International Conference on Machine Learning (ICML) - 2025

Website:

Venue Year Papers
Repro. Score Reproducibility Score based on Gundersen et al. (2025)
Doc. Mean Doc. Median Dataset Doc. Code Doc. Other Doc. % Empirical % Industry Website
ICML 2025 3330 0.61 4.42 5.0 1.52 0.64 2.26 94.95% 36.69%
Pseudocode
Open Source Code
Open Datasets
Dataset Splits
Hardware Specification
Software Dependencies
Experiment Setup
"Who experiences large model decay and why?" A Hierarchical Framework for Diagnosing Heterogeneous Performance Drift 4
"Why Is There a Tumor?": Tell Me the Reason, Show Me the Evidence 5
$K^2$VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecasting 6
$S^2$FGL: Spatial Spectral Federated Graph Learning 4
$\mathcalVista\mathcalDPO$: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models 4
$\mathrmμ$nit Scaling: Simple and Scalable FP8 LLM Training 2
$\textttI$^2$MoE$: Interpretable Multimodal Interaction-aware Mixture-of-Experts 6
$∞$-Video: A Training-Free Approach to Long Video Understanding via Continuous-Time Memory Consolidation 4
(How) Can Transformers Predict Pseudo-Random Numbers? 4
(How) Do Language Models Track State? 5
3D Question Answering via only 2D Vision-Language Models 4
3D-LMVIC: Learning-based Multi-View Image Compression with 3D Gaussian Geometric Priors 5
A Bayesian Model Selection Criterion for Selecting Pretraining Checkpoints 3
A Bregman Proximal Viewpoint on Neural Operators 4
A Causal World Model Underlying Next Token Prediction: Exploring GPT in a Controlled Environment 5
A Certified Unlearning Approach without Access to Source Data 5
A Chaotic Dynamics Framework Inspired by Dorsal Stream for Event Signal Processing 5
A Checks-and-Balances Framework for Context-Aware Ethical AI Alignment 4
A Classification View on Meta Learning Bandits 3
A Closer Look at Backdoor Attacks on CLIP 4
A Closer Look at Generalized BH Algorithm for Out-of-Distribution Detection 4
A Closer Look at Multimodal Representation Collapse 3
A Closer Look at Transformers for Time Series Forecasting: Understanding Why They Work and Where They Struggle 3
A Cognac Shot To Forget Bad Memories: Corrective Unlearning for Graph Neural Networks 5
A Comprehensive Framework for Analyzing the Convergence of Adam: Bridging the Gap with SGD 1
A Computationally Efficient Algorithm for Infinite-Horizon Average-Reward Linear MDPs 1
A Cross Modal Knowledge Distillation & Data Augmentation Recipe for Improving Transcriptomics Representations through Morphological Features 4
A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Attention Networks 1
A First-order Generative Bilevel Optimization Framework for Diffusion Models 6
A Forget-and-Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Control 3
A General Framework for Inference-time Scaling and Steering of Diffusion Models 5
A General Graph Spectral Wavelet Convolution via Chebyshev Order Decomposition 5
A General Representation-Based Approach to Multi-Source Domain Adaptation 3
A Generalizable Physics-Enhanced State Space Model for Long-Term Dynamics Forecasting in Complex Environments 5
A Generalization Result for Convergence in Learning-to-Optimize 3
A Generalization Theory for Zero-Shot Prediction 5
A Generic Family of Graphical Models: Diversity, Efficiency, and Heterogeneity 4
A Geometric Approach to Personalized Recommendation with Set-Theoretic Constraints Using Box Embeddings 6
A Hitchhiker’s Guide to Scaling Law Estimation 4
A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks 5
A Lens into Interpretable Transformer Mistakes via Semantic Dependency 3
A Likelihood Based Approach to Distribution Regression Using Conditional Deep Generative Models 3
A Machine Learning Approach to Duality in Statistical Physics 3
A Manifold Perspective on the Statistical Generalization of Graph Neural Networks 4
A Market for Accuracy: Classification Under Competition 5
A Mathematical Framework for AI-Human Integration in Work 2
A Memory Efficient Randomized Subspace Optimization Method for Training Large Language Models 5
A Meta-learner for Heterogeneous Effects in Difference-in-Differences 2
A Mixed-Curvature based Pre-training Paradigm for Multi-Task Vehicle Routing Solver 5
A Mixture-Based Framework for Guiding Diffusion Models 5
A Model of Place Field Reorganization During Reward Maximization 2
A Multi-Region Brain Model to Elucidate the Role of Hippocampus in Spatially Embedded Decision-Making 1
A Near Linear Query Lower Bound for Submodular Maximization 1
A Near-Optimal Single-Loop Stochastic Algorithm for Convex Finite-Sum Coupled Compositional Optimization 5
A New Approach to Backtracking Counterfactual Explanations: A Unified Causal Framework for Efficient Model Interpretability 2
A New Concentration Inequality for Sampling Without Replacement and Its Application for Transductive Learning 1
A Non-Asymptotic Convergent Analysis for Scored-Based Graph Generative Model via a System of Stochastic Differential Equations 3
A Non-isotropic Time Series Diffusion Model with Moving Average Transitions 4
A Novel Characterization of the Population Area Under the Risk Coverage Curve (AURC) and Rates of Finite Sample Estimators 4
A Parameter-Free and Near-Optimal Zeroth-Order Algorithm for Stochastic Convex Optimization 3
A Parametric Contextual Online Learning Theory of Brokerage 1
A Peer-review Look on Multi-modal Clustering: An Information Bottleneck Realization Method 5
A Physics-Augmented Deep Learning Framework for Classifying Single Molecule Force Spectroscopy Data 7
A Physics-Informed Machine Learning Framework for Safe and Optimal Control of Autonomous Systems 3
A Reasoning-Based Approach to Cryptic Crossword Clue Solving 6
A Recipe for Causal Graph Regression: Confounding Effects Revisited 4
A Reduction Framework for Distributionally Robust Reinforcement Learning under Average Reward 3
A Reductions Approach to Risk-Sensitive Reinforcement Learning with Optimized Certainty Equivalents 3
A Rescaling-Invariant Lipschitz Bound Based on Path-Metrics for Modern ReLU Network Parameterizations 6
A Sample Efficient Conditional Independence Test in the Presence of Discretization 4
A Selective Learning Method for Temporal Graph Continual Learning 6
A Sharper Global Convergence Analysis for Average Reward Reinforcement Learning via an Actor-Critic Approach 1
A Simple Model of Inference Scaling Laws 3
A Square Peg in a Square Hole: Meta-Expert for Long-Tailed Semi-Supervised Learning 7
A Stronger Mixture of Low-Rank Experts for Fine-Tuning Foundation Models 5
A Sub-Problem Quantum Alternating Operator Ansatz for Correlation Clustering 3
A Tale of Two Structures: Do LLMs Capture the Fractal Complexity of Language? 2
A Theoretical Framework For Overfitting In Energy-based Modeling 2
A Theoretical Justification for Asymmetric Actor-Critic Algorithms 1
A Theoretical Study of (Hyper) Self-Attention through the Lens of Interactions: Representation, Training, Generalization 2
A Theory for Conditional Generative Modeling on Multiple Data Sources 4
A Trichotomy for List Transductive Online Learning 1
A Two-Stage Learning-to-Defer Approach for Multi-Task Learning 6
A Unified Approach to Routing and Cascading for LLMs 5
A Unified Comparative Study with Generalized Conformity Scores for Multi-Output Conformal Regression 5
A Unified Framework for Entropy Search and Expected Improvement in Bayesian Optimization 4
A Unified Framework for Generalization Error Analysis of Learning with Arbitrary Discrete Weak Features 4
A Unified Theoretical Analysis of Private and Robust Offline Alignment: from RLHF to DPO 3
A Unified View on Learning Unnormalized Distributions via Noise-Contrastive Estimation 1
A Variational Framework for Improving Naturalness in Generative Spoken Language Models 5
A Variational Information Theoretic Approach to Out-of-Distribution Detection 5
A Variational Perspective on Generative Protein Fitness Optimization 4
A Versatile Influence Function for Data Attribution with Non-Decomposable Loss 5
A-PSRO: A Unified Strategy Learning Method with Advantage Metric for Normal-form Games 4
AAAR-1.0: Assessing AI’s Potential to Assist Research 4
ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $α$-$β$-Divergence 6
ABNet: Adaptive explicit-Barrier Net for Safe and Scalable Robot Learning 5
ADDQ: Adaptive distributional double Q-learning 5
ADHMR: Aligning Diffusion-based Human Mesh Recovery via Direct Preference Optimization 3
ADIOS: Antibody Development via Opponent Shaping 5
AEQA-NAT : Adaptive End-to-end Quantization Alignment Training Framework for Non-autoregressive Machine Translation 4
AGAV-Rater: Adapting Large Multimodal Model for AI-Generated Audio-Visual Quality Assessment 5
AI for Global Climate Cooperation: Modeling Global Climate Negotiations, Agreements, and Long-Term Cooperation in RICE-N 5
AKORN: Adaptive Knots generated Online for RegressioN splines 3
AKRMap: Adaptive Kernel Regression for Trustworthy Visualization of Cross-Modal Embeddings 5
ALMTokenizer: A Low-bitrate and Semantic-rich Audio Codec Tokenizer for Audio Language Modeling 5
AMPO: Active Multi Preference Optimization for Self-play Preference Selection 3
ARS: Adaptive Reward Scaling for Multi-Task Reinforcement Learning 3
ATA: Adaptive Task Allocation for Efficient Resource Management in Distributed Machine Learning 4
AUTOCIRCUIT-RL: Reinforcement Learning-Driven LLM for Automated Circuit Topology Generation 4
Ab Initio Nonparametric Variable Selection for Scalable Symbolic Regression with Large $p$ 6
Accelerated Diffusion Models via Speculative Sampling 3
Accelerating LLM Inference with Lossless Speculative Decoding Algorithms for Heterogeneous Vocabularies 5
Accelerating Large Language Model Reasoning via Speculative Search 4
Accelerating Linear Recurrent Neural Networks for the Edge with Unstructured Sparsity 6
Accelerating PDE-Constrained Optimization by the Derivative of Neural Operators 5
Accelerating Quantum Reinforcement Learning with a Quantum Natural Policy Gradient Based Approach 1
Accelerating Spectral Clustering under Fairness Constraints 4
Accelerating Unbiased LLM Evaluation via Synthetic Feedback 6
Accurate Identification of Communication Between Multiple Interacting Neural Populations 3
Accurate and Efficient World Modeling with Masked Latent Transformers 4
Achieving Linear Speedup and Near-Optimal Complexity for Decentralized Optimization over Row-stochastic Networks 3
Action Dubber: Timing Audible Actions via Inflectional Flow 6
Action-Constrained Imitation Learning 4
Action-Dependent Optimality-Preserving Reward Shaping 3
Action-Minimization Meets Generative Modeling: Efficient Transition Path Sampling with the Onsager-Machlup Functional 5
ActionPiece: Contextually Tokenizing Action Sequences for Generative Recommendation 6
Activation Space Interventions Can Be Transferred Between Large Language Models 4
Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss 5
Active Evaluation Acquisition for Efficient LLM Benchmarking 4
Active Fine-Tuning of Multi-Task Policies 4
Active Learning for Efficient Discovery of Optimal Combinatorial Perturbations 5
Active Learning of Deep Neural Networks via Gradient-Free Cutting Planes 6
Active Learning with Selective Time-Step Acquisition for PDEs 5
Active Reward Modeling: Adaptive Preference Labeling for Large Language Model Alignment 5
Active Treatment Effect Estimation via Limited Samples 5
Active feature acquisition via explainability-driven ranking 4
Actor-Critics Can Achieve Optimal Sample Efficiency 4
Ad Hoc Teamwork via Offline Goal-Based Decision Transformers 3
Ad-Hoc Human-AI Coordination Challenge 4
AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism 6
AdaPTS: Adapting Univariate Foundation Models to Probabilistic Multivariate Time Series Forecasting 4
AdaSplash: Adaptive Sparse Flash Attention 5
AdaWorld: Learning Adaptable World Models with Latent Actions 4
Adapter Naturally Serves as Decoupler for Cross-Domain Few-Shot Semantic Segmentation 4
Adapting Precomputed Features for Efficient Graph Condensation 5
Adapting While Learning: Grounding LLMs for Scientific Problems with Tool Usage Adaptation 5
Adapting to Evolving Adversaries with Regularized Continual Robust Training 4
Adapting to Linear Separable Subsets with Large-Margin in Differentially Private Learning 2
Adaptive Data Collection for Robust Learning Across Multiple Distributions 4
Adaptive Elicitation of Latent Information Using Natural Language 4
Adaptive Estimation and Learning under Temporal Distribution Shift 4
Adaptive Exploration for Multi-Reward Multi-Policy Evaluation 4
Adaptive Flow Matching for Resolving Small-Scale Physics 5
Adaptive Learn-then-Test: Statistically Valid and Efficient Hyperparameter Selection 3
Adaptive Localization of Knowledge Negation for Continual LLM Unlearning 5
Adaptive Median Smoothing: Adversarial Defense for Unlearned Text-to-Image Diffusion Models at Inference Time 5
Adaptive Message Passing: A General Framework to Mitigate Oversmoothing, Oversquashing, and Underreaching 4
Adaptive Multi-prompt Contrastive Network for Few-shot Out-of-distribution Detection 4
Adaptive Partitioning Schemes for Optimistic Optimization 5
Adaptive Sample Sharing for Multi Agent Linear Bandits 5
Adaptive Self-improvement LLM Agentic System for ML Library Development 3
Adaptive Sensitivity Analysis for Robust Augmentation against Natural Corruptions in Image Segmentation 6
Adaptive kernel predictors from feature-learning infinite limits of neural networks 3
AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence 4
Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization 5
Addressing Imbalanced Domain-Incremental Learning through Dual-Balance Collaborative Experts 6
Addressing Misspecification in Simulation-based Inference through Data-driven Calibration 5
Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint Matching 6
Adjusting Model Size in Continual Gaussian Processes: How Big is Big Enough? 7
Adjustment for Confounding using Pre-Trained Representations 5
AdvAgent: Controllable Blackbox Red-teaming on Web Agents 6
AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion Models 5
AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs 6
Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations 4
Advancing Personalized Learning with Neural Collapse for Long-Tail Challenge 3
Adversarial Combinatorial Semi-bandits with Graph Feedback 1
Adversarial Cooperative Rationalization: The Risk of Spurious Correlations in Even Clean Datasets 5
Adversarial Inception Backdoor Attacks against Reinforcement Learning 5
Adversarial Inputs for Linear Algebra Backends 7
Adversarial Perturbations Are Formed by Iteratively Learning Linear Combinations of the Right Singular Vectors of the Adversarial Jacobian 5
Adversarial Reasoning at Jailbreaking Time 5
Adversarial Robust Generalization of Graph Neural Networks 5
Adversarial Robustness in Two-Stage Learning-to-Defer: Algorithms and Guarantees 6
Adversarial Robustness via Deformable Convolution with Stochasticity 6
Adversaries Can Misuse Combinations of Safe Models 4
Aequa: Fair Model Rewards in Collaborative Learning via Slimmable Networks 6
AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models 5
AffinityFlow: Guided Flows for Antibody Affinity Maturation 4
Agent Reviewers: Domain-specific Multimodal Agents with Shared Memory for Paper Review 5
Agent Workflow Memory 5
Agent-Centric Actor-Critic for Asynchronous Multi-Agent Reinforcement Learning 4
Agent-as-a-Judge: Evaluate Agents with Agents 4
Aggregation Buffer: Revisiting DropEdge with a New Parameter Block 5
Aggregation of Dependent Expert Distributions in Multimodal Variational Autoencoders 6
Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction 5
Alberta Wells Dataset: Pinpointing Oil and Gas Wells from Satellite Imagery 5
Algorithm Development in Neural Networks: Insights from the Streaming Parity Task 4
Algorithmic Recourse for Long-Term Improvement 7
Algorithms and Hardness for Active Learning on Graphs 4
Algorithms with Calibrated Machine Learning Predictions 3
Aligned Multi Objective Optimization 3
Aligning LLMs by Predicting Preferences from User Writing Samples 5
Aligning Multimodal Representations through an Information Bottleneck 3
Aligning Protein Conformation Ensemble Generation with Physical Feedback 5
Aligning Spoken Dialogue Models from User Interactions 3
Aligning with Logic: Measuring, Evaluating and Improving Logical Preference Consistency in Large Language Models 6
All-Purpose Mean Estimation over R: Optimal Sub-Gaussianity with Outlier Robustness and Low Moments Performance 1
All-atom Diffusion Transformers: Unified generative modelling of molecules and materials 6
All-atom inverse protein folding through discrete flow matching 4
Almost Optimal Fully Dynamic $k$-Center Clustering with Recourse 1
Alpha-SQL: Zero-Shot Text-to-SQL using Monte Carlo Tree Search 6
AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization 4
AlphaPO: Reward Shape Matters for LLM Alignment 3
AlphaQCM: Alpha Discovery in Finance with Distributional Reinforcement Learning 4
AlphaVerus: Bootstrapping Formally Verified Code Generation through Self-Improving Translation and Treefinement 5
An Adaptive Orthogonal Convolution Scheme for Efficient and Flexible CNN Architectures 6
An All-Atom Generative Model for Designing Protein Complexes 5
An Analysis for Reasoning Bias of Language Models with Small Initialization 3
An Architecture Search Framework for Inference-Time Techniques 4
An Asymptotically Optimal Approximation Algorithm for Multiobjective Submodular Maximization at Scale 6
An Augmentation-Aware Theory for Self-Supervised Contrastive Learning 4
An Effective and Secure Federated Multi-View Clustering Method with Information-Theoretic Perspective 5
An Efficient Matrix Multiplication Algorithm for Accelerating Inference in Binary and Ternary Neural Networks 5
An Efficient Private GPT Never Autoregressively Decodes 2
An Efficient Pruner for Large Language Model with Theoretical Guarantee 5
An Efficient Search-and-Score Algorithm for Ancestral Graphs using Multivariate Information Scores for Complex Non-linear and Categorical Data 3
An Empirical Study on Configuring In-Context Learning Demonstrations for Unleashing MLLMs’ Sentimental Perception Capability 4
An End-to-End Model for Logits-Based Large Language Models Watermarking 5
An Error Analysis of Flow Matching for Deep Generative Modeling 0
An Expressive and Self-Adaptive Dynamical System for Efficient Function Learning 3
An Improved Clique-Picking Algorithm for Counting Markov Equivalent DAGs via Super Cliques Transfer 3
An Instrumental Value for Data Production and its Application to Data Pricing 4
An Interpretable N-gram Perplexity Threat Model for Large Language Model Jailbreaks 4
An Online Adaptive Sampling Algorithm for Stochastic Difference-of-convex Optimization with Time-varying Distributions 2
An Online Statistical Framework for Out-of-Distribution Detection 2
An Optimistic Algorithm for online CMDPS with Anytime Adversarial Constraints 2
An analytic theory of creativity in convolutional diffusion models 3
An in depth look at the Procrustes-Wasserstein distance: properties and barycenters 4
AnalogGenie-Lite: Enhancing Scalability and Precision in Circuit Topology Discovery through Lightweight Graph Modeling 6
Analytical Construction on Geometric Architectures: Transitioning from Static to Temporal Link Prediction 6
Analytical Lyapunov Function Discovery: An RL-based Generative Approach 4
Analyze Feature Flow to Enhance Interpretation and Steering in Language Models 3
Angle Domain Guidance: Latent Diffusion Requires Rotation Rather Than Extrapolation 4
Annealing Flow Generative Models Towards Sampling High-Dimensional and Multi-Modal Distributions 5
Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning Attack 4
AnyEdit: Edit Any Knowledge Encoded in Language Models 4
Anytime-Constrained Equilibria in Polynomial Time 1
Approximate Differential Privacy of the $\ell_2$ Mechanism 3
Approximate Forest Completion and Learning-Augmented Algorithms for Metric Minimum Spanning Trees 5
Approximately Correct Label Distribution Learning 5
Approximating Latent Manifolds in Neural Networks via Vanishing Ideals 5
Approximation to Smooth Functions by Low-Rank Swish Networks 3
Arbitrarily-Conditioned Multi-Functional Diffusion for Multi-Physics Emulation 6
Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models 5
Are High-Quality AI-Generated Images More Difficult for Models to Detect? 2
Are LLMs Prescient? A Continuous Evaluation using Daily News as the Oracle 4
Are Large Brainwave Foundation Models Capable Yet ? Insights from Fine-Tuning 3
Are Large Language Models Ready for Multi-Turn Tabular Data Analysis? 4
Are Sparse Autoencoders Useful? A Case Study in Sparse Probing 3
Armijo Line-search Can Make (Stochastic) Gradient Descent Provably Faster 3
ArrayDPS: Unsupervised Blind Speech Separation with a Diffusion Prior 7
Arrow: Accelerator for Time Series Causal Discovery with Time Weaving 5
Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models 6
AssistanceZero: Scalably Solving Assistance Games 4
AsymRnR: Video Diffusion Transformers Acceleration with Asymmetric Reduction and Restoration 4
Asymmetric Decision-Making in Online Knowledge Distillation: Unifying Consensus and Divergence 3
AtlasD: Automatic Local Symmetry Discovery 4
Attention Mechanisms Perspective: Exploring LLM Processing of Graph-Structured Data 3
Attention-Level Speculation 7
Attention-Only Transformers via Unrolled Subspace Denoising 3
Attributes Shape the Embedding Space of Face Recognition Models 4
AuPair: Golden Example Pairs for Code Repair 4
Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities 6
Auditing $f$-differential privacy in one run 4
Auditing Prompt Caching in Language Model APIs 3
Auto-reconfiguration for Latency Minimization in CPU-based DNN Serving 4
AutoAL: Automated Active Learning with Differentiable Query Strategy Search 6
AutoAdvExBench: Benchmarking Autonomous Exploitation of Adversarial Example Defenses 4
AutoCATE: End-to-End, Automated Treatment Effect Estimation 5
AutoElicit: Using Large Language Models for Expert Prior Elicitation in Predictive Modelling 6
AutoEval Done Right: Using Synthetic Data for Model Evaluation 6
AutoGFM: Automated Graph Foundation Model with Adaptive Architecture Customization 6
AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML 7
AutoStep: Locally adaptive involutive MCMC 4
Autoencoder-Based Hybrid Replay for Class-Incremental Learning 4
Autoformulation of Mathematical Optimization Models Using LLMs 3
Automated Benchmark Generation for Repository-Level Coding Tasks 3
Automated Hypothesis Validation with Agentic Sequential Falsifications 5
Automated Red Teaming with GOAT: the Generative Offensive Agent Tester 3
Automatic Differentiation of Optimization Algorithms with Time-Varying Updates 3
Automatic Reward Shaping from Confounded Offline Data 4
Automatically Identify and Rectify: Robust Deep Contrastive Multi-view Clustering in Noisy Scenarios 5
Automatically Interpreting Millions of Features in Large Language Models 4
Autonomy-of-Experts Models 6
Average Certified Radius is a Poor Metric for Randomized Smoothing 5
Average Sensitivity of Hierarchical $k$-Median Clustering 5
Avoiding Catastrophe in Online Learning by Asking for Help 1
Avoiding Leakage Poisoning: Concept Interventions Under Distribution Shifts 6
Avoiding spurious sharpness minimization broadens applicability of SAM 4
AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders 4
B-score: Detecting biases in large language models using response history 3
BAME: Block-Aware Mask Evolution for Efficient N:M Sparse Training 6
BARK: A Fully Bayesian Tree Kernel for Black-box Optimization 5
BARNN: A Bayesian Autoregressive and Recurrent Neural Network 6
BAnG: Bidirectional Anchored Generation for Conditional RNA Design 6
BCE vs. CE in Deep Feature Learning 3
BDC-CLIP: Brownian Distance Covariance for Adapting CLIP to Action Recognition 4
BECAME: Bayesian Continual Learning with Adaptive Model Merging 6
BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute 5
BILBO: BILevel Bayesian Optimization 5
BOOD: Boundary-based Out-Of-Distribution Data Generation 5
BOPO: Neural Combinatorial Optimization via Best-anchored and Objective-guided Preference Optimization 6
BRIDGE: Bootstrapping Text to Control Time-Series Generation via Multi-Agent Iterative Optimization and Diffusion Modeling 6
BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning 3
BSLoRA: Enhancing the Parameter Efficiency of LoRA with Intra-Layer and Inter-Layer Sharing 6
BSO: Binary Spiking Online Optimization Algorithm 5
BSemiFL: Semi-supervised Federated Learning via a Bayesian Approach 6
BaWA: Automatic Optimizing Pruning Metric for Large Language Models with Balanced Weight and Activation 4
BackSlash: Rate Constrained Optimized Training of Large Language Models 2
Backdoor Attacks in Token Selection of Attention Mechanism 3
BalancEdit: Dynamically Balancing the Generality-Locality Trade-off in Multi-modal Model Editing 5
Balanced Learning for Domain Adaptive Semantic Segmentation 5
Balancing Efficiency and Expressiveness: Subgraph GNNs with Walk-Based Centrality 6
Balancing Interference and Correlation in Spatial Experimental Designs: A Causal Graph Cut Approach 4
Balancing Model Efficiency and Performance: Adaptive Pruner for Long-tailed Data 5
Balancing Preservation and Modification: A Region and Semantic Aware Metric for Instruction-Based Image Editing 4
Balancing the Scales: A Theoretical and Algorithmic Framework for Learning from Imbalanced Data 3
BanditSpec: Adaptive Speculative Decoding via Bandit Algorithms 6
Banyan: Improved Representation Learning with Explicit Structure 5
Batch List-Decodable Linear Regression via Higher Moments 1
BaxBench: Can LLMs Generate Correct and Secure Backends? 4
Bayesian Active Learning for Bivariate Causal Discovery 3
Bayesian Basis Function Approximation for Scalable Gaussian Process Priors in Deep Generative Models 5
Bayesian Inference for Correlated Human Experts and Classifiers 5
Bayesian Neural Scaling Law Extrapolation with Prior-Data Fitted Networks 5
Bayesian Optimization from Human Feedback: Near-Optimal Regret Bounds 5
Bayesian Weight Enhancement with Steady-State Adaptation for Test-time Adaptation in Dynamic Environments 5
Be Confident: Uncovering Overfitting in MLLM Multi-Task Tuning 4
Be a Goldfish: Forgetting Bad Conditioning in Sparse Linear Regression via Variational Autoencoders 2
Behavior-Regularized Diffusion Policy Optimization for Offline Reinforcement Learning 5
Behavior-agnostic Task Inference for Robust Offline In-context Reinforcement Learning 4
Behavioral Exploration: Learning to Explore via In-Context Adaptation 4
Bellman Unbiasedness: Toward Provably Efficient Distributional Reinforcement Learning with General Value Function Approximation 1
Benchmarking Abstract and Reasoning Abilities Through A Theoretical Perspective 5
Benchmarking Quantum Reinforcement Learning 6
Benefits of Early Stopping in Gradient Descent for Overparameterized Logistic Regression 0
Benign Overfitting in Token Selection of Attention Mechanism 4
Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety 5
Best Subset Selection: Optimal Pursuit for Feature Selection and Elimination 5
Best of Both Worlds: Advantages of Hybrid Graph Sequence Models 2
Best of Both Worlds: Regret Minimization versus Minimax Play 4
Better to Teach than to Give: Domain Generalized Semantic Segmentation via Agent Queries with Diffusion Model Guidance 5
Beyond Atoms: Enhancing Molecular Pretrained Representations with 3D Space Modeling 4
Beyond Bradley-Terry Models: A General Preference Model for Language Model Alignment 4
Beyond CVaR: Leveraging Static Spectral Risk Measures for Enhanced Decision-Making in Distributional Reinforcement Learning 3
Beyond Communication Overhead: A Multilevel Monte Carlo Approach for Mitigating Compression Bias in Distributed Learning 4
Beyond Confidence: Exploiting Homogeneous Pattern for Semi-Supervised Semantic Segmentation 5
Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts 6
Beyond Entropy: Region Confidence Proxy for Wild Test-Time Adaptation 5
Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence 3
Beyond Log-Concavity and Score Regularity: Improved Convergence Bounds for Score-Based Generative Models in W2-distance 0
Beyond Low-rank Decomposition: A Shortcut Approach for Efficient On-Device Learning 7
Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation 4
Beyond Message Passing: Neural Graph Pattern Machine 6
Beyond Minimax Rates in Group Distributionally Robust Optimization via a Novel Notion of Sparsity 3
Beyond One-Hot Labels: Semantic Mixing for Model Calibration 5
Beyond Self-Interest: How Group Strategies Reshape Content Creation in Recommendation Platforms? 2
Beyond Self-Repellent Kernels: History-Driven Target Towards Efficient Nonlinear MCMC on General Graphs 3
Beyond Sensor Data: Foundation Models of Behavioral Data from Wearables Improve Health Predictions 3
Beyond Task-Specific Reasoning: A Unified Conditional Generative Framework for Abstract Visual Reasoning 4
Beyond The Rainbow: High Performance Deep Reinforcement Learning on a Desktop PC 6
Beyond Topological Self-Explainable GNNs: A Formal Explainability Perspective 6
Beyond Zero Initialization: Investigating the Impact of Non-Zero Initialization on LoRA Fine-Tuning Dynamics 4
Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion 7
Bi-perspective Splitting Defense: Achieving Clean-Seed-Free Backdoor Security 5
BiAssemble: Learning Collaborative Affordance for Bimanual Geometric Assembly 3
BiMaCoSR: Binary One-Step Diffusion Model Leveraging Flexible Matrix Compression for Real Super-Resolution 5
BiMark: Unbiased Multilayer Watermarking for Large Language Models 4
Bifurcate then Alienate: Incomplete Multi-view Clustering via Coupled Distribution Learning with Linear Overhead 3
Binary Hypothesis Testing for Softmax Models and Leverage Score Models 0
BinauralFlow: A Causal and Streamable Approach for High-Quality Binaural Speech Synthesis with Flow Matching Models 5
Bipartite Ranking From Multiple Labels: On Loss Versus Label Aggregation 3
Bivariate Causal Discovery with Proxy Variables: Integral Solving and Beyond 2
Black-Box Adversarial Attacks on LLM-Based Code Completion 5
Blink of an eye: a simple theory for feature localization in generative models 3
BlockDialect: Block-wise Fine-grained Mixed Format Quantization for Energy-Efficient LLM Inference 4
BoA: Attention-aware Post-training Quantization without Backpropagation 5
Bongard in Wonderland: Visual Puzzles that Still Make AI Go Mad? 4
Boost-and-Skip: A Simple Guidance-Free Diffusion for Minority Generation 4
Boosting Adversarial Robustness with CLAT: Criticality Leveraged Adversarial Training 5
Boosting Masked ECG-Text Auto-Encoders as Discriminative Learners 5
Boosting Multi-Domain Fine-Tuning of Large Language Models through Evolving Interactions between Samples 5
Boosting Protein Graph Representations through Static-Dynamic Fusion 5
Boosting Virtual Agent Learning and Reasoning: A Step-Wise, Multi-Dimensional, and Generalist Reward Model with Benchmark 3
Bootstrapping Self-Improvement of Language Model Programs for Zero-Shot Schema Matching 7
BounDr.E: Predicting Drug-likeness via Biomedical Knowledge Alignment and EM-like One-Class Boundary Optimization 6
Bounded Rationality for LLMs: Satisficing Alignment at Inference-Time 3
BoxLM: Unifying Structures and Semantics of Medical Concepts for Diagnosis Prediction in Healthcare 5
Branches: Efficiently Seeking Optimal Sparse Decision Trees via AO* 6
Breaking Barriers: Combinatorial Algorithms for Non-Monotone Submodular Maximization with Sublinear Adaptivity and $1/e$ Approximation 4
Breaking Silos: Adaptive Model Fusion Unlocks Better Time Series Forecasting 6
Breaking the $n^1.5$ Additive Error Barrier for Private and Efficient Graph Sparsification via Private Expander Decomposition 1
Breaking the Barrier of Hard Samples: A Data-Centric Approach to Synthetic Data for Medical Tasks 5
Breaking the Curse of Multiagency in Robust Multi-Agent Reinforcement Learning 1
Breaking the Quadratic Barrier: Robust Cardinality Sketches for Adaptive Queries 2
Bridging Fairness and Efficiency in Conformal Inference: A Surrogate-Assisted Group-Clustered Approach 3
Bridging Layout and RTL: Knowledge Distillation based Timing Prediction 5
Bridging Protein Sequences and Microscopy Images with Unified Diffusion Models 5
Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging 4
Broadband Ground Motion Synthesis by Diffusion Model with Minimal Condition 5
Byzantine-Resilient Federated Alternating Gradient Descent and Minimization for Partly-Decoupled Low Rank Matrix Learning 3
C-3PO: Compact Plug-and-Play Proxy Optimization to Achieve Human-like Retrieval-Augmented Generation 5
C2IQL: Constraint-Conditioned Implicit Q-learning for Safe Offline Reinforcement Learning 4
CABS: Conflict-Aware and Balanced Sparsification for Enhancing Model Merging 7
CACTI: Leveraging Copy Masking and Contextual Information to Improve Tabular Data Imputation 5
CAD-Editor: A Locate-then-Infill Framework with Automated Training Data Synthesis for Text-Based CAD Editing 5
CALM: Consensus-Aware Localized Merging for Multi-Task Learning 5
CAN: Leveraging Clients As Navigators for Generative Replay in Federated Continual Learning 3
CASE-Bench: Context-Aware SafEty Benchmark for Large Language Models 5
CAT Merging: A Training-Free Approach for Resolving Conflicts in Model Merging 6
CAT: Contrastive Adversarial Training for Evaluating the Robustness of Protective Perturbations in Latent Diffusion Models 4
CEGA: A Cost-Effective Approach for Graph-Based Model Extraction and Acquisition 6
CERTAIN: Context Uncertainty-aware One-Shot Adaptation for Context-based Offline Meta Reinforcement Learning 2
CFP-Gen: Combinatorial Functional Protein Generation via Diffusion Language Models 5
CFPT: Empowering Time Series Forecasting through Cross-Frequency Interaction and Periodic-Aware Timestamp Modeling 6
CHATS: Combining Human-Aligned Optimization and Test-Time Sampling for Text-to-Image Generation 4
CLARIFY: Contrastive Preference Reinforcement Learning for Untangling Ambiguous Queries 4
CLIMB: Data Foundations for Large Scale Multimodal Clinical Foundation Models 5
CLOVER: Cross-Layer Orthogonal Vectors Pruning 5
CMoS: Rethinking Time Series Prediction Through the Lens of Chunk-wise Spatial Correlations 6
COExpander: Adaptive Solution Expansion for Combinatorial Optimization 7
COGNATE: Acceleration of Sparse Tensor Programs on Emerging Hardware using Transfer Learning 3
COKE: Core Kernel for More Efficient Approximation of Kernel Weights in Multiple Kernel Clustering 4
COMRECGC: Global Graph Counterfactual Explainer through Common Recourse 5
COSDA: Counterfactual-based Susceptibility Risk Framework for Open-Set Domain Adaptation 7
CPCF: A Cross-Prompt Contrastive Framework for Referring Multimodal Large Language Models 4
CRANE: Reasoning with constrained LLM generation 5
CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization 5
CSG-ODE: ControlSynth Graph ODE For Modeling Complex Evolution of Dynamic Graphs 4
CSTrack: Enhancing RGB-X Tracking via Compact Spatiotemporal Features 5
CSV-Occ: Fusing Multi-frame Alignment for Occupancy Prediction with Temporal Cross State Space Model and Central Voting Mechanism 5
CTBench: A Library and Benchmark for Certified Training 5
CUPS: Improving Human Pose-Shape Estimators with Conformalized Deep Uncertainty 4
CVE-Bench: A Benchmark for AI Agents’ Ability to Exploit Real-World Web Application Vulnerabilities 4
Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing 5
CaDA: Cross-Problem Routing Solver with Constraint-Aware Dual-Attention 4
Cache Me If You Must: Adaptive Key-Value Quantization for Large Language Models 7
Calibrated Language Models and How to Find Them with Label Smoothing 6
Calibrated Physics-Informed Uncertainty Quantification 5
Calibrated Value-Aware Model Learning with Probabilistic Environment Models 3
Calibrating Video Watch-time Predictions with Credible Prototype Alignment 4
Can Biologically Plausible Temporal Credit Assignment Rules Match BPTT for Neural Similarity? E-prop as an Example 5
Can Classic GNNs Be Strong Baselines for Graph-level Tasks? Simple Architectures Meet Excellence 5
Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression 4
Can DBNNs Robust to Environmental Noise for Resource-constrained Scenarios? 6
Can Diffusion Models Learn Hidden Inter-Feature Rules Behind Images? 4
Can Large Language Models Understand Intermediate Representations in Compilers? 5
Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark 4
Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective 6
Can Transformers Learn Full Bayesian Inference in Context? 6
Can Transformers Reason Logically? A Study in SAT Solving 4
Can We Predict Performance of Large Models across Vision-Language Tasks? 5
Cannot See the Forest for the Trees: Invoking Heuristics and Biases to Elicit Irrational Choices of LLMs 2
Canonical Rank Adaptation: An Efficient Fine-Tuning Strategy for Vision Transformers 5
Cape: Context-Aware Prompt Perturbation Mechanism with Differential Privacy 5
Capturing Temporal Dynamics in Large-Scale Canopy Tree Height Estimation 5
Catch Your Emotion: Sharpening Emotion Perception in Multimodal Large Language Models 5
Catching Two Birds with One Stone: Reward Shaping with Dual Random Networks for Balancing Exploration and Exploitation 6
CateKV: On Sequential Consistency for Long-Context LLM Inference Acceleration 5
Categorical Distributional Reinforcement Learning with Kullback-Leibler Divergence: Convergence and Asymptotics 3
Categorical Schrödinger Bridge Matching 6
Catoni Contextual Bandits are Robust to Heavy-tailed Rewards 1
Causal Abstraction Inference under Lossy Representations 3
Causal Abstraction Learning based on the Semantic Embedding Principle 4
Causal Attribution Analysis for Continuous Outcomes 1
Causal Discovery from Conditionally Stationary Time Series 5
Causal Effect Identification in lvLiNGAM from Higher-Order Cumulants 4
Causal Invariance-aware Augmentation for Brain Graph Contrastive Learning 6
Causal Logistic Bandits with Counterfactual Fairness Constraints 2
Causal-PIK: Causality-based Physical Reasoning with a Physics-Informed Kernel 5
Causality Inspired Federated Learning for OOD Generalization 4
Causality-Aware Contrastive Learning for Robust Multivariate Time-Series Anomaly Detection 5
Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated Attention 3
CellFlux: Simulating Cellular Morphology Changes via Flow Matching 4
Censor Dependent Variational Inference 4
Certifiably Robust Model Evaluation in Federated Learning under Meta-Distributional Shifts 5
Certification for Differentially Private Prediction in Gradient-Based Training 5
Certified Unlearning for Neural Networks 4
Chameleon: A Flexible Data-mixing Framework for Language Model Pretraining and Finetuning 5
Channel Normalization for Time Series Channel Identification 5
Chaos Meets Attention: Transformers for Large-Scale Dynamical Prediction 5
Chip Placement with Diffusion Models 3
Circumventing Backdoor Space via Weight Symmetry 6
Clients Collaborate: Flexible Differentially Private Federated Learning with Guaranteed Improvement of Utility-Privacy Trade-off 5
Clipped SGD Algorithms for Performative Prediction: Tight Bounds for Stochastic Bias and Remedies 5
Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-Tailed 5
Clone-Robust AI Alignment 1
Closed-Loop Long-Horizon Robotic Planning via Equilibrium Sequence Modeling 5
Closed-form Solutions: A New Perspective on Solving Differential Equations 5
Clustering Items through Bandit Feedback: Finding the Right Feature out of Many 3
Clustering Properties of Self-Supervised Learning 6
Clustering via Self-Supervised Diffusion 3
CoCoA-Mix: Confusion-and-Confidence-Aware Mixture Model for Context Optimization 4
CoDy: Counterfactual Explainers for Dynamic Graphs 5
CoMemo: LVLMs Need Image Context with Image Memory 4
CoPINN: Cognitive Physics-Informed Neural Networks 4
CoSER: Coordinating LLM-Based Persona Simulation of Established Roles 5
CoastalBench: A Decade-Long High-Resolution Dataset to Emulate Complex Coastal Processes 5
Code-Generated Graph Representations Using Multiple LLM Agents for Material Properties Prediction 6
CodeIO: Condensing Reasoning Patterns via Code Input-Output Prediction 3
CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance 5
CodeSync: Synchronizing Large Language Models with Dynamic Code Evolution at Scale 5
CogMath: Assessing LLMs’ Authentic Mathematical Ability from a Human Cognitive Perspective 4
CogReact: A Reinforced Framework to Model Human Cognitive Reaction Modulated by Dynamic Intervention 6
CollabLLM: From Passive Responders to Active Collaborators 3
Collaborative Mean Estimation Among Heterogeneous Strategic Agents: Individual Rationality, Fairness, and Truthful Contribution 1
Collapse or Thrive: Perils and Promises of Synthetic Data in a Self-Generating World 2
Collapse-Proof Non-Contrastive Self-Supervised Learning 5
CombiMOTS: Combinatorial Multi-Objective Tree Search for Dual-Target Molecule Generation 6
Combinatorial Reinforcement Learning with Preference Feedback 3
Come Together, But Not Right Now: A Progressive Strategy to Boost Low-Rank Adaptation 6
CommVQ: Commutative Vector Quantization for KV Cache Compression 5
Communicating Activations Between Language Model Agents 3
Commute Graph Neural Networks 5
Compact Matrix Quantum Group Equivariant Neural Networks 1
Comparing Comparisons: Informative and Easy Human Feedback with Distinguishability Queries 4
Comparing Few to Rank Many: Active Human Preference Learning Using Randomized Frank-Wolfe Method 5
Compelling ReLU Networks to Exhibit Exponentially Many Linear Regions at Initialization and During Training 5
Competing Bandits in Matching Markets via Super Stability 2
Competitively Consistent Clustering 2
Complete-Tree Space Favors Data-Efficient Link Prediction 5
Complex Wavelet Mutual Information Loss: A Multi-Scale Loss Function for Semantic Segmentation 5
Componential Prompt-Knowledge Alignment for Domain Incremental Learning 6
Compositional Causal Reasoning Evaluation in Language Models 4
Compositional Condition Question Answering in Tabular Understanding 4
Compositional Flows for 3D Molecule and Synthesis Pathway Co-design 6
Compositional Generalization via Forced Rendering of Disentangled Latents 4
Compositional Risk Minimization 5
Compositional Scene Understanding through Inverse Generative Modeling 6
Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead 5
Compressed Image Generation with Denoising Diffusion Codebook Models 5
Compressing tree ensembles through Level-wise Optimization and Pruning 6
Compression via Pre-trained Transformers: A Study on Byte-Level Multimodal Data 4
Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders 3
Compute or Load KV Cache? Why Not Both? 5
Computing Optimal Transport Maps and Wasserstein Barycenters Using Conditional Normalizing Flows 5
Computing Voting Rules with Improvement Feedback 2
ConText: Driving In-context Learning for Text Removal and Segmentation 5
Concentration Distribution Learning from Label Distributions 5
Concept Reachability in Diffusion Models: Beyond Dataset Constraints 3
Concept-Based Unsupervised Domain Adaptation 4
Concept-Centric Token Interpretation for Vector-Quantized Generative Models 4
ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features 5
Concurrent Reinforcement Learning with Aggregated States via Randomized Least Squares Value Iteration 3
Conditional Diffusion Model with Nonlinear Data Transformation for Time Series Forecasting 6
Conditioning Diffusions Using Malliavin Calculus 3
ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization 5
Confidence Difference Reflects Various Supervised Signals in Confidence-Difference Classification 3
Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention 3
Conformal Anomaly Detection in Event Sequences 6
Conformal Prediction as Bayesian Quadrature 4
Conformal Prediction with Cellwise Outliers: A Detect-then-Impute Approach 4
Conformal Tail Risk Control for Large Language Model Alignment 6
Conformity Score Averaging for Classification 5
Confounder-Free Continual Learning via Recursive Feature Normalization 5
Connecting Thompson Sampling and UCB: Towards More Efficient Trade-offs Between Privacy and Regret 3
Consensus Based Stochastic Optimal Control 5
Consensus Is All You Get: The Role of Attention in Transformers 3
Conservative Offline Goal-Conditioned Implicit V-Learning 4
Constant Stepsize Local GD for Logistic Regression: Acceleration by Instability 4
Constrain Alignment with Sparse Autoencoders 3
Constrained Belief Updates Explain Geometric Structures in Transformer Representations 1
Constrained Exploitability Descent: An Offline Reinforcement Learning Method for Finding Mixed-Strategy Nash Equilibrium 3
Constrained Online Convex Optimization with Polyak Feasibility Steps 3
Constrained Pareto Set Identification with Bandit Feedback 5
Context Matters: Query-aware Dynamic Long Sequence Modeling of Gigapixel Images 5
Context is Key: A Benchmark for Forecasting with Essential Textual Information 5
Context-Informed Neural ODEs Unexpectedly Identify Broken Symmetries: Insights from the Poincaré–Hopf Theorem 3
Contextual Bandits for Unbounded Context Distributions 3
Contextual Linear Bandits with Delay as Payoff 2
Contextual Online Decision Making with Infinite-Dimensional Functional Regression 1
Contextual Optimization Under Model Misspecification: A Tractable and Generalizable Approach 1
Contextures: Representations from Contexts 4
Continual Generalized Category Discovery: Learning and Forgetting from a Bayesian Perspective 6
Continual Reinforcement Learning by Planning with Online World Models 6
Continuous Bayesian Model Selection for Multivariate Causal Discovery 5
Continuous Semi-Implicit Models 6
Continuous Visual Autoregressive Generation via Score Maximization 4
Continuous-Time Analysis of Heavy Ball Momentum in Min-Max Games 3
Continuously Updating Digital Twins using Large Language Models 4
Contour Integration Underlies Human-Like Vision 4
Contract Design Under Approximate Best Responses 1
Contradiction Retrieval via Contrastive Learning with Sparsity 4
Contrastive Learning with Simplicial Convolutional Networks for Short-Text Classification 5
Contrastive Localized Language-Image Pre-Training 5
Contrastive Private Data Synthesis via Weighted Multi-PLM Fusion 5
Contrastive Visual Data Augmentation 5
Control and Realism: Best of Both Worlds in Layout-to-Image without Training 2
Controllable Data Generation with Hierarchical Neural Representations 4
Controlled Generation with Equivariant Variational Flow Matching 2
Controlling Large Language Model with Latent Action 4
Controlling Neural Collapse Enhances Out-of-Distribution Detection and Transfer Learning 5
Controlling Underestimation Bias in Constrained Reinforcement Learning for Safe Exploration 6
Convergence Analysis of Policy Gradient Methods with Dynamic Stochasticity 5
Convergence of Consistency Model with Multistep Sampling under General Data Assumptions 2
Convergence of Mean-Field Langevin Stochastic Descent-Ascent for Distributional Minimax Optimization 1
Convergence of Policy Mirror Descent Beyond Compatible Function Approximation 1
Convex Markov Games: A New Frontier for Multi-Agent Reinforcement Learning 3
Cooperation of Experts: Fusing Heterogeneous Information with Large Margin 6
Copilot Arena: A Platform for Code LLM Evaluation in the Wild 4
Core Context Aware Transformers for Long Context Language Modeling 6
Core Knowledge Deficits in Multi-Modal Language Models 3
CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models 5
Correlated Errors in Large Language Models 4
Correlation Clustering Beyond the Pivot Algorithm 3
Cost-efficient Collaboration between On-device and Cloud Language Models 5
CostFilter-AD: Enhancing Anomaly Detection through Matching Cost Filtering 5
Counterfactual Contrastive Learning with Normalizing Flows for Robust Treatment Effect Estimation 4
Counterfactual Effect Decomposition in Multi-Agent Sequential Decision Making 5
Counterfactual Graphical Models: Constraints and Inference 1
Counterfactual Voting Adjustment for Quality Assessment and Fairer Voting in Online Platforms with Helpfulness Evaluation 1
Counting atoms faster: policy-based nuclear magnetic resonance pulse sequencing for atomic abundance measurement 2
Counting in Small Transformers: The Delicate Interplay between Attention and Feed-Forward Layers 4
Cover learning for large-scale topology representation 5
Covered Forest: Fine-grained generalization analysis of graph neural networks 5
Cowpox: Towards the Immunity of VLM-based Multi-Agent Systems 4
Cradle: Empowering Foundation Agents towards General Computer Control 6
Craftium: Bridging Flexibility and Efficiency for Rich 3D Single- and Multi-Agent Environments 3
Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM’s Reasoning Capability 3
Cross-City Latent Space Alignment for Consistency Region Embedding 4
Cross-Modal Alignment via Variational Copula Modelling 7
Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination 4
Cross-regularization: Adaptive Model Complexity through Validation Gradients 4
CtrlSynth: Controllable Image Text Synthesis for Data-Efficient Multimodal Learning 3
Curriculum Learning for Biological Sequence Prediction: The Case of De Novo Peptide Sequencing 6
Curse of High Dimensionality Issue in Transformer for Long Context Modeling 5
CursorCore: Assist Programming through Aligning Anything 5
CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection 6
Curvature Enhanced Data Augmentation for Regression 6
Curvature-aware Graph Attention for PDEs on Manifolds 5
Customizing the Inductive Biases of Softmax Attention using Structured Matrices 3
Cut out and Replay: A Simple yet Versatile Strategy for Multi-Label Online Continual Learning 5
D-Fusion: Direct Preference Optimization for Aligning Diffusion Models with Visually Consistent Samples 6
DA-KD: Difficulty-Aware Knowledge Distillation for Efficient Large Language Models 5
DAMA: Data- and Model-aware Alignment of Multi-modal LLMs 5
DANCE: Dual Unbiased Expansion with Group-acquired Alignment for Out-of-distribution Graph Fairness Learning 4
DCBM: Data-Efficient Visual Concept Bottleneck Models 6
DCTdiff: Intriguing Properties of Image Generative Modeling in the DCT Space 5
DEALing with Image Reconstruction: Deep Attentive Least Squares 5
DEFAME: Dynamic Evidence-based FAct-checking with Multimodal Experts 6
DIME: Diffusion-Based Maximum Entropy Reinforcement Learning 5
DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning 4
DIS-CO: Discovering Copyrighted Content in VLMs Training Data 6
DISCO: learning to DISCover an evolution Operator for multi-physics-agnostic prediction 5
DLP: Dynamic Layerwise Pruning in Large Language Models 6
DMM: Distributed Matrix Mechanism for Differentially-Private Federated Learning Based on Constant-Overhead Linear Secret Resharing 5
DMOSpeech: Direct Metric Optimization via Distilled Diffusion Model in Zero-Shot Speech Synthesis 5
DOLPHIN: A Programmable Framework for Scalable Neurosymbolic Learning 6
DPCore: Dynamic Prompt Coreset for Continual Test-Time Adaptation 5
DPO Meets PPO: Reinforced Token Optimization for RLHF 5
DRAG: Data Reconstruction Attack using Guided Diffusion 6
DS-VLM: Diffusion Supervision Vision Language Model 3
DSBRouter: End-to-end Global Routing via Diffusion Schrödinger Bridge 6
DSP: Dynamic Sequence Parallelism for Multi-Dimensional Transformers 2
DTZO: Distributed Trilevel Zeroth Order Learning with Provable Non-Asymptotic Convergence 4
DUNIA: Pixel-Sized Embeddings via Cross-Modal Alignment for Earth Observation Applications 5
DVI:A Derivative-based Vision Network for INR 5
Data Mixing Optimization for Supervised Fine-Tuning of Large Language Models 4
Data-Driven Selection of Instrumental Variables for Additive Nonlinear, Constant Effects Models 4
Data-Juicer Sandbox: A Feedback-Driven Suite for Multimodal Data-Model Co-development 5
Data-driven Design of Randomized Control Trials with Guaranteed Treatment Effects 2
DataDecide: How to Predict Best Pretraining Data with Small Experiments 4
Dataflow-Guided Neuro-Symbolic Language Models for Type Inference 5
David and Goliath: Small One-step Model Beats Large Diffusion with Score Post-training 5
De-AntiFake: Rethinking the Protective Perturbations Against Voice Cloning Attacks 5
De-coupled NeuroGF for Shortest Path Distance Approximations on Large Terrain Graphs 3
De-mark: Watermark Removal in Large Language Models 4
DeFoG: Discrete Flow Matching for Graph Generation 6
Decision Making under the Exponential Family: Distributionally Robust Optimisation with Bayesian Ambiguity Sets 6
Decision Mixer: Integrating Long-term and Local Dependencies via Dynamic Token Selection for Decision-Making 6
Decision Theoretic Foundations for Conformal Prediction: Optimal Uncertainty Quantification for Risk-Averse Agents 3
Decision-aware Training of Spatiotemporal Forecasting Models to Select a Top-K Subset of Sites for Intervention 5
Decoding Rewards in Competitive Games: Inverse Game Theory with Entropy Regularization 1
Decomposition of Graphic Design with Unified Multimodal Model 5
Decoupled SGDA for Games with Intermittent Strategy Communication 5
Deep Bayesian Filter for Bayes-Faithful Data Assimilation 5
Deep Electromagnetic Structure Design Under Limited Evaluation Budgets 2
Deep Fuzzy Multi-view Learning for Reliable Classification 6
Deep Linear Network Training Dynamics from Random Initialization: Data, Width, Depth, and Hyperparameter Transfer 1
Deep Neural Cellular Potts Models 4
Deep Principal Support Vector Machines for Nonlinear Sufficient Dimension Reduction 5
Deep Reinforcement Learning from Hierarchical Preference Design 3
Deep Ridgelet Transform and Unified Universality Theorem for Deep and Shallow Joint-Group-Equivariant Machines 0
Deep Streaming View Clustering 4
Deep Sturm–Liouville: From Sample-Based to 1D Regularization with Learnable Orthogonal Basis Functions 5
Deep Unsupervised Hashing via External Guidance 5
DeepCrossAttention: Supercharging Transformer Residual Connections 4
DeepLayout: Learning Neural Representations of Circuit Placement Layout 4
Defending LVLMs Against Vision Attacks Through Partial-Perception Supervision 3
Delay-DSGN: A Dynamic Spiking Graph Neural Network with Delay Mechanisms for Evolving Graph 4
Deliberation in Latent Space via Differentiable Cache Augmentation 2
Delta Decompression for MoE-based LLMs Compression 5
Demeaned Sparse: Efficient Anomaly Detection by Residual Estimate 4
Demonstration Selection for In-Context Learning via Reinforcement Learning 2
Demystifying Catastrophic Forgetting in Two-Stage Incremental Object Detector 4
Demystifying Cost-Efficiency in LLM Serving over Heterogeneous GPUs 5
Demystifying Long Chain-of-Thought Reasoning 5
Demystifying Singular Defects in Large Language Models 3
Demystifying the Paradox of Importance Sampling with an Estimated History-Dependent Behavior Policy in Off-Policy Evaluation 2
Dendritic Localized Learning: Toward Biologically Plausible Algorithm 5
Density Ratio Estimation with Conditional Probability Paths 5
Density Ratio Estimation-based Bayesian Optimization with Semi-Supervised Learning 5
Dequantified Diffusion-Schrödinger Bridge for Density Ratio Estimation 4
Design Considerations in Offline Preference-based RL 2
Designing Cyclic Peptides via Harmonic SDE with Atom-Bond Modeling 6
Detecting Strategic Deception with Linear Probes 4
Determinant Estimation under Memory Constraints and Neural Scaling Laws 5
Determining Layer-wise Sparsity for Large Language Models Through a Theoretical Perspective 6
Deterministic Sparse Fourier Transform for Continuous Signals with Frequency Gap 1
Devil is in the Details: Density Guidance for Detail-Aware Generation with Flow Models 4
DexScale: Automating Data Scaling for Sim2Real Generalizable Robot Control 5
DiLQR: Differentiable Iterative Linear Quadratic Regulator via Implicit Differentiation 5
DiMa: Understanding the Hardness of Online Matching Problems via Diffusion Models 3
DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generation 4
Diagonal Symmetrization of Neural Network Solvers for the Many-Electron Schrödinger Equation 4
Dialogue Without Limits: Constant-Sized KV Caches for Extended Response in LLMs 5
Diff-MoE: Diffusion Transformer with Time-Aware and Space-Adaptive Experts 3
DiffAdvMAP: Flexible Diffusion-Based Framework for Generating Natural Unrestricted Adversarial Examples 5
DiffMS: Diffusion Generation of Molecules Conditioned on Mass Spectra 4
Differentiable Quadratic Optimization For the Maximum Independent Set Problem 5
Differentiable Solver Search for Fast Diffusion Sampling 4
Differentiable Structure Learning with Ancestral Constraints 4
Differential Coding for Training-Free ANN-to-SNN Conversion 4
Differential Privacy Guarantees of Markov Chain Monte Carlo Algorithms 0
Differential Privacy Under Class Imbalance: Methods and Empirical Insights 4
Differentially Private Analysis for Binary Response Models: Optimality, Estimation, and Inference 3
Differentially Private Boxplots 5
Differentially Private Federated $k$-Means Clustering with Server-Side Data 4
Differentially Private Space-Efficient Algorithms for Counting Distinct Elements in the Turnstile Model 1
Diffuse Everything: Multimodal Diffusion Models on Arbitrary State Spaces 5
Diffusion Adversarial Post-Training for One-Step Video Generation 3
Diffusion Counterfactual Generation with Semantic Abduction 6
Diffusion Instruction Tuning 6
Diffusion Models are Secretly Exchangeable: Parallelizing DDPMs via Auto Speculation 5
Diffusion Sampling Correction via Approximately 10 Parameters 6
Diffusion models for Gaussian distributions: Exact solutions and Wasserstein errors 2
Diffusion on Language Model Encodings for Protein Sequence Generation 4
Diffusion-based Adversarial Purification from the Perspective of the Frequency Domain 5
DiffusionVLA: Scaling Robot Foundation Models via Unified Diffusion and Autoregression 4
Dimension-Free Adaptive Subgradient Methods with Frequent Directions 5
Dimension-Independent Rates for Structured Neural Density Estimation 1
Dimensionality Reduction on Complex Vector Spaces for Euclidean Distance with Dynamic Weights 2
DipLLM: Fine-Tuning LLM for Strategic Decision-making in Diplomacy 1
Direct Density Ratio Optimization: A Statistically Consistent Approach to Aligning Large Language Models 2
Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator 5
Direct Motion Models for Assessing Generated Videos 4
Direct Prediction Set Minimization via Bilevel Conformal Classifier Training 5
Directed Graph Grammars for Sequence-based Learning 5
Directly Forecasting Belief for Reinforcement Learning with Delays 4
Discovering Global False Negatives On the Fly for Self-supervised Contrastive Learning 6
Discovering Latent Causal Graphs from Spatiotemporal Data 4
Discovering Physics Laws of Dynamical Systems via Invariant Function Learning 4
Discovering Spoofing Attempts on Language Model Watermarks 3
Discovering Symbolic Cognitive Models from Human and Animal Behavior 5
Discovering a Zero (Zero-Vector Class of Machine Learning) 2
Discrepancies are Virtue: Weak-to-Strong Generalization through Lens of Intrinsic Dimension 3
Discrepancy Minimization in Input-Sparsity Time 3
Discrete Markov Probabilistic Models: An Improved Discrete Score-Based Framework with sharp convergence bounds under minimal assumptions 4
Discrete Neural Algorithmic Reasoning 6
Discrete and Continuous Difference of Submodular Minimization 4
Discriminative Finetuning of Generative Large Language Models without Reward Models and Human Preference Data 6
Discriminative Policy Optimization for Token-Level Reward Models 6
Disentangled Graph Spectral Domain Adaptation 4
Disentangling Invariant Subgraph via Variance Contrastive Estimation under Distribution Shifts 6
Disentangling and Integrating Relational and Sensory Information in Transformer Architectures 5
Disparate Conditional Prediction in Multiclass Classifiers 4
Diss-l-ECT: Dissecting Graph Data with Local Euler Characteristic Transforms 4
Dissecting Submission Limit in Desk-Rejections: A Mathematical Analysis of Fairness in AI Conference Policies 4
DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs 6
Distillation Scaling Laws 5
Distillation of Discrete Diffusion through Dimensional Correlations 4
Distilling the Knowledge in Data Pruning 3
Distinguishing Cause from Effect with Causal Velocity Models 5
Distributed Conformal Prediction via Message Passing 5
Distributed Differentially Private Data Analytics via Secure Sketching 5
Distributed Event-Based Learning via ADMM 4
Distributed Nonparametric Estimation: from Sparse to Dense Samples per Terminal 0
Distributed Parallel Gradient Stacking(DPGS): Solving Whole Slide Image Stacking Challenge in Multi-Instance Learning 5
Distributed Retraction-Free and Communication-Efficient Optimization on the Stiefel Manifold 4
Distribution-aware Fairness Learning in Medical Image Segmentation From A Control-Theoretic Perspective 6
Distributional Diffusion Models with Scoring Rules 4
Distributionally Robust Active Learning for Gaussian Process Regression 3
Distributionally Robust Multi-Agent Reinforcement Learning for Dynamic Chute Mapping 3
Distributionally Robust Policy Learning under Concept Drifts 6
Diverging Preferences: When do Annotators Disagree and do Models Know? 4
Diverse Prototypical Ensembles Improve Robustness to Subpopulation Shift 6
Diversified Flow Matching with Translation Identifiability 4
Diversifying Policy Behaviors with Extrinsic Behavioral Curiosity 4
Diversity By Design: Leveraging Distribution Matching for Offline Model-Based Optimization 5
Divide and Conquer: Exploring Language-centric Tree Reasoning for Video Question-Answering 3
Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents via Offline Hierarchical Reinforcement Learning 6
Divide and Conquer: Learning Label Distribution with Subtasks 6
Diving into Self-Evolving Training for Multimodal Reasoning 4
Do Bayesian Neural Networks Actually Behave Like Bayesian Models? 5
Do Multiple Instance Learning Models Transfer? 5
Do NOT Think That Much for 2+3=? On the Overthinking of Long Reasoning Models 2
Do Not Mimic My Voice : Speaker Identity Unlearning for Zero-Shot Text-to-Speech 3
Do Vision-Language Models Really Understand Visual Language? 4
Do We Need to Verify Step by Step? Rethinking Process Supervision from a Theoretical Perspective 1
Do We Really Need Message Passing in Brain Network Modeling? 5
DocKS-RAG: Optimizing Document-Level Relation Extraction through LLM-Enhanced Hybrid Prompt Tuning 4
DocVXQA: Context-Aware Visual Explanations for Document Question Answering 3
Does Data Scaling Lead to Visual Compositional Generalization? 5
Does Generation Require Memorization? Creative Diffusion Models using Ambient Diffusion 4
Does Graph Prompt Work? A Data Operation Perspective with Theoretical Analysis 3
Does Low Rank Adaptation Lead to Lower Robustness against Training-Time Attacks? 4
Does One-shot Give the Best Shot? Mitigating Model Inconsistency in One-shot Federated Learning 6
Does learning the right latent variables necessarily improve in-context learning? 4
Domain-Adapted Diffusion Model for PROTAC Linker Design Through the Lens of Density Ratio in Chemical Space 4
Domain2Vec: Vectorizing Datasets to Find the Optimal Data Mixture without Training 4
Don’t Restart, Just Reuse: Reoptimizing MILPs with Dynamic Parameters 6
Double Machine Learning for Causal Inference under Shared-State Interference 2
Double-Filter: Efficient Fine-tuning of Pre-trained Vision-Language Models via Patch&Layer Filtering 6
Doubly Protected Estimation for Survival Outcomes Utilizing External Controls for Randomized Clinical Trials 2
Doubly Robust Conformalized Survival Analysis with Right-Censored Data 5
Doubly Robust Fusion of Many Treatments for Policy Learning 3
DragLoRA: Online Optimization of LoRA Adapters for Drag-based Image Editing in Diffusion Model 5
DragSolver: A Multi-Scale Transformer for Real-World Automotive Drag Coefficient Estimation 4
DreamDPO: Aligning Text-to-3D Generation with Human Preferences via Direct Preference Optimization 5
DriveGPT: Scaling Autoregressive Behavior Models for Driving 4
Drug-TTA: Test-Time Adaptation for Drug Virtual Screening via Multi-task Meta-Auxiliary Learning 5
Dual Feature Reduction for the Sparse-group Lasso and its Adaptive Variant 6
Dueling Convex Optimization with General Preferences 1
DyCodeEval: Dynamic Benchmarking of Reasoning Capabilities in Code Large Language Models Under Data Contamination 6
DyPolySeg: Taylor Series-Inspired Dynamic Polynomial Fitting Network for Few-shot Point Cloud Semantic Segmentation 4
DynaMind: Reasoning over Abstract Video Dynamics for Embodied Decision-Making 4
Dynamic Mixture of Curriculum LoRA Experts for Continual Multimodal Instruction Tuning 5
Dynamic Similarity Graph Construction with Kernel Density Estimation 6
Dynamic Sparse Training of Diagonally Sparse Networks 5
Dynamical Modeling of Behaviorally Relevant Spatiotemporal Patterns in Neural Imaging Data 5
Dynamical phases of short-term memory mechanisms in RNNs 4
E-LDA: Toward Interpretable LDA Topic Models with Strong Guarantees in Logarithmic Parallel Time 4
EAGLES: Towards Effective, Efficient, and Economical Federated Graph Learning via Unified Sparsification 6
EARL-BO: Reinforcement Learning for Multi-Step Lookahead, High-Dimensional Bayesian Optimization 5
EARTH: Epidemiology-Aware Neural ODE with Continuous Disease Transmission Graph 3
EEG-Language Pretraining for Highly Label-Efficient Clinical Phenotyping 6
EFDTR: Learnable Elliptical Fourier Descriptor Transformer for Instance Segmentation 4
EGPlace: An Efficient Macro Placement Method via Evolutionary Search with Greedy Repositioning Guided Mutation 6
ELEMENTAL: Interactive Learning from Demonstrations and Vision-Language Models for Reward Design in Robotics 4
ELITE: Enhanced Language-Image Toxicity Evaluation for Safety 0
ELMO : Efficiency via Low-precision and Peak Memory Optimization in Large Output Spaces 6
ELoRA: Low-Rank Adaptation for Equivariant GNNs 4
ENAHPool: The Edge-Node Attention-based Hierarchical Pooling for Graph Neural Networks 3
ENSUR: Equitable and Statistically Unbiased Recommendation 5
EPIC: Efficient Position-Independent Caching for Serving Large Language Models 5
EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling 5
ERICT: Enhancing Robustness by Identifying Concept Tokens in Zero-Shot Vision Language Models 5
ESPFormer: Doubly-Stochastic Attention with Expected Sliced Transport Plans 5
ETTA: Elucidating the Design Space of Text-to-Audio Models 6
EVOLvE: Evaluating and Optimizing LLMs For In-Context Exploration 3
Earley-Driven Dynamic Pruning for Efficient Structured Decoding 5
EasyInv: Toward Fast and Better DDIM Inversion 6
EasyRef: Omni-Generalized Group Image Reference for Diffusion Models via Multimodal LLM 3
EcoMapper: Generative Modeling for Climate-Aware Satellite Imagery 4
Edge-Colored Clustering in Hypergraphs: Beyond Minimizing Unsatisfied Edges 5
EditLord: Learning Code Transformation Rules for Code Editing 5
Editable Concept Bottleneck Models 5
Editable Noise Map Inversion: Encoding Target-image into Noise For High-Fidelity Image Manipulation 5
EduLLM: Leveraging Large Language Models and Framelet-Based Signed Hypergraph Neural Networks for Student Performance Prediction 4
Effective and Efficient Masked Image Generation Models 4
EffiCoder: Enhancing Code Generation in Large Language Models through Efficiency-Aware Fine-tuning 5
Efficient ANN-SNN Conversion with Error Compensation Learning 2
Efficient Bisection Projection to Ensure Neural-Network Solution Feasibility for Optimization over General Set 6
Efficient Core-set Selection for Deep Learning Through Squared Loss Minimization 4
Efficient Curvature-Aware Hypergradient Approximation for Bilevel Optimization 5
Efficient Diffusion Models for Symmetric Manifolds 5
Efficient Distributed Optimization under Heavy-Tailed Noise 5
Efficient Federated Incomplete Multi-View Clustering 5
Efficient Fine-Grained Guidance for Diffusion Model Based Symbolic Music Generation 6
Efficient First-Order Optimization on the Pareto Set for Multi-Objective Learning under Preference Guidance 6
Efficient Generative Modeling with Residual Vector Quantization-Based Tokens 4
Efficient Graph Continual Learning via Lightweight Graph Neural Tangent Kernels-based Dataset Distillation 6
Efficient Heterogeneity-Aware Federated Active Data Selection 4
Efficient Length-Generalizable Attention via Causal Retrieval for Long-Context Language Modeling 6
Efficient LiDAR Reflectance Compression via Scanning Serialization 5
Efficient Logit-based Knowledge Distillation of Deep Spiking Neural Networks for Full-Range Timestep Deployment 6
Efficient Long Context Fine-tuning with Chunk Flow 4
Efficient Molecular Conformer Generation with SO(3)-Averaged Flow Matching and Reflow 6
Efficient Motion Prompt Learning for Robust Visual Tracking 5
Efficient Multi-modal Long Context Learning for Training-free Adaptation 6
Efficient Multivariate Robust Mean Estimation Under Mean-Shift Contamination 1
Efficient Network Automatic Relevance Determination 5
Efficient Noise Calculation in Deep Learning-based MRI Reconstructions 6
Efficient Online Reinforcement Learning for Diffusion Policy 6
Efficient Optimization with Orthogonality Constraint: a Randomized Riemannian Submanifold Method 6
Efficient Parallel Training Methods for Spiking Neural Networks with Constant Time Complexity 4
Efficient Personalized Adaptation for Physiological Signal Foundation Model 4
Efficient Quantification of Multimodal Interaction at Sample Level 3
Efficient Robotic Policy Learning via Latent Space Backward Planning 3
Efficient Robust Conformal Prediction via Lipschitz-Bounded Networks 5
Efficient Skill Discovery via Regret-Aware Optimization 6
Efficient Source-free Unlearning via Energy-Guided Data Synthesis and Discrimination-Aware Multitask Optimization 4
Efficient Time Series Processing for Transformers and State-Space Models through Token Merging 4
Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs 5
Efficient and Scalable Density Functional Theory Hamiltonian Prediction through Adaptive Sparsity 6
Efficient and Separate Authentication Image Steganography Network 5
Efficiently Access Diffusion Fisher: Within the Outer Product Span Space 5
Efficiently Serving Large Multimodal Models Using EPD Disaggregation 6
Efficiently Vectorized MCMC on Modern Accelerators 5
EgoPrivacy: What Your First-Person Camera Says About You? 5
Ehrenfeucht-Haussler Rank and Chain of Thought 0
Eigen Analysis of Conjugate Kernel and Neural Tangent Kernel 2
Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias 5
Eliciting Language Model Behaviors with Investigator Agents 5
Elucidating Flow Matching ODE Dynamics via Data Geometry and Denoisers 2
Elucidating the Design Space of Multimodal Protein Language Models 5
Elucidating the design space of language models for image generation 3
Embedding Safety into RL: A New Take on Trust Region Methods 4
EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents 5
Emergence and Effectiveness of Task Vectors in In-Context Learning: An Encoder Decoder Perspective 4
Emergence in non-neural models: grokking modular arithmetic via average gradient outer product 4
Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs 2
Emergent Response Planning in LLMs 3
Emergent Symbolic Mechanisms Support Abstract Reasoning in Large Language Models 6
EmoGrowth: Incremental Multi-label Emotion Decoding with Augmented Emotional Relation Graph 6
Emoji Attack: Enhancing Jailbreak Attacks Against Judge LLM Detection 3
Emotional Face-to-Speech 4
Empirical Privacy Variance 7
Empower Structure-Based Molecule Optimization with Gradient Guided Bayesian Flow Networks 6
Empowering World Models with Reflection for Embodied Video Prediction 4
EnIGMA: Interactive Tools Substantially Assist LM Agents in Finding Security Vulnerabilities 4
Enabling Optimal Decisions in Rehearsal Learning under CARE Condition 4
EncryptedLLM: Privacy-Preserving Large Language Model Inference via GPU-Accelerated Fully Homomorphic Encryption 4
End-to-End Learning Framework for Solving Non-Markovian Optimal Control 3
Energy-Based Flow Matching for Generating 3D Molecular Structure 6
Energy-Based Preference Model Offers Better Offline Alignment than the Bradley-Terry Preference Model 4
Enforcing Idempotency in Neural Networks 3
Enforcing Latent Euclidean Geometry in Single-Cell VAEs for Manifold Interpolation 7
Enhancing Adversarial Robustness with Conformal Prediction: A Framework for Guaranteed Model Reliability 6
Enhancing Certified Robustness via Block Reflector Orthogonal Layers and Logit Annealing Loss 6
Enhancing Cooperative Multi-Agent Reinforcement Learning with State Modelling and Adversarial Exploration 5
Enhancing Decision-Making of Large Language Models via Actor-Critic 6
Enhancing Diversity In Parallel Agents: A Maximum State Entropy Exploration Story 2
Enhancing Foundation Models for Time Series Forecasting via Wavelet-based Tokenization 6
Enhancing Foundation Models with Federated Domain Knowledge Infusion 7
Enhancing Graph Contrastive Learning for Protein Graphs from Perspective of Invariance 5
Enhancing Graph Invariant Learning from a Negative Inference Perspective 6
Enhancing Ligand Validity and Affinity in Structure-Based Drug Design with Multi-Reward Optimization 4
Enhancing Logits Distillation with Plug&Play Kendall’s $τ$ Ranking Loss 6
Enhancing Parallelism in Decentralized Stochastic Convex Optimization 3
Enhancing Performance of Explainable AI Models with Constrained Concept Refinement 6
Enhancing Rating-Based Reinforcement Learning to Effectively Leverage Feedback from Large Vision-Language Models 4
Enhancing Spectral GNNs: From Topology and Perturbation Perspectives 5
Enhancing Statistical Validity and Power in Hybrid Controlled Trials: A Randomization Inference Approach with Conformal Selective Borrowing 6
Enhancing Target-unspecific Tasks through a Features Matrix 3
Enhancing Treatment Effect Estimation via Active Learning: A Counterfactual Covering Perspective 6
Enhancing Visual Localization with Cross-Domain Image Generation 5
Enhancing the Influence of Labels on Unlabeled Nodes in Graph Convolutional Networks 5
EnsLoss: Stochastic Calibrated Loss Ensembles for Preventing Overfitting in Classification 3
Ensemble Distribution Distillation via Flow Matching 5
Ensemble Learned Bloom Filters: Two Oracles are Better than One 5
EpiCoder: Encompassing Diversity and Complexity in Code Generation 5
Epsilon-VAE: Denoising as Visual Decoding 4
EquivaMap: Leveraging LLMs for Automatic Equivalence Checking of Optimization Formulations 4
Equivalence is All: A Unified View for Self-supervised Graph Learning 4
Equivariant Neural Tangent Kernels 3
Equivariant Polynomial Functional Networks 5
EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers 3
Ergodic Generative Flows 3
Erwin: A Tree-based Hierarchical Transformer for Large-scale Physical Systems 7
EvFocus: Learning to Reconstruct Sharp Images from Out-of-Focus Event Streams 4
Evaluating Judges as Evaluators: The JETTS Benchmark of LLM-as-Judges as Test-Time Scaling Evaluators 4
Evaluating LLMs Across Multi-Cognitive Levels: From Medical Knowledge Mastery to Scenario-Based Problem Solving 4
Evaluating Neuron Explanations: A Unified Framework with Sanity Checks 4
Event-Customized Image Generation 4
Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition 1
EvoControl: Multi-Frequency Bi-Level Control for High-Frequency Continuous Control 5
EvoMesh: Adaptive Physical Simulation with Hierarchical Graph Evolutions 4
EvoPress: Accurate Dynamic Model Compression via Evolutionary Search 6
Evolving Minds: Logic-Informed Inference from Temporal Action Patterns 5
Evolving Prompts In-Context: An Open-ended, Self-replicating Perspective 6
Ex-VAD: Explainable Fine-grained Video Anomaly Detection Based on Visual-Language Models 4
ExLM: Rethinking the Impact of $\texttt[MASK]$ Tokens in Masked Language Models 5
ExPLoRA: Parameter-Efficient Extended Pre-Training to Adapt Vision Transformers under Domain Shifts 6
Exact Recovery of Sparse Binary Vectors from Generalized Linear Measurements 1
Exact Upper and Lower Bounds for the Output Distribution of Neural Networks with Random Inputs 4
Exact risk curves of signSGD in High-Dimensions: quantifying preconditioning and noise-compression effects 4
Exactly Tight Information-theoretic Generalization Bounds via Binary Jensen-Shannon Divergence 4
Exogenous Isomorphism for Counterfactual Identifiability 4
ExpProof : Operationalizing Explanations for Confidential Models with ZKPs 6
Expected Variational Inequalities 1
Expert Race: A Flexible Routing Strategy for Scaling Diffusion Transformer with Mixture of Experts 3
Explainable Concept Generation through Vision-Language Preference Learning for Understanding Neural Networks’ Internal Representations 6
Explaining the role of Intrinsic Dimensionality in Adversarial Training 6
Explaining, Fast and Slow: Abstraction and Refinement of Provable Explanations 4
Explanatory Instructions: Towards Unified Vision Tasks Understanding and Zero-shot Generalization 5
Explicit Discovery of Nonlinear Symmetries from Dynamic Data 5
Explicit Exploration for High-Welfare Equilibria in Game-Theoretic Multiagent Reinforcement Learning 3
Explicit Preference Optimization: No Need for an Implicit Reward Model 4
Exploiting Curvature in Online Convex Optimization with Delayed Feedback 4
Exploiting Presentative Feature Distributions for Parameter-Efficient Continual Learning of Large Language Models 5
Exploiting Similarity for Computation and Communication-Efficient Decentralized Optimization 3
Exploring Criteria of Loss Reweighting to Enhance LLM Unlearning 7
Exploring Invariance in Images through One-way Wave Equations 4
Exploring Large Action Sets with Hyperspherical Embeddings using von Mises-Fisher Sampling 4
Exploring Representations and Interventions in Time Series Foundation Models 6
Exploring Vision Semantic Prompt for Efficient Point Cloud Understanding 4
Exploring and Mitigating Adversarial Manipulation of Voting-Based Leaderboards 4
Exponential Family Variational Flow Matching for Tabular Data Generation 4
Expressive Power of Graph Neural Networks for (Mixed-Integer) Quadratic Programs 7
Expressive Score-Based Priors for Distribution Matching with Geometry-Preserving Regularization 5
ExtPose: Robust and Coherent Pose Estimation by Extending ViTs 3
Extracting Rare Dependence Patterns via Adaptive Sample Reweighting 5
Extractive Structures Learned in Pretraining Enable Generalization on Finetuned Facts 4
Extreme Value Policy Optimization for Safe Reinforcement Learning 6
FAB-PPI: Frequentist, Assisted by Bayes, Prediction-Powered Inference 6
FACTER: Fairness-Aware Conformal Thresholding and Prompt Engineering for Enabling Fair LLM-Based Recommender Systems 7
FDGen: A Fairness-Aware Graph Generation Model 1
FEAT-KD: Learning Concise Representations for Single and Multi-Target Regression via TabNet Knowledge Distillation 4
FG-CLIP: Fine-Grained Visual and Textual Alignment 5
FIC-TSC: Learning Time Series Classification with Fisher Information Constraint 6
FLAM: Frame-Wise Language-Audio Modeling 3
FOCoOp: Enhancing Out-of-Distribution Robustness in Federated Prompt Learning for Vision-Language Models 5
FOUNDER: Grounding Foundation Models in World Models for Open-Ended Embodied Decision Making 3
FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training 5
FSL-SAGE: Accelerating Federated Split Learning via Smashed Activation Gradient Estimation 5
FSTLLM: Spatio-Temporal LLM for Few Shot Time Series Forecasting 5
FactTest: Factuality Testing in Large Language Models with Finite-Sample and Distribution-Free Guarantees 5
Fair Clustering via Alignment 5
FairICP: Encouraging Equalized Odds via Inverse Conditional Permutation 5
FairPFN: A Tabular Foundation Model for Causal Fairness 6
Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective 1
Fairness on Principal Stratum: A New Perspective on Counterfactual Fairness 1
Falcon: Fast Visuomotor Policies via Partial Denoising 5
False Coverage Proportion Control for Conformal Prediction 5
Falsification of Unconfoundedness by Testing Independence of Causal Mechanisms 4
Fast Estimation of Partial Dependence Functions using Trees 7
Fast Exact Unlearning for In-Context Learning Data for LLMs 4
Fast Incomplete Multi-view Clustering by Flexible Anchor Learning 4
Fast Inference with Kronecker-Sparse Matrices 5
Fast Large Language Model Collaborative Decoding via Speculation 5
Fast Min-$ε$ Segmented Regression using Constant-Time Segment Merging 4
Fast Tensor Completion via Approximate Richardson Iteration 7
Fast Video Generation with Sliding Tile Attention 5
Fast and Low-Cost Genomic Foundation Models via Outlier Removal 4
Fast and Provable Algorithms for Sparse PCA with Improved Sample Complexity 3
Fast and Robust: Task Sampling with Posterior and Diversity Synergies for Adaptive Decision-Makers in Randomized Environments 6
Fast, Accurate Manifold Denoising by Tunneling Riemannian Optimization 6
FastCAV: Efficient Computation of Concept Activation Vectors for Explaining Deep Neural Networks 5
Faster Approximation Algorithms for k-Center via Data Reduction 6
Faster Global Minimum Cut with Predictions 4
Faster Rates for Private Adversarial Bandits 1
Faster Stochastic Optimization with Arbitrary Delays via Adaptive Asynchronous Mini-Batching 4
Faster and Stronger: When ANN-SNN Conversion Meets Parallel Spiking Calculation 6
Feasible Action Search for Bandit Linear Programs via Thompson Sampling 4
FeatSharp: Your Vision Model Features, Sharper 4
Feature Importance Metrics in the Presence of Missing Data 2
Feature Learning beyond the Lazy-Rich Dichotomy: Insights from Representational Geometry 5
Feature Shift Localization Network 5
Feature learning from non-Gaussian inputs: the case of Independent Component Analysis in high dimensions 2
Feature out! Let Raw Image as Your Condition for Blind Face Restoration 5
Feature-Mapping Topology Optimization with Neural Heaviside Signed Distance Functions 3
Features are fate: a theory of transfer learning in high-dimensional regression 2
FedBEns: One-Shot Federated Learning based on Bayesian Ensemble 6
FedClean: A General Robust Label Noise Correction for Federated Learning 4
FedECADO: A Dynamical System Model of Federated Learning 3
FedOne: Query-Efficient Federated Learning for Black-box Discrete Prompt Learning 5
FedPHA: Federated Prompt Learning for Heterogeneous Client Adaptation 7
FedSMU: Communication-Efficient and Generalization-Enhanced Federated Learning through Symbolic Model Updates 7
FedSSI: Rehearsal-Free Continual Federated Learning with Synergistic Synaptic Intelligence 5
Federated Causal Structure Learning with Non-identical Variable Sets 3
Federated Disentangled Tuning with Textual Prior Decoupling and Visual Dynamic Adaptation 4
Federated Generalised Variational Inference: A Robust Probabilistic Federated Learning Framework 5
Federated In-Context Learning: Iterative Refinement for Improved Answer Quality 4
Federated Incomplete Multi-view Clustering with Globally Fused Graph Guidance 4
Federated Learning for Feature Generalization with Convex Constraints 5
Federated Node-Level Clustering Network with Cross-Subgraph Link Mending 6
Federated Oriented Learning: A Practical One-Shot Personalized Federated Learning Framework 5
Feedforward Few-shot Species Range Estimation 5
Ferret: Federated Full-Parameter Tuning at Scale for Large Language Models 5
Few-Shot Learner Generalizes Across AI-Generated Image Detection 6
Feynman-Kac Correctors in Diffusion: Annealing, Guidance, and Product of Experts 4
FicGCN: Unveiling the Homomorphic Encryption Efficiency from Irregular Graph Convolutional Networks 5
Field Matching: an Electrostatic Paradigm to Generate and Transfer Data 5
Finding Wasserstein Ball Center: Efficient Algorithm and The Applications in Fairness 5
Fine-Grained Captioning of Long Videos through Scene Graph Consolidation 6
Finite-Sample Convergence Bounds for Trust Region Policy Optimization in Mean Field Games 2
Finite-Time Analysis of Discrete-Time Stochastic Interpolants 2
Finite-Time Convergence Rates in Stochastic Stackelberg Games with Smooth Algorithmic Agents 4
Finite-Time Global Optimality Convergence in Deep Neural Actor-Critic Methods for Decentralized Multi-Agent Reinforcement Learning 3
FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing 5
FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain 3
Fishers for Free? Approximating the Fisher Information Matrix by Recycling the Squared Gradient Accumulator 4
Fixed-Confidence Multiple Change Point Identification under Bandit Feedback 2
Fixing the Double Penalty in Data-Driven Weather Forecasting Through a Modified Spherical Harmonic Loss Function 5
Fixing the Loose Brake: Exponential-Tailed Stopping Time in Best Arm Identification 2
FlashTP: Fused, Sparsity-Aware Tensor Product for Machine Learning Interatomic Potentials 6
Flat-LoRA: Low-Rank Adaptation over a Flat Loss Landscape 5
FlatQuant: Flatness Matters for LLM Quantization 5
Fleet of Agents: Coordinated Problem Solving with Large Language Models 5
Flex3D: Feed-Forward 3D Generation with Flexible Reconstruction Model and Input View Curation 3
FlexControl: Computation-Aware Conditional Control with Differentiable Router for Text-to-Image Generation 5
FlexTok: Resampling Images into 1D Token Sequences of Flexible Length 4
FlexiClip: Locality-Preserving Free-Form Character Animation 3
FlexiReID: Adaptive Mixture of Expert for Multi-Modal Person Re-Identification 4
Flexibility-conditioned protein structure design with flow matching 6
Flexible Tails for Normalizing Flows 5
Flexible and Efficient Grammar-Constrained Decoding 2
Flexible, Efficient, and Stable Adversarial Attacks on Machine Unlearning 7
FlipAttack: Jailbreak LLMs via Flipping 4
FloE: On-the-Fly MoE Inference on Memory-constrained GPU 4
Floating-Point Neural Networks Can Represent Almost All Floating-Point Functions 0
Flopping for FLOPs: Leveraging Equivariance for Computational Efficiency 6
Flow Matching for Denoised Social Recommendation 5
Flow Matching for Few-Trial Neural Adaptation with Stable Latent Dynamics 5
Flow Q-Learning 5
Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples 6
Flow-based Domain Randomization for Learning and Sequencing Robotic Skills 3
Flow-field inference from neural data using deep recurrent networks 4
Flow-of-Options: Diversified and Improved LLM Reasoning by Thinking Through Options 4
FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching 3
FlowDrag: 3D-aware Drag-based Image Editing with Mesh-guided Deformation Vector Flow Fields 4
Flowing Datasets with Wasserstein over Wasserstein Gradient Flows 5
Fluctuations of the largest eigenvalues of transformed spiked Wigner matrices 1
Focal-SAM: Focal Sharpness-Aware Minimization for Long-Tailed Classification 5
Focus On This, Not That! Steering LLMs with Adaptive Feature Specification 5
Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning 5
Foundation Model Insights and a Multi-Model Approach for Superior Fine-Grained One-shot Subset Selection 4
Foundation Molecular Grammar: Multi-Modal Foundation Models Induce Interpretable Molecular Graph Languages 4
Fourier Position Embedding: Enhancing Attention’s Periodic Extension for Length Generalization 5
FourierMamba: Fourier Learning Integration with State Space Models for Image Deraining 4
Fragments to Facts: Partial-Information Fragment Inference from LLMs 5
FrameBridge: Improving Image-to-Video Generation with Bridge Models 4
Fraud-Proof Revenue Division on Subscription Platforms 3
Free Process Rewards without Process Labels 4
FreeMesh: Boosting Mesh Generation with Coordinates Merging 4
Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM 2
From Black Boxes to Transparent Minds: Evaluating and Enhancing the Theory of Mind in Multimodal Large Language Models 3
From Complex to Atomic: Enhancing Augmented Generation via Knowledge-Aware Dual Rewriting and Reasoning 4
From Crowdsourced Data to High-quality Benchmarks: Arena-Hard and Benchbuilder Pipeline 4
From Debate to Equilibrium: Belief-Driven Multi-Agent LLM Reasoning via Bayesian Nash Equilibrium 5
From Feature Interaction to Feature Generation: A Generative Paradigm of CTR Prediction Models 4
From Individual Experience to Collective Evidence: A Reporting-Based Framework for Identifying Systemic Harms 5
From Jack of All Trades to Master of One: Specializing LLM-based Autoraters to a Test Set 4
From Kernels to Features: A Multi-Scale Adaptive Theory of Feature Learning 5
From Language Models over Tokens to Language Models over Characters 5
From Local Details to Global Context: Advancing Vision-Language Models with Attention-Based Selection 6
From Logits to Hierarchies: Hierarchical Clustering made Simple 5
From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories, and Applications 6
From Mechanistic Interpretability to Mechanistic Biology: Training, Evaluating, and Interpreting Sparse Autoencoders on Protein Language Models 4
From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information? 4
From Pixels to Perception: Interpretable Predictions via Instance-wise Grouped Feature Selection 4
From RAG to Memory: Non-Parametric Continual Learning for Large Language Models 5
From Spectrum-free towards Baseline-view-free: Double-track Proximity Driven Multi-view Clustering 3
From Theory to Practice: Rethinking Green and Martin Kernels for Unleashing Graph Transformers 5
From Thousands to Billions: 3D Visual Language Grounding via Render-Supervised Distillation from 2D VLMs 4
From Token to Rhythm: A Multi-Scale Approach for ECG-Language Pretraining 5
From Uncertain to Safe: Conformal Adaptation of Diffusion Models for Safe PDE Control 5
From Weight-Based to State-Based Fine-Tuning: Further Memory Reduction on LoRA with Parallel Control 5
Fully Dynamic Embedding into $\ell_p$ Spaces 1
Fully Dynamic Euclidean Bi-Chromatic Matching in Sublinear Update Time 5
Fully Heteroscedastic Count Regression with Deep Double Poisson Networks 5
FunBO: Discovering Acquisition Functions for Bayesian Optimization with FunSearch 4
Function Encoders: A Principled Approach to Transfer Learning in Hilbert Spaces 4
Function-Space Learning Rates 4
Function-to-Style Guidance of LLMs for Code Translation 3
Functional Alignment Can Mislead: Examining Model Stitching 5
Fundamental Bias in Inverting Random Sampling Matrices with Application to Sub-sampled Newton 2
Fundamental Limits of Visual Autoregressive Transformers: Universal Approximation Abilities 1
Fundamental limits of learning in sequence multi-index models and deep attention networks: high-dimensional asymptotics and sharp thresholds 5
FuseUNet: A Multi-Scale Feature Fusion Method for U-like Networks 6
Fusing Reward and Dueling Feedback in Stochastic Bandits 2
G-Adaptivity: optimised graph-based mesh relocation for finite element methods 5
G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks 6
G-Sim: Generative Simulations with Large Language Models and Gradient-Free Calibration 5
GANQ: GPU-Adaptive Non-Uniform Quantization for Large Language Models 6
GAPrompt: Geometry-Aware Point Cloud Prompt for 3D Vision Model 6
GCAL: Adapting Graph Models to Evolving Domain Shifts 4
GEFA: A General Feature Attribution Framework Using Proxy Gradient Estimation 7
GHOST: Generalizable One-Shot Federated Graph Learning with Proxy-Based Topology Knowledge Retention 7
GIVE: Structured Reasoning of Large Language Models with Knowledge Graph Inspired Veracity Extrapolation 4
GLGENN: A Novel Parameter-Light Equivariant Neural Networks Architecture Based on Clifford Geometric Algebras 2
GMAIL: Generative Modality Alignment for generated Image Learning 5
GPEN: Global Position Encoding Network for Enhanced Subgraph Representation Learning 4
GPTAQ: Efficient Finetuning-Free Quantization for Asymmetric Calibration 7
GRADEO: Towards Human-Like Evaluation for Text-to-Video Generation via Multi-Step Reasoning 4
GRAIL: Graph Edit Distance and Node Alignment using LLM-Generated Code 6
GRAM: A Generative Foundation Reward Model for Reward Generalization 5
GRU: Mitigating the Trade-off between Unlearning and Retention for LLMs 7
GS-Bias: Global-Spatial Bias Learner for Single-Image Test-Time Adaptation of Vision-Language Models 4
GSM-$∞$: How Do your LLMs Behave over Infinitely Increasing Reasoning Complexity and Context Length? 5
GTR: A General, Multi-View, and Dynamic Framework for Trajectory Representation Learning 7
Galileo: Learning Global & Local Features of Many Remote Sensing Modalities 5
Gamma Distribution PCA-Enhanced Feature Learning for Angle-Robust SAR Target Recognition 5
Gandalf the Red: Adaptive Security for LLMs 4
Gap-Dependent Bounds for Federated $Q$-Learning 3
GaussMark: A Practical Approach for Structural Watermarking of Language Models 5
GaussMarker: Robust Dual-Domain Watermark for Diffusion Models 4
Gaussian Mixture Flow Matching Models 6
GenMol: A Drug Discovery Generalist with Discrete Diffusion 5
GenZSL: Generative Zero-Shot Learning Via Inductive Variational Autoencoder 5
General agents need world models 2
General framework for online-to-nonconvex conversion: Schedule-free SGD is also effective for nonconvex optimization 1
Generalists vs. Specialists: Evaluating LLMs on Highly-Constrained Biophysical Sequence Optimization Tasks 4
Generalizable Multi-Camera 3D Object Detection from a Single Source via Fourier Cross-View Learning 4
Generalization Analysis for Controllable Learning 0
Generalization Analysis for Supervised Contrastive Representation Learning under Non-IID Settings 1
Generalization Bounds via Meta-Learned Model Representations: PAC-Bayes and Sample Compression Hypernetworks 6
Generalization Performance of Ensemble Clustering: From Theory to Algorithm 4
Generalization Principles for Inference over Text-Attributed Graphs with Large Language Models 6
Generalization and Robustness of the Tilted Empirical Risk 1
Generalization in Federated Learning: A Conditional Mutual Information Framework 4
Generalization of noisy SGD in unbounded non-convex settings 0
Generalized Category Discovery via Reciprocal Learning and Class-Wise Distribution Regularization 5
Generalized Interpolating Discrete Diffusion 6
Generalized Random Forests Using Fixed-Point Trees 6
Generalized Smooth Bilevel Optimization with Nonconvex Lower-Level 4
Generalized Venn and Venn-Abers Calibration with Applications in Conformal Prediction 4
Generalized additive models via direct optimization of regularized decision stump forests 6
Generalizing Causal Effects from Randomized Controlled Trials to Target Populations across Diverse Environments 6
Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? 4
Generating Hypotheses of Dynamic Causal Graphs in Neuroscience: Leveraging Generative Factor Models of Observed Time Series 5
Generation from Noisy Examples 1
Generative Audio Language Modeling with Continuous-valued Tokens and Masked Next-Token Prediction 3
Generative Data Mining with Longtail-Guided Diffusion 6
Generative Human Trajectory Recovery via Embedding-Space Conditional Diffusion 5
Generative Intervention Models for Causal Perturbation Modeling 4
Generative Modeling Reinvents Supervised Learning: Label Repurposing with Predictive Consistency Learning 6
Generative Point Cloud Registration 5
Generative Social Choice: The Next Generation 6
GeoPixel: Pixel Grounding Large Multimodal Model in Remote Sensing 5
Geometric Algebra Planes: Convex Implicit Neural Volumes 4
Geometric Contact Flows: Contactomorphisms for Dynamics and Control 5
Geometric Feature Embedding for Effective 3D Few-Shot Class Incremental Learning 5
Geometric Generative Modeling with Noise-Conditioned Graph Networks 5
Geometric Hyena Networks for Large-scale Equivariant Learning 6
Geometric Median (GM) Matching for Robust k-Subset Selection from Noisy Data 5
Geometric Representation Condition Improves Equivariant Molecule Generation 6
Geometric Resampling in Nearly Linear Time for Follow-the-Perturbed-Leader with Best-of-Both-Worlds Guarantee in Bandit Problems 5
Geometric and Physical Constraints Synergistically Enhance Neural PDE Surrogates 5
Geometry Informed Tokenization of Molecules for Language Model Generation 5
Geometry-Informed Neural Networks 5
Global Context-aware Representation Learning for Spatially Resolved Transcriptomics 6
Global Convergence and Rich Feature Learning in $L$-Layer Infinite-Width Neural Networks under $μ$ Parametrization 3
Global Optimization with a Power-Transformed Objective and Gaussian Smoothing 5
Global curvature for second-order optimization of neural networks 4
Global-Local Dirichlet Processes for Clustering Grouped Data in the Presence of Group-Specific Idiosyncratic Variables 5
GoIRL: Graph-Oriented Inverse Reinforcement Learning for Multimodal Trajectory Prediction 4
Goal-Oriented Skill Abstraction for Offline Multi-Task Reinforcement Learning 6
Going Deeper into Locally Differentially Private Graph Neural Networks 4
GradPS: Resolving Futile Neurons in Parameter Sharing Network for Multi-Agent Reinforcement Learning 5
Gradient Aligned Regression via Pairwise Losses 6
Gradient Boosting Reinforcement Learning 5
Gradient Descent Converges Arbitrarily Fast for Logistic Regression via Large and Adaptive Stepsizes 1
Gradient Flow Provably Learns Robust Classifiers for Orthonormal GMMs 1
Gradient Inversion of Multimodal Models 3
Gradient-based Explanations for Deep Learning Survival Models 6
Gradual Transition from Bellman Optimality Operator to Bellman Operator in Online Reinforcement Learning 3
Grammar-Forced Translation of Natural Language to Temporal Logic using LLMs 4
Graph Adaptive Autoregressive Moving Average Models 5
Graph Attention is Not Always Beneficial: A Theoretical Analysis of Graph Attention Mechanisms via Contextual Stochastic Block Models 5
Graph Diffusion for Robust Multi-Agent Coordination 4
Graph Generative Pre-trained Transformer 6
Graph Inverse Style Transfer for Counterfactual Explainability 6
Graph Minimum Factorization Distance and Its Application to Large-Scale Graph Data Clustering 6
Graph Neural Network Generalization With Gaussian Mixture Model Based Augmentation 6
Graph World Model 5
Graph-Assisted Stitching for Offline Hierarchical Reinforcement Learning 5
Graph-Based Algorithms for Diverse Similarity Search 6
Graph-Supported Dynamic Algorithm Configuration for Multi-Objective Combinatorial Optimization 5
Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models 5
Graph4MM: Weaving Multimodal Learning with Structural Information 5
GraphCL: Graph-based Clustering for Semi-Supervised Medical Image Segmentation 5
GraphGPT: Generative Pre-trained Graph Eulerian Transformer 5
Gravity-Bench-v1: A Benchmark on Gravitational Physics Discovery for Agents 3
Great Models Think Alike and this Undermines AI Oversight 3
Gridded Transformer Neural Processes for Spatio-Temporal Data 5
Griffin: Towards a Graph-Centric Relational Database Foundation Model 5
GrokFormer: Graph Fourier Kolmogorov-Arnold Transformers 5
Grokking Beyond the Euclidean Norm of Model Parameters 4
Grokking at the Edge of Linear Separability 2
Grokking in the Wild: Data Augmentation for Real-World Multi-Hop Reasoning with Transformers 4
Guarantees of a Preconditioned Subgradient Algorithm for Overparameterized Asymmetric Low-rank Matrix Recovery 6
GuardAgent: Safeguard LLM Agents via Knowledge-Enabled Reasoning 2
Guardians of Image Quality: Benchmarking Defenses Against Adversarial Attacks on Image Quality Metrics 5
Guided Search Strategies in Non-Serializable Environments with Applications to Software Engineering Agents 3
Guided Structural Inference: Leveraging Priors with Soft Gating Mechanisms 6
Guided Zeroth-Order Methods for Stochastic Non-convex Problems with Decision-Dependent Distributions 6
GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance 7
Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding 4
H-Tuning: Toward Low-Cost and Efficient ECG-based Cardiovascular Disease Detection with Pre-Trained Models 6
HALoS: Hierarchical Asynchronous Local SGD over Slow Networks for Geo-Distributed Large Language Model Training 6
HEAP: Hyper Extended A-PDHG Operator for Constrained High-dim PDEs 5
HGOT: Self-supervised Heterogeneous Graph Neural Network with Optimal Transport 3
HPS: Hard Preference Sampling for Human Preference Alignment 4
HYGMA: Hypergraph Coordination Networks with Dynamic Grouping for Multi-Agent Reinforcement Learning 4
Habitizing Diffusion Planning for Efficient and Effective Decision Making 5
Handling Imbalanced Pseudolabels for Vision-Language Models with Concept Alignment and Confusion-Aware Calibrated Margin 5
HaploVL: A Single-Transformer Baseline for Multi-Modal Understanding 6
Hardware and Software Platform Inference 5
HarmoniCa: Harmonizing Training and Inference for Better Feature Caching in Diffusion Transformer Acceleration 5
Harmonizing Geometry and Uncertainty: Diffusion with Hyperspheres 5
Harnessing Heterogeneous Statistical Strength for Personalized Federated Learning via Hierarchical Bayesian Inference 6
HashAttention: Semantic Sparsity for Faster Inference 5
Haste Makes Waste: A Simple Approach for Scaling Graph Neural Networks 5
Heads up! Large Language Models Can Perform Tasks Without Your Instruction via Selective Attention Head Masking 5
HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation 4
Heavy-Tailed Linear Bandits: Huber Regression with One-Pass Update 2
Hessian Geometry of Latent Space in Generative Models 4
HetSSNet: Spatial-Spectral Heterogeneous Graph Learning Network for Panchromatic and Multispectral Images Fusion 4
Heterogeneous Data Game: Characterizing the Model Competition Across Multiple Data Sources 2
Heterogeneous Label Shift: Theory and Algorithm 3
Heterogeneous Sufficient Dimension Reduction and Subspace Clustering 5
Heterogeneous Treatment Effect in Time-to-Event Outcomes: Harnessing Censored Data with Recursively Imputed Trees 5
Hgformer: Hyperbolic Graph Transformer for Collaborative Filtering 4
Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models 3
Hi-Patch: Hierarchical Patch GNN for Irregular Multivariate Time Series 6
HiRemate: Hierarchical Approach for Efficient Re-materialization of Neural Networks 4
Hidden No More: Attacking and Defending Private Third-Party LLM Inference 6
Hide & Seek: Transformer Symmetries Obscure Sharpness & Riemannian Geometry Finds It 3
Hierarchical Equivariant Policy via Frame Transfer 4
Hierarchical Graph Tokenization for Molecule-Language Alignment 6
Hierarchical Masked Autoregressive Models with Low-Resolution Token Pivots 5
Hierarchical Overlapping Clustering on Graphs: Cost Function, Algorithm and Scalability 5
Hierarchical Planning for Complex Tasks with Knowledge Graph-RAG and Symbolic Verification 3
Hierarchical Refinement: Optimal Transport to Infinity and Beyond 6
Hierarchical Reinforcement Learning with Targeted Causal Interventions 5
Hierarchical Reinforcement Learning with Uncertainty-Guided Diffusional Subgoals 3
High Dynamic Range Novel View Synthesis with Single Exposure 3
High Probability Bound for Cross-Learning Contextual Bandits with Unknown Context Distributions 2
High-Dimensional Prediction for Sequential Decision Making 1
High-Dimensional Tensor Regression With Oracle Properties 4
High-Fidelity Simultaneous Speech-To-Speech Translation 5
Highly Compressed Tokenizer Can Generate Without Training 6
History-Guided Video Diffusion 5
Holistic Physics Solver: Learning PDEs in a Unified Spectral-Physical Space 5
Homophily Enhanced Graph Domain Adaptation 4
How Compositional Generalization and Creativity Improve as Diffusion Models are Trained 3
How Contaminated Is Your Benchmark? Measuring Dataset Leakage in Large Language Models with Kernel Divergence 5
How Distributed Collaboration Influences the Diffusion Model Training? A Theoretical Perspective 4
How Do Images Align and Complement LiDAR? Towards a Harmonized Multi-modal 3D Panoptic Segmentation 5
How Do Large Language Monkeys Get Their Power (Laws)? 4
How Do Transformers Learn Variable Binding in Symbolic Programs? 2
How Effective Can Dropout Be in Multiple Instance Learning ? 7
How Expressive are Knowledge Graph Foundation Models? 6
How Far Is Video Generation from World Model: A Physical Law Perspective 4
How Much Can Transfer? BRIDGE: Bounded Multi-Domain Graph Foundation Model with Generalization Guarantees 7
How Much Can We Forget about Data Contamination? 5
How Transformers Learn Regular Language Recognition: A Theoretical Study on Training Dynamics and Implicit Bias 3
How Transformers Learn Structured Data: Insights From Hierarchical Filtering 4
How does Labeling Error Impact Contrastive Learning? A Perspective from Data Dimensionality Reduction 3
How to Evaluate and Mitigate IP Infringement in Visual Generative AI? 4
How to Move Your Dragon: Text-to-Motion Synthesis for Large-Vocabulary Objects 5
How to Synthesize Text Data without Model Collapse? 5
How to Train Your Multi-Exit Model? Analyzing the Impact of Training Strategies 4
How to set AdamW’s weight decay as you scale model and dataset size 5
Human Body Restoration with One-Step Diffusion Model and A New Benchmark 5
Human Cognition-Inspired Hierarchical Fuzzy Learning Machine 5
Human-Aligned Image Models Improve Visual Decoding from the Brain 4
Hybrid Batch Normalisation: Resolving the Dilemma of Batch Normalisation in Federated Learning 4
Hybrid Quantum-Classical Multi-Agent Pathfinding 6
Hybrid Spiking Vision Transformer for Object Detection with Event Cameras 3
HybridGS: High-Efficiency Gaussian Splatting Data Compression using Dual-Channel Sparse Representation and Point Cloud Encoder 6
Hyper-Transforming Latent Diffusion Models 5
Hyper: Hyperparameter Robust Efficient Exploration in Reinforcement Learning 3
HyperIMTS: Hypergraph Neural Network for Irregular Multivariate Time Series Forecasting 6
HyperIV: Real-time Implied Volatility Smoothing 5
HyperNear: Unnoticeable Node Injection Attacks on Hypergraph Neural Networks 5
HyperTree Planning: Enhancing LLM Reasoning via Hierarchical Thinking 5
Hyperband-based Bayesian Optimization for Black-box Prompt Selection 4
Hyperbolic-PDE GNN: Spectral Graph Neural Networks in the Perspective of A System of Hyperbolic Partial Differential Equations 5
Hyperspherical Normalization for Scalable Deep Reinforcement Learning 5
Hypo3D: Exploring Hypothetical Reasoning in 3D 3
Hypothesis Testing for Generalized Thurstone Models 3
I Think, Therefore I Diffuse: Enabling Multimodal In-Context Reasoning in Diffusion Models 4
IBCircuit: Towards Holistic Circuit Discovery with Information Bottleneck 3
ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks 2
IL-SOAR : Imitation Learning with Soft Optimistic Actor cRitic 5
IMPACT: Iterative Mask-based Parallel Decoding for Text-to-Audio Generation with Diffusion Modeling 4
IMTS is Worth Time $\times$ Channel Patches: Visual Masked Autoencoders for Irregular Multivariate Time Series Prediction 5
INRFlow: Flow Matching for INRs in Ambient Space 2
IRBridge: Solving Image Restoration Bridge with Pre-trained Generative Diffusion Models 4
IT$^3$: Idempotent Test-Time Training 3
ITBench: Evaluating AI Agents across Diverse Real-World IT Automation Tasks 5
ITFormer: Bridging Time Series and Natural Language for Multi-Modal QA with Large-Scale Multitask Dataset 5
Identifiable Object Representations under Spatial Ambiguities 4
Identification of Latent Confounders via Investigating the Tensor Ranks of the Nonlinear Observations 3
Identifying Causal Direction via Variational Bayesian Compression 4
Identifying Metric Structures of Deep Latent Variable Models 3
Identifying Neural Dynamics Using Interventional State Space Models 4
Identifying and Understanding Cross-Class Features in Adversarial Training 5
Identifying biological perturbation targets through causal differential networks 5
Idiosyncrasies in Large Language Models 4
Imagine While Reasoning in Space: Multimodal Visualization-of-Thought 4
Imitation Learning from a Single Temporally Misaligned Video 4
Implicit Bias of Gradient Descent for Non-Homogeneous Deep Networks 0
Implicit Language Models are RNNs: Balancing Parallelization and Expressivity 5
Implicit Regularization for Tubal Tensor Factorizations via Gradient Descent 4
Implicit Riemannian Optimism with Applications to Min-Max Problems 2
Implicit Subgraph Neural Network 5
Implicit degree bias in the link prediction task 6
Importance Corrected Neural JKO Sampling 5
Importance Sampling for Nonlinear Models 3
Impossible Videos 3
Improved Algorithm for Deep Active Learning under Imbalance via Optimal Separation 6
Improved Approximations for Hard Graph Problems using Predictions 5
Improved Coresets for Vertical Federated Learning: Regularized Linear and Logistic Regressions 5
Improved Discretization Complexity Analysis of Consistency Models: Variance Exploding Forward Process and Decay Discretization Scheme 0
Improved Expressivity of Hypergraph Neural Networks through High-Dimensional Generalized Weisfeiler-Leman Algorithms 6
Improved Last-Iterate Convergence of Shuffling Gradient Methods for Nonsmooth Convex Optimization 1
Improved Learning via k-DTW: A Novel Dissimilarity Measure for Curves 6
Improved Lower Bounds for First-order Stochastic Non-convex Optimization under Markov Sampling 1
Improved Off-policy Reinforcement Learning in Biological Sequence Design 5
Improved Online Confidence Bounds for Multinomial Logistic Bandits 2
Improved Regret Analysis in Gaussian Process Bandits: Optimality for Noiseless Reward, RKHS norm, and Non-Stationary Variance 1
Improved Sample Complexity for Private Nonsmooth Nonconvex Optimization 1
Improved Theoretically-Grounded Evolutionary Algorithms for Subset Selection with a Linear Cost Constraint 3
Improved and Oracle-Efficient Online $\ell_1$-Multicalibration 1
Improving Compositional Generation with Diffusion Models Using Lift Scores 5
Improving Consistency Models with Generator-Augmented Flows 6
Improving Continual Learning Performance and Efficiency with Auxiliary Classifiers 4
Improving Diversity in Language Models: When Temperature Fails, Change the Loss 5
Improving Flow Matching by Aligning Flow Divergence 5
Improving Generalization in Federated Learning with Highly Heterogeneous Data via Momentum-Based Stochastic Controlled Weight Averaging 4
Improving Generalization with Flat Hilbert Bayesian Inference 5
Improving LLM Safety Alignment with Dual-Objective Optimization 5
Improving LLM Video Understanding with 16 Frames Per Second 5
Improving LLMs for Recommendation with Out-Of-Vocabulary Tokens 5
Improving Memory Efficiency for Training KANs via Meta Learning 5
Improving Model Alignment Through Collective Intelligence of Open-Source Models 4
Improving Multi-Class Calibration through Normalization-Aware Isotonic Techniques 4
Improving Multimodal Learning Balance and Sufficiency through Data Remixing 5
Improving Out-of-Distribution Detection via Dynamic Covariance Calibration 5
Improving Out-of-Distribution Detection with Markov Logic Networks 6
Improving Parallel Program Performance with LLM Optimizers via Agent-System Interfaces 4
Improving Rationality in the Reasoning Process of Language Models through Self-playing Game 5
Improving Reward Model Generalization from Adversarial Process Enhanced Preferences 5
Improving Soft Unification with Knowledge Graph Embedding Methods 5
Improving Transformer World Models for Data-Efficient RL 6
Improving Value Estimation Critically Enhances Vanilla Policy Gradient 3
Improving Your Model Ranking on Chatbot Arena by Vote Rigging 6
Improving Zero-Shot Adversarial Robustness in Vision-Language Models by Closed-form Alignment of Adversarial Path Simplices 4
Improving the Continuity of Goal-Achievement Ability via Policy Self-Regularization for Goal-Conditioned Reinforcement Learning 4
Improving the Diffusability of Autoencoders 5
Improving the Effective Receptive Field of Message-Passing Neural Networks 5
Improving the Scaling Laws of Synthetic Data with Deliberate Practice 4
Improving the Statistical Efficiency of Cross-Conformal Prediction 4
Improving the Variance of Differentially Private Randomized Experiments through Clustering 3
In-Context Adaptation to Concept Drift for Learned Database Operations 7
In-Context Deep Learning via Transformer Models 3
In-Context Denoising with One-Layer Transformers: Connections between Attention and Associative Memory Retrieval 2
In-Context Fine-Tuning for Time-Series Foundation Models 4
In-Context Learning and Occam’s Razor 4
In-Context Learning as Conditioned Associative Memory Retrieval 4
In-Context Linear Regression Demystified: Training Dynamics and Mechanistic Interpretability of Multi-Head Softmax Attention 3
In-Context Reinforcement Learning From Suboptimal Historical Data 4
Incentivize without Bonus: Provably Efficient Model-based Online Multi-agent RL for Markov Games 1
Incorporating Arbitrary Matrix Group Equivariance into KANs 5
Incremental Gradient Descent with Small Epoch Counts is Surprisingly Slow on Ill-Conditioned Problems 3
Independence Tests for Language Models 4
Inducing, Detecting and Characterising Neural Modules: A Pipeline for Functional Interpretability in Reinforcement Learning 5
Inductive Gradient Adjustment for Spectral Bias in Implicit Neural Representations 4
Inductive Moment Matching 4
InfAlign: Inference-aware language model alignment 4
Inference-Time Alignment of Diffusion Models with Direct Noise Optimization 3
Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models 5
Info-Coevolution: An Efficient Framework for Data Model Coevolution 5
InfoCons: Identifying Interpretable Critical Concepts in Point Clouds via Information Theory 6
InfoSAM: Fine-Tuning the Segment Anything Model from An Information-Theoretic Perspective 5
InfoSEM: A Deep Generative Model with Informative Priors for Gene Regulatory Network Inference 3
Information Bottleneck-guided MLPs for Robust Spatial-temporal Forecasting 7
Instance Correlation Graph-based Naive Bayes 5
Instance-Optimal Pure Exploration for Linear Bandits on Continuous Arms 4
Instruct2See: Learning to Remove Any Obstructions Across Distributions 7
Instruction-Following Pruning for Large Language Models 4
IntLoRA: Integral Low-rank Adaptation of Quantized Diffusion Models 6
Integer Programming for Generalized Causal Bootstrap Designs 4
Integrating Intermediate Layer Optimization and Projected Gradient Descent for Solving Inverse Problems with Diffusion Models 5
Integration-free Kernels for Equivariant Gaussian Process Modelling 6
Interaction-Aware Gaussian Weighting for Clustered Federated Learning 5
Interchangeable Token Embeddings for Extendable Vocabulary and Alpha-Equivalence 6
Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviors 4
Interpolating Neural Network-Tensor Decomposition (INN-TD): a scalable and interpretable approach for large-scale physics-based problems 4
Interpreting CLIP with Hierarchical Sparse Autoencoders 5
Interpreting the Repeated Token Phenomenon in Large Language Models 3
Intersectional Fairness in Reinforcement Learning with Large State and Constraint Spaces 2
Introducing 3D Representation for Dense Volume-to-Volume Translation via Score Fusion 5
Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning 4
Invariant Deep Uplift Modeling for Incentive Assignment in Online Marketing via Probability of Necessity and Sufficiency 5
Inverse Bridge Matching Distillation 6
Inverse Flow and Consistency Models 7
Inverse Optimization via Learning Feasible Regions 5
Inverse Problem Sampling in Latent Space Using Sequential Monte Carlo 5
Inverse Reinforcement Learning with Switching Rewards and History Dependency for Characterizing Animal Behaviors 6
Inverse problems with experiment-guided AlphaFold 4
Investigating Non-Transitivity in LLM-as-a-Judge 4
Investigating the Overlooked Hessian Structure: From CNNs to LLMs 3
Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment 4
Is Complex Query Answering Really Complex? 4
Is Noise Conditioning Necessary for Denoising Generative Models? 4
Is Your Model Fairly Certain? Uncertainty-Aware Fairness Evaluation for LLMs 2
Isolated Causal Effects of Natural Language 5
Iterative Vectors: In-Context Gradient Steering without Backpropagation 6
It’s My Data Too: Private ML for Datasets with Multi-User Training Examples 4
Jacobian Sparse Autoencoders: Sparsify Computations, Not Just Activations 5
Janus: Dual-Server Multi-Round Secure Aggregation with Verifiability for Federated Learning 5
Joint Learning of Energy-based Models and their Partition Function 4
Joint Localization and Activation Editing for Low-Resource Fine-Tuning 5
Joint Metric Space Embedding by Unbalanced Optimal Transport with Gromov–Wasserstein Marginal Penalization 5
Joint MoE Scaling Laws: Mixture of Experts Can Be Memory Efficient 4
Joker: Joint Optimization Framework for Lightweight Kernel Machines 6
Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning 5
K$^2$IE: Kernel Method-based Kernel Intensity Estimators for Inhomogeneous Poisson Processes 6
KABB: Knowledge-Aware Bayesian Bandits for Dynamic Expert Coordination in Multi-Agent Systems 4
KAN-AD: Time Series Anomaly Detection with Kolmogorov–Arnold Networks 4
KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search 6
KEA: Keeping Exploration Alive by Proactively Coordinating Exploration Strategies 3
KGMark: A Diffusion Watermark for Knowledge Graphs 4
KIND: Knowledge Integration and Diversion for Training Decomposable Models 4
KV Shifting Attention Enhances Language Modeling 6
KVTuner: Sensitivity-Aware Layer-Wise Mixed-Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference 5
Kandinsky Conformal Prediction: Beyond Class- and Covariate-Conditional Coverage 4
Kernel Quantile Embeddings and Associated Probability Metrics 5
Kernel-based Unsupervised Embedding Alignment for Enhanced Visual Representation in Vision-language Models 5
KernelBench: Can LLMs Write Efficient GPU Kernels? 6
KinDEL: DNA-Encoded Library Dataset for Kinase Inhibitors 6
Kinetic Langevin Diffusion for Crystalline Materials Generation 6
Knowledge Retention in Continual Model-Based Reinforcement Learning 5
Knowledge Swapping via Learning and Unlearning 6
Knowledge-Guided Wasserstein Distributionally Robust Optimization 3
KoNODE: Koopman-Driven Neural Ordinary Differential Equations with Evolving Parameters for Time Series Analysis 6
Kona: An Efficient Privacy-Preservation Framework for KNN Classification by Communication Optimization 6
KoopSTD: Reliable Similarity Analysis between Dynamical Systems via Approximating Koopman Spectrum with Timescale Decoupling 3
L-Diffusion: Laplace Diffusion for Efficient Pathology Image Segmentation 3
L3A: Label-Augmented Analytic Adaptation for Multi-Label Class Incremental Learning 4
LADA: Scalable Label-Specific CLIP Adapter for Continual Learning 5
LAION-C: An Out-of-Distribution Benchmark for Web-Scale Vision Models 5
LARM: Large Auto-Regressive Model for Long-Horizon Embodied Intelligence 3
LASER: Attention with Exponential Transformation 5
LAST SToP for Modeling Asynchronous Time Series 4
LAuReL: Learned Augmented Residual Layer 3
LBI-FL: Low-Bit Integerized Federated Learning with Temporally Dynamic Bit-Width Allocation 5
LDMol: A Text-to-Molecule Diffusion Model with Structurally Informative Latent Space Surpasses AR Models 6
LEAPS: A discrete neural sampler via locally equivariant networks 4
LEMoN: Label Error Detection using Multimodal Neighbors 6
LETS Forecast: Learning Embedology for Time Series Forecasting 4
LEVIS: Large Exact Verifiable Input Spaces for Neural Networks 6
LGDM: Latent Guidance in Diffusion Models for Perceptual Evaluations 6
LIFT the Veil for the Truth: Principal Weights Emerge after Rank Reduction for Reasoning-Focused Supervised Fine-Tuning 5
LIMEFLDL: A Local Interpretable Model-Agnostic Explanations Approach for Label Distribution Learning 4
LIVS: A Pluralistic Alignment Dataset for Inclusive Public Spaces 5
LLM Alignment as Retriever Optimization: An Information Retrieval Perspective 4
LLM Data Selection and Utilization via Dynamic Bi-level Optimization 3
LLM Enhancers for GNNs: An Analysis from the Perspective of Causal Mechanism Identification 5
LLM-Assisted Semantically Diverse Teammate Generation for Efficient Multi-agent Coordination 3
LLM-Augmented Chemical Synthesis and Design Decision Programs 4
LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models 4
LLMScan: Causal Scan for LLM Misbehavior Detection 5
LLMs Can Reason Faster Only If We Let Them 4
LLMs can see and hear without any training 4
LLMs on the Line: Data Determines Loss-to-Loss Scaling Laws 2
LLaVA-ReID: Selective Multi-image Questioner for Interactive Person Re-Identification 5
LMAct: A Benchmark for In-Context Imitation Learning with Long Multimodal Demonstrations 6
LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models 5
LOB-Bench: Benchmarking Generative AI for Finance - an Application to Limit Order Book Data 5
LOCATE 3D: Real-World Object Localization via Self-Supervised Learning in 3D 5
LOGO — Long cOntext aliGnment via efficient preference Optimization 3
LRA-QViT: Integrating Low-Rank Approximation and Quantization for Robust and Efficient Vision Transformers 4
LSCD: Lomb–Scargle Conditioned Diffusion for Time series Imputation 6
LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models 5
La RoSA: Enhancing LLM Efficiency via Layerwise Rotated Sparse Activation 5
LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models 4
LaMAGIC2: Advanced Circuit Formulations for Language Model-Based Analog Topology Generation 6
LaRA: Benchmarking Retrieval-Augmented Generation and Long-Context LLMs – No Silver Bullet for LC or RAG Routing 4
Label Distribution Propagation-based Label Completion for Crowdsourcing 4
Ladder-Residual: Parallelism-Aware Architecture for Accelerating Large Model Inference with Communication Overlapping 4
LangDAug: Langevin Data Augmentation for Multi-Source Domain Generalization in Medical Image Segmentation 6
LangTime: A Language-Guided Unified Model for Time Series Forecasting with Proximal Policy Optimization 6
Language Models May Verbatim Complete Text They Were Not Explicitly Trained On 6
Language Models as Implicit Tree Search 4
Language Models over Canonical Byte-Pair Encodings 5
LapSum - One Method to Differentiate Them All: Ranking, Sorting and Top-k Selection 5
Laplace Transform Based Low-Complexity Learning of Continuous Markov Semigroups 5
Large Continual Instruction Assistant 4
Large Displacement Motion Transfer with Unsupervised Anytime Interpolation 3
Large Language Model-driven Large Neighborhood Search for Large-Scale MILP Problems 6
Large Language Models are Demonstration Pre-Selectors for Themselves 5
Large Language Models to Diffusion Finetuning 5
Large Language-Geometry Model: When LLM meets Equivariance 4
Larger or Smaller Reward Margins to Select Preferences for LLM Alignment? 5
Latent Action Learning Requires Supervision in the Presence of Distractors 5
Latent Diffusion Planning for Imitation Learning 5
Latent Imputation before Prediction: A New Computational Paradigm for De Novo Peptide Sequencing 5
Latent Mamba Operator for Partial Differential Equations 6
Latent Preference Coding: Aligning Large Language Models via Discrete Latent Codes 3
Latent Score-Based Reweighting for Robust Classification on Imbalanced Tabular Data 5
Latent Thought Models with Variational Bayes Inference-Time Computation 5
Latent Variable Causal Discovery under Selection Bias 4
Latent Variable Estimation in Bayesian Black-Litterman Models 3
Layer by Layer: Uncovering Hidden Representations in Language Models 2
Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language Models 5
Layer-wise Quantization for Quantized Optimistic Dual Averaging 5
Lean and Mean Adaptive Optimization via Subset-Norm and Subspace-Momentum with Convergence Guarantees 5
Learn Beneficial Noise as Graph Augmentation 5
Learn Singularly Perturbed Solutions via Homotopy Dynamics 4
Learn from Downstream and Be Yourself in Multimodal Large Language Models Fine-Tuning 5
Learn to Vaccinate: Combining Structure Learning and Effective Vaccination for Epidemic and Outbreak Control 6
Learnable Spatial-Temporal Positional Encoding for Link Prediction 6
Learngene Tells You How to Customize: Task-Aware Parameter Initialization at Flexible Scales 4
Learning Adaptive Lighting via Channel-Aware Guidance 4
Learning Adversarial MDPs with Stochastic Hard Constraints 1
Learning Along the Arrow of Time: Hyperbolic Geometry for Backward-Compatible Representation Learning 3
Learning Attribute-Aware Hash Codes for Fine-Grained Image Retrieval via Query Optimization 5
Learning Bayesian Nash Equilibrium in Auction Games via Approximate Best Response 4
Learning Cascade Ranking as One Network 6
Learning Changes in Graphon Attachment Network Models 3
Learning Classifiers That Induce Markets 5
Learning Compact Semantic Information for Incomplete Multi-View Missing Multi-Label Classification 4
Learning Condensed Graph via Differentiable Atom Mapping for Reaction Yield Prediction 5
Learning Configurations for Data-Driven Multi-Objective Optimization 3
Learning Curves of Stochastic Gradient Descent in Kernel Regression 0
Learning Distances from Data with Normalizing Flows and Score Matching 5
Learning Distribution-wise Control in Representation Space for Language Models 4
Learning Dynamics in Continual Pre-Training for Large Language Models 2
Learning Dynamics under Environmental Constraints via Measurement-Induced Bundle Structures 4
Learning Efficient Robotic Garment Manipulation with Standardization 4
Learning Event Completeness for Weakly Supervised Video Anomaly Detection 3
Learning Extrapolative Sequence Transformations from Markov Chains 5
Learning Fused State Representations for Control from Multi-View Observations 5
Learning Gaussian DAG Models without Condition Number Bounds 6
Learning Imbalanced Data with Beneficial Label Noise 6
Learning Imperfect Information Extensive-form Games with Last-iterate Convergence under Bandit Feedback 5
Learning In-context $n$-grams with Transformers: Sub-$n$-grams Are Near-Stationary Points 3
Learning Initial Basis Selection for Linear Programming via Duality-Inspired Tripartite Graph Representation and Comprehensive Supervision 5
Learning Input Encodings for Kernel-Optimal Implicit Neural Representations 5
Learning Invariant Causal Mechanism from Vision-Language Models 6
Learning Joint Interventional Effects from Single-Variable Interventions in Additive Models 3
Learning Latent Graph Structures and their Uncertainty 5
Learning Likelihood-Free Reference Priors 4
Learning Mean Field Control on Sparse Graphs 4
Learning Minimum-Size BDDs: Towards Efficient Exact Algorithms 7
Learning Mixtures of Experts with EM: A Mirror Descent Perspective 3
Learning Monotonic Probabilities with a Generative Cost Model 4
Learning Multi-Level Features with Matryoshka Sparse Autoencoders 4
Learning Optimal Multimodal Information Bottleneck Representations 4
Learning Parametric Distributions from Samples and Preferences 3
Learning Policy Committees for Effective Personalization in MDPs with Diverse Tasks 6
Learning Progress Driven Multi-Agent Curriculum 4
Learning Representations of Instruments for Partial Identification of Treatment Effects 6
Learning Robust Neural Processes with Risk-Averse Stochastic Optimization 6
Learning Safe Control via On-the-Fly Bandit Exploration 2
Learning Safe Strategies for Value Maximizing Buyers in Uniform Price Auctions 3
Learning Safety Constraints for Large Language Models 5
Learning Single Index Models with Diffusion Priors 5
Learning Smooth and Expressive Interatomic Potentials for Physical Property Prediction 6
Learning Soft Sparse Shapes for Efficient Time-Series Classification 7
Learning State-Based Node Representations from a Class Hierarchy for Fine-Grained Open-Set Detection 6
Learning Strategic Language Agents in the Werewolf Game with Iterative Latent Space Policy Optimization 1
Learning Survival Distributions with the Asymmetric Laplace Distribution 5
Learning Time-Aware Causal Representation for Model Generalization in Evolving Domains 5
Learning Time-Varying Multi-Region Brain Communications via Scalable Markovian Gaussian Processes 4
Learning Utilities from Demonstrations in Markov Decision Processes 3
Learning Vision and Language Concepts for Controllable Image Generation 3
Learning With Multi-Group Guarantees For Clusterable Subpopulations 1
Learning curves theory for hierarchically compositional data with power-law distributed features 3
Learning dynamics in linear recurrent neural networks 2
Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning 3
Learning from Sample Stability for Deep Clustering 5
Learning from Suboptimal Data in Continuous Control via Auto-Regressive Soft Q-Network 5
Learning from True-False Labels via Multi-modal Prompt Retrieving 6
Learning from others’ mistakes: Finetuning machine translation models with span-level error annotations 3
Learning multivariate Gaussians with imperfect advice 3
Learning the Electronic Hamiltonian of Large Atomic Structures 5
Learning the RoPEs: Better 2D and 3D Position Encodings with STRING 3
Learning to (Learn at Test Time): RNNs with Expressive Hidden States 4
Learning to Generate Projections for Reducing Dimensionality of Heterogeneous Linear Programming Problems 6
Learning to Incentivize in Repeated Principal-Agent Problems with Adversarial Agent Arrivals 0
Learning to Keep a Promise: Scaling Language Model Decoding Parallelism with Learned Asynchronous Decoding 3
Learning to Match Unpaired Data with Minimum Entropy Coupling 5
Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge 3
Learning to Quantize for Training Vector-Quantized Networks 5
Learning to Reuse Policies in State Evolvable Environments 4
Learning to Route LLMs with Confidence Tokens 5
Learning to Steer Learners in Games 2
Learning to Stop: Deep Learning for Mean Field Optimal Stopping 3
Learning to Trust Bellman Updates: Selective State-Adaptive Regularization for Offline RL 5
Learning with Exact Invariances in Polynomial Time 2
Learning with Expected Signatures: Theory and Applications 5
Learning with Selectively Labeled Data from Multiple Decision-makers 5
Learning without Isolation: Pathway Protection for Continual Learning 6
Learning-Augmented Algorithms for MTS with Bandit Access to Multiple Predictors 1
Learning-Augmented Hierarchical Clustering 1
Learning-Order Autoregressive Models with Application to Molecular Graph Generation 4
Learnings from Scaling Visual Tokenizers for Reconstruction and Generation 5
Learnware Specification via Dual Alignment 3
Lego Sketch: A Scalable Memory-augmented Neural Network for Sketching Data Streams 5
LensLLM: Unveiling Fine-Tuning Dynamics for LLM Selection 5
Less is More: Federated Graph Learning with Alleviating Topology Heterogeneity from A Causal Perspective 4
Let LLM Tell What to Prune and How Much to Prune 4
Leveraging Diffusion Model as Pseudo-Anomalous Graph Generator for Graph-Level Anomaly Detection 5
Leveraging Model Guidance to Extract Training Data from Personalized Diffusion Models 5
Leveraging Offline Data in Linear Latent Contextual Bandits 5
Leveraging Online Olympiad-Level Math Problems for LLMs Training and Contamination-Resistant Evaluation 4
Leveraging Per-Instance Privacy for Machine Unlearning 4
Leveraging Predictive Equivalence in Decision Trees 5
Leveraging Randomness in Model and Data Partitioning for Privacy Amplification 4
Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration 5
Leveraging Sparsity for Sample-Efficient Preference Learning: A Theoretical Perspective 3
Lexico: Extreme KV Cache Compression via Sparse Coding over Universal Dictionaries 5
LieRE: Lie Rotational Positional Encodings 6
Liger: Linearizing Large Language Models to Gated Recurrent Structures 4
LightGTS: A Lightweight General Time Series Forecasting Model 5
LightningDrag: Lightning Fast and Accurate Drag-based Image Editing Emerging from Videos 4
Lightspeed Geometric Dataset Distance via Sliced Optimal Transport 4
Lightweight Dataset Pruning without Full Training via Example Difficulty and Prediction Uncertainty 5
Lightweight Online Adaption for Time Series Foundation Model Forecasts 5
Lightweight Protocols for Distributed Private Quantile Estimation 4
Lightweight-Mark: Rethinking Deep Learning-Based Watermarking 3
Limitations of measure-first protocols in quantum machine learning 0
LineFlow: A Framework to Learn Active Control of Production Lines 5
Linear $Q$-Learning Does Not Diverge in $L^2$: Convergence Rates to a Bounded Set 1
Linear Bandits with Partially Observable Features 2
Linear Contextual Bandits With Interference 4
Linear Mode Connectivity between Multiple Models modulo Permutation Symmetries 6
Linear Transformers as VAR Models: Aligning Autoregressive Attention Mechanisms with Autoregressive Forecasting 6
Linear convergence of Sinkhorn’s algorithm for generalized static Schrödinger bridge 1
Linearization Turns Neural Operators into Function-Valued Gaussian Processes 3
LipsNet++: Unifying Filter and Controller into a Policy Network 5
LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models 5
LoRA Training Provably Converges to a Low-Rank Global Minimum Or It Fails Loudly (But it Probably Won’t Fail) 2
LoRA-Gen: Specializing Large Language Model via Online LoRA Generation 4
LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently 6
Local Identifying Causal Relations in the Presence of Latent Variables 5
Local Manifold Approximation and Projection for Manifold-Aware Diffusion Planning 4
Local Pan-privacy for Federated Analytics 1
Locality Preserving Markovian Transition for Instance Retrieval 4
Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing 3
Log-Sum-Exponential Estimator for Off-Policy Evaluation and Learning 5
Logarithmic Regret for Online KL-Regularized Reinforcement Learning 2
Logits are All We Need to Adapt Closed Models 5
Long-Form Speech Generation with Spoken Language Models 4
Long-Short Alignment for Effective Long-Context Modeling in LLMs 4
Long-Term TalkingFace Generation via Motion-Prior Conditional Diffusion Model 4
LongRoPE2: Near-Lossless LLM Context Window Scaling 5
LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding 5
Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models 6
Looking Beyond the Top-1: Transformers Determine Top Tokens in Order 3
Loss Functions and Operators Generated by f-Divergences 5
LotteryCodec: Searching the Implicit Representation in a Random Network for Low-Complexity Image Compression 5
Low-Dimension-to-High-Dimension Generalization and Its Implications for Length Generalization 3
Low-Rank Adapting Models for Sparse Autoencoders 4
Low-Rank Tensor Transitions (LoRT) for Transferable Tensor Regression 5
Low-Rank Thinning 7
Low-distortion and GPU-compatible Tree Embeddings in Hyperbolic Space 4
LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits 4
Lower Bounds for Chain-of-Thought Reasoning in Hard-Attention Transformers 4
M$^3$HF: Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed Quality 5
M+: Extending MemoryLLM with Scalable Long-Term Memory 5
M2PDE: Compositional Generative Multiphysics and Multi-component PDE Simulation 5
M3-JEPA: Multimodal Alignment via Multi-gate MoE based on the Joint-Embedding Predictive Architecture 4
MA-LoT: Model-Collaboration Lean-based Long Chain-of-Thought Reasoning enhances Formal Theorem Proving 5
MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces 5
MAPLE: Many-Shot Adaptive Pseudo-Labeling for In-Context Learning 4
MARGE: Improving Math Reasoning with Guided Exploration 4
MARS: Unleashing the Power of Variance Reduction for Training Large Models 6
MAS-GPT: Training LLMs to Build LLM-based Multi-Agent Systems 6
MASS: Mathematical Data Selection via Skill Graphs for Pretraining Large Language Models 5
MATH-Perturb: Benchmarking LLMs’ Math Reasoning Abilities against Hard Perturbations 3
MATS: An Audio Language Model under Text-only Supervision 5
MCU: An Evaluation Framework for Open-Ended Game Agents 4
MDDM: Practical Message-Driven Generative Image Steganography Based on Diffusion Models 4
MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents 4
MENTOR: Mixture-of-Experts Network with Task-Oriented Perturbation for Visual Reinforcement Learning 4
MERGE$^3$: Efficient Evolutionary Merging on Consumer-grade GPUs 6
MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training 6
MF-LAL: Drug Compound Generation Using Multi-Fidelity Latent Space Active Learning 5
MGD$^3$ : Mode-Guided Dataset Distillation using Diffusion Models 5
MIB: A Mechanistic Interpretability Benchmark 5
MIPT: Multilevel Informed Prompt Tuning for Robust Molecular Property Prediction 5
MIRROR: Make Your Object-Level Multi-View Generation More Consistent with Training-Free Rectification 4
MITIGATING OVER-EXPLORATION IN LATENT SPACE OPTIMIZATION USING LES 4
ML$^2$-GCL: Manifold Learning Inspired Lightweight Graph Contrastive Learning 7
MM-RLHF: The Next Step Forward in Multimodal LLM Alignment 3
MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency 2
MMInference: Accelerating Pre-filling for Long-Context Visual Language Models via Modality-Aware Permutation Sparse Attention 5
MMedPO: Aligning Medical Vision-Language Models with Clinical-Aware Multimodal Preference Optimization 7
MODA: MOdular Duplex Attention for Multimodal Perception, Cognition, and Emotion Understanding 3
MODULI: Unlocking Preference Generalization via Diffusion Models for Offline Multi-Objective Reinforcement Learning 5
MOGIC: Metadata-infused Oracle Guidance for Improved Extreme Classification 5
MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking 4
MP-Nav: Enhancing Data Poisoning Attacks against Multimodal Learning 4
MPO: An Efficient Post-Processing Framework for Mixing Diverse Preference Alignment 4
MTL-UE: Learning to Learn Nothing for Multi-Task Learning 5
MTSTRec: Multimodal Time-Aligned Shared Token Recommender 4
MUDDFormer: Breaking Residual Bottlenecks in Transformers via Multiway Dynamic Dense Connections 7
MVA: Linear Attention with High-order Query-Keys Integration and Multi-level Vocabulary Decomposition 2
Machine Learning meets Algebraic Combinatorics: A Suite of Datasets Capturing Research-level Conjecturing Ability in Pure Mathematics 6
Machines and Mathematical Mutations: Using GNNs to Characterize Quiver Mutation Classes 4
Mahalanobis++: Improving OOD Detection via Feature Normalization 4
Maintaining Proportional Committees with Dynamic Candidate Sets 1
Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment 6
Making Hard Problems Easier with Custom Data Distributions and Loss Regularization: A Case Study in Modular Arithmetic 4
MapEval: A Map-Based Evaluation of Geo-Spatial Reasoning in Foundation Models 4
Mask-Enhanced Autoregressive Prediction: Pay Less Attention to Learn More 3
MaskTwins: Dual-form Complementary Masking for Domain-Adaptive Image Segmentation 6
Masked Autoencoders Are Effective Tokenizers for Diffusion Models 5
Masked Generative Nested Transformers with Decode Time Scaling 4
Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding 3
Mastering Board Games by External and Internal Planning with Language Models 3
Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision Transformer 4
Mastering Multiple-Expert Routing: Realizable $H$-Consistency and Strong Guarantees for Learning to Defer 2
MathConstruct: Challenging LLM Reasoning with Constructive Proofs 5
Matrix Completion with Incomplete Side Information via Orthogonal Complement Projection 3
Matryoshka Quantization 3
Maximal Update Parametrization and Zero-Shot Hyperparameter Transfer for Fourier Neural Operators 5
Maximizing Intermediate Checkpoint Value in LLM Pretraining with Bayesian Optimization 3
Maximum Coverage in Turnstile Streams with Applications to Fingerprinting Measures 5
Maximum Entropy Reinforcement Learning with Diffusion Policy 5
Maximum Total Correlation Reinforcement Learning 5
Measuring Diversity in Synthetic Datasets 5
Measuring Diversity: Axioms and Challenges 0
Measuring In-Context Computation Complexity via Hidden State Prediction 5
Measuring Representational Shifts in Continual Learning: A Linear Transformation Perspective 2
Measuring Variable Importance in Heterogeneous Treatment Effects with Confidence 4
Mechanisms of Projective Composition of Diffusion Models 3
Mechanistic PDE Networks for Discovery of Governing Equations 2
Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization 3
MedRAX: Medical Reasoning Agent for Chest X-ray 5
MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding 4
MemFreezing: A Novel Adversarial Attack on Temporal Graph Neural Networks under Limited Future Knowledge 6
Memorization Sinks: Isolating Memorization during LLM Training 3
Memory Layers at Scale 4
Merge-Friendly Post-Training Quantization for Multi-Target Domain Adaptation 2
Meta Optimality for Demographic Parity Constrained Regression via Post-Processing 1
Meta-Black-Box-Optimization through Offline Q-function Learning 5
Meta-Reinforcement Learning with Adaptation from Human Feedback via Preference-Order-Preserving Task Embedding 5
MetaAgent: Automatically Constructing Multi-Agent Systems Based on Finite State Machines 5
MetaOptimize: A Framework for Optimizing Step Sizes and Other Meta-parameters 6
Metadata Conditioning Accelerates Language Model Pre-training 5
Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation 1
MetricEmbedding: Accelerate Metric Nearness by Tropical Inner Product 5
MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance 5
Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse 3
Mind the Gap: A Practical Attack on GGUF Quantization 5
Mind the Gap: a Spectral Analysis of Rank Collapse and Signal Propagation in Attention Layers 2
MindAligner: Explicit Brain Functional Alignment for Cross-Subject Visual Decoding from Limited fMRI Data 5
MindCustomer: Multi-Context Image Generation Blended with Brain Signal 4
MindLLM: A Subject-Agnostic and Versatile Model for fMRI-to-text Decoding 5
Minerva: A Programmable Memory Test Benchmark for Language Models 4
Minimalist Concept Erasure in Generative Models 4
Minimax Optimal Regret Bound for Reinforcement Learning with Trajectory Feedback 1
Minimum Width for Universal Approximation using Squashable Activation Functions 0
MiraGe: Editable 2D Images using Gaussian Splatting 4
Mirror, Mirror of the Flow: How Does Regularization Shape Implicit Bias? 3
MissScore: High-Order Score Estimation in the Presence of Missing Data 5
Mitigating Heterogeneous Token Overfitting in LLM Knowledge Editing 3
Mitigating Local Cohesion and Global Sparseness in Graph Contrastive Learning with Fuzzy Boundaries 3
Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidance 6
Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification 4
Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn 5
MixBridge: Heterogeneous Image-to-Image Backdoor Attack through Mixture of Schrödinger Bridges 5
MixMin: Finding Data Mixtures via Convex Minimization 5
Mixed-curvature decision trees and random forests 5
Mixture of Experts Made Intrinsically Interpretable 4
Mixture of Experts Provably Detect and Learn the Latent Cluster Structure in Gradient-Based Learning 2
Mixture of Hidden-Dimensions: Not All Hidden-States’ Dimensions are Needed in Transformer 4
Mixture of Lookup Experts 5
MoE-SVD: Structured Mixture-of-Experts LLMs Compression via Singular Value Decomposition 5
MoEQuant: Enhancing Quantization for Mixture-of-Experts Large Language Models via Expert-Balanced Sampling and Affinity Guidance 6
MoH: Multi-Head Attention as Mixture-of-Head Attention 4
MoHAVE: Mixture of Hierarchical Audio-Visual Experts for Robust Speech Recognition 3
MoMa: Modulating Mamba for Adapting Image Foundation Models to Video Recognition 4
MoRAgent: Parameter Efficient Agent Tuning with Mixture-of-Roles 5
Modalities Contribute Unequally: Enhancing Medical Multi-modal Learning through Adaptive Modality Token Re-balancing 5
Model Immunization from a Condition Number Perspective 4
Model Steering: Learning with a Reference Model Improves Generalization Bounds and Scaling Laws 5
Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence 6
Model Uncertainty Quantification by Conformal Prediction in Continual Learning 3
Model-Based Exploration in Monitored Markov Decision Processes 4
Modeling All-Atom Glycan Structures via Hierarchical Message Passing and Multi-Scale Pre-training 5
Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent 7
Models of Heavy-Tailed Mechanistic Universality 3
Modified K-means Algorithm with Local Optimality Guarantees 4
Modular Duality in Deep Learning 4
Modularized Self-Reflected Video Reasoner for Multimodal LLM with Application to Video Question Answering 5
Modulated Diffusion: Accelerating Generative Modeling with Modulated Quantization 3
Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts 4
Momentum-Driven Adaptivity: Towards Tuning-Free Asynchronous Federated Learning 3
Monte Carlo Tree Diffusion for System 2 Planning 3
Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Design 7
Monte-Carlo Tree Search with Uncertainty Propagation via Optimal Transport 3
More Than Meets the Eye: Enhancing Multi-Object Tracking Even with Prolonged Occlusions 5
Morse: Dual-Sampling for Lossless Acceleration of Diffusion Models 6
MuLan: Adapting Multilingual Diffusion Models for Hundreds of Languages with Negligible Cost 4
Multi-Armed Bandits with Interference: Bridging Causal Inference and Adversarial Bandits 2
Multi-Domain Graph Foundation Models: Robust Knowledge Transfer via Topology Alignment 6
Multi-Marginal Stochastic Flow Matching for High-Dimensional Snapshot Data at Irregular Time Points 5
Multi-Modal Object Re-identification via Sparse Mixture-of-Experts 4
Multi-Objective Causal Bayesian Optimization 5
Multi-Session Budget Optimization for Forward Auction-based Federated Learning 4
Multi-Stage Manipulation with Demonstration-Augmented Reward, Policy, and World Model Learning 5
Multi-Timescale Dynamics Model Bayesian Optimization for Plasma Stabilization in Tokamaks 2
Multi-Turn Code Generation Through Single-Step Rewards 6
Multi-View Graph Clustering via Node-Guided Contrastive Encoding 3
Multi-agent Architecture Search via Agentic Supernet 6
Multi-band Frequency Reconstruction for Neural Psychoacoustic Coding 5
Multi-objective Linear Reinforcement Learning with Lexicographic Rewards 1
MultiPDENet: PDE-embedded Learning with Multi-time-stepping for Accelerated Flow Simulation 4
Multiaccuracy and Multicalibration via Proxy Groups 4
Multidimensional Adaptive Coefficient for Inference Trajectory Optimization in Flow and Diffusion 5
Multilayer Matrix Factorization via Dimension-Reducing Diffusion Variational Inference 2
Multimodal Medical Code Tokenizer 6
Multinoulli Extension: A Lossless Yet Effective Probabilistic Framework for Subset Selection over Partition Constraints 6
Multiobjective distribution matching 3
Multiple-policy Evaluation via Density Estimation 1
Multivariate Conformal Selection 5
MuseControlLite: Multifunctional Music Generation with Lightweight Conditioners 5
Mutual Learning for SAM Adaptation: A Dual Collaborative Network Framework for Source-Free Domain Transfer 4
MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design 4
N2GON: Neural Networks for Graph-of-Net with Position Awareness 5
NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations 6
NEAR: Neural Electromagnetic Array Response 3
NETS: A Non-equilibrium Transport Sampler 3
NExtLong: Toward Effective Long-Context Training without Long Documents 5
NICE Data Selection for Instruction Tuning in LLMs with Non-differentiable Evaluation Metric 5
NMA-tune: Generating Highly Designable and Dynamics Aware Protein Backbones 6
NTK-DFL: Enhancing Decentralized Federated Learning in Heterogeneous Settings via Neural Tangent Kernel 5
NTPP: Generative Speech Language Modeling for Dual-Channel Spoken Dialogue via Next-Token-Pair Prediction 5
Natural Perturbations for Black-box Training of Neural Networks by Zeroth-Order Optimization 5
Navigating Conflicting Views: Harnessing Trust for Learning 7
Navigating Semantic Drift in Task-Agnostic Class-Incremental Learning 5
Navigating the Social Welfare Frontier: Portfolios for Multi-objective Reinforcement Learning 3
Near Optimal Best Arm Identification for Clustered Bandits 3
Near Optimal Non-asymptotic Sample Complexity of 1-Identification 2
Near-Optimal Consistency-Robustness Trade-Offs for Learning-Augmented Online Knapsack Problems 4
Near-Optimal Decision Trees in a SPLIT Second 6
Near-Optimal Sample Complexity for MDPs via Anchoring 1
Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback 1
Near-optimal Sketchy Natural Gradients for Physics-Informed Neural Networks 4
Nearly Optimal Algorithms for Contextual Dueling Bandits from Adversarial Feedback 2
Nearly Optimal Sample Complexity for Learning with Label Proportions 4
NegMerge: Sign-Consensual Weight Merging for Machine Unlearning 4
Neighbour-Driven Gaussian Process Variational Autoencoders for Scalable Structured Latent Modelling 5
Nemotron-CORTEXA: Enhancing LLM Agents for Software Engineering Tasks via Improved Localization and Solution Diversity 4
NestQuant: nested lattice quantization for matrix products and LLMs 5
Nested Expectations with Kernel Quadrature 2
Nesterov Method for Asynchronous Pipeline Parallel Optimization 6
Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning 3
Neural Collapse Beyond the Unconstrained Features Model: Landscape, Dynamics, and Generalization in the Mean-Field Regime 4
Neural Discovery in Mathematics: Do Machines Dream of Colored Planes? 4
Neural Encoding and Decoding at Scale 5
Neural Event-Triggered Control with Optimal Scheduling 4
Neural Genetic Search in Discrete Spaces 5
Neural Graph Matching Improves Retrieval Augmented Generation in Molecular Machine Learning 5
Neural Guided Diffusion Bridges 3
Neural Interpretable PDEs: Harmonizing Fourier Insights with Attention for Scalable and Interpretable Physics Discovery 6
Neural Representational Consistency Emerges from Probabilistic Neural-Behavioral Representation Alignment 5
Neural Solver Selection for Combinatorial Optimization 4
NeuralCohort: Cohort-aware Neural Representation Learning for Healthcare Analytics 5
NeuroTree: Hierarchical Functional Brain Pathway Decoding for Mental Health Disorders 7
NeuronTune: Towards Self-Guided Spurious Bias Mitigation 4
Neurosymbolic World Models for Sequential Decision Making 3
Neutral residues: revisiting adapters for model extension 2
New Bounds for Sparse Variational Gaussian Processes 4
NextCoder: Robust Adaptation of Code LMs to Diverse Code Edits 5
No Free Lunch from Random Feature Ensembles: Scaling Laws and Near-Optimality Conditions 3
No Metric to Rule Them All: Toward Principled Evaluations of Graph-Learning Datasets 5
No Soundness in the Real World: On the Challenges of the Verification of Deployed Neural Networks 6
No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces 5
No-Regret is not enough! Bandits with General Constraints through Adaptive Regret Minimization 1
NoLiMa: Long-Context Evaluation Beyond Literal Matching 3
Noise Conditional Variational Score Distillation 6
Noise-Guided Predicate Representation Extraction and Diffusion-Enhanced Discretization for Scene Graph Generation 6
Noisy SIGNSGD Is More Differentially Private Than You (Might) Think 5
Non-Asymptotic Length Generalization 1
Non-Asymptotic and Non-Lipschitzian Bounds on Optimal Values in Stochastic Optimization Under Heavy Tails 2
Non-Stationary Predictions May Be More Informative: Exploring Pseudo-Labels with a Two-Phase Pattern of Training Dynamics 5
Non-asymptotic Error Bounds in $\mathcalW_2$-Distance with Sqrt(d) Dimension Dependence and First Order Convergence for Langevin Monte Carlo beyond Log-Concavity 1
Non-stationary Diffusion For Probabilistic Time Series Forecasting 5
Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability 1
Nonconvex Theory of $M$-estimators with Decomposable Regularizers 0
Nonlinear transformers can perform inference-time feature learning 2
Nonlinearly Preconditioned Gradient Methods under Generalized Smoothness 3
Nonparametric Identification of Latent Concepts 3
Nonparametric Modern Hopfield Models 6
Nonparametric Teaching for Graph Property Learners 5
Normalizing Flows are Capable Generative Models 5
Not All Tokens Matter All The Time: Dynamic Token Aggregation Towards Efficient Detection Transformers 4
Not All Wrong is Bad: Using Adversarial Examples for Unlearning 6
Not all solutions are created equal: An analytical dissociation of functional and representational similarity in deep linear neural networks 3
Novelty Detection in Reinforcement Learning with World Models 3
O-MAPL: Offline Multi-agent Preference Learning 4
OOD-Chameleon: Is Algorithm Selection for OOD Generalization Learnable? 4
OR-Bench: An Over-Refusal Benchmark for Large Language Models 3
OTTER: A Vision-Language-Action Model with Text-Aware Visual Feature Extraction 5
OV-MER: Towards Open-Vocabulary Multimodal Emotion Recognition 3
OW-VAP: Visual Attribute Parsing for Open World Object Detection 5
OWLS: Scaling Laws for Multilingual Speech Recognition and Translation Models 6
Objective drives the consistency of representational similarity across datasets 4
Observation Interference in Partially Observable Assistance Games 1
Occult: Optimizing Collaborative Communications across Experts for Accelerated Parallel MoE Training and Inference 5
Of Mice and Machines: A Comparison of Learning Between Real World Mice and RL Agents 2
Off-Policy Actor-Critic for Adversarial Observation Robustness: Virtual Alternative Training via Symmetric Policy Evaluation 5
Off-Policy Evaluation under Nonignorable Missing Data 5
Offline Learning for Combinatorial Multi-armed Bandits 4
Offline Model-based Optimization for Real-World Molecular Discovery 5
Offline Opponent Modeling with Truncated Q-driven Instant Policy Refinement 2
Offline-to-Online Reinforcement Learning with Classifier-Free Diffusion Generation 4
Olica: Efficient Structured Pruning of Large Language Models without Retraining 7
OmiAD: One-Step Adaptive Masked Diffusion Model for Multi-class Anomaly Detection via Adversarial Distillation 6
Omni-Angle Assault: An Invisible and Powerful Physical Adversarial Attack on Face Recognition 3
OmniArch: Building Foundation Model for Scientific Computing 5
OmniAudio: Generating Spatial Audio from 360-Degree Video 4
OmniBal: Towards Fast Instruction-Tuning for Vision-Language Models via Omniverse Computation Balance 4
On Differential Privacy for Adaptively Solving Search Problems via Sketching 1
On Efficient Estimation of Distributional Treatment Effects under Covariate-Adaptive Randomization 5
On Exact Bit-level Reversible Transformers Without Changing Architecture 4
On Explaining Equivariant Graph Networks via Improved Relevance Propagation 4
On Expressive Power of Looped Transformers: Theoretical Analysis and Enhancement via Timestep Encoding 5
On Fine-Grained Distinct Element Estimation 6
On Learning Parallel Pancakes with Mostly Uniform Weights 1
On Linear Convergence in Smooth Convex-Concave Bilinearly-Coupled Saddle-Point Optimization: Lower Bounds and Optimal Algorithms 1
On Measuring Long-Range Interactions in Graph Neural Networks 4
On Mitigating Affinity Bias through Bandits with Evolving Biased Feedback 3
On Path to Multimodal Generalist: General-Level and General-Bench 3
On Teacher Hacking in Language Model Distillation 3
On Temperature Scaling and Conformal Prediction of Deep Classifiers 5
On The Concurrence of Layer-wise Preconditioning Methods and Provable Feature Learning 1
On Understanding Attention-Based In-Context Learning for Categorical Data 5
On Volume Minimization in Conformal Regression 5
On Zero-Initialized Attention: Optimal Prompt and Gating Factor Estimation 5
On the Adversarial Robustness of Multi-Kernel Clustering 3
On the Alignment between Fairness and Accuracy: from the Perspective of Adversarial Robustness 4
On the Benefits of Active Data Collection in Operator Learning 3
On the Clean Generalization and Robust Overfitting in Adversarial Training from Two Theoretical Views: Representation Complexity and Training Dynamics 3
On the Convergence of Continuous Single-timescale Actor-critic 1
On the Diversity of Adversarial Ensemble Learning 5
On the Duality between Gradient Transformations and Adapters 2
On the Dynamic Regret of Following the Regularized Leader: Optimism with History Pruning 3
On the Emergence of Position Bias in Transformers 3
On the Generalization Ability of Next-Token-Prediction Pretraining 5
On the Guidance of Flow Matching 6
On the Impact of Performative Risk Minimization for Binary Random Variables 3
On the Importance of Embedding Norms in Self-Supervised Learning 5
On the Importance of Gaussianizing Representations 6
On the Interplay between Graph Structure and Learning Algorithms in Graph Neural Networks 2
On the Learnability of Distribution Classes with Adaptive Adversaries 0
On the Local Complexity of Linear Regions in Deep ReLU Networks 2
On the Out-of-Distribution Generalization of Self-Supervised Learning 6
On the Power of Context-Enhanced Learning in LLMs 2
On the Power of Learning-Augmented Search Trees 1
On the Private Estimation of Smooth Transport Maps 2
On the Provable Separation of Scales in Maximal Update Parameterization 2
On the Query Complexity of Verifier-Assisted Language Generation 4
On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agents 3
On the Robustness of Reward Models for Language Model Alignment 5
On the Role of Label Noise in the Feature Learning Process 3
On the Similarities of Embeddings in Contrastive Learning 5
On the Statistical Mechanisms of Distributional Compositional Generalization 2
On the Tension between Byzantine Robustness and No-Attack Accuracy in Distributed Learning 5
On the Training Convergence of Transformers for In-Context Classification of Gaussian Mixtures 2
On the Vulnerability of Applying Retrieval-Augmented Generation within Knowledge-Intensive Application Domains 3
On-Device Collaborative Language Modeling via a Mixture of Generalists and Specialists 6
On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention for Long-Context LLM Serving 4
One Arrow, Two Hawks: Sharpness-aware Minimization for Federated Learning via Global Model Trajectory 7
One Diffusion Step to Real-World Super-Resolution via Flow Trajectory Distillation 4
One Example Shown, Many Concepts Known! Counterexample-Driven Conceptual Reasoning in Mathematical LLMs 4
One Image is Worth a Thousand Words: A Usability Preservable Text-Image Collaborative Erasing Framework 4
One Leaf Reveals the Season: Occlusion-Based Contrastive Learning with Semantic-Aware Views for Efficient Visual Representation 6
One Stone, Two Birds: Enhancing Adversarial Defense Through the Lens of Distributional Discrepancy 6
One Wave To Explain Them All: A Unifying Perspective On Feature Attribution 4
One-Pass Feature Evolvable Learning with Theoretical Guarantees 5
One-Shot Heterogeneous Federated Learning with Local Model-Guided Diffusion Models 5
One-Step Diffusion Policy: Fast Visuomotor Policies via Diffusion Distillation 4
One-Step Generalization Ratio Guided Optimization for Domain Generalization 6
One-dimensional Path Convolution 4
OneForecast: A Universal Framework for Global and Regional Weather Forecasting 6
Online Clustering of Dueling Bandits 3
Online Conformal Prediction via Online Optimization 5
Online Curvature-Aware Replay: Leveraging $\mathbf2^nd$ Order Information for Online Continual Learning 6
Online Detection of LLM-Generated Texts via Sequential Hypothesis Testing by Betting 4
Online Differentially Private Conformal Prediction for Uncertainty Quantification 3
Online Episodic Convex Reinforcement Learning 4
Online Laplacian-Based Representation Learning in Reinforcement Learning 3
Online Learning in Risk Sensitive constrained MDP 3
Online Learning in the Random-Order Model 1
Online Learning with Unknown Constraints 1
Online Linear Classification with Massart Noise 1
Online Pre-Training for Offline-to-Online Reinforcement Learning 5
Online Robust Reinforcement Learning Through Monte-Carlo Planning 4
Online Sparsification of Bipartite-Like Clusters in Graphs 4
Open Materials Generation with Stochastic Interpolants 6
Open Your Eyes: Vision Enhances Message Passing Neural Networks in Link Prediction 6
Open-Det: An Efficient Learning Framework for Open-Ended Detection 5
OpenworldAUC: Towards Unified Evaluation and Optimization for Open-world Prompt Tuning 5
OptMATH: A Scalable Bidirectional Data Synthesis Framework for Optimization Modeling 5
Optimal Algorithm for Max-Min Fair Bandit 2
Optimal Auction Design in the Joint Advertising 3
Optimal Decision Tree Pruning Revisited: Algorithms and Complexity 5
Optimal Fair Learning Robust to Adversarial Distribution Shift 0
Optimal Information Retention for Time-Series Explanations 5
Optimal Sensor Scheduling and Selection for Continuous-Discrete Kalman Filtering with Auxiliary Dynamics 3
Optimal Survey Design for Private Mean Estimation 3
Optimal Task Order for Continual Learning of Multiple Tasks 5
Optimal Transfer Learning for Missing Not-at-Random Matrix Completion 2
Optimal Transport Barycenter via Nonconvex-Concave Minimax Optimization 4
Optimal and Practical Batched Linear Bandit Algorithm 2
Optimal transport-based conformal prediction 4
Optimistic Algorithms for Adaptive Estimation of the Average Treatment Effect 4
Optimization Proxies using Limited Labeled Data and Training Time – A Semi-Supervised Bayesian Neural Network Approach 5
Optimization for Neural Operators can Benefit from Width 4
Optimization over Sparse Support-Preserving Sets: Two-Step Projection with Global Optimality Guarantees 6
Optimizing Adaptive Attacks against Watermarks for Language Models 6
Optimizing Language Models for Inference Time Objectives using Reinforcement Learning 4
Optimizing Large Language Model Training Using FP4 Quantization 5
Optimizing Noise Distributions for Differential Privacy 4
Optimizing Robustness and Accuracy in Mixture of Experts: A Dual-Model Approach 4
Optimizing Social Network Interventions via Hypergradient-Based Recommender System Design 6
Optimizing Temperature for Language Models with Multi-Sample Inference 6
Optimizing Test-Time Compute via Meta Reinforcement Finetuning 3
Oracle-MoE: Locality-preserving Routing in the Oracle Space for Memory-constrained Large Language Model Inference 3
OrcaLoca: An LLM Agent Framework for Software Issue Localization 5
Organize the Web: Constructing Domains Enhances Pre-Training Data Curation 7
Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models 4
Origin Identification for Text-Guided Image-to-Image Diffusion Models 5
OrthoRank: Token Selection via Sink Token Orthogonality for Efficient LLM inference 4
Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection 5
Orthus: Autoregressive Interleaved Image-Text Generation with Modality-Specific Heads 5
Oscillation-Reduced MXFP4 Training for Vision Transformers 5
Otter: Generating Tests from Issues to Validate SWE Patches 3
Outlier Gradient Analysis: Efficiently Identifying Detrimental Training Samples for Deep Learning Models 7
Outlier-Aware Post-Training Quantization for Discrete Graph Diffusion Models 4
Outsourced Diffusion Sampling: Efficient Posterior Inference in Latent Spaces of Generative Models 6
Over-Tokenized Transformer: Vocabulary is Generally Worth Scaling 5
Overcoming Multi-step Complexity in Multimodal Theory-of-Mind Reasoning: A Scalable Bayesian Planner 5
Overcoming Non-monotonicity in Transducer-based Streaming Generation 6
Overcoming Spurious Solutions in Semi-Dual Neural Optimal Transport: A Smoothing Approach for Learning the Optimal Transport Plan 4
Overcoming Vocabulary Mismatch: Vocabulary-agnostic Teacher Guided Language Modeling 4
Overcoming the Curse of Dimensionality in Reinforcement Learning Through Approximate Factorization 3
Overestimation in LLM Evaluation: A Controlled Large-Scale Study on Data Contamination’s Impact on Machine Translation 3
Overtrained Language Models Are Harder to Fine-Tune 4
P(all-atom) Is Unlocking New Path For Protein Design 5
PAC Learning with Improvements 6
PAC-Bayes Analysis for Recalibration in Classification 5
PAK-UCB Contextual Bandit: An Online Learning Approach to Prompt-Aware Selection of Generative Models and LLMs 4
PANDAS: Improving Many-shot Jailbreaking via Positive Affirmation, Negative Demonstration, and Adaptive Sampling 3
PARM: Multi-Objective Test-Time Alignment via Preference-Aware Autoregressive Reward Model 6
PARQ: Piecewise-Affine Regularized Quantization 4
PASS: Private Attributes Protection with Stochastic Data Substitution 4
PCEvolve: Private Contrastive Evolution for Synthetic Dataset Generation via Few-Shot Private Data and Generative APIs 6
PDE-Controller: LLMs for Autoformalization and Reasoning of PDEs 5
PDE-Transformer: Efficient and Versatile Transformers for Physics Simulations 6
PDUDT: Provable Decentralized Unlearning under Dynamic Topologies 6
PEAKS: Selecting Key Training Examples Incrementally via Prediction Error Anchored by Kernel Similarity 5
PEINR: A Physics-enhanced Implicit Neural Representation for High-Fidelity Flow Field Reconstruction 6
PENCIL: Long Thoughts with Short Memory 3
PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting for Novel View Synthesis 4
PIGDreamer: Privileged Information Guided World Models for Safe Partially Observable Reinforcement Learning 4
PILAF: Optimal Human Preference Sampling for Reward Modeling 4
PINNsAgent: Automated PDE Surrogation with Large Language Models 4
PIPA: Preference Alignment as Prior-Informed Statistical Estimation 4
PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by Watching Stuff Drop 5
POQD: Performance-Oriented Query Decomposer for Multi-vector retrieval 4
POROver: Improving Safety and Reducing Overrefusal in Large Language Models with Overgeneration and Preference Optimization 6
PPDiff: Diffusing in Hybrid Sequence-Structure Space for Protein-Protein Complex Design 4
PRIME: Deep Imbalanced Regression with Proxies 4
PROTOCOL: Partial Optimal Transport-enhanced Contrastive Learning for Imbalanced Multi-view Clustering 4
PROXSPARSE: REGULARIZED LEARNING OF SEMI-STRUCTURED SPARSITY MASKS FOR PRETRAINED LLMS 5
PTTA: Purifying Malicious Samples for Test-Time Model Adaptation 7
Pairwise Maximum Likelihood For Multi-Class Logistic Regression Model With Multiple Rare Classes 4
PaperBench: Evaluating AI’s Ability to Replicate AI Research 4
Parallel Simulation for Log-concave Sampling and Score-based Diffusion Models 1
ParallelComp: Parallel Long-Context Compressor for Length Extrapolation 5
Parameter-Efficient Fine-Tuning of State Space Models 6
Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models 2
Parametric Scaling Law of Tuning Bias in Conformal Prediction 4
Pareto Merging: Multi-Objective Optimization for Preference-Aware Model Merging 5
Pareto-Optimal Fronts for Benchmarking Symbolic Regression Algorithms 4
Pareto-Optimality, Smoothness, and Stochasticity in Learning-Augmented One-Max-Search 1
Pareto-frontier Entropy Search with Variational Lower Bound Maximization 4
Parrot: Multilingual Visual Instruction Tuning 6
Partially Observable Reinforcement Learning with Memory Traces 3
Partition First, Embed Later: Laplacian-Based Feature Partitioning for Refined Embedding and Visualization of High-Dimensional Data 5
Patch-wise Structural Loss for Time Series Forecasting 5
PatchPilot: A Cost-Efficient Software Engineering Agent with Early Attempts on Formal Verification 4
Penalizing Infeasible Actions and Reward Scaling in Reinforcement Learning with Offline Data 6
PepTune: De Novo Generation of Therapeutic Peptides with Multi-Objective-Guided Discrete Diffusion 7
Perception in Reflection 5
Perceptual-GS: Scene-adaptive Perceptual Densification for Gaussian Splatting 4
Perceptually Constrained Precipitation Nowcasting Model 4
Peri-LN: Revisiting Normalization Layer in the Transformer Architecture 2
Peripheral Memory for LLMs: Integration of Sequential Memory Banks with Adaptive Querying 2
Permutation Equivariant Neural Networks for Symmetric Tensors 4
Permutation-Free High-Order Interaction Tests 6
Permutation-based Rank Test in the Presence of Discretization and Application in Causal Discovery with Mixed Data 3
Persistent Topological Features in Large Language Models 6
PertEval-scFM: Benchmarking Single-Cell Foundation Models for Perturbation Effect Prediction 6
Pessimism Principle Can Be Effective: Towards a Framework for Zero-Shot Transfer Reinforcement Learning 5
Pfeife: Automatic Pipeline Parallelism for PyTorch 6
PhantomWiki: On-Demand Datasets for Reasoning and Retrieval Evaluation 5
Phase and Amplitude-aware Prompting for Enhancing Adversarial Robustness 5
Phase transitions for the existence of unregularized M-estimators in single index models 1
Physics Aware Neural Networks for Unsupervised Binding Energy Prediction 6
Physics-Informed DeepONets for drift-diffusion on metric graphs: simulation and parameter identification 4
Physics-Informed Generative Modeling of Wireless Channels 7
Physics-Informed Weakly Supervised Learning For Interatomic Potentials 5
Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models 6
PiD: Generalized AI-Generated Images Detection with Pixelwise Decomposition Residuals 3
PieClam: A Universal Graph Autoencoder Based on Overlapping Inclusive and Exclusive Communities 5
Piloting Structure-Based Drug Design via Modality-Specific Optimal Schedule 6
PipeOffload: Improving Scalability of Pipeline Parallelism with Memory Optimization 3
Pivoting Factorization: A Compact Meta Low-Rank Representation of Sparsity for Efficient Inference in Large Language Models 6
Pixel-level Certified Explanations via Randomized Smoothing 4
Pixel2Feature Attack (P2FA): Rethinking the Perturbed Space to Enhance Adversarial Transferability 4
Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks 5
Plausible Token Amplification for Improving Accuracy of Differentially Private In-Context Learning Based on Implicit Bayesian Inference 5
PlaySlot: Learning Inverse Latent Dynamics for Controllable Object-Centric Video Prediction and Planning 5
Playmate: Flexible Control of Portrait Animation via 3D-Implicit Space Guided Diffusion 5
Point Cloud Dataset Distillation 4
Point-Level Topological Representation Learning on Point Clouds 5
Pointwise Information Measures as Confidence Estimators in Deep Neural Networks: A Comparative Study 4
PoisonBench: Assessing Language Model Vulnerability to Poisoned Preference Data 6
PoisonedEye: Knowledge Poisoning Attack on Retrieval-Augmented Generation based Large Vision-Language Models 5
PokéChamp: an Expert-level Minimax Language Agent 4
Policy Design for Two-sided Platforms with Participation Dynamics 3
Policy Filtration for RLHF to Mitigate Noise in Reward Models 5
Policy Gradient with Tree Expansion 6
Policy Guided Tree Search for Enhanced LLM Reasoning 4
Policy Optimization for CMDPs with Bandit Feedback: Learning Stochastic and Adversarial Constraints 1
Policy Regularization on Globally Accessible States in Cross-Dynamics Reinforcement Learning 4
Policy-Regret Minimization in Markov Games with Function Approximation 1
Policy-labeled Preference Learning: Is Preference Enough for RLHF? 3
Poly2Vec: Polymorphic Fourier-Based Encoding of Geospatial Objects for GeoAI Applications 6
PolyConf: Unlocking Polymer Conformation Generation through Hierarchical Generative Models 4
Polynomial Time Learning Augmented Algorithms for NP-hard Permutation Problems 0
Polynomial-Delay MAG Listing with Novel Locally Complete Orientation Rules 2
Polynomial-Time Approximability of Constrained Reinforcement Learning 1
Portable Reward Tuning: Towards Reusable Fine-Tuning across Different Pretrained Models 5
Position: A Theory of Deep Learning Must Include Compositional Sparsity 0
Position: AI Agents Need Authenticated Delegation 0
Position: AI Competitions Provide the Gold Standard for Empirical Rigor in GenAI Evaluation 0
Position: AI Evaluation Should Learn from How We Test Humans 3
Position: AI Safety Must Embrace an Antifragile Perspective 0
Position: AI Safety should prioritize the Future of Work 0
Position: AI Scaling: From Up to Down and Out 0
Position: AI Should Not Be An Imitation Game: Centaur Evaluations 0
Position: AI’s growing due process problem 0
Position: Algebra Unveils Deep Learning - An Invitation to Neuroalgebraic Geometry 0
Position: All Current Generative Fidelity and Diversity Metrics are Flawed 3
Position: An Empirically Grounded Identifiability Theory Will Accelerate Self Supervised Learning Research 0
Position: Beyond Assistance – Reimagining LLMs as Ethical and Adaptive Co-Creators in Mental Health Care 0
Position: Build Agent Advocates, Not Platform Agents 0
Position: Causal Machine Learning Requires Rigorous Synthetic Experiments for Broader Adoption 3
Position: Certified Robustness Does Not (Yet) Imply Model Security 0
Position: Challenges and Future Directions of Data-Centric AI Alignment 1
Position: Constants are Critical in Regret Bounds for Reinforcement Learning 4
Position: Contextual Integrity is Inadequately Applied to Language Models 0
Position: Current Model Licensing Practices are Dragging Us into a Quagmire of Legal Noncompliance 1
Position: Deep Learning is Not So Mysterious or Different 3
Position: Democratic AI is Possible. The Democracy Levels Framework Shows How It Might Work. 0
Position: Don’t Use the CLT in LLM Evals With Fewer Than a Few Hundred Datapoints 3
Position: Editing Large Language Models Poses Serious Safety Risks 0
Position: Enough of Scaling LLMs! Lets Focus on Downscaling 1
Position: Evaluating Generative AI Systems Is a Social Science Measurement Challenge 0
Position: Explainable AI Cannot Advance Without Better User Studies 3
Position: Formal Mathematical Reasoning—A New Frontier in AI 1
Position: Future Research and Challenges Remain Towards AI for Software Engineering 1
Position: General Intelligence Requires Reward-based Pretraining 5
Position: Generative AI Regulation Can Learn from Social Media Regulation 0
Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks 5
Position: Graph Matching Systems Deserve Better Benchmarks 4
Position: Human Baselines in Model Evaluations Need Rigor and Transparency (With Recommendations & Reporting Checklist) 2
Position: Humanity Faces Existential Risk from Gradual Disempowerment 0
Position: In-House Evaluation Is Not Enough. Towards Robust Third-Party Evaluation and Flaw Disclosure for General-Purpose AI 0
Position: It Is Time We Test Neural Computation In Vitro 0
Position: Iterative Online-Offline Joint Optimization is Needed to Manage Complex LLM Copyright Risks 0
Position: LLM Social Simulations Are a Promising Research Method 0
Position: LLMs Need a Bayesian Meta-Reasoning Framework for More Robust and Generalizable Reasoning 2
Position: Language model developers should report train-test overlap 2
Position: Lifetime tuning is incompatible with continual reinforcement learning 2
Position: Machine Learning Models Have a Supply Chain Problem 4
Position: Medical Large Language Model Benchmarks Should Prioritize Construct Validity 2
Position: Not All Explanations for Deep Learning Phenomena Are Equally Valuable 0
Position: Political Neutrality in AI Is Impossible — But Here Is How to Approximate It 4
Position: Principles of Animal Cognition to Improve LLM Evaluations 2
Position: Probabilistic Modelling is Sufficient for Causal Inference 0
Position: Rethinking Explainable Machine Learning as Applied Statistics 0
Position: Rethinking LLM Bias Probing Using Lessons from the Social Sciences 1
Position: Retrieval-augmented systems can be dangerous medical communicators 3
Position: Scaling LLM Agents Requires Asymptotic Analysis with LLM Primitives 1
Position: Societal Impacts Research Requires Benchmarks for Creative Composition Tasks 1
Position: Solve Layerwise Linear Models First to Understand Neural Dynamical Phenomena (Neural Collapse, Emergence, Lazy/Rich Regime, and Grokking) 3
Position: Spectral GNNs Rely Less on Graph Fourier Basis than Conceived 1
Position: Stop treating ‘AGI’ as the north-star goal of AI research 0
Position: Strong Consumer Protection is an Inalienable Defense for AI Safety in the United States 0
Position: Supervised Classifiers Answer the Wrong Questions for OOD Detection 3
Position: The AI Conference Peer Review Crisis Demands Author Feedback and Reviewer Rewards 3
Position: The Artificial Intelligence and Machine Learning Community Should Adopt a More Transparent and Regulated Peer Review Process 1
Position: The Categorization of Race in ML is a Flawed Premise 3
Position: The Future of Bayesian Prediction Is Prior-Fitted 2
Position: The Most Expensive Part of an LLM *should* be its Training Data 1
Position: The Right to AI 0
Position: Theory of Mind Benchmarks are Broken for Large Language Models 3
Position: Truly Self-Improving Agents Require Intrinsic Metacognitive Learning 0
Position: Trustworthy AI Agents Require the Integration of Large Language Models and Formal Methods 2
Position: Uncertainty Quantification Needs Reassessment for Large Language Model Agents 0
Position: We Can’t Understand AI Using our Existing Vocabulary 2
Position: We Need An Algorithmic Understanding of Generative AI 2
Position: We Need Responsible, Application-Driven (RAD) AI Research 0
Position: When Incentives Backfire, Data Stops Being Human 0
Position: You Can’t Manufacture a NeRF 2
Positional Attention: Expressivity and Learnability of Algorithmic Computation 3
Positional Encoding meets Persistent Homology on Graphs 5
Positive-unlabeled AUC Maximization under Covariate Shift 5
Posterior Inference with Diffusion Models for High-dimensional Black-box Optimization 6
Potemkin Understanding in Large Language Models 2
Power Mean Estimation in Stochastic Continuous Monte-Carlo Tree Search 3
Pre-Training Graph Contrastive Masked Autoencoders are Strong Distillers for EEG 5
Pre-training Auto-regressive Robotic Models with 4D Representations 4
Preconditioned Riemannian Gradient Descent Algorithm for Low-Multilinear-Rank Tensor Completion 6
Predicting High-precision Depth on Low-Precision Devices Using 2D Hilbert Curves 5
Predicting mutational effects on protein binding from folding energy 6
Predicting the Susceptibility of Examples to Catastrophic Forgetting 5
Prediction models that learn to avoid missing values 5
Prediction via Shapley Value Regression 6
Prediction-Aware Learning in Multi-Agent Systems 3
Prediction-Powered Adaptive Shrinkage Estimation 6
Prediction-Powered E-Values 4
Predictive Data Selection: The Data That Predicts Is the Data That Teaches 5
Predictive Performance of Deep Quantum Data Re-uploading Models 3
Preference Adaptive and Sequential Text-to-Image Generation 3
Preference Controllable Reinforcement Learning with Advanced Multi-Objective Optimization 5
Preference Learning for AI Alignment: a Causal Perspective 4
Preference Optimization for Combinatorial Optimization Problems 4
Preference learning made easy: Everything should be understood through win rate 2
Preference-CFR: Beyond Nash Equilibrium for Better Game Strategies 4
Premise-Augmented Reasoning Chains Improve Error Identification in Math reasoning with LLMs 5
Preserving AUC Fairness in Learning with Noisy Protected Groups 6
Pretraining Generative Flow Networks with Inexpensive Rewards for Molecular Graph Generation 4
Prices, Bids, Values: One ML-Powered Combinatorial Auction to Rule Them All 7
Primal-Dual Neural Algorithmic Reasoning 7
Primitive Vision: Improving Diagram Understanding in MLLMs 5
Primphormer: Efficient Graph Transformers with Primal Representations 3
Principal-Agent Bandit Games with Self-Interested and Exploratory Learning Agents 1
Principled Algorithms for Optimizing Generalized Metrics in Binary Classification 3
Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples 6
Prior Knowledge Guided Neural Architecture Generation 5
Privacy Amplification Through Synthetic Data: Insights from Linear Regression 1
Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting 5
Privacy Attacks on Image AutoRegressive Models 5
Privacy-Preserving Federated Convex Optimization: Balancing Partial-Participation and Efficiency via Noise Cancellation 3
Privacy-Shielded Image Compression: Defending Against Exploitation from Vision-Language Pretrained Models 5
Private Federated Learning using Preference-Optimized Synthetic Data 6
Private Lossless Multiple Release 2
Private Model Personalization Revisited 4
ProDiff: Prototype-Guided Diffusion for Minimal Information Trajectory Imputation 5
ProSec: Fortifying Code LLMs with Proactive Security Alignment 5
Proactive Agents for Multi-Turn Text-to-Image Generation Under Uncertainty 5
Probabilistic Factorial Experimental Design for Combinatorial Interventions 5
Probabilistic Group Mask Guided Discrete Optimization for Incremental Learning 4
Probabilistic Interactive 3D Segmentation with Hierarchical Neural Processes 4
Probably Approximately Global Robustness Certification 6
Probing Visual Language Priors in VLMs 3
Procurement Auctions via Approximately Optimal Submodular Optimization 3
Product of Experts with LLMs: Boosting Performance on ARC Is a Matter of Perspective 6
Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale 5
Progressive Tempering Sampler with Diffusion 4
Progressively Label Enhancement for Large Language Model Alignment 5
Projection Optimization: A General Framework for Multi-Objective and Multi-Group RLHF 3
Projection Pursuit Density Ratio Estimation 5
Promoting Ensemble Diversity with Interactive Bayesian Distributional Robustness for Fine-tuning Foundation Models 5
Prompt-based Depth Pruning of Large Language Models 5
Prompt-to-Leaderboard: Prompt-Adaptive LLM Evaluations 6
ProofAug: Efficient Neural Theorem Proving via Fine-grained Proof Structure Analysis 7
Propagate and Inject: Revisiting Propagation-Based Feature Imputation for Graphs with Partially Observed Features 6
Propagation of Chaos for Mean-Field Langevin Dynamics and its Application to Model Ensemble 4
Proposer-Agent-Evaluator (PAE): Autonomous Skill Discovery For Foundation Model Internet Agents 4
Protein Structure Tokenization: Benchmarking and New Recipe 6
Proto Successor Measure: Representing the Behavior Space of an RL Agent 4
Protriever: End-to-End Differentiable Protein Homology Search for Fitness Prediction 5
Provable Benefit of Random Permutations over Uniform Sampling in Stochastic Coordinate Descent 2
Provable Benefits of Unsupervised Pre-training and Transfer Learning via Single-Index Models 1
Provable Efficiency of Guidance in Diffusion Models for General Data Distribution 2
Provable In-Context Vector Arithmetic via Retrieving Task Concepts 2
Provable Length Generalization in Sequence Prediction via Spectral Filtering 2
Provable Maximum Entropy Manifold Exploration via Diffusion Models 4
Provable Policy Gradient for Robust Average-Reward MDPs Beyond Rectangularity 6
Provable Zero-Shot Generalization in Offline Reinforcement Learning 1
Provable and Practical Online Learning Rate Adaptation with Hypergradient Descent 4
Provably Cost-Sensitive Adversarial Defense via Randomized Smoothing 6
Provably Efficient Algorithm for Best Scoring Rule Identification in Online Principal-Agent Information Acquisition 1
Provably Efficient Exploration in Inverse Constrained Reinforcement Learning 4
Provably Efficient RL for Linear MDPs under Instantaneous Safety Constraints in Non-Convex Feature Spaces 3
Provably Improving Generalization of Few-shot models with Synthetic Data 5
Provably Near-Optimal Federated Ensemble Distillation with Negligible Overhead 7
Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting 4
Prune ’n Predict: Optimizing LLM Decision-making with Conformal Prediction 3
Pruning for GNNs: Lower Complexity with Comparable Expressiveness 4
Putnam-AXIOM: A Functional & Static Benchmark for Measuring Higher Level Mathematical Reasoning in LLMs 4
Puzzle: Distillation-Based NAS for Inference-Optimized LLMs 4
PyTDC: A multimodal machine learning training, evaluation, and inference platform for biomedical foundation models 3
Q-Supervised Contrastive Representation: A State Decoupling Framework for Safe Offline Reinforcement Learning 4
Q-VDiT: Towards Accurate Quantization and Distillation of Video-Generation Diffusion Transformers 2
QEM-Bench: Benchmarking Learning-based Quantum Error Mitigation and QEMFormer as a Multi-ranged Context Learning Baseline 6
QLASS: Boosting Language Agent Inference via Q-Guided Stepwise Search 6
QMamba: On First Exploration of Vision Mamba for Image Quality Assessment 5
QPRL : Learning Optimal Policies with Quasi-Potential Functions for Asymmetric Traversal 3
QT-DoG: Quantization-Aware Training for Domain Generalization 6
QUTE: Quantifying Uncertainty in TinyML models with Early-exit-assisted ensembles for model-monitoring 4
QoS-Efficient Serving of Multiple Mixture-of-Expert LLMs Using Partial Runtime Reconfiguration 5
QuEST: Stable Training of LLMs with 1-Bit Weights and Activations 5
QuEst: Enhancing Estimates of Quantile-Based Distributional Measures Using Model Predictions 3
QuRe: Query-Relevant Retrieval through Hard Negative Sampling in Composed Image Retrieval 6
Quadratic Upper Bound for Boosting Robustness 4
Quadruple Attention in Many-body Systems for Accurate Molecular Property Predictions 5
Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space Models 5
QuanONet: Quantum Neural Operator with Application to Differential Equation 3
QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache 4
Quantifying Memory Utilization with Effective State-Size 5
Quantifying Prediction Consistency Under Fine-tuning Multiplicity in Tabular LLMs 3
Quantifying Treatment Effects: Estimating Risk Ratios via Observational Studies 2
Quantum Algorithms for Finite-horizon Markov Decision Processes 1
Quantum Optimization via Gradient-Based Hamiltonian Descent 4
Quantum Speedup for Hypergraph Sparsification 1
Quantum Speedups in Regret Analysis of Infinite Horizon Average-Reward Markov Decision Processes 1
R*: Efficient Reward Design via Reward Structure Evolution and Parameter Alignment Optimization with Large Language Models 5
R.I.P.: Better Models by Survival of the Fittest Prompts 4
R2-T2: Re-Routing in Test-Time for Multimodal Mixture-of-Experts 5
R3DM: Enabling Role Discovery and Diversity Through Dynamics Models in Multi-agent Reinforcement Learning 5
RAGGED: Towards Informed Design of Scalable and Stable RAG Systems 4
RAPID: Long-Context Inference with Retrieval-Augmented Speculative Decoding 6
RATE: Causal Explainability of Reward Models with Imperfect Counterfactuals 5
RBench: Graduate-level Multi-disciplinary Benchmarks for LLM & MLLM Complex Reasoning Evaluation 3
RE-Bench: Evaluating Frontier AI R&D Capabilities of Language Model Agents against Human Experts 6
RE-IMAGINE: Symbolic Benchmark Synthesis for Reasoning Evaluation 2
REG: Rectified Gradient Guidance for Conditional Diffusion Models 5
REINFORCE Adversarial Attacks on Large Language Models: An Adaptive, Distributional, and Semantic Objective 7
RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers 4
RISE: Radius of Influence based Subgraph Extraction for 3D Molecular Graph Explanation 5
RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning 5
RLTHF: Targeted Human Feedback for LLM Alignment 5
ROME is Forged in Adversity: Robust Distilled Datasets via Information Bottleneck 6
ROPO: Robust Preference Optimization for Large Language Models 5
ROS: A GNN-based Relax-Optimize-and-Sample Framework for Max-$k$-Cut Problems 7
RULEBREAKERS: Challenging LLMs at the Crossroads between Formal Logic and Human-like Reasoning 5
RUN: Reversible Unfolding Network for Concealed Object Segmentation 6
RWKVQuant: Quantizing the RWKV Family with Proxy Guided Hybrid of Scalar and Vector Quantization 5
RZ-NAS: Enhancing LLM-guided Neural Architecture Search via Reflective Zero-Cost Strategy 4
Radio: Rate–Distortion Optimization for Large Language Model Compression 6
Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving Testing 6
Random Feature Representation Boosting 6
Random Policy Evaluation Uncovers Policies of Generative Flow Networks 4
Random Registers for Cross-Domain Few-Shot Learning 4
Randomized Dimensionality Reduction for Euclidean Maximization and Diversity Measures 4
Rank-One Modified Value Iteration 3
Ranked Entropy Minimization for Continual Test-Time Adaptation 4
Ranked from Within: Ranking Large Multimodal Models Without Labels 5
Ranking with Multiple Oracles: From Weak to Strong Stochastic Transitivity 2
Rapid Overfitting of Multi-Pass SGD in Stochastic Convex Optimization 1
Raptor: Scalable Train-Free Embeddings for 3D Medical Volumes Leveraging Pretrained 2D Foundation Models 5
Re-ranking Reasoning Context with Tree Search Makes Large Vision-Language Models Stronger 6
ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding 5
ReFrame: Layer Caching for Accelerated Inference in Real-Time Rendering 4
RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers 4
ReQFlow: Rectified Quaternion Flow for Efficient and High-Quality Protein Backbone Generation 5
ReVISE: Learning to Refine at Test-Time via Intrinsic Self-Verification 5
Reaction Graph: Towards Reaction-Level Modeling for Chemical Reactions with 3D Structures 7
RealRAG: Retrieval-augmented Realistic Image Generation via Self-reflective Contrastive Learning 2
Reasoning Limitations of Multimodal Large Language Models. A case study of Bongard Problems 6
Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation 5
Reasoning-as-Logic-Units: Scaling Test-Time Reasoning in Large Language Models Through Logic Unit Alignment 4
Recommendations with Sparse Comparison Data: Provably Fast Convergence for Nonconvex Matrix Factorization 2
Reconstructing Cell Lineage Trees from Phenotypic Features with Metric Learning 3
Rectifying Conformity Scores for Better Conditional Coverage 6
Reducing Confounding Bias without Data Splitting for Causal Inference via Optimal Transport 4
Reducing Tool Hallucination via Reliability Alignment 6
Reducing Variance of Stochastic Optimization for Approximating Nash Equilibria in Normal-Form Games 4
Redundancy Undermines the Trustworthiness of Self-Interpretable GNNs 4
ReferSplat: Referring Segmentation in 3D Gaussian Splatting 5
Refined generalization analysis of the Deep Ritz Method and Physics-Informed Neural Networks 0
Refining Adaptive Zeroth-Order Optimization at Ease 3
Reflect-then-Plan: Offline Model-Based Planning through a Doubly Bayesian Lens 4
Reflection-Bench: Evaluating Epistemic Agency in Large Language Models 3
Reflection-Window Decoding: Text Generation with Selective Refinement 3
Regress, Don’t Guess: A Regression-like Loss on Number Tokens for Language Models 7
Regression for the Mean: Auto-Evaluation and Inference with Few Labels through Post-hoc Regression 3
Regret-Free Reinforcement Learning for Temporal Logic Specifications 3
Regularized Langevin Dynamics for Combinatorial Optimization 6
Reidentify: Context-Aware Identity Generation for Contextual Multi-Agent Reinforcement Learning 4
ReinboT: Amplifying Robot Visual-Language Manipulation with Reinforcement Learning 4
Reinforce LLM Reasoning through Multi-Agent Reflection 5
Reinforced Learning Explicit Circuit Representations for Quantum State Characterization from Local Measurements 2
Reinforced Lifelong Editing for Language Models 6
Reinforcement Learning Control of a Physical Robot Device for Assisted Human Walking without a Simulator 5
Reinforcement Learning for Quantum Control under Physical Constraints 4
Reinforcement Learning with Adaptive Reward Modeling for Expensive-to-Evaluate Systems 4
Reinforcement Learning with Random Time Horizons 5
Reinforcement Learning with Segment Feedback 2
Rejecting Hallucinated State Targets during Planning 4
RelGNN: Composite Message Passing for Relational Deep Learning 3
Relating Misfit to Gain in Weak-to-Strong Generalization Beyond the Squared Loss 3
Relational Conformal Prediction for Correlated Time Series 5
Relational Invariant Learning for Robust Solvation Free Energy Prediction 4
Relative Error Fair Clustering in the Weak-Strong Oracle Model 4
Reliable Algorithm Selection for Machine Learning-Guided Design 5
Reliable and Efficient Amortized Model-based Evaluation 4
RepLoRA: Reparameterizing Low-rank Adaptation via the Perspective of Mixture of Experts 3
RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing 4
Representation Preserving Multiclass Agnostic to Realizable Reduction 1
Representation Shattering in Transformers: A Synthetic Study with Knowledge Editing 4
Representation Surgery in Model Merging with Probabilistic Modeling 4
Representations Shape Weak-to-Strong Generalization: Theoretical Insights and Empirical Predictions 3
Representative Language Generation 0
Representative Ranking for Deliberation in the Public Sphere 3
ResKoopNet: Learning Koopman Representations for Complex Dynamics with Spectral Residuals 4
ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank Residuals 6
ResearchTown: Simulator of Human Research Community 6
Residual Matrix Transformers: Scaling the Size of the Residual Stream 4
Residual TPP: A Unified Lightweight Approach for Event Stream Data Analysis 4
Resolving Lexical Bias in Model Editing 6
RestoreGrad: Signal Restoration Using Conditional Denoising Diffusion Models with Jointly Learned Prior 5
Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning Approach 6
Rethink GraphODE Generalization within Coupled Dynamical System 5
Rethink the Role of Deep Learning towards Large-scale Quantum Systems 2
Rethinking Addressing in Language Models via Contextualized Equivariant Positional Encoding 5
Rethinking Aleatoric and Epistemic Uncertainty 3
Rethinking Benign Overfitting in Two-Layer Neural Networks 2
Rethinking Causal Ranking: A Balanced Perspective on Uplift Model Evaluation 5
Rethinking Chain-of-Thought from the Perspective of Self-Training 5
Rethinking Confidence Scores and Thresholds in Pseudolabeling-based SSL 6
Rethinking External Slow-Thinking: From Snowball Errors to Probability of Correct Reasoning 3
Rethinking Latent Redundancy in Behavior Cloning: An Information Bottleneck Approach for Robot Manipulation 4
Rethinking Point Cloud Data Augmentation: Topologically Consistent Deformation 6
Rethinking Score Distilling Sampling for 3D Editing and Generation 6
Rethinking Time Encoding via Learnable Transformation Functions 4
Rethinking the Bias of Foundation Model under Long-tailed Distribution 3
Rethinking the Stability-Plasticity Trade-off in Continual Learning from an Architectural Perspective 5
Rethinking the Temperature for Federated Heterogeneous Distillation 5
Retraining with Predicted Hard Labels Provably Increases Model Accuracy 3
Retraining-free Merging of Sparse MoE via Hierarchical Clustering 6
Retrieval Augmented Time Series Forecasting 5
Retrieval Augmented Zero-Shot Enzyme Generation for Specified Substrate 3
Retrieval-Augmented Language Model for Knowledge-aware Protein Encoding 4
Retrieval-Augmented Perception: High-resolution Image Perception Meets Visual RAG 4
Return Capping: Sample Efficient CVaR Policy Gradient Optimisation 4
Return of the Latent Space COWBOYS: Re-thinking the use of VAEs for Bayesian Optimisation of Structured Spaces 5
Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks 5
ReverB-SNN: Reversing Bit of the Weight and Activation for Spiking Neural Networks 4
Revisiting Chain-of-Thought in Code Generation: Do Language Models Need to Learn Reasoning before Coding? 4
Revisiting Continuity of Image Tokens for Cross-domain Few-shot Learning 5
Revisiting Convergence: Shuffling Complexity Beyond Lipschitz Smoothness 3
Revisiting Cooperative Off-Policy Multi-Agent Reinforcement Learning 3
Revisiting Differentially Private Algorithms for Decentralized Online Learning 4
Revisiting Diffusion Models: From Generative Pre-training to One-Step Generation 3
Revisiting Instance-Optimal Cluster Recovery in the Labeled Stochastic Block Model 4
Revisiting Neural Networks for Few-Shot Learning: A Zero-Cost NAS Perspective 4
Revisiting Noise Resilience Strategies in Gesture Recognition: Short-Term Enhancement in sEMG Analysis 6
Revisiting Non-Acyclic GFlowNets in Discrete Environments 3
Revisiting Unbiased Implicit Variational Inference 4
Revisiting the Predictability of Performative, Social Events 1
Revolve: Optimizing AI Systems by Tracking Response Evolution in Textual Optimization 5
Reward Modeling with Ordinal Feedback: Wisdom of the Crowd 4
Reward Translation via Reward Machine in Semi-Alignable MDPs 2
Reward-Augmented Data Enhances Direct Preference Alignment of LLMs 4
Reward-Guided Iterative Refinement in Diffusion Models at Test-Time with Applications to Protein and DNA Design 5
Reward-Guided Prompt Evolving in Reinforcement Learning for LLMs 6
Reward-Guided Speculative Decoding for Efficient LLM Reasoning 5
Reward-free World Models for Online Imitation Learning 5
Rhomboid Tiling for Geometric Graph Deep Learning 5
Riemann Tensor Neural Networks: Learning Conservative Systems with Physics-Constrained Networks 4
Riemannian Diffusion Adaptation for Distributed Optimization on Manifolds 6
Right Now, Wrong Then: Non-Stationary Direct Preference Optimization under Preference Drift 5
Right Time to Learn: Promoting Generalization via Bio-inspired Spacing Effect in Knowledge Distillation 5
Ringmaster ASGD: The First Asynchronous SGD with Optimal Time Complexity 4
Risk and cross validation in ridge regression with correlated samples 3
Risk-Sensitive Theory of Mind: Coordinating with Agents of Unknown Bias using Cumulative Prospect Theory 4
RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language Models 6
Robot-Gated Interactive Imitation Learning with Adaptive Intervention Mechanism 5
Robust Automatic Modulation Classification with Fuzzy Regularization 2
Robust Autonomy Emerges from Self-Play 5
Robust Conformal Outlier Detection under Contaminated Reference Data 5
Robust Consensus Anchor Learning for Efficient Multi-view Subspace Clustering 3
Robust ML Auditing using Prior Knowledge 3
Robust Multi-Agent Reinforcement Learning with Stochastic Adversary 3
Robust Multi-bit Text Watermark with LLM-based Paraphrasers 4
Robust Multimodal Large Language Models Against Modality Conflict 4
Robust Noise Attenuation via Adaptive Pooling of Transformer Outputs 5
Robust Offline Reinforcement Learning with Linearly Structured $f$-Divergence Regularization 4
Robust Reward Alignment via Hypothesis Space Batch Cutting 3
Robust Secure Swap: Responsible Face Swap With Persons of Interest Redaction and Provenance Traceability 4
Robust Sparsification via Sensitivity 5
Robust Spatio-Temporal Centralized Interaction for OOD Learning 6
Robust and Conjugate Spatio-Temporal Gaussian Processes 5
RobustLight: Improving Robustness via Diffusion Reinforcement Learning for Traffic Signal Control 5
RobustZero: Enhancing MuZero Reinforcement Learning Robustness to State Perturbations 4
RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression 5
Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction 4
RollingQ: Reviving the Cooperation Dynamics in Multimodal Transformer 5
RuleAdapter: Dynamic Rules for training Safety Reward Models in RLHF 3
Runtime Analysis of Evolutionary NAS for Multiclass Classification 1
Rényi Neural Processes 5
S2-Track: A Simple yet Strong Approach for End-to-End 3D Multi-Object Tracking 4
S4S: Solving for a Fast Diffusion Model Solver 4
SADA: Stability-guided Adaptive Diffusion Acceleration 5
SAE-V: Interpreting Multimodal Models for Enhanced Alignment 6
SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability 5
SAFE: Finding Sparse and Flat Minima to Improve Pruning 6
SAFER: A Calibrated Risk-Aware Multimodal Recommendation Model for Dynamic Treatment Regimes 4
SAH-Drive: A Scenario-Aware Hybrid Planner for Closed-Loop Vehicle Trajectory Generation 5
SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation 6
SAN: Hypothesizing Long-Term Synaptic Development and Neural Engram Mechanism in Scalable Model’s Parameter-Efficient Fine-Tuning 4
SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer 4
SAND: One-Shot Feature Selection with Additive Noise Distortion 5
SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders 6
SBGD: Improving Graph Diffusion Generative Model via Stochastic Block Diffusion 4
SCENIR: Visual Semantic Clarity through Unsupervised Scene Graph Retrieval 5
SCENT: Robust Spatiotemporal Learning for Continuous Scientific Data via Scalable Conditioned Neural Fields 5
SCISSOR: Mitigating Semantic Bias through Cluster-Aware Siamese Networks for Robust Classification 4
SDE Matching: Scalable and Simulation-Free Training of Latent Stochastic Differential Equations 5
SDMG: Smoothing Your Diffusion Models for Powerful Graph Representation Learning 5
SDP-CROWN: Efficient Bound Propagation for Neural Network Verification with Tightness of Semidefinite Programming 4
SE(3)-Equivariant Diffusion Policy in Spherical Fourier Space 3
SEAD: Unsupervised Ensemble of Streaming Anomaly Detectors 5
SECOND: Mitigating Perceptual Hallucination in Vision-Language Models via Selective and Contrastive Decoding 5
SEFE: Superficial and Essential Forgetting Eliminator for Multimodal Continual Instruction Tuning 5
SEMU: Singular Value Decomposition for Efficient Machine Unlearning 5
SENSEI: Semantic Exploration Guided by Foundation Models to Learn Versatile World Models 5
SERENA: A Unified Stochastic Recursive Variance Reduced Gradient Framework for Riemannian Non-Convex Optimization 4
SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training 4
SGD Jittering: A Training Strategy for Robust and Accurate Model-Based Architectures 5
SHARP-Distill: A 68$\times$ Faster Recommender System with Hypergraph Neural Networks and Language Models 5
SHE: Streaming-media Hashing Retrieval 6
SHIELD: Multi-task Multi-distribution Vehicle Routing Solver with Sparsity and Hierarchy 5
SIMPLEMIX: Frustratingly Simple Mixing of Off- and On-policy Data in Language Model Preference Learning 2
SING: Spatial Context in Large Language Model for Next-Gen Wearables 3
SITCOM: Step-wise Triple-Consistent Diffusion Sampling For Inverse Problems 6
SK-VQA: Synthetic Knowledge Generation at Scale for Training Context-Augmented Multimodal LLMs 6
SKIM: Any-bit Quantization Pushing The Limits of Post-Training Quantization 5
SKOLR: Structured Koopman Operator Linear RNN for Time-Series Forecasting 5
SLiM: One-shot Quantization and Sparsity with Low-rank Approximation for LLM Weight Compression 6
SMART-PC: Skeletal Model Adaptation for Robust Test-Time Training in Point Clouds 5
SNS-Bench: Defining, Building, and Assessing Capabilities of Large Language Models in Social Networking Services 3
SOLD: Slot Object-Centric Latent Dynamics Models for Relational Manipulation Learning from Pixels 4
SPACE: Your Genomic Profile Predictor is a Powerful DNA Foundation Model 5
SPD: Sync-Point Drop for Efficient Tensor Parallelism of Large Language Models 4
SPEX: Scaling Feature Interaction Explanations for LLMs 5
SPHINX: Structural Prediction using Hypergraph Inference Network 3
SPMC: Self-Purifying Federated Backdoor Defense via Margin Contribution 5
SPRI: Aligning Large Language Models with Context-Situated Principles 6
SSHR: More Secure Generative Steganography with High-Quality Revealed Secret Images 4
STAIR: Improving Safety Alignment with Introspective Reasoning 6
STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings 4
STAR: Learning Diverse Robot Skill Abstractions through Rotation-Augmented Vector Quantization 5
STD-FD: Spatio-Temporal Distribution Fitting Deviation for AIGC Forgery Identification 6
STP: Self-play LLM Theorem Provers with Iterative Conjecturing and Proving 6
SToFM: a Multi-scale Foundation Model for Spatial Transcriptomics 6
SUICA: Learning Super-high Dimensional Sparse Implicit Neural Representations for Spatial Transcriptomics 5
SWAN: SGD with Normalization and Whitening Enables Stateless LLM Training 5
SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering? 5
Sable: a Performant, Efficient and Scalable Sequence Model for MARL 6
Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets 5
Safe-EF: Error Feedback for Non-smooth Constrained Optimization 3
SafeArena: Evaluating the Safety of Autonomous Web Agents 2
SafeAuto: Knowledge-Enhanced Safe Autonomous Driving with Multimodal Foundation Models 6
SafeMap: Robust HD Map Construction from Incomplete Observations 4
Safely Learning Optimal Auctions: A Testable Learning Framework for Mechanism Design 1
Safety Alignment Can Be Not Superficial With Explicit Safety Signals 4
Safety Certificate against Latent Variables with Partially Unidentifiable Dynamics 2
Safety Reasoning with Guidelines 4
Safety-Polarized and Prioritized Reinforcement Learning 4
SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behavior 3
SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization 6
Sample Complexity of Branch-length Estimation by Maximum Likelihood 1
Sample Complexity of Correlation Detection in the Gaussian Wigner Model 3
Sample Complexity of Distributionally Robust Off-Dynamics Reinforcement Learning with Online Interaction 5
Sample Efficient Demonstration Selection for In-Context Learning 5
Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling Verification 5
Sample-Optimal Agnostic Boosting with Unlabeled Data 5
Sample-specific Noise Injection for Diffusion-based Adversarial Purification 7
Sampling Binary Data by Denoising through Score Functions 3
Sampling from Binary Quadratic Distributions via Stochastic Localization 5
Sanity Checking Causal Representation Learning on a Simple Real-World System 5
Sassha: Sharpness-aware Adaptive Second-order Optimization with Stable Hessian Approximation 5
Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search 5
Scaffold with Stochastic Gradients: New Analysis with Linear Speed-Up 4
Scalable Approximation Algorithms for $p$-Wasserstein Distance and Its Variants 4
Scalable Attribute-Missing Graph Clustering via Neighborhood Differentiation 5
Scalable Equilibrium Sampling with Sequential Boltzmann Generators 6
Scalable First-order Method for Certifying Optimal k-Sparse GLMs 7
Scalable Gaussian Processes with Latent Kronecker Structure 5
Scalable Generation of Spatial Transcriptomics from Histology Images via Whole-Slide Flow Matching 7
Scalable Meta-Learning via Mixed-Mode Differentiation 4
Scalable Model Merging with Progressive Layer-wise Distillation 5
Scalable Non-Equivariant 3D Molecule Generation via Rotational Alignment 6
Scalable Private Partition Selection via Adaptive Weighting 4
Scalable Sobolev IPM for Probability Measures on a Graph 4
Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks 3
Scaling Inference-Efficient Language Models 5
Scaling Large Motion Models with Million-Level Human Motions 4
Scaling Laws for Differentially Private Language Models 5
Scaling Laws for Floating–Point Quantization Training 2
Scaling Laws for Forgetting during Finetuning with Pretraining Data Injection 3
Scaling Laws for Pre-training Agents and World Models 3
Scaling Laws for Task-Optimized Models of the Primate Visual Ventral Stream 5
Scaling Laws for Upcycling Mixture-of-Experts Language Models 6
Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More 5
Scaling Probabilistic Circuits via Monarch Matrices 4
Scaling Sparse Feature Circuits For Studying In-Context Learning 5
Scaling Test-Time Compute Without Verification or RL is Suboptimal 4
Scaling Trends in Language Model Robustness 5
Scaling Value Iteration Networks to 5000 Layers for Extreme Long-Term Planning 4
Scaling Video-Language Models to 10K Frames via Hierarchical Differential Distillation 6
Schwarz–Schur Involution: Lightspeed Differentiable Sparse Linear Solvers 5
Score Matching with Missing Data 4
Score as Action: Fine Tuning Diffusion Generative Models by Continuous-time Reinforcement Learning 4
Score-Based Diffusion Policy Compatible with Reinforcement Learning via Optimal Transport 4
Score-based Pullback Riemannian Geometry: Extracting the Data Manifold Geometry using Anisotropic Flows 3
Score-of-Mixture Training: One-Step Generative Model Training Made Simple via Score Estimation of Mixture Distributions 5
SecEmb: Sparsity-Aware Secure Federated Learning of On-Device Recommender System with Large Embedding 5
Secant Line Search for Frank-Wolfe Algorithms 5
Securing Equal Share: A Principled Approach for Learning Multiplayer Symmetric Games 2
SeedLoRA: A Fusion Approach to Efficient LLM Fine-Tuning 3
Segment Anyword: Mask Prompt Inversion for Open-Set Grounded Segmentation 7
Selective Preference Aggregation 7
Selective Prompt Anchoring for Code Generation 5
Selective Response Strategies for GenAI 3
Self-Bootstrapping for Versatile Test-Time Adaptation 6
Self-Consistency Preference Optimization 3
Self-Consuming Generative Models with Adversarially Curated Data 4
Self-Discriminative Modeling for Anomalous Graph Detection 5
Self-Disentanglement and Re-Composition for Cross-Domain Few-Shot Segmentation 2
Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI 6
Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges 4
Self-Organizing Visual Prototypes for Non-Parametric Representation Learning 5
Self-Play $Q$-Learners Can Provably Collude in the Iterated Prisoner’s Dilemma 3
Self-Supervised Learning of Intertwined Content and Positional Features for Object Detection 5
Self-Supervised Transformers as Iterative Solution Improvers for Constraint Satisfaction 5
Self-cross Feature based Spiking Neural Networks for Efficient Few-shot Learning 3
Self-supervised Adversarial Purification for Graph Neural Networks 6
Self-supervised Masked Graph Autoencoder via Structure-aware Curriculum 6
SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Models 6
Semantic Shift Estimation via Dual-Projection and Classifier Reconstruction for Exemplar-Free Class-Incremental Learning 4
Semantics-aware Test-time Adaptation for 3D Human Pose Estimation 3
Semi-Supervised Blind Quality Assessment with Confidence-quantifiable Pseudo-label Learning for Authentic Images 5
SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator 3
Separating Knowledge and Perception with Procedural Data 4
Set Valued Predictions For Robust Domain Generalization 5
Settling the Maximin Share Fairness for Scheduling among Groups of Machines 1
ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference 5
Sharp Generalization for Nonparametric Regression by Over-Parameterized Neural Networks: A Distribution-Free Analysis in Spherical Covariate 4
Sharp Optimality of Simple, Plug-in Estimation of the Fisher Information of a Smoothed Density 0
ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning 3
Shielded Diffusion: Generating Novel and Diverse Images using Sparse Repellency 5
Shifting Time: Time-series Forecasting with Khatri-Rao Neural Operators 6
Shortcut-connected Expert Parallelism for Accelerating Mixture of Experts 3
Should Decision-Makers Reveal Classifiers in Online Strategic Classification? 1
Sidechain conditioning and modeling for full-atom protein sequence design with FAMPNN 6
Signed Laplacians for Constrained Graph Clustering 5
Simple Path Structural Encoding for Graph Transformers 5
Simple Policy Optimization 4
Simple Randomized Rounding for Max-Min Eigenvalue Augmentation 0
Simple and Critical Iterative Denoising: A Recasting of Discrete Diffusion in Graph Generation 4
Simplicity Bias and Optimization Threshold in Two-Layer ReLU Networks 3
Simplifying DINO via Coding Rate Regularization 5
Simultaneous Multi-Robot Motion Planning with Projected Diffusion Models 6
Since Faithfulness Fails: The Performance Limits of Neural Causal Discovery 2
Sketch to Adapt: Fine-Tunable Sketches for Efficient LLM Adaptation 6
SketchDNN: Joint Continuous-Discrete Diffusion for CAD Sketch Generation 4
Skip the Equations: Learning Behavior of Personalized Dynamical Systems Directly From Data 4
SkipGPT: Each Token is One of a Kind 5
Skrr: Skip and Re-use Text Encoder Layers for Memory Efficient Text-to-Image Generation 5
Sleeping Reinforcement Learning 3
SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models 6
Sliding Puzzles Gym: A Scalable Benchmark for State Representation in Visual Reinforcement Learning 5
SlimLLM: Accurate Structured Pruning for Large Language Models 5
Slimming the Fat-Tail: Morphing-Flow for Adaptive Time Series Modeling 5
Smooth Interpolation for Improved Discrete Graph Generative Models 6
Smoothed Preference Optimization via ReNoise Inversion for Aligning Diffusion Models with Varied Human Preferences 4
Socialized Coevolution: Advancing a Better World through Cross-Task Collaboration 6
Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration 3
Softmax is not Enough (for Sharp Size Generalisation) 6
Solving Linear-Gaussian Bayesian Inverse Problems with Decoupled Diffusion Sequential Monte Carlo 5
Solving Probabilistic Verification Problems of Neural Networks using Branch and Bound 6
Solving Satisfiability Modulo Counting Exactly with Probabilistic Circuits 6
Solving Zero-Sum Convex Markov Games 2
SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song Generation 5
Sorbet: A Neuromorphic Hardware-Compatible Transformer-Based Spiking Language Model 6
Sort Before You Prune: Improved Worst-Case Guarantees of the DiskANN Family of Graphs 4
Sortformer: A Novel Approach for Permutation-Resolved Speaker Supervision in Speech-to-Text Systems 5
Sounding that Object: Interactive Object-Aware Image to Audio Generation 3
Soup-of-Experts: Pretraining Specialist Models via Parameters Averaging 4
SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference 5
Sparse Autoencoders for Hypothesis Generation 6
Sparse Autoencoders, Again? 3
Sparse Causal Discovery with Generative Intervention for Unsupervised Graph Domain Adaptation 4
Sparse Spectral Training and Inference on Euclidean and Hyperbolic Neural Networks 7
Sparse Training from Random Initialization: Aligning Lottery Ticket Masks using Weight Symmetry 3
Sparse Video-Gen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity 5
Sparse-pivot: Dynamic correlation clustering for node insertions 4
SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity 5
SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference 6
Sparsing Law: Towards Large Language Models with Greater Activation Sparsity 6
Spatial Reasoning with Denoising Models 4
SpeCache: Speculative Key-Value Caching for Efficient Generation of LLMs 4
Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions 5
Spectral-Aware Reservoir Computing for Fast and Accurate Time Series Classification 7
Speculate, then Collaborate: Fusing Knowledge of Language Models during Decoding 4
Speculative Prefill: Turbocharging TTFT with Lightweight and Training-Free Token Importance Estimation 6
Speeding up Policy Simulation in Supply Chain RL 4
Spherical-Nested Diffusion Model for Panoramic Image Outpainting 4
SpikF: Spiking Fourier Network for Efficient Long-term Prediction 6
SpikeVideoFormer: An Efficient Spike-Driven Video Transformer with Hamming Attention and $\mathcalO(T)$ Complexity 5
Splitting & Integrating: Out-of-Distribution Detection via Adversarial Gradient Attribution 4
Splitting with Importance-aware Updating for Heterogeneous Federated Learning with Large Language Models 4
Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization 4
Square$χ$PO: Differentially Private and Robust $χ^2$-Preference Optimization in Offline Direct Alignment 3
Stability and Generalization Analysis of Decentralized SGD: Sharper Bounds Beyond Lipschitzness and Smoothness 1
Stability and Generalization Capability of Subgraph Reasoning Models for Inductive Knowledge Graph Completion 4
Stabilizing Sample Similarity in Representation via Mitigating Random Consistency 7
Stable Fair Graph Representation Learning with Lipschitz Constraint 4
Stable Offline Value Function Learning with Bisimulation-based Representations 3
Stacey: Promoting Stochastic Steepest Descent via Accelerated $\ell_p$-Smooth Nonconvex Optimization 5
Staged and Physics-Grounded Learning Framework with Hyperintensity Prior for Pre-Contrast MRI Synthesis 3
Star Attention: Efficient LLM Inference over Long Sequences 6
Statistical Collusion by Collectives on Learning Platforms 4
Statistical Hypothesis Testing for Auditing Robustness in Language Models 3
Statistical Query Hardness of Multiclass Linear Classification with Random Classification Noise 0
Statistical Test for Feature Selection Pipelines by Selective Inference 6
Statistical and Computational Guarantees of Kernel Max-Sliced Wasserstein Distances 5
Stay Hungry, Keep Learning: Sustainable Plasticity for Deep Reinforcement Learning 5
Stay-Positive: A Case for Ignoring Real Image Features in Fake Image Detection 5
Stealing That Free Lunch: Exposing the Limits of Dyna-Style Reinforcement Learning 4
Stealix: Model Stealing via Prompt Evolution 5
StealthInk: A Multi-bit and Stealthy Watermark for Large Language Models 5
Steer LLM Latents for Hallucination Detection 7
Steerable Transformers for Volumetric Data 5
Steering Protein Language Models 5
Step-DAD: Semi-Amortized Policy-Based Bayesian Experimental Design 4
Stochastic Control for Fine-tuning Diffusion Models: Optimality, Regularity, and Convergence 2
Stochastic Deep Restoration Priors for Imaging Inverse Problems 4
Stochastic Encodings for Active Feature Acquisition 6
Stochastic Forward–Backward Deconvolution: Training Diffusion Models with Finite Noisy Datasets 5
Stochastic Layer-Wise Shuffle for Improving Vision Mamba Training 5
Stochastic Online Conformal Prediction with Semi-Bandit Feedback 3
Stochastic Poisson Surface Reconstruction with One Solve using Geometric Gaussian Processes 4
Stochastic Smoothed Primal-Dual Algorithms for Nonconvex Optimization with Linear Inequality Constraints 1
Strategic A/B testing via Maximum Probability-driven Two-armed Bandit 3
Strategic Planning: A Top-Down Approach to Option Generation 4
Strategy Coopetition Explains the Emergence and Transience of In-Context Learning 3
Stray Intrusive Outliers-Based Feature Selection on Intra-Class Asymmetric Instance Distribution or Multiple High-Density Clusters 6
Stream-level Flow Matching with Gaussian Processes 6
Streamline Without Sacrifice - Squeeze out Computation Redundancy in LMM 4
Strengthen Out-of-Distribution Detection Capability with Progressive Self-Knowledge Distillation 7
Strong and Weak Identifiability of Optimization-based Causal Discovery in Non-linear Additive Noise Models 5
Stronger Neyman Regret Guarantees for Adaptive Experimental Design 4
Structure Is All You Need: Structural Representation Learning on Hyper-Relational Knowledge Graphs 6
Structure-Guided Large Language Models for Text-to-SQL Generation 2
Structure-informed Risk Minimization for Robust Ensemble Learning 5
Structured Preconditioners in Adaptive Optimization: A Unified Analysis 2
Sub-Sequential Physics-Informed Learning with State Space Model 4
Subgoal-Guided Policy Heuristic Search with Learned Subgoals 7
Subgroups Matter for Robust Bias Mitigation 4
Subobject-level Image Tokenization 5
Subspace Optimization for Large Language Models with Convergence Guarantees 5
Suitability Filter: A Statistical Framework for Classifier Evaluation in Real-World Deployment Settings 4
Sum-of-Parts: Self-Attributing Neural Networks with End-to-End Learning of Feature Groups 6
Sundial: A Family of Highly Capable Time Series Foundation Models 5
Super Deep Contrastive Information Bottleneck for Multi-modal Clustering 4
Supercharging Graph Transformers with Advective Diffusion 7
Supervised Contrastive Learning from Weakly-Labeled Audio Segments for Musical Version Matching 6
Surrogate Prompt Learning: Towards Efficient and Diverse Prompt Learning for Vision-Language Models 6
Survival Analysis via Density Estimation 7
Symmetric Reinforcement Learning Loss for Robust Learning on Diverse Tasks and Model Scales 5
Symmetry-Aware GFlowNets 5
Symmetry-Driven Discovery of Dynamical Variables in Molecular Simulations 2
Symmetry-Robust 3D Orientation Estimation 4
SynEVO: A neuro-inspired spatiotemporal evolutional framework for cross-domain adaptation 5
SyncMind: Measuring Agent Out-of-Sync Recovery in Collaborative Software Engineering 5
Synonymous Variational Inference for Perceptual Image Compression 4
Synthesizing Images on Perceptual Boundaries of ANNs for Uncovering and Manipulating Human Perceptual Variability 5
Synthesizing Privacy-Preserving Text Data via Finetuning *without* Finetuning Billion-Scale LLMs 7
Synthesizing Software Engineering Data in a Test-Driven Manner 6
Synthetic Face Datasets Generation via Latent Space Exploration from Brownian Identity Diffusion 6
Synthetic Text Generation for Training Large Language Models via Gradient Matching 5
System-Aware Unlearning Algorithms: Use Lesser, Forget Faster 2
T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling 4
TANGO: Clustering with Typicality-Aware Nonlocal Mode-Seeking and Graph-Cut Optimization 6
TAROT: Targeted Data Selection via Optimal Transport 6
TCP-Diffusion: A Multi-modal Diffusion Model for Global Tropical Cyclone Precipitation Forecasting with Change Awareness 7
TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization 4
TIMING: Temporality-Aware Integrated Gradients for Time Series Explanation 5
TINED: GNNs-to-MLPs by Teacher Injection and Dirichlet Energy Distillation 5
TLLC: Transfer Learning-based Label Completion for Crowdsourcing 4
TMetaNet: Topological Meta-Learning Framework for Dynamic Link Prediction 6
TOPLOC: A Locality Sensitive Hashing Scheme for Trustless Verifiable Inference 5
TRACE Back from the Future: A Probabilistic Reasoning Approach to Controllable Language Generation 6
TRUST-VLM: Thorough Red-Teaming for Uncovering Safety Threats in Vision-Language Models 3
TS-SNN: Temporal Shift Module for Spiking Neural Networks 5
TSP: A Two-Sided Smoothed Primal-Dual Method for Nonconvex Bilevel Optimization 4
TTFSFormer: A TTFS-based Lossless Conversion of Spiking Transformer 4
TUMTraf VideoQA: Dataset and Benchmark for Unified Spatio-Temporal Video Understanding in Traffic Scenes 4
TabFSBench: Tabular Benchmark for Feature Shifts in Open Environments 4
TabFlex: Scaling Tabular Learning to Millions with Linear Attention 6
TabICL: A Tabular Foundation Model for In-Context Learning on Large Data 5
TabNAT: A Continuous-Discrete Joint Generative Framework for Tabular Data 6
TabPFN Unleashed: A Scalable and Effective Solution to Tabular Classification Problems 5
TabSDS: a Lightweight, Fully Non-Parametric, and Model Free Approach for Generating Synthetic Tabular Data 5
Tackling Dimensional Collapse toward Comprehensive Universal Domain Adaptation 2
Tackling View-Dependent Semantics in 3D Language Gaussian Splatting 5
Taming Diffusion for Dataset Distillation with High Representativeness 6
Taming Knowledge Conflicts in Language Models 5
Taming Rectified Flow for Inversion and Editing 4
Target Concrete Score Matching: A Holistic Framework for Discrete Diffusion 4
Targeted Low-rank Refinement: Enhancing Sparse Language Models with Precision 4
Targeted Unlearning with Single Layer Unlearning Gradient 6
Targeted control of fast prototyping through domain-specific interface 2
Task Generalization with Autoregressive Compositional Structure: Can Learning from $D$ Tasks Generalize to $D^T$ Tasks? 5
Task-Agnostic Pre-training and Task-Guided Fine-tuning for Versatile Diffusion Planner 5
Task-Aware Virtual Training: Enhancing Generalization in Meta-Reinforcement Learning for Out-of-Distribution Tasks 6
Task-Gated Multi-Expert Collaboration Network for Degraded Multi-Modal Image Fusion 6
TeDS: Joint Learning of Diachronic and Synchronic Perspectives in Quaternion Space for Temporal Knowledge Graph Completion 3
TeLoGraF: Temporal Logic Planning via Graph-encoded Flow Matching 5
Teaching Language Models to Critique via Reinforcement Learning 4
Teaching Physical Awareness to LLMs through Sounds 3
Teaching Transformers Causal Reasoning through Axiomatic Training 5
Telling Peer Direct Effects from Indirect Effects in Observational Network Data 4
Temperature-Annealed Boltzmann Generators 6
Temporal Difference Flows 3
Temporal Distance-aware Transition Augmentation for Offline Model-based Reinforcement Learning 5
Temporal Misalignment in ANN-SNN Conversion and its Mitigation via Probabilistic Spiking Neurons 6
Temporal Query Network for Efficient Multivariate Time Series Forecasting 6
Tensor Decomposition Based Memory-Efficient Incremental Learning 3
Tensor Product Neural Networks for Functional ANOVA Model 5
Tensor-Var: Efficient Four-Dimensional Variational Data Assimilation 5
Tensorized Multi-View Multi-Label Classification via Laplace Tensor Rank 3
Test-Time Adaptation for Online Vision-Language Navigation with Feedback-based Reinforcement Learning 5
Test-Time Adaptation with Binary Feedback 5
Test-Time Canonicalization by Foundation Models for Robust Perception 5
Test-Time Graph Neural Dataset Search With Generative Projection 3
Test-Time Learning for Large Language Models 7
Test-Time Multimodal Backdoor Detection by Contrastive Prompting 6
Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback 4
Test-Time Selective Adaptation for Uni-Modal Distribution Shift in Multi-Modal Data 4
Test-Time Training Provably Improves Transformers as In-context Learners 3
Test-time Adaptation on Graphs via Adaptive Subgraph-based Selection and Regularized Prototypes 6
Test-time Adapted Reinforcement Learning with Action Entropy Regularization 4
Test-time Correlation Alignment 4
Testing Conditional Mean Independence Using Generative Neural Networks 5
Testing the Limits of Fine-Tuning for Improving Visual Cognition in Vision Language Models 5
Text-to-CAD Generation Through Infusing Visual Feedback in Large Language Models 5
Text-to-LoRA: Instant Transformer Adaption 5
TextCenGen: Attention-Guided Text-Centric Background Adaptation for Text-to-Image Generation 5
Textual Unlearning Gives a False Sense of Unlearning 3
Textural or Textual: How Vision-Language Models Read Text in Images 6
The Batch Complexity of Bandit Pure Exploration 2
The Berkeley Function Calling Leaderboard (BFCL): From Tool Use to Agentic Evaluation of Large Language Models 1
The Best of Both Worlds: Bridging Quality and Diversity in Data Selection with Bipartite Graph 4
The Brain’s Bitter Lesson: Scaling Speech Decoding With Self-Supervised Learning 4
The Butterfly Effect: Neural Network Training Trajectories Are Highly Sensitive to Initial Conditions 5
The Canary’s Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text 5
The Case for Learned Provenance-based System Behavior Baseline 5
The Complexity of Learning Sparse Superposed Features with Feedback 4
The Courage to Stop: Overcoming Sunk Cost Fallacy in Deep Reinforcement Learning 5
The Devil Is in the Details: Tackling Unimodal Spurious Correlations for Generalizable Multimodal Reward Models 4
The Diffusion Duality 6
The Disparate Benefits of Deep Ensembles 5
The Double-Ellipsoid Geometry of CLIP 2
The Elicitation Game: Evaluating Capability Elicitation Techniques 5
The Emperor’s New Clothes in Benchmarking? A Rigorous Examination of Mitigation Strategies for LLM Benchmark Data Contamination 6
The Empirical Mean is Minimax Optimal for Local Glivenko-Cantelli 1
The Energy Loss Phenomenon in RLHF: A New Perspective on Mitigating Reward Hacking 4
The Four Color Theorem for Cell Instance Segmentation 6
The Generalized Skew Spectrum of Graphs 4
The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence 5
The Global Convergence Time of Stochastic Gradient Descent in Non-Convex Landscapes: Sharp Estimates via Large Deviations 2
The Harder Path: Last Iterate Convergence for Uncoupled Learning in Zero-Sum Games with Bandit Feedback 1
The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions 6
The Hidden Joules: Evaluating the Energy Consumption of Vision Backbones for Progress Towards More Efficient Model Inference 7
The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models Via Visual Information Steering 5
The Illusion of Role Separation: Hidden Shortcuts in LLM Role Learning (and How to Fix Them) 3
The Impact of On-Policy Parallelized Data Collection on Deep Reinforcement Learning Networks 3
The Importance of Being Lazy: Scaling Limits of Continual Learning 4
The Jailbreak Tax: How Useful are Your Jailbreak Outputs? 3
The Limits of Predicting Agents from Behaviour 0
The Limits of Tractable Marginalization 0
The Lock-in Hypothesis: Stagnation by Algorithm 2
The Logical Implication Steering Method for Conditional Interventions on Transformer Generation 4
The Missing Alignment Link of In-context Learning on Sequences 5
The Noisy Laplacian: a Threshold Phenomenon for Non-Linear Dimension Reduction 2
The Number of Trials Matters in Infinite-Horizon General-Utility Markov Decision Processes 3
The Panaceas for Improving Low-Rank Decomposition in Communication-Efficient Federated Learning 4
The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret 1
The Polynomial Stein Discrepancy for Assessing Moment Convergence 3
The Power of Random Features and the Limits of Distribution-Free Gradient Descent 1
The Price of Freedom: Exploring Expressivity and Runtime Tradeoffs in Equivariant Tensor Products 6
The Price of Linear Time: Error Analysis of Structured Kernel Interpolation 1
The Relationship Between No-Regret Learning and Online Conformal Prediction 4
The Ripple Effect: On Unforeseen Complications of Backdoor Attacks 4
The Role of Randomness in Stability 1
The Role of Sparsity for Length Generalization in LLMs 3
The Sample Complexity of Online Strategic Decision Making with Information Asymmetry and Knowledge Transportability 1
The Sharpness Disparity Principle in Transformers for Accelerating Language Model Pre-Training 4
The Sparse-Plus-Low-Rank Quasi-Newton Method for Entropic-Regularized Optimal Transport 6
The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training 4
The Surprising Effectiveness of Test-Time Training for Few-Shot Learning 6
The Synergy of LLMs & RL Unlocks Offline Learning of Generalizable Language-Conditioned Policies with Low-fidelity Data 4
The Underlying Universal Statistical Structure of Natural Datasets 1
The Value of Prediction in Identifying the Worst-Off 3
The dark side of the forces: assessing non-conservative force models for atomistic machine learning 6
The impact of uncertainty on regularized learning in games 0
The underlying structures of self-attention: symmetry, directionality, and emergent dynamics in Transformer training 3
Theoretical Limitations of Ensembles in the Age of Overparameterization 4
Theoretical Performance Guarantees for Partial Domain Adaptation via Partial Optimal Transport 3
Theoretical guarantees on the best-of-n alignment policy 1
Theoretically Unmasking Inference Attacks Against LDP-Protected Clients in Federated Vision Models 5
Thermalizer: Stable autoregressive neural emulation of spatiotemporal chaos 4
Thickness-aware E(3)-Equivariant 3D Mesh Neural Networks 4
Think Smarter not Harder: Adaptive Reasoning with Inference Aware Optimization 6
Think Twice, Act Once: A Co-Evolution Framework of LLM and RL for Large-Scale Decision Making 4
Thinking LLMs: General Instruction Following with Thought Generation 3
Three-Dimensional Trajectory Prediction with 3DMoTraj Dataset 5
Tight and Fast Bounds for Multi-Label Learning 0
Tightening Causal Bounds via Covariate-Aware Optimal Transport 5
Tilted Sharpness-Aware Minimization 4
Time Series Representations with Hard-Coded Invariances 5
Time to Spike? Understanding the Representational Power of Spiking Neural Networks in Discrete Time 2
Time-Aware World Model for Adaptive Prediction and Control 5
Time-VLM: Exploring Multimodal Vision-Language Models for Augmented Time Series Forecasting 5
TimeBase: The Power of Minimalism in Efficient Long-term Time Series Forecasting 5
TimeBridge: Non-Stationarity Matters for Long-term Time Series Forecasting 5
TimeDART: A Diffusion Autoregressive Transformer for Self-Supervised Time Series Representation 5
TimeFilter: Patch-Specific Spatial-Temporal Graph Filtration for Time Series Forecasting 5
TimePoint: Accelerated Time Series Alignment via Self-Supervised Keypoint and Descriptor Learning 5
TimePro: Efficient Multivariate Long-term Time Series Forecasting with Variable- and Time-Aware Hyper-state 5
TimeStacker: A Novel Framework with Multilevel Observation for Capturing Nonstationary Patterns in Time Series Forecasting 6
TimeStep Master: Asymmetrical Mixture of Timestep LoRA Experts for Versatile and Efficient Diffusion Models in Vision 4
TinyMIG: Transferring Generalization from Vision Foundation Models to Single-Domain Medical Imaging 4
To Each Metric Its Decoding: Post-Hoc Optimal Decision Rules of Probabilistic Hierarchical Classifiers 5
To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models 4
ToMA: Token Merge with Attention for Diffusion Models 4
Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning 4
Token Cleaning: Fine-Grained Data Selection for LLM Supervised Fine-Tuning 6
Token Coordinated Prompt Attention is Needed for Visual Prompting 4
Token Signature: Predicting Chain-of-Thought Gains with Token Decoding Feature in Large Language Models 5
TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation 4
Tokenized Bandit for LLM Decoding and Alignment 3
Tool Unlearning for Tool-Augmented LLMs 4
TopInG: Topologically Interpretable Graph Learning via Persistent Rationale Filtration 4
TopoTune: A Framework for Generalized Combinatorial Complex Neural Networks 6
Topological Signatures of Adversaries in Multimodal Alignments 5
Topology-Aware Dynamic Reweighting for Distribution Shifts on Graph 6
Topology-aware Neural Flux Prediction Guided by Physics 2
Toward Data-centric Directed Graph Learning: An Entropy-driven Approach 6
Toward Efficient Kernel-Based Solvers for Nonlinear PDEs 3
Toward Robust Hyper-Detailed Image Captioning: A Multiagent Approach and Dual Evaluation Metrics for Factuality and Coverage 4
Toward a Unified Theory of Gradient Descent under Generalized Smoothness 3
Towards Attributions of Input Variables in a Coalition 1
Towards Better-than-2 Approximation for Constrained Correlation Clustering 1
Towards Black-Box Membership Inference Attack for Diffusion Models 6
Towards Cost-Effective Reward Guided Text Generation 6
Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement Learning 6
Towards Escaping from Class Dependency Modeling for Multi-Dimensional Classification 4
Towards Global-level Mechanistic Interpretability: A Perspective of Modular Circuits of Large Language Models 5
Towards Graph Foundation Models: Learning Generalities Across Graphs via Task-Trees 4
Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond 5
Towards Learning to Complete Anything in Lidar 4
Towards Lifelong Model Editing via Simulating Ideal Editor 4
Towards Memorization Estimation: Fast, Formal and Free 3
Towards Practical Defect-Focused Automated Code Review 5
Towards Rationale-Answer Alignment of LVLMs via Self-Rationale Calibration 3
Towards Robust Influence Functions with Flat Validation Minima 5
Towards Robustness and Explainability of Automatic Algorithm Selection 4
Towards Theoretical Understanding of Sequential Decision Making with Preference Feedback 0
Towards Trustworthy Federated Learning with Untrusted Participants 4
Towards Understanding Catastrophic Forgetting in Two-layer Convolutional Neural Networks 2
Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis 5
Towards Understanding Gradient Dynamics of the Sliced-Wasserstein Distance via Critical Point Analysis 2
Towards Understanding Parametric Generalized Category Discovery on Graphs 6
Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings 4
Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation 4
Towards a Formal Theory of Representational Compositionality 5
Towards a General Time Series Forecasting Model with Unified Representation and Adaptive Transfer 5
Towards a Mechanistic Explanation of Diffusion Model Generalization 3
Towards a Unified Framework of Clustering-based Anomaly Detection 4
Towards an Explainable Comparison and Alignment of Feature Embeddings 4
Towards characterizing the value of edge embeddings in Graph Neural Networks 3
Towards flexible perception with visual memory 4
Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models 4
Towards the Causal Complete Cause of Multi-Modal Representation Learning 6
Towards the Efficient Inference by Incorporating Automated Computational Phenotypes under Covariate Shift 4
TraceGrad: a Framework Learning Expressive SO(3)-equivariant Non-linear Representations for Electronic-Structure Hamiltonian Prediction 6
Tracking Most Significant Shifts in Infinite-Armed Bandits 1
Tracking The Best Expert Privately 1
Tractable Transformers for Flexible Conditional Generation 4
Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions 4
Training Deep Learning Models with Norm-Constrained LMOs 6
Training Diffusion-based Generative Models with Limited Data 5
Training Dynamics of In-Context Learning in Linear Attention 1
Training Flexible Models of Genetic Variant Effects from Functional Annotations using Accelerated Linear Algebra 5
Training High Performance Spiking Neural Network by Temporal Model Calibration 4
Training Software Engineering Agents and Verifiers with SWE-Gym 6
Training a Generally Curious Agent 6
Trajectory Inference with Smooth Schrödinger Bridges 6
Trajectory World Models for Heterogeneous Environments 6
TransPL: VQ-Code Transition Matrices for Pseudo-Labeling of Time Series Unsupervised Domain Adaptation 6
Transfer Learning for Nonparametric Contextual Dynamic Pricing 5
Transfer Q-Learning with Composite MDP Structures 1
Transformative or Conservative? Conservation laws for ResNets and Transformers 4
Transformer-Based Spatial-Temporal Counterfactual Outcomes Estimation 4
Transolver++: An Accurate Neural Solver for PDEs on Million-Scale Geometries 6
Tree-Sliced Wasserstein Distance with Nonlinear Projection 5
Tree-Sliced Wasserstein Distance: A Geometric Perspective 4
TreeLoRA: Efficient Continual Learning via Layer-Wise LoRAs Guided by a Hierarchical Gradient-Similarity Tree 6
Triple-Optimistic Learning for Stochastic Contextual Bandits with General Constraints 3
Trust-Region Twisted Policy Improvement 6
Trusted Multi-View Classification with Expert Knowledge Constraints 5
Trustworthy Machine Learning through Data-Specific Indistinguishability 3
TruthFlow: Truthful LLM Generation via Representation Flow Correction 6
TtBA: Two-third Bridge Approach for Decision-Based Adversarial Attack 6
TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs 5
Tuning LLM Judge Design Decisions for 1/1000 of the Cost 5
Tuning Sequential Monte Carlo Samplers via Greedy Incremental Divergence Minimization 4
Two Tickets are Better than One: Fair and Accurate Hiring Under Strategic LLM Manipulations 5
TypyBench: Evaluating LLM Type Inference for Untyped Python Repositories 5
UDora: A Unified Red Teaming Framework against LLM Agents by Dynamically Hijacking Their Own Reasoning 5
UGPhysics: A Comprehensive Benchmark for Undergraduate Physics Reasoning with Large Language Models 4
UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction 2
UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent 4
Ultra Lowrate Image Compression with Semantic Residual Coding and Compression-aware Diffusion 5
Ultra-Resolution Adaptation with Ease 5
UltraTWD: Optimizing Ultrametric Trees for Tree-Wasserstein Distance 6
UnHiPPO: Uncertainty-aware Initialization for State Space Models 3
Unbiased Evaluation of Large Language Models from a Causal Perspective 2
Unbiased Recommender Learning from Implicit Feedback via Weakly Supervised Learning 6
UncertainSAM: Fast and Efficient Uncertainty Quantification of the Segment Anything Model 5
Uncertainty Estimation for Heterophilic Graphs Through the Lens of Information Theory 6
Uncertainty Quantification for LLM-Based Survey Simulations 5
Uncertainty-Based Extensible Codebook for Discrete Federated Learning in Heterogeneous Data Silos 6
Unconstrained Robust Online Convex Optimization 1
Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning 5
Understanding Chain-of-Thought in LLMs through Information Theory 2
Understanding Complexity in VideoQA via Visual Program Generation 6
Understanding Fixed Predictions via Confined Regions 6
Understanding Generalization in Quantum Machine Learning with Margins 3
Understanding High-Dimensional Bayesian Optimization 3
Understanding Input Selectivity in Mamba: Impact on Approximation Power, Memorization, and Associative Recall Capacity 2
Understanding Mode Connectivity via Parameter Space Symmetry 0
Understanding Model Ensemble in Transferable Adversarial Attack 2
Understanding Model Reprogramming for CLIP via Decoupling Visual Prompts 5
Understanding Multimodal LLMs Under Distribution Shifts: An Information-Theoretic Approach 3
Understanding Nonlinear Implicit Bias via Region Counts in Input Space 5
Understanding Overadaptation in Supervised Fine-Tuning: The Role of Ensemble Methods 5
Understanding Sharpness Dynamics in NN Training with a Minimalist Example: The Effects of Dataset Difficulty, Depth, Stochasticity, and More 3
Understanding Synthetic Context Extension via Retrieval Heads 4
Understanding and Improving Length Generalization in Recurrent Models 4
Understanding and Mitigating Memorization in Diffusion Models for Tabular Data 5
Understanding and Mitigating Memorization in Generative Models via Sharpness of Probability Landscapes 4
Understanding and Mitigating Miscalibration in Prompt Tuning for Vision-Language Models 4
Understanding the Emergence of Multimodal Representation Alignment 4
Understanding the Forgetting of (Replay-based) Continual Learning via Feature Learning: Angle Matters 2
Understanding the Kronecker Matrix-Vector Complexity of Linear Algebra 0
Understanding the Limits of Deep Tabular Methods with Temporal Shift 4
Understanding the Logic of Direct Preference Alignment through Logic 5
Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism 2
Understanding the Statistical Accuracy-Communication Trade-off in Personalized Federated Learning with Minimax Guarantees 4
Understanding the Unfairness in Network Quantization 5
Understanding the difficulties of posterior predictive estimation 5
UniDB: A Unified Diffusion Bridge Framework via Stochastic Optimal Control 6
UniMC: Taming Diffusion Transformer for Unified Keypoint-Guided Multi-Class Image Generation 4
UniMate: A Unified Model for Mechanical Metamaterial Generation, Property Prediction, and Condition Confirmation 6
UniMoMo: Unified Generative Modeling of 3D Molecules for De Novo Binder Design 5
UniSim: A Unified Simulator for Time-Coarsened Dynamics of Biomolecules 5
Unifews: You Need Fewer Operations for Efficient Graph Neural Networks 6
Unified Analysis of Continuous Weak Features Learning with Applications to Learning from Missing Data 4
Unified Breakdown Analysis for Byzantine Robust Gossip 4
Unified K-Means Clustering with Label-Guided Manifold Learning 5
Unified Screening for Multiple Diseases 2
Uniform Mean Estimation for Heavy-Tailed Distributions via Median-of-Means 1
Unifying 2D and 3D Vision-Language Understanding 5
Unifying Knowledge from Diverse Datasets to Enhance Spatial-Temporal Modeling: A Granularity-Adaptive Geographical Embedding Approach 5
Unifying Specialized Visual Encoders for Video Language Models 5
Unisolver: PDE-Conditional Transformers Towards Universal Neural PDE Solvers 5
Unisoma: A Unified Transformer-based Solver for Multi-Solid Systems 6
Universal Approximation Theorem of Deep Q-Networks 1
Universal Approximation of Mean-Field Models via Transformers 4
Universal Biological Sequence Reranking for Improved De Novo Peptide Sequencing 5
Universal Length Generalization with Turing Programs 2
Universal Neural Optimal Transport 5
Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment 6
Unlocking Post-hoc Dataset Inference with Synthetic Data 5
Unlocking the Capabilities of Large Vision-Language Models for Generalizable and Explainable Deepfake Detection 5
Unlocking the Power of Rehearsal in Continual Learning: A Theoretical Perspective 5
Unlocking the Power of SAM 2 for Few-Shot Segmentation 5
Unnatural Languages Are Not Bugs but Features for LLMs 5
Unpaired Point Cloud Completion via Unbalanced Optimal Transport 4
Unraveling the Interplay between Carryover Effects and Reward Autocorrelations in Switchback Experiments 3
Unsupervised Learning for Class Distribution Mismatch 6
Unveiling AI’s Blind Spots: An Oracle for In-Domain, Out-of-Domain, and Adversarial Errors 5
Unveiling Markov heads in Pretrained Language Models for Offline Reinforcement Learning 4
Upcycling Text-to-Image Diffusion Models for Multi-Task Capabilities 4
Update Your Transformer to the Latest Release: Re-Basin of Task Vectors 5
Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting 7
VCT: Training Consistency Models with Variational Noise Coupling 5
VIP: Vision Instructed Pre-training for Robotic Manipulation 3
VTGaussian-SLAM: RGBD SLAM for Large Scale Scenes with Splatting View-Tied 3D Gaussians 4
Validating Mechanistic Interpretations: An Axiomatic Approach 6
Value-Based Deep RL Scales Predictably 2
Variance as a Catalyst: Efficient and Transferable Semantic Erasure Adversarial Attack for Customized Diffusion Models 4
Variance-Reduced Forward-Reflected-Backward Splitting Methods for Nonmonotone Generalized Equations 3
Variational Control for Guidance in Diffusion Models 6
Variational Counterfactual Intervention Planning to Achieve Target Outcomes 5
Variational Learning of Fractional Posteriors 5
Variational Phylogenetic Inference with Products over Bipartitions 5
Variational Rectified Flow Matching 3
Vector Grimoire: Codebook-based Shape Generation under Raster Image Supervision 5
VerbalTS: Generating Time Series from Texts 5
Verification Learning: Make Unsupervised Neuro-Symbolic System Feasible 5
VersaPRM: Multi-Domain Process Reward Model via Synthetic Reasoning Data 5
ViTally Consistent: Scaling Biological Representation Learning for Cell Microscopy 4
Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations 5
Video-Enhanced Offline Reinforcement Learning: A Model-Based Approach 4
VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models 4
VideoRoPE: What Makes for Good Video Rotary Position Embedding? 4
VinePPO: Refining Credit Assignment in RL Training of LLMs 5
Vintix: Action Model via In-Context Reinforcement Learning 5
Vision Graph Prompting via Semantic Low-Rank Decomposition 4
Vision-Language Model Selection and Reuse for Downstream Adaptation 5
Vision-Language Models Create Cross-Modal Task Representations 4
VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters 5
Visual Abstraction: A Plug-and-Play Approach for Text-Visual Retrieval 6
Visual Attention Never Fades: Selective Progressive Attention ReCalibration for Detailed Image Captioning in Multimodal Large Language Models 5
Visual Autoregressive Modeling for Image Super-Resolution 5
Visual Generation Without Guidance 6
Visual Graph Arena: Evaluating Visual Conceptualization of Vision and Multimodal Large Language Models 4
Visual and Domain Knowledge for Professional-level Graph-of-Thought Medical Reasoning 2
Volume Optimality in Conformal Prediction with Structured Prediction Sets 5
Volume-Aware Distance for Robust Similarity Learning 5
Voronoi-grid-based Pareto Front Learning and Its Application to Collaborative Federated Learning 7
Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning 6
WATCH: Adaptive Monitoring for AI Deployments via Weighted-Conformal Martingales 5
WAVE: Weighted Autoregressive Varying Gate for Time Series Forecasting 5
WGFormer: An SE(3)-Transformer Driven by Wasserstein Gradient Flows for Molecular Ground-State Conformation Prediction 5
WILTing Trees: Interpreting the Distance Between MPNN Embeddings 5
WMAdapter: Adding WaterMark Control to Latent Diffusion Models 5
WMarkGPT: Watermarked Image Understanding via Multimodal Large Language Models 5
WOMD-Reasoning: A Large-Scale Dataset for Interaction Reasoning in Driving 6
Wait-Less Offline Tuning and Re-solving for Online Decision Making 3
Wasserstein Flow Matching: Generative Modeling Over Families of Distributions 5
Wasserstein Policy Optimization 4
Watch Out Your Album! On the Inadvertent Privacy Memorization in Multi-Modal Large Language Models 4
WeGeFT: Weight-Generative Fine-Tuning for Multi-Faceted Efficient Adaptation of Large Models 5
Weak-to-Strong Generalization Even in Random Feature Networks, Provably 2
Weak-to-Strong Jailbreaking on Large Language Models 4
Weakly Supervised Anomaly Detection via Dual-Tailed Kernel 5
Weakly-Supervised Contrastive Learning for Imprecise Class Labels 5
Weight matrices compression based on PDB model in deep neural networks 6
Weisfeiler and Leman Go Gambling: Why Expressive Lottery Tickets Win 4
What Do Learning Dynamics Reveal About Generalization in LLM Mathematical Reasoning? 3
What Has a Foundation Model Found? Using Inductive Bias to Probe for World Models 4
What If We Recaption Billions of Web Images with LLaMA-3? 4
What Limits Bidirectional Model’s Generative Capabilities? A Uni-Bi-Directional Mixture-of-Expert Method For Bidirectional Fine-tuning 4
What Limits Virtual Agent Application? OmniBench: A Scalable Multi-Dimensional Benchmark for Essential Virtual Agent Capabilities 4
What Makes In-context Learning Effective for Mathematical Reasoning 6
What Makes a Good Feedforward Computational Graph? 3
What can large language models do for sustainable food? 4
What makes an Ensemble (Un) Interpretable? 1
When Bad Data Leads to Good Models 4
When Can Proxies Improve the Sample Complexity of Preference Learning? 2
When Data-Free Knowledge Distillation Meets Non-Transferable Teacher: Escaping Out-of-Distribution Trap is All You Need 5
When Diffusion Models Memorize: Inductive Biases in Probability Flow of Minimum-Norm Shallow Neural Nets 1
When Do LLMs Help With Node Classification? A Comprehensive Analysis 5
When Dynamic Data Selection Meets Data Augmentation: Achieving Enhanced Training Acceleration 4
When Every Millisecond Counts: Real-Time Anomaly Detection via the Multimodal Asynchronous Hybrid Network 4
When Maximum Entropy Misleads Policy Optimization 3
When Model Knowledge meets Diffusion Model: Diffusion-assisted Data-free Image Synthesis with Alignment of Domain and Class 5
When Will It Fail?: Anomaly to Prompt for Forecasting Future Anomalies in Time Series 4
When and How Does CLIP Enable Domain and Compositional Generalization? 6
When can in-context learning generalize out of task distribution? 3
When do neural networks learn world models? 3
When to Forget? Complexity Trade-offs in Machine Unlearning 4
When to retrain a machine learning model 4
When, Where and Why to Average Weights? 6
Where is the Truth? The Risk of Getting Confounded in a Continual World 5
Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems 4
Which Attention Heads Matter for In-Context Learning? 4
Whitened CLIP as a Likelihood Surrogate of Images and Captions 4
Whoever Started the interference Should End It: Guiding Data-Free Model Merging via Task Vectors 7
Why Has Predicting Downstream Capabilities of Frontier AI Models with Scale Remained Elusive? 4
Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas 4
Widening the Network Mitigates the Impact of Data Heterogeneity on FedAvg 4
WikiBigEdit: Understanding the Limits of Lifelong Knowledge Editing in LLMs 5
WildChat-50M: A Deep Dive Into the Role of Synthetic Data in Post-Training 4
Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale 3
Winner-takes-all for Multivariate Probabilistic Time Series Forecasting 5
Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement Learning 5
World Model Implanting for Test-time Adaptation of Embodied Agents 4
WorldSimBench: Towards Video Generation Models as World Simulators 4
Wrapped Gaussian on the manifold of Symmetric Positive Definite Matrices 5
Wyckoff Transformer: Generation of Symmetric Crystals 6
WyckoffDiff – A Generative Diffusion Model for Crystal Symmetry 6
X-Hacking: The Threat of Misguided AutoML 5
X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP 4
XAttention: Block Sparse Attention with Antidiagonal Scoring 5
XAttnMark: Learning Robust Audio Watermarking with Cross-Attention 3
You Always Recognize Me (YARM): Robust Texture Synthesis Against Multi-View Corruption 5
You Get What You Give: Reciprocally Fair Federated Learning 5
Zebra: In-Context Generative Pretraining for Solving Parametric PDEs 4
ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning 3
Zero Shot Generalization of Vision-Based RL Without Data Augmentation 4
Zero-Inflated Bandits 4
Zero-Shot Adaptation of Parameter-Efficient Fine-Tuning in Diffusion Models 3
Zero-Shot Cyclic Peptide Design via Composable Geometric Constraints 7
Zero-Shot Generalization of GNNs over Distinct Attribute Domains 6
Zero-Shot Offline Imitation Learning via Optimal Transport 5
Zero-shot Meta-learning for Tabular Prediction Tasks with Adversarially Pre-trained Transformer 5
ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think 4
ZipAR: Parallel Autoregressive Image Generation through Spatial Locality 3
am-ELO: A Stable Framework for Arena-based LLM Evaluation 4
any4: Learned 4-bit Numeric Representation for LLMs 7
e-GAI: e-value-based Generalized $α$-Investing for Online False Discovery Rate Control 6
iDPA: Instance Decoupled Prompt Attention for Incremental Medical Object Detection 4
iN2V: Bringing Transductive Node Embeddings to Inductive Graphs 4
polybasic Speculative Decoding Through a Theoretical Perspective 6
rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking 4
scSSL-Bench: Benchmarking Self-Supervised Learning for Single-Cell Data 4
sciLaMA: A Single-Cell Representation Learning Framework to Leverage Prior Knowledge from Large Language Models 5
unMORE: Unsupervised Multi-Object Segmentation via Center-Boundary Reasoning 4
video-SALMONN-o1: Reasoning-enhanced Audio-visual Large Language Model 4
xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference 5