-Centric Image Editing from Videos and Simulation
Fast Rates in Stochastic Online Convex Optimization by Exploiting the Curvature of Feasible Sets
FEDMEKI: A Benchmark for Scaling Medical Foundation Models via Federated Knowledge Injection
AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning
Learning Mixtures of Unknown Causal Interventions
Physics-Guided Neural Impulse Response Field via Implicit Wave Propagation Modeling
DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA
Towards Learning Group-Equivariant Features for Domain Adaptive 3D Detection
Make Your LLM Fully Utilize the Context
ImageNet3D: Towards General-Purpose Object-Level 3D Understanding
BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languages
Reawakening knowledge: Anticipatory recovery from catastrophic interference via structured training
Transductive Sample Complexities Are Compact
FairJob: A Real-World Dataset for Fairness in Online Systems
Physics-Regularized Multi-Modal Image Assimilation for Brain Tumor Localization
A Data-Centric Perspective on Evaluating Machine Learning Models for Tabular Data
Linearly Decomposing and Recomposing Vision Transformers for Diverse-Scale Models
Reparameterizable Tree-structured Variational Inference for Instance-level Correlation Capturing
DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos
INQUIRE: A Natural World Text-to-Image Retrieval Benchmark
The Poisson Midpoint Method for Langevin Dynamics: Provably Efficient Discretization for Diffusion Models
Why Do We Need Weight Decay in Modern Deep Learning?
Schedule Your Edit: A Simple yet Effective Diffusion Noise Schedule for Image Editing
Randomized Strategic Facility Location with Predictions
FUSU: A Multi-temporal-source Land Use Change Segmentation Dataset for Fine-grained Urban Semantic Understanding
United We Stand, Divided We Fall: Fingerprinting Deep Neural Networks via Adversarial Trajectories
A multi-UAV dataset for multi-object tracking and re-identification of wild antelopes
Empowering and Assessing the Utility of Large Language Models in Crop Science
pcaGAN: Improving Posterior-Sampling cGANs via Principal Component Regularization
Online Control in Population Dynamics
A Retrospective on the Robot Air Hockey Challenge: Benchmarking Robust, Reliable, and Safe Learning Techniques for Real-world Robotics
SlimSAM: 0.1% Data Makes Segment Anything Slim
OSLO: One-Shot Label-Only Membership Inference Attacks
CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs
A Taxonomy of Challenges to Curating Fair Datasets
Towards Next-Generation Logic Synthesis: A Scalable Neural Circuit Generation Framework
DiGRAF: Diffeomorphic Graph-Adaptive Activation Function
ClavaDDPM: Multi-relational Data Synthesis with Cluster-guided Diffusion Models
Analyzing & Reducing the Need for Learning Rate Warmup in Neural Network Optimization
Codec Avatar Studio: Paired Human Captures for Complete, Driveable, and Generalizable Avatars
DetectEval: Benchmarking LLM-Generated Text Detection in Real-World Scenarios
Constrained Adaptive Attack: Effective Adversarial Attack Against Deep Neural Networks for Tabular Data
4DBInfer: A 4D Benchmarking Toolbox for Graph-Centric Predictive Modeling on RDBs
Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching
OneBit: Towards Extremely Low-bit Large Language Models
Mutli-Armed Bandits with Network Interference
Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition
Reconstruction of Manipulated Garment with Guided Deformation Prior
MedCalc-Bench: Evaluating Large Language Models for Medical Calculations
Hidden in Plain Sight: Evaluating Abstract Shape Recognition in Vision-Language Models
SceneDiffuser: Efficient and Controllable Driving Simulation Initialization and Rollout
Orchid: Flexible and Data-Dependent Convolution for Sequence Modeling
Navigating Chemical Space with Latent Flows
Bandits with Ranking Feedback
On Differentially Private Subspace Estimation in a Distribution-Free Setting
A Careful Examination of Large Language Model Performance on Grade School Arithmetic
An Accelerated Gradient Method for Convex Smooth Simple Bilevel Optimization
Rethinking Parity Check Enhanced Symmetry-Preserving Ansatz
Predicting the Performance of Foundation Models via Agreement-on-the-Line
Towards Comprehensive Detection of Chinese Harmful Memes: Dataset and Detector
Never Miss A Beat: An Efficient Recipe for Context Window Extension of Large Language Models with Consistent “Middle” Enhancement
ConMe: Rethinking Evaluation of Compositional Reasoning for Modern VLMs
Towards Open-Vocabulary Semantic Segmentation Without Semantic Labels
SureMap: Simultaneous mean estimation for single-task and multi-task disaggregated evaluation
Learning to grok: Emergence of in-context learning and skill composition in modular arithmetic tasks
Unified Covariate Adjustment for Causal Inference
T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models
$\texttt{Model-GLUE}$: Democratized LLM Scaling for A Large Model Zoo in the Wild
Distributionally Robust Reinforcement Learning with Interactive Data Collection: Fundamental Hardness and Near-Optimal Algorithm
Learning Elastic Costs to Shape Monge Displacements
Cell ontology guided transcriptome foundation model
Markovian Flow Matching: Accelerating MCMC with Continuous Normalizing Flows
Foundations of Multivariate Distributional Reinforcement Learning
Precise asymptotics of reweighted least-squares algorithms for linear diagonal networks
Collaborative Video Diffusion: Consistent Multi-video Generation with Camera Control
Navigating the Maze of Explainable AI: A Systematic Approach to Evaluating Methods and Metrics
IncomeSCM: From tabular data set to time-series simulator and causal estimation benchmark
Is Multiple Object Tracking a Matter of Specialization?
Equivariant Flow-Matching for Molecular Conformer Generation
Scalable Early Childhood Reading Performance Prediction
Streaming Long Video Understanding with Large Language Models
Elucidating the Design Space of Dataset Condensation
Text-Guided Image Editing in Around 7 Steps with Invertible Consistency Distillation
Don't Look Twice: Faster Video Transformers with Run-Length Tokenization
IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos
InfiBench: Evaluating the Question-Answering Capabilities of Code Large Language Models
Disentangling and mitigating the impact of task similarity for continual learning
cPAPERS: A Dataset of Situated and Multimodal Interactive Conversations in Scientific Papers
Fair Allocation in Dynamic Mechanism Design
FairMedFM: Fairness Benchmarking for Medical Imaging Foundation Models
Gradient Rewiring for Editable Graph Neural Network Training
VisMin: Visual Minimal-Change Understanding
ABCFair: an Adaptable Benchmark approach for Comparing Fairness Methods
PUZZLES: A Benchmark for Neural Algorithmic Reasoning
FIARSE: Model-Heterogeneity Federated Learning via Importance-Aware Submodel Extraction
Infusing Synthetic Data with Real-World Patterns for Zero-Shot Material State Segmentation
HEMM: Holistic Evaluation of Multimodal Foundation Models
Bridging Multicalibration and Out-of-distribution Generalization Beyond Covariate Shift
Identifying Equivalent Training Dynamics
Image2Struct: A Benchmark for Evaluating Vision-Language Models in Extracting Structured Information from Images
Denoising Diffusion Path: Attribution Noise Reduction with An Auxiliary Diffusion Model
CoLLaM: A Comprehensive Chinese Legal Benchmark for Evaluating Large Language Models
CleanDiffuser: An Easy-to-use Modularized Library for Diffusion Models in Decision Making
LAVIB: A Large-scale Video Interpolation Benchmark
Adam on Local Time: Addressing Nonstationarity in RL with Relative Adam Timesteps
OVT-B: A New Large-Scale Benchmark for Open-Vocabulary Multi-Object Tracking
Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation
Secret Collusion among Generative AI Agents
AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents
IndicVoices-R: Unlocking a Massive Multilingual Multi-speaker Speech Corpus for Scaling Indian TTS
Self-Labeling the Job Shop Scheduling Problem
NetworkGym: Reinforcement Learning Environments for Multi-Access Traffic Management in Network Simulation
MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions
Distributed Sparse Regression via Penalization
Instruction-Guided Visual Masking
A Unified Recipe for Deriving (Time-Uniform) PAC-Bayes Bounds
Optimal Design for Human Feedback
Convolutions and More as Einsum: A Tensor Network Perspective with Advances for Second-Order Methods
Nonparametric Copula Models for Multivariate, Mixed, and Missing Data
Divide-and-Conquer Meets Consensus: Unleashing the Power of Functions in Code Generation
Training Binary Neural Networks via Gaussian Variational Inference and Low-Rank Semidefinite Programming
No-regret Bandit Exploration based on Soft Tree Ensemble Model
Topological Hidden Markov Models
Stopping Bayesian Optimization with Probabilistic Regret Bounds
Numerically Stable Sparse Gaussian Processes via Minimum Separation using Cover Trees
Robust Reinforcement Learning from Corrupted Human Feedback
Fourier Neural Operator with Learned Deformations for PDEs on General Geometries
Metrizing Weak Convergence with Maximum Mean Discrepancies
Optimal Clustering with Bandit Feedback
On Statistical Rates and Provably Efficient Criteria of Latent Diffusion Transformers (DiTs)
Transfer Learning with Informative Priors: Simple Baselines Better than Previously Reported
Faster Diffusion: Rethinking the Role of the Encoder for Diffusion Model Inference
Identity Decoupling for Multi-Subject Personalization of Text-to-Image Models
[Re] Classwise-Shapley values for data valuation
[Re] Reproducibility Study of “Explaining Temporal Graph Models Through an Explorer-Navigator Framework"
On the Reproducibility of: "Learning Perturbations to Explain Time Series Predictions"
Lookback Prophet Inequalitites
Chain-of-Thought Unfaithfulness as Disguised Accuracy
Reproducibility Study Of Learning Fair Graph Representations Via Automated Data Augmentations
Improving Generalization and Convergence by Enhancing Implicit Regularization
Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor
CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patterns
LLaMo: Large Language Model-based Molecular Graph Assistant
Oja's Algorithm for Sparse PCA
Return of Unconditional Generation: A Self-supervised Representation Generation Method
Axioms for AI Alignment from Human Feedback
Unrolled denoising networks that provably learn to perform optimal Bayesian inference
Preference Learning Algorithms Do Not Learn Preference Rankings
Wasserstein Gradient Boosting: A General Framework with Applications to Posterior Regression
Can LLMs Implicitly Learn Numeric Parameter Constraints in Data Science APIs?
Can neural operators always be continuously discretized?
Exploring Prompting Methods for Mitigating Class Imbalance through Synthetic Data Generation with Large Language Models
On the Comparison between Multi-modal and Single-modal Contrastive Learning
Multimodal Conformal Prediction in Dynamic Environments
Learning Linear Causal Representations from General Environments: Identifiability and Intrinsic Ambiguity
Probabilistic size-and-shape functional mixed models
Scaling laws for learning with real and surrogate data
Verified Safe Reinforcement Learning for Neural Network Dynamic Models
How Molecules Impact Cells: Unlocking Contrastive PhenoMolecular Retrieval
From Linear to Linearizable Optimization: A Novel Framework with Applications to Stationary and Non-stationary DR-submodular Optimization
Towards the Dynamics of a DNN Learning Symbolic Interactions
Sample and Computationally Efficient Robust Learning of Gaussian Single-Index Models
UniIF: Unified Molecule Inverse Folding
Learning Optimal Lattice Vector Quantizers for End-to-end DNN Image Compression
Easy Regional Contrastive Learning of Expressive Visual Fashion Representations
Retrieval-Augumented Diffusion Models for Time Series Forecasting
On Weak Regret Analysis for Dueling Bandits
Active Learning for Derivative-Based Global Sensitivity Analysis with Gaussian Processes
Exploring Consistency in Graph Representations: from Graph Kernels to Graph Neural Networks
Implicitly Guided Design with PropEn: Match your Data to Follow the Gradient
Bayesian Identification of the Hamiltonian Inductive Bias in Dynamical Systems
Not so griddy: Internal representations of RNNs path integrating more than one agent
Population Predictive Coding: a structured Bayesian inference algorithm
Fair Secretaries with Unfair Predictions
You May Better Reconstruct Anomalous over Normal Graphs: Analysis and a Simple Method for Reconstruction-based Graph-Level Anomaly Detection
PLIP: Language-Image Pre-training for Person Representation Learning
Large Language Model Unlearning via Embedding-Corrupted Prompts
Fairness-Aware Meta-Learning via Nash Bargaining
Fully First-Order Methods for Linearly Constrained Bilevel Optimization
AMOR: A Recipe for Building Adaptable Modular Knowledge Agents Through Process Feedback
Statistical Efficiency of Distributional Temporal Difference
Navigating the Effect of Parametrization for Dimensionality Reduction
EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric Views
Image-aware Evaluation of Generated Medical Reports
Nuclear Norm Regularization for Deep Learning
Stochastic Optimization Schemes for Performative Prediction with Nonconvex Loss
Poisson Variational Autoencoder
Neur2BiLO: Neural Bilevel Optimization
Grid4D: 4D Decomposed Hash Encoding for High-fidelity Dynamic Scene Rendering
LaKD: Length-agnostic Knowledge Distillation for Trajectory Prediction with Any Length Observations
Non-Stationary Learning of Neural Networks with Automatic Soft Parameter Reset
How Transformers Utilize Multi-Head Attention in In-Context Learning? A Case Study on Sparse Linear Regression
SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusion
Compositional Generalization Across Distributional Shifts with Sparse Tree Operations
TrajCLIP: Pedestrian trajectory prediction method using contrastive learning and idempotent networks
MatFormer: Nested Transformer for Elastic Inference
AnyFit: Controllable Virtual Try-on for Any Combination of Attire Across Any Scenario
Bigger, Regularized, Optimistic: scaling for compute and sample efficient continuous control
GFlowNet Assisted Biological Sequence Editing
To Learn or Not to Learn, That is the Question
Provably Efficient Reinforcement Learning for Infinite-Horizon Average-Reward Linear MDPs
Fully Explicit Dynamic Gaussian Splatting
Online Learning of Delayed Choices
Reciprocal Reward Influence Encourages Cooperation From Self-Interested Agents
Pandora's Box: Towards Building Universal Attackers against Real-World Large Vision-Language Models
Exponential Quantum Communication Advantage in Distributed Inference and Learning
Improving Temporal Link Prediction via Temporal Walk Matrix Projection
Biologically-Motivated Learning Model for Instructed Visual Processing
Polyak Meets Parameter-free Clipped Gradient Descent
Generalizable and Animatable Gaussian Head Avatar
Adaptive Exploration for Data-Efficient General Value Function Evaluations
Neural Collapse to Multiple Centers For Imbalanced Data
Gene-Gene Relationship Modeling Based on Genetic Evidence for Single-Cell RNA-Seq Data Imputation
Diffeomorphic interpolation for efficient persistence-based topological optimization
Achieving Optimal Clustering in Gaussian Mixture Models with Anisotropic Covariance Structures
Near-Optimality of Contrastive Divergence Algorithms
FlexCap: Describe Anything in Images in Controllable Detail
Federated Fine-tuning of Large Language Models under Heterogeneous Tasks and Client Resources
Learning to Understand: Identifying Interactions via the Möbius Transform
Can large language models explore in-context?
SARAD: Spatial Association-Aware Anomaly Detection and Diagnosis for Multivariate Time Series
Neural Pose Representation Learning for Generating and Transferring Non-Rigid Object Poses
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
A Unifying Post-Processing Framework for Multi-Objective Learn-to-Defer Problems
Least Squares Regression Can Exhibit Under-Parameterized Double Descent
A-FedPD: Aligning Dual-Drift is All Federated Primal-Dual Learning Need
Action Imitation in Common Action Space for Customized Action Image Synthesis
Breaking Determinism: Fuzzy Modeling of Sequential Recommendation Using Discrete State Space Diffusion Model
Binding in hippocampal-entorhinal circuits enables compositionality in cognitive maps
TPC: Test-time Procrustes Calibration for Diffusion-based Human Image Animation
Understanding Multi-Granularity for Open-Vocabulary Part Segmentation
Low-Rank Optimal Transport through Factor Relaxation with Latent Coupling
Rethinking Optimal Transport in Offline Reinforcement Learning
Contrastive losses as generalized models of global epistasis
LLM Dataset Inference: Detect Datasets, not Strings
An engine not a camera: Measuring performative power of online search
Propensity Score Alignment of Unpaired Multimodal Data
GraphVis: Boosting LLMs with Visual Knowledge Graph Integration
Efficient Federated Learning against Heterogeneous and Non-stationary Client Unavailability
Out-Of-Distribution Detection with Diversification (Provably)
Instance-Optimal Private Density Estimation in the Wasserstein Distance
CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts
Belief-State Query Policies for Planning With Preferences Under Partial Observability
Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable
When and How Does Synthetic Data Improve Reasoning Capabilities of Language Models?
Learning to Predict Structural Vibrations
Scaling Retrieval-Based Language Models with a Trillion-Token Datastore
Looks Too Good To Be True: An Information-Theoretic Analysis of Hallucinations in Generative Restoration Models
No Regrets: Investigating and Improving Regret Approximations for Curriculum Discovery
Causal Effect Identification in a Sub-Population with Latent Variables
Vidu4D: Single Generated Video to High-Fidelity 4D Reconstruction with Dynamic Gaussian Surfels
Beyond Primal-Dual Methods in Bandits with Stochastic and Adversarial Constraints
Improved Algorithms for Contextual Dynamic Pricing
Sm: enhanced localization in Multiple Instance Learning for medical imaging classification
3DET-Mamba: Causal Sequence Modelling for End-to-End 3D Object Detection
TOPA: Extend Large Language Models for Video Understanding via Text-Only Pre-Alignment
UDON: Universal Dynamic Online distillatioN for generic image representations
Stochastic Concept Bottleneck Models
Improving Robustness of 3D Point Cloud Recognition from a Fourier Perspective
Soft-Label Integration for Robust Toxicity Classification
Theoretical guarantees in KL for Diffusion Flow Matching
Linear Regression using Heterogeneous Data Batches
Customizing Language Models with Instance-wise LoRA for Sequential Recommendation
Generalizable Person Re-identification via Balancing Alignment and Uniformity
Does Worst-Performing Agent Lead the Pack? Analyzing Agent Dynamics in Unified Distributed SGD
Instructor-inspired Machine Learning for Robust Molecular Property Prediction
DiffuserLite: Towards Real-time Diffusion Planning
CoFie: Learning Compact Neural Surface Representations with Coordinate Fields
Kraken: Inherently Parallel Transformers For Efficient Multi-Device Inference
Star-Agents: Automatic Data Optimization with LLM Agents for Instruction Tuning
Task Me Anything
Gated Slot Attention for Efficient Linear-Time Sequence Modeling
Data-faithful Feature Attribution: Mitigating Unobservable Confounders via Instrumental Variables
Revisiting Score Propagation in Graph Out-of-Distribution Detection
Reinforcement Learning Policy as Macro Regulator Rather than Macro Placer
Kronecker-Factored Approximate Curvature for Physics-Informed Neural Networks
MambaLRP: Explaining Selective State Space Sequence Models
RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation
Dual-frame Fluid Motion Estimation with Test-time Optimization and Zero-divergence Loss
To Believe or Not to Believe Your LLM
Diffusion-Reward Adversarial Imitation Learning
Neural Isometries: Taming Transformations for Equivariant ML
Distributed-Order Fractional Graph Operating Network
Nesterov acceleration despite very noisy gradients
Rethinking the Capacity of Graph Neural Networks for Branching Strategy
On the Robustness of Spectral Algorithms for Semirandom Stochastic Block Models
An Analysis of Elo Rating Systems via Markov Chains
Fairness and Efficiency in Online Class Matching
Chain of Thoughtlessness? An Analysis of CoT in Planning
Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing
Probabilistic Federated Prompt-Tuning in Data Imbalance Settings
Input-to-State Stable Coupled Oscillator Networks for Closed-form Model-based Control in Latent Space
Rethinking Model-based, Policy-based, and Value-based Reinforcement Learning via the Lens of Representation Complexity
Multi-Winner Reconfiguration
Prior-itizing Privacy: A Bayesian Approach to Setting the Privacy Budget in Differential Privacy
MergeMinds: Boosting Multilingual Reasoning with the Built-in Capabilities of LLMs
Normal-GS: 3D Gaussian Splatting with Normal-Involved Rendering
Functional Gradient Flows for Constrained Sampling
Tell What You Hear From What You See - Video to Audio Generation Through Text
VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector Banks
Acceleration Exists! Optimization Problems When Oracle Can Only Compare Objective Function Values
LP-3DGS: Learning to Prune 3D Gaussian Splatting
Improved Sample Complexity for Multiclass PAC Learning
Parameter Competition Balancing for Model Merging
Towards the Transferability of Rewards Recovered via Regularized Inverse Reinforcement Learning
Bridge-IF: Learning Inverse Protein Folding with Markov Bridges
Toward Conditional Distribution Calibration in Survival Prediction
RMLR: Extending Multinomial Logistic Regression into General Geometries
John Ellipsoids via Lazy Updates
Mitigating Covariate Shift in Behavioral Cloning via Robust Distribution Correction Estimation
Set-Based Prompting: Provably Solving the Language Model Order Dependency Problem
From Chaos to Clarity: 3DGS in the Dark
Nonlinear dynamics of localization in neural receptive fields
Deep Learning in Medical Image Registration: Magic or Mirage?
Automated Multi-Task Learning for Joint Disease Prediction on Electronic Health Records
Coherent 3D Scene Diffusion From a Single RGB Image
OPEL: Optimal Transport Guided ProcedurE Learning
In-Context Learning with Transformers: Softmax Attention Adapts to Function Lipschitzness
The Star Geometry of Critic-Based Regularizer Learning
Compressing Large Language Models using Low Rank and Low Precision Decomposition
Vaccine: Perturbation-aware Alignment for Large Language Models Finetuning
MotionCraft: Physics-Based Zero-Shot Video Generation
Unifying Generation and Prediction on Graphs with Latent Graph Diffusion
Text to Blind Motion
Entropy Coding of Large Unordered Data Structures
How many classifiers do we need?
Neglected Hessian component explains mysteries in sharpness regularization
ELSA: Exploiting Layer-wise N:M Sparsity for Vision Transformer Acceleration
Exact Gradients for Stochastic Spiking Neural Networks Driven by Rough Signals
AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation
Quality-Improved and Property-Preserved Polarimetric Imaging via Complementarily Fusing
CODA: A Correlation-Oriented Disentanglement and Augmentation Modeling Scheme for Better Resisting Subpopulation Shifts
LiteVAE: Lightweight and Efficient Variational Autoencoders for Latent Diffusion Models
A Compositional Atlas for Algebraic Circuits
SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
Towards Robust Multimodal Sentiment Analysis with Incomplete Data
Once Read is Enough: Finetuning-free Language Models with Cluster-guided Sparse Experts for Long-tail Domain Knowledge
DiffPO: A causal diffusion model for predicting potential outcomes of treatments
Dueling over Dessert, Mastering the Art of Repeated Cake Cutting
Online Relational Inference for Evolving Multi-agent Interacting System
Demystifying Encoding: Detecting Explanations that Hide Information in the Selection
DMNet: Self-comparison Driven Model for Subject-independent Seizure Detection
S2HPruner: Soft-to-Hard Distillation Bridges the Discretization Gap in Pruning
Self-Distilled Depth Refinement with Noisy Poisson Fusion
Calibrated Self-Rewarding Vision Language Models
One for All: Multi-Domain Joint Training for Point Cloud Based 3D Object Detection
Dual-Personalizing Adapter for Federated Foundation Models
Understanding and Minimising Outlier Features in Neural Network Training
Estimating Generalization Performance Along the Trajectory of Proximal SGD in Robust Regression
Code Repair with LLMs gives an Exploration-Exploitation Tradeoff
Self-playing Adversarial Language Game Enhances LLM Reasoning
Masked Pre-training Enables Universal Zero-shot Denoiser
Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation Models
A Label is Worth A Thousand Images in Dataset Distillation
A theoretical design of concept sets: improving the predictability of Concept Bottleneck Models
SparseLLM: Towards Global Pruning of Pre-trained Language Models
Measuring Per-Unit Interpretability at Scale Without Humans
Generalization Bounds via Conditional $f$-Information
Balancing Multimodal Learning with Classifier-guided Gradient Modulation
One-Step Diffusion Distillation through Score Implicit Matching
Neuro-Vision to Language: Enhancing Visual Reconstruction and Language Interaction through Brain Recordings
Policy Mirror Descent with Lookahead
Forgetting, Ignorance or Myopia: Revisiting Key Challenges in Online Continual Learning
From an Image to a Scene: Learning to Imagine the World from a Million 360° Videos
Capability v.s. Behavior in Compositional Generalization: A Learning Dynamics Perspective
Infinite Limits of Multi-head Transformer Dynamics
Particle Semi-Implicit Variational Inference
Dual Risk Minimization: Towards Next-Level Robustness in Fine-tuning Zero-Shot Models
Zipfian Whitening
Make-An-Agent: A Generalizable Policy Network Generator with Behavior-Prompted Diffusion
The Limits of Transfer Reinforcement Learning with Latent Low-rank Structure
Artificial Generational Intelligence: Cultural Accumulation in Reinforcement Learning
Smoothie: Label Free Language Model Routing
Effective Sharpness Aware Minimization Requires Layerwise Perturbation Scaling
DFBA: Data Free Backdoor Attacks
Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms
SuperDeepFool: a new fast and accurate minimal adversarial attack
Stochastic Kernel Regularisation Improves Generalisation in Deep Kernel Machines
Self-Play Fine-tuning of Diffusion Models for Text-to-image Generation
Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning rates
Stealth edits to large language models
Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit
Continual learning with the neural tangent ensemble
Most Influential Subset Selection: Challenges, Promises, and Beyond
Prune and Repaint: Content-Aware Image Retargeting for any Ratio
IODA: Instance-Guided One-shot Domain Adaptation for Super-Resolution
Universal Sample Coding
Reinforcement Learning Under Latent Dynamics: Toward Statistical and Algorithmic Modularity
Adaptive Proximal Gradient Method for Convex Optimization
Symmetry Discovery Beyond Affine Transformations
Conjugated Semantic Pool Improves OOD Detection with Pre-trained Vision-Language Models
Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision
Parametric model reduction of mean-field and stochastic systems via higher-order action matching
DOPPLER: Differentially Private Optimizers with Low-pass Filter for Privacy Noise Reduction
Graph Coarsening with Message-Passing Guarantees
Semidefinite Relaxations of the Gromov-Wasserstein Distance
Monomial Matrix Group Equivariant Neural Functional Networks
Uncertainty-based Offline Variational Bayesian Reinforcement Learning for Robustness under Diverse Data Corruptions
3-in-1: 2D Rotary Adaptation for Efficient Finetuning, Efficient Batching and Composability
Local Anti-Concentration Class: Logarithmic Regret for Greedy Linear Contextual Bandit
MIDGArD: Modular Interpretable Diffusion over Graphs for Articulated Designs
Super Consistency of Neural Network Landscapes and Learning Rate Transfer
Moving Off-the-Grid: Scene-Grounded Video Representations
Sequoia: Scalable and Robust Speculative Decoding
A Nearly Optimal and Low-Switching Algorithm for Reinforcement Learning with General Function Approximation
AdvAD: Exploring Non-Parametric Diffusion for Imperceptible Adversarial Attacks
Semi-supervised Knowledge Transfer Across Multi-omic Single-cell Data
SOI: Scaling Down Computational Complexity by Estimating Partial States of the Model
The Impact of Initialization on the Finetuning Dynamics in LoRA
Adapting Diffusion Models for Improved Prompt Compliance and Controllable Image Synthesis
Learning-Augmented Dynamic Submodular Maximization
Approximation-Aware Bayesian Optimization
Consistency Purification: Effective and Efficient Diffusion Purification towards Certified Robustness
Efficient Recurrent Off-Policy RL Requires a Context-Encoder-Specific Learning Rate
Reinforced Cross-Domain Knowledge Distillation on Time Series Data
Latent Representation Matters: Human-like Sketches in One-shot Drawing Tasks
When to Act and When to Ask: Policy Learning With Deferral Under Hidden Confounding
Learning to Reason via Program Generation, Emulation, and Search
Dynamical Conditional Optimal Transport through Simulation-Free Flows
AirSketch: Generative Motion to Sketch
Explaining Text Datasets with Language Parameters
Enhancing Consistency-Based Image Generation via Adversarialy-Trained Classification and Energy-Based Discrimination
DU-Shapley: A Shapley Value Proxy for Efficient Dataset Valuation
Transformer Efficiently Learns Low-dimensional Target Functions In-context
Partial Structure Discovery is Sufficient for No-regret Learning in Causal Bandits
Sample Complexity of Algorithm Selection Using Neural Networks and Its Applications to Branch-and-Cut
SVFT: Parameter-Efficient Fine-Tuning with Singular Vectors
Efficient Sign-Based Optimization: Accelerating Convergence via Variance Reduction
Unifying Homophily and Heterophily for Spectral Graph Neural Networks via Triple Filter Ensembles
Calibrating Reasoning in Language Models with Internal Consistency
AdaFlow
FIFO-Diffusion: Generating Infinite Videos from Text without Training
JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models
AlterMOMA: Fusion Redundancy Pruning for Camera-LiDAR Fusion Models with Alternative Modality Masking
Mean-Field Analysis for Learning Subspace-Sparse Polynomials with Gaussian Input
Mixture of Demonstrations for In-Context Learning
Test-Time Debiasing of Vision-Language Embeddings
Integrating Deep Metric Learning with Coreset for Active Learning in 3D Segmentation
Achieving Domain-Independent Certified Robustness via Knowledge Continuity
Adam with model exponential moving average is effective for nonconvex optimization
Learning from Uncertain Data: From Possible Worlds to Possible Models
Harnessing Heuristics for Deep Reinforcement Learning via Constrained Optimization
Optimal deep learning of holomorphic operators between Banach spaces
2D-OOB: Attributing Data Contribution through Joint Valuation Framework
Bileve: Securing Text Provenance in Large Language Models Against Spoofing with Bi-level Signature
$\epsilon$-Softmax: Approximating One-Hot Vectors for Mitigating Label Noise
Remix-DiT: Mixing Diffusion Transformers for Multi-Expert Denoising
Learning Segmentation from Point Trajectories
Average gradient outer product as a mechanism for deep neural collapse
High Rank Path Development: an approach of learning the filtration of stochastic processes
Optimization Can Learn Johnson Lindenstrauss Embeddings
Can Language Models Learn to Skip Steps?
Algorithmic Collective Action in Recommender Systems: Promoting Songs by Reordering Playlists
Batched Energy-Entropy acquisition for Bayesian Optimization
Taming the Long Tail in Human Mobility Prediction
Probabilistic Weather Forecasting with Hierarchical Graph Neural Networks
RoPINN: Region Optimized Physics-Informed Neural Networks
Stabilize the Latent Space for Image Autoregressive Modeling: A Unified Perspective
Learning Cortico-Muscular Dependence through Orthonormal Decomposition of Density Ratios
Sparse-view Pose Estimation and Reconstruction via Analysis by Generative Synthesis
MonoMAE: Enhancing Monocular 3D Detection through Depth-Aware Masked Autoencoders
Toward a Theory of Tokenization in LLMs
Alignment at Pre-training! Towards Native Alignment for Arabic LLMs
Human Expertise in Algorithmic Prediction
Solving Inverse Problems via Diffusion Optimal Control
Quantum Algorithms for Non-smooth Non-convex Optimization
Hierarchical Selective Classification
Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learning
How In-Context Learning Emerges from Training on Unstructured Data: The Role of Co-Occurrence, Positional Information, and Noise Structures
Multi-modal Transfer Learning between Biological Foundation Models
Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates
The Implicit Bias of Adam on Separable Data
On $f$-Divergence Principled Domain Adaptation: An Improved Framework
pFedClub: Controllable Heterogeneous Model Aggregation for Personalized Federated Learning
Causal vs. Anticausal merging of predictors
Co-occurrence is not Factual Association in Language Models
Feedback control guides credit assignment in biological circuits
Simplified and Generalized Masked Diffusion for Discrete Data
RestoreAgent: Autonomous Image Restoration Agent via Multimodal Large Language Models
Take A Shortcut Back: Mitigating the Gradient Vanishing for Training Spiking Neural Networks
Do Counterfactually Fair Image Classifiers Satisfy Group Fairness? -- A Theoretical and Empirical Study
Is Programming by Example solved by LLMs?
Approximated Orthogonal Projection Unit: Stabilizing Regression Network Training Using Natural Gradient
ManiPose: Manifold-Constrained Multi-Hypothesis 3D Human Pose Estimation
On the Use of Anchoring for Training Vision Models
Learning Diffusion at Lightspeed
Equivariant Machine Learning on Graphs with Nonlinear Spectral Filters
MomentumSMoE: Integrating Momentum into Sparse Mixture of Experts
Causal Discovery from Event Sequences by Local Cause-Effect Attribution
Proving Theorems Recursively
Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion
A Simple and Optimal Approach for Universal Online Learning with Gradient Variations
Class Distribution Shifts in Zero-Shot Learning: Learning Robust Representations
MAmmoTH2: Scaling Instructions from the Web
Controlled maximal variability along with reliable performance in recurrent neural networks
Neural Concept Binder
AV-Cloud: Spatial Audio Rendering Through Audio-Visual Cloud Splatting
Multi-Label Learning with Stronger Consistency Guarantees
FedNE: Surrogate-Assisted Federated Neighbor Embedding for Privacy-Preserving Dimensionality Reduction
Improving Sparse Decomposition of Language Model Activations with Gated Sparse Autoencoders
Neural Gaffer: Relighting Any Object via Diffusion
Multimodal foundation world models for generalist embodied agents
Bridging Geometric States via Generative Modeling
G2D: From Global to Dense Radiography Representation Learning via Vision-Language Pre-training
PERIA: Perceive, Reason, Imagine, Act via Holistic Language and Vision Planning for Manipulation
UniMTS: Unified Pre-training for Motion Time Series
HiCo: Hierarchical Controllable Diffusion Model for Layout-to-image Generation
Hamiltonian Monte Carlo on ReLU Neural Networks is Inefficient
Understanding Linear Probing then Fine-tuning Language Models from NTK Perspective
Time-Varying LoRA: Towards Effective Cross-Domain Fine-Tuning of Diffusion Models
VFIMamba: Video Frame Interpolation with State Space Models
Leveraging Environment Interaction for Automated PDDL Generation and Planning with Large Language Models
Improving the Training of Rectified Flows
Does Video-Text Pretraining Help Open-Vocabulary Online Action Detection?
Rapid Plug-in Defenders
Pretrained Optimization Model for Zero-Shot Black Box Optimization
CogVLM: Visual Expert for Pretrained Language Models
Flatten Anything: Unsupervised Neural Surface Parameterization
Energy-Guided Continuous Entropic Barycenter Estimation for General Costs
Conservative Fine-Tuning of Diffusion Models from Offline Data
Transformers Can Do Arithmetic with the Right Embeddings
Solving Zero-Sum Markov Games with Continous State via Spectral Dynamic Embedding
Referring Human Pose and Mask Estimation In the Wild
PaGoDA: Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teacher
PaDeLLM-NER: Parallel Decoding in Large Language Models for Named Entity Recognition
RobIR: Robust Inverse Rendering for High-Illumination Scenes
Navigating Extremes: Dynamic Sparsity in Large Output Spaces
Private Geometric Median
Implicit Optimization Bias of Next-token Prediction in Linear Models
Is Cross-validation the Gold Standard to Evaluate Model Performance?
Robust Sparse Regression with Non-Isotropic Designs
Diversity from the Void: Training Adaptive Agents in Open-Ended Simulators
Mission Impossible: A Statistical Perspective on Jailbreaking LLMs
Gradient-variation Online Learning under Generalized Smoothness
Auditing Local Explanations is Hard
Generative Modeling of Molecular Dynamics Trajectories
Model Collapse Demystified: The Case of Regression
A Theoretical Perspective for Speculative Decoding Algorithm
Bandits with Preference Feedback: A Stackelberg Game Perspective
The Fine-Grained Complexity of Gradient Computation for Training Large Language Models
A Tractable Inference Perspective of Offline RL
Learning Formal Mathematics From Intrinsic Motivation
Physics-Informed Variational State-Space Gaussian Processes
Treatment of Statistical Estimation Problems in Randomized Smoothing for Adversarial Robustness
Linear Transformers are Versatile In-Context Learners
Private Stochastic Convex Optimization with Heavy Tails: Near-Optimality from Simple Reductions
Implicit Curriculum in Procgen Made Explicit
Polynomial-Time Computation of Exact $\Phi$-Equilibria in Polyhedral Games
Bounds for the smallest eigenvalue of the NTK for arbitrary spherical data of arbitrary dimension
Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks
A Universal Growth Rate for Learning with Smooth Surrogate Losses
Policy-shaped prediction: avoiding distractions in model-based RL
An Equivalence Between Static and Dynamic Regret Minimization
Classification Diffusion Models: Revitalizing Density Ratio Estimation
Improving self-training under distribution shifts via anchored confidence with theoretical guarantees
SpeedLoader: An I/O efficient scheme for heterogeneous and distributed LLM operation
Learning to be Smooth: An End-to-End Differentiable Particle Smoother
Efficiency for Free: Ideal Data Are Transportable Representations
Aligning Audio-Visual Joint Representations with an Agentic Workflow
Learning Hybrid Models for Digital Twins of Dynamical Systems
Déjà Vu Memorization in Vision–Language Models
On the Role of Information Structure in Reinforcement Learning for Partially-Observable Sequential Teams and Games
Learning Optimal Tax Design in Nonatomic Congestion Games
How Diffusion Models Learn to Factorize and Compose
Streaming Bayes GFlowNets
On Divergence Measures for Training GFlowNets
Distribution Learning with Valid Outputs Beyond the Worst-Case
Information-theoretic Limits of Online Classification with Noisy Labels
Non-convolutional graph neural networks.
Learning from Snapshots of Discrete and Continuous Data Streams
First-Order Minimax Bilevel Optimization
Edit Distance Robust Watermarks via Indexing Pseudorandom Codes
Last-Iterate Convergence for Generalized Frank-Wolfe in Monotone Variational Inequalities
CosAE: Learnable Fourier Series for Image Restoration
Slot State Space Models
Great Minds Think Alike: The Universal Convergence Trend of Input Salience
Any2Policy: Learning Visuomotor Policy with Any-Modality
S-STE: Continuous Pruning Function for Efficient 2:4 Sparse Pre-training
Universal Rates of Empirical Risk Minimization
Active, anytime-valid risk controlling prediction sets
Instance-Specific Asymmetric Sensitivity in Differential Privacy
Optimal Classification under Performative Distribution Shift
Training Data Attribution via Approximate Unrolling
Graph Structure Inference with BAM: Introducing the Bilinear Attention Mechanism
The Sample Complexity of Gradient Descent in Stochastic Convex Optimization
Private and Personalized Frequency Estimation in a Federated Setting
Segment Anything without Supervision
Safety through feedback in Constrained RL
ClashEval: Quantifying the tug-of-war between an LLM’s internal prior and external evidence
Alignment for Honesty
Capturing the denoising effect of PCA via compression ratio
Inference of Neural Dynamics Using Switching Recurrent Neural Networks
Length Optimization in Conformal Prediction
Autonomous Driving with Spiking Neural Networks
Localizing Memorization in SSL Vision Encoders
Dynamics of Supervised and Reinforcement Learning in the Non-Linear Perceptron
Identifying Selections for Unsupervised Subtask Discovery
Contextual Multinomial Logit Bandits with General Value Functions
Generalized Eigenvalue Problems with Generative Priors
GS-Blur: A 3D Scene-Based Dataset for Realistic Image Deblurring
We use cookies to store which papers have been visited.
I agree
Successful Page Load
NeurIPS uses cookies for essential functions only. We do not sell your personal information.
Our Privacy Policy »
Accept Cookies
We use cookies to store which papers have been visited.
I agree
