ICML 2026 Accepted Papers

The full list of 6,634 papers accepted at ICML 2026 (International Conference on Machine Learning). Click any title for details, similar papers, and links to the original source. You can also search these papers by meaning, not just keywords.

Poster: 6,060Spotlight: 406Oral: 168

CoMem: Context Management with A Decoupled Long-Context ModelPoster
CoPE: A Framework for Optimizing Coordination between Planning and Execution in LLM-based AgentsPoster
CoPE: Continual Probe-guided Expansion for Large Vision-Language ModelsPoster
CoRe: Collaborative Reasoning via Cross TeachingPoster
CoRe: Combined Rewards with Vision-Language Model Feedback for Preference-Aligned Reinforcement LearningPoster
CoRe: Context-Robust Remasking for Diffusion Language ModelsPoster
CoT is Not the Chain of Truth: An Empirical Internal Analysis of Reasoning LLMs for Fake News GenerationPoster
Coarse-Grained Boltzmann GeneratorsPoster
CoarseBind: Fast and Accurate Binding Affinity Prediction through Coarse Structural RepresentationsPoster
CocoRNA: Collective RNA Design with Cooperative Multi-agent Reinforcement LearningPoster
Code2Video: A Code-centric Paradigm for Educational Video CreationPoster
Code2Worlds: Empowering Coding LLMs for 4D World GenerationPoster
CodeChemist: Test-Time Scaling for Low-Resource Code Generation via Functional Knowledge TransferPoster
CodeClash: Benchmarking Goal-Oriented Software EngineeringPoster
CodeMamba: Shifting from Target Semantics to Self-Supervised Background Manifold Learning for Singularity Detection in Infrared SequencesPoster
CodeTaste: Can LLMs Generate Human-Level Code Refactorings?Poster
Coevolutionary Continuous Discrete Diffusion: Make Your Diffusion Language Model a Latent ReasonerPoster
CofactGVR: Counterfactual Intervention for Grounded Visual ReasoningPoster
Cognitive Fatigue in Autoregressive Transformers: Formalization and MeasurementPoster
Cold-Start Personalization via Training-Free Priors from Structured World ModelsPoster
CollabBench: Benchmarking and Unleashing Collaborative Ability of LLMs with Diverse Players via Proactive EngagementPoster
Collaborative Disagreement Resolution for Scalable OversightPoster
Collaborative Learning for Semi-Supervised LiDAR Semantic SegmentationPoster
Collaborative Threshold WatermarkingPoster
Collaborative and Efficient Fine-tuning: Leveraging Task SimilarityPoster
Collaborative likelihood-ratio estimation over graphsPoster
Colorful Pinball: Density-Weighted Quantile Regression for Conditional Guarantee of Conformal PredictionPoster
Coloring the Noise: Adversarial Sobolev Alignment for Faithful Image Super ResolutionPoster
Column Thresholding for Sparse Spiked Wigner Models: Improved Signal Strength RequirementsPoster
CombinationTS: A Modular Framework for Understanding Time-Series Forecasting ModelsPoster
Combinatorial Sparse PCA Beyond the Spiked Identity ModelPoster
Commit to the Bit: Reactive Reinforcement Learning Done RightPoster
Comp-Attn: Present-and-Align Attention for Compositional Video GennerationPoster
Compact Conformal SubgraphsPoster
Comparing Deterministic and Soft Policy Gradients for Optimizing Gaussian Mixture ActorsPoster
Compass-RoPE: Isotropic Rotary Position Embeddings for Vision TransformersPoster
Compile to Compress: Boosting Formal Theorem Provers by Compiler OutputsPoster
CompleteP for RL: Maintaining Feature Learning When Scaling Deep Reinforcement LearningPoster
ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool SandboxPoster
Complexity bounds for Dirichlet process slice samplersPoster
Complexity of Decentralized Optimization with Mixed Affine ConstraintsPoster
Component-Wise Composite Likelihood Distillation for Censored Time-to-Event DataPoster
Compositional Behavioral Semantics and Metrics for State Abstraction in Reinforcement LearningPoster
Compositional Generative Modeling from Decentralized DataPoster
Compositional Perception and Generalizing Induction: Latent Compositional Manifold Assumption on Generalized Category DiscoveryPoster
Compositional Planning with Jumpy World ModelsPoster
Compositional Transduction with Latent Analogies for Offline Goal-Conditioned Reinforcement LearningPoster
Compress then Merge: From Multiple LoRAs into One Low-Rank AdapterPoster
Compressed Sensing for Capability Localization in Large Language ModelsPoster
Computational Arbitrage in AI Model MarketsPoster
Computationally-efficient Graph Modeling with Refined Graph Random FeaturesPoster
Compute When Worth It: Risk Control for Reasoning on a Compute BudgetPoster
Compute as Teacher: Turning Inference Compute Into Reference-Free SupervisionPoster
Computing Provable Bounds for Exact Shapley Values of Neural NetworksPoster
ConEx: Human-Interpretable Saliency Maps via Concept-Aware AttributionPoster
ConFlux: Multivariate Time Series in Flux, One Unified Forecast in ConfluenceOral
ConFu: Contemplate the Future for Better Speculative SamplingPoster
ConPress: Learning Efficient Reasoning from Multi-Question Contextual PressurePoster
ConServe: Fine-Grained GPU Harvesting for LLM Online and Offline Co-ServingPoster
ConTSG-Bench: A Unified Benchmark for Conditional Time Series GenerationPoster
Concept Concentration for Faithful Representation InterventionPoster
Concept Heterogeneity-aware Representation SteeringPoster
Concept Removal for Frontier Image Generative ModelsPoster
Concept-Guided Tokenization: Closing the Gap Between Reconstruction and GenerationPoster
ConceptMoE: Adaptive Token-to-Concept Compression for Implicit Compute AllocationPoster
Condition Number Based Low-Bit Quantization for Image Super-ResolutionPoster
Condition-Aware Graph Flow Matching for Modeling the Distributions of Complex Physical SystemsPoster
Conditional Clifford-Steerable CNNs for PDE ModelingPoster
Conditional Coverage Diagnostics for Conformal PredictionPoster
Conditional Diffusion SamplingPoster
Conditional Distributional Treatment Effects: Doubly Robust Estimation and TestingPoster
Conditional Equivalence of DPO and RLHF: Assumptions, Failure Modes, and Provable AlignmentSpotlight
Conditional KRR: Injecting Unpenalized Features into Kernel Methods with Applications to Kernel ThresholdingPoster
Conditional Quantile Adjusted Conformal Prediction for Time SeriesPoster
Conditionally Site-Independent Neural Evolution of Antibody SequencesPoster
Conf-Gen: Conformal Uncertainty Quantification for Generative ModelsPoster
Confidence and Difficulty-Adaptive Policy Optimization for LLM ReasoningPoster
Confidence is Not Universal: Task-Dependent Calibration and Emergent Behavior in LLMsPoster
Configurable Reward Model for Balanced Safety AlignmentPoster
Conflict-Aware Adaptive Alignment for LLM Hallucination MitigationPoster
Conflict-Aware Additive Guidance for Flow Models under Compositional RewardsPoster
Conflicting Biases at the Edge of Stability: Norm versus Sharpness RegularizationPoster
Conformal Calibration TransferPoster
Conformal Path Reasoning: Trustworthy Knowledge Graph Question Answering via Path-Level CalibrationPoster
Conformal Policy ControlSpotlight
Conformal Prediction for Early Stopping in Mixed Integer OptimizationPoster
Conformal Reliability: A New Evaluation Metric for Conditional GenerationPoster
Conformal Risk-Averse Decision Making with Action Conditional GuaranteePoster
Connecting Independently Trained Modes via Layer-Wise ConnectivityPoster
ConsMSA: Semantic Distribution Consistency Learning for Multimodal Sentiment AnalysisPoster
Conservation Laws for Modern Neural ArchitecturesSpotlight
Consistency Deep Equilibrium ModelsPoster
Consistency Training Is Not Neutral to AlignmentPoster
Consistent Diffusion Language ModelsPoster
Consistent Zero-Shot Imitation with Contrastive Goal InferencePoster
Constitutional Black-Box Monitoring for Scheming in LLM AgentsPoster
Constrained Adaptive Rejection SamplingPoster
Constrained Bayesian Experimental Design via Online PlanningPoster
Constrained Flow Optimization via Sequential Fine-Tuning for Molecular DesignPoster
Constrained Meta Reinforcement Learning with Provable Test-Time SafetyPoster
Constrained Multi-Objective Reinforcement Learning with Max-Min CriterionPoster
Constrained hybrid modelling to predict microbial dynamics and organic matter turnover in soil systemsPoster
Constructing Industrial-Scale Optimization Modeling BenchmarkPoster
Content-Style Identification via Differential IndependencePoster
Context Distillation Retains Post-Training Capabilities in Continually Trained LMsSpotlight
Context Forcing: Consistent Autoregressive Video Generation with Long ContextPoster
Context Tuning for In-Context OptimizationPoster
Context-Aware Reaonser : Enhancing Contextual Reasoning in Multimodal Large Language ModelsPoster
Context-Driven Incremental Compression for Multi-Turn Dialogue GenerationPoster
Context-free Recognition with TransformersPoster
Context-level Language Modeling by Learning Predictive Context EmbeddingsPoster
Contextual Rollout Bandits for Reinforcement Learning with Verifiable RewardsPoster
Contextual Slate GLM Bandits with Limited AdaptivityPoster
Contextualized Privacy Defense for LLM AgentsPoster
Contextualized Visual Personalization in Vision-Language ModelsPoster
Continual GUI AgentsPoster
Continual Learning With Participation Privacy: An Auditable Buffering-Aggregation RecipePoster
Continual Learning of Domain-Invariant RepresentationsPoster
Continual Learning through Control MinimizationPoster
Continual Model Routing in Evolving Model HubsPoster
Continual Segmentation under Joint NonstationarityPoster
Continuity-Regularized Flow Matching for Offline Reinforcement LearningPoster
Continuous Diffusion Models Can Obey Formal SyntaxPoster
Continuous Variable Hamiltonian Learning at Heisenberg Limit via Displacement-Random Unitary TransformationPoster
Continuous Viewpoint Adaptation for Single View 3D Object ReconstructionPoster
Continuous-Time Piecewise-Linear Recurrent Neural NetworksPoster
Contractive Anchor Resolvent Diffusion for Incomplete Multi-View ClusteringPoster
Contrastive Diffusion Alignment: Learning Structured Latents for Controllable GenerationPoster
Contrastive Flow Map MatchingPoster
Contrastive Geometric Learning Unlocks Unified Structure- and Ligand-Based Drug DesignPoster
Contrastive Order Learning: A General Framework for Ordinal RegressionPoster
Contrastive Reasoning Alignment: Reinforcement Learning from Hidden RepresentationsPoster
Contrastive Representation Regularization for Vision-Language-Action ModelsPoster
Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIPPoster
Contrastive Symbolic Regression: Aligned Representations, Adaptive Prediction, and Diverse EnsemblesPoster
Contrastive Weak-to-Strong GeneralizationPoster
ContrastiveCFG: Guiding Diffusion Sampling by Contrasting Positive and Negative ConceptsPoster
Contribution Weights: A Geometrical Analysis of Self-Attention TransformersPoster
Control Consistency Losses for Diffusion BridgesSpotlight
Controllable Molecule Generation via Sparse Representation Editing: An Interpretability-Driven PerspectivePoster
Controllable and explainable personality sliders for LLMs at inference timePoster
Controlled Collaboration Geometry for Personalized Federated LearningPoster
Controlled Dynamics Attractor TransformerPoster
Controlled LLM Training on Spectral SphereOral
Controlled SDEs for Long-Horizon Motion Generation under Latent Decision UncertaintyPoster
Controlling the Risk of Corrupted Contexts for Language Models via Early-ExitingPoster
Convergence Analysis of Decentralized Hessian-/Jacobian-Free Algorithm for Nonconvex Stochastic Bilevel OptimizationPoster
Convergence Analysis of the Lion Optimizer in Centralized and Distributed SettingsPoster
Convergence Rate Analysis of the AdamW-Style Shampoo: Unifying One-sided and Two-Sided PreconditioningPoster
Convergence Rate of the Last Iterate of Stochastic Proximal AlgorithmsPoster
Convergence of Two-Timescale Stochastic Approximation with Markovian Samples and Applications in Reinforcement LearningPoster
Convergent World Representations and Divergent TasksPoster
Conversation for Non-verifiable Learning: Self-Evolving Large Language Models through Meta-EvaluationPoster
Convex Basins in Single-Index Model Loss Landscapes: Applications to Robust Recovery under Strong Adversarial CorruptionPoster
Convex Dataset Valuation for Post-TrainingPoster
Convex Distance Operator Transport: Convex and Geometry-Preserving InformationPoster
Convex Low-resource Accent-Robust Language Detection in Speech RecognitionPoster
Convex Optimization for Alignment and Preference Learning on a Single GPUPoster
ConvexBench: Can LLMs Recognize Convex Functions?Poster
Convolutional Learnable-Group Weightless Neural NetworkPoster
CooT: Learning to Coordinate In-Context with Coordination TransformersPoster
CoopEval: Benchmarking Cooperation-Sustaining Mechanisms and LLM Agents in Social DilemmasPoster
Cooperative variance estimation and Bayesian neural networks disentangle aleatoric and epistemic uncertaintiesPoster
Coordinated Disentanglement with Iterative Mode Discovery Under Hidden CorrelationsPoster
Copula-SVI: Vine-Copula Variational Inference for Instance-Level Correlation CapturingPoster
Copyright-Bench: Agentic Evaluation of Copyright Law ComplianceSpotlight
CorrSteer: Generation-Time LLM Steering via Correlated Sparse Autoencoder FeaturesPoster
Correct looks better: Pairwise comparisons reveal accuracy rankingsPoster
Corrected Samplers for Discrete Flow ModelsPoster
Correcting Overparameterization Effects in Fair Empirical Risk MinimizationPoster
Correcting Split Selection in Online Decision Trees via Anytime-Valid InferenceSpotlight
Correcting Visual Blur Induced by Attention Distraction to Reduce Hallucinations: Algorithm and TheoryPoster
Correcting in Hindsight: Editing Past Key-Value States for Robust LLM ReasoningPoster
CorrectionPlanner: Self-Correction Planner with Reinforcement Learning in Autonomous DrivingPoster
Correctness-Optimized Residual Activation Lens (CORAL): Transferrable and Calibration-Aware Inference-Time SteeringPoster
Correspondence Cognitive Learning for Multi-Modal Object Re-IdentificationPoster
Corrigibility Transformation: Constructing Goals That Accept UpdatesPoster
Corruption-Tolerant Asynchronous Q-Learning with Near-Optimal RatesPoster
Cost-aware Stopping for Bayesian OptimizationPoster
Counterfactual Bootstrap for Robust Meta-Reinforcement LearningPoster
Counterfactual Occlusion-Aware Learning via Visibility Intervention for LiDAR Anomaly DetectionPoster
Counterfactual Residual Data Augmentation for RegressionPoster
CountsDiff: A diffusion model on the natural numbers for generation and imputation of count-based dataPoster
Coupled Cluster con MoLe: Molecular Orbital Learning for Neural WavefunctionsPoster
Coupled Training with Privileged Features and Unlabeled DataPoster
Coupled Trigger Optimization and Vulnerable Parameter Alignment for Persistent Backdoor Attacks on Federated LearningPoster
Coupled Variational Reinforcement Learning for Language Model General ReasoningPoster
Courtroom Analogy: New Perspective on Uncertainty-Aware ClassificationPoster
Covariance Volume Maximization for Embodied Latent Exploration in Deep Reinforcement LearningPoster
Covariance estimation using Markov chain Monte CarloPoster
CoverPruneGS: Coverage-Preserving Structured Pruning for Hierarchical 3D Gaussian Splatting from Sparse-View Monocular VideosPoster
Coverage Improvement and Fast Convergence of On-policy Preference LearningPoster
Coverage ≠ Exposure: Auditable Control of Same-Support Tail Failures under Multimodal MissingnessPoster
Coverage, Not Averages: Semantic Stratification for Trustworthy Retrieval EvaluationPoster
Cram Less to Fit More: Training Data Pruning Improves Memorization of FactsPoster
Creat3r: Confidence Reaggregation for Exploration-aware Active 3D ReconstructionPoster
Credibility-Aware Weighting Federated Causal Discovery for Time SeriesPoster
Credible Information Subset Decomposition: An End-to-End Multi-fidelity Learning Model by Modeling Label InformationPoster
Credit Assignment via Neural Manifold Noise CorrelationPoster
Credit-assigned Policy Gradient for Early Stage Retrieval in Two-stage RankingPoster
Crisp: A Spectral-Based Interaction Strategy for Multivariate Time Series ForecastingPoster
CrispEdit: Low-Curvature Projections for Scalable Non-Destructive LLM EditingPoster
Criterion-Conditional In-Context Learning: Evaluating Criterion-Shift Adaptation in Vision-Language ModelsPoster
Critique-Guided Distillation for Robust Reasoning via RefinementPoster
Cross-Chirality Generalization by Axial Vectors for Hetero-Chiral Protein-Peptide Interaction DesignPoster
Cross-Embodiment Robot Foundation World Models with Latent ActionsPoster
Cross-Modal Knowledge Distillation without Paired Data: Theoretical Foundations and AlgorithmsPoster
Cross-Modal Semantic Decoupling and Transfer for Text-to-Visible-Infrared Person Re-IdentificationPoster
Cross-Subject Modeling for Widefield Calcium Imaging via Atlas-Aligned Spatiotemporal TokenizationPoster
Cross-Tactile Sensor Representation LearningPoster
Cross-View Lewis Weight Fusion Empowering Exemplar Replay for Federated Class-Incremental LearningPoster
Cross-task Calibration for Asynchronous Federated Continual LearningPoster
CrossQ: Task-Aligned Cross-Token Conditional Quantization for Late Interaction RetrievalPoster
Crowd4D: Scene-Aware Monocular 4D Crowd ReconstructionPoster
CryoACE: An Atom-centric Framework for Accurate and Automated Model Building in Cryo-EMPoster
Curated Synthetic Data Doesn’t Have to Collapse: A Theoretical Study of Generative Retraining with Pluralistic PreferencesPoster
Curating the Future: A Scalable Recipe for Training Open-Ended ForecastersPoster
Cure-SFT: Diagnostic-Guided Data Curation for Instruction TuningPoster
Curriculum Reinforcement Learning for Black-Box Prompt Tuning via Large Language ModelsPoster
Curriculum-Guided Layer Scaling for Language Model PretrainingPoster
CurvZO: Adaptive Curvature-Guided Sparse Zeroth-Order Optimization for Efficient LLM Fine-TuningPoster
Cutting LLM Evaluation Costs with SySRs: A Bandit Algorithm that Provably Exploits Model SimilarityPoster
CyberCycle: Scalable Real-World Benchmark for AI Agents' End-to-End Cybersecurity CapabilitiesPoster
CyberJurors: A Multi-Agent Simulation Task for E-Commerce Disputes VerdictPoster
Cycle-of-Science: Reliable Reasoning through Counterfactual Verification for Agent Decision MakingPoster
D$^2$O: A Dual Debiasing Operator for Training-Free Test-Time Adaptation of Vision–Language ModelsPoster
D$^3$: Dynamic Directional Graph-Constrained Data Scheduling for LLM TrainingPoster
D-ARL: A Distribution-Matched Asynchronous Reinforcement Learning Framework for Language ReasoningPoster
D-CORE: Incentivizing Task Decomposition in Large Reasoning Models for Complex Tool UsePoster
D-FUSEr: Diverse Failure, Unified Success via Error-Distribution Shaping in LLM ReasoningPoster
DADP: Domain Adaptive Diffusion PolicyPoster
DAG-MoE: From Simple Mixture to Structural Aggregation in Mixture-of-ExpertsPoster
DAG: A Dual Correlation Network for Time Series Forecasting with Exogenous VariablesPoster
DAISI: Data Assimilation with Inverse Sampling using Stochastic InterpolantsPoster
DAL: A Practical Prior-Free Black-Box Framework for Piecewise Stationary BanditsPoster
DANCE: Dynamic, Available, Neighbor-gated Condensation for Federated Text-Attributed GraphsPoster
DARC: Disagreement-Aware Alignment via Risk-Constrained DecodingPoster
DART: Distribution-Aware Adaptive Relational Transfer for Adversarial Attacks against Closed-Source MLLMsPoster
DARTS: Distribution-Aware Active Rollout Trajectory Shaping for Accelerating LLM Reinforcement LearningPoster
DASH: Faster Shampoo via Batched Block Preconditioning and Efficient Inverse-Root SolversPoster
DAVE: Distribution-aware Attribution via ViT Gradient DecompositionSpotlight
DB-KSVD: Scalable Alternating Optimization for Disentangling High-Dimensional Embedding SpacesPoster
DC-LA: Difference-of-Convex Langevin AlgorithmPoster
DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping DecodingPoster
DC-W2S: Dual-Consensus Weak-to-Strong Training for Reliable Process Reward Modeling in Biological ReasoningPoster
DDGA: Dirichlet Distributional Gradient Aggregation for Transferable Vision-Language Adversarial AttacksPoster
DDIM Inversion as a Perturbation Amplifier: Breaking Mimicry Protection via Reconstruction Error MinimizationPoster
DDP-WM: Disentangled Dynamics Prediction for Efficient World ModelsPoster
DDSVM: A Differentiable Framework for Deep Support Vector Machines with Iterative Geometry-Aware OptimizationPoster
DECO: Decoupled Multimodal Diffusion Transformer for Bimanual Dexterous Manipulation with a Plugin Tactile AdapterPoster
DECOR: Learning to Decompose and Collaborate in Deep Search via Multi-Agent Reinforcement LearningPoster
DEER: A Benchmark for Evaluating Deep Research Agents on Expert Report GenerationPoster
DEGAP: Dynamic Entropy-Guided Attention Perturbation for Contrastive Decoding in Large Vision-Language ModelsPoster
DELTA4: Sparse Matrix-Vector Multiplication for Low SparsitySpotlight
DF-ExpEnse: Diffusion Filtered Exploration for Sample Efficient FinetuningPoster
DF-LoGiT: Data-Free Logic-Gated Backdoor Attacks in Vision TransformersPoster
DFSAttn: Dynamic Fine-grained Sparse Attention for Efficient Video GenerationPoster
DFlash: Block Diffusion for Flash Speculative DecodingPoster
DGG-HMR: Multi-Person Human Mesh Recovery with Depth-Guided Geometric AnchoringPoster
DGS-Net: Distillation-Guided Gradient Surgery for CLIP Fine-Tuning in AI-Generated Image DetectionSpotlight
DISCO: Mitigating Bias in Deep Learning with Conditional Distance CorrelationOral
DISSOLVR: An Interpretable and Fast Framework for Aqueous and Organic Solubility PredictionPoster
DITING: A Weak Degradation Listener for Battery Lifetime Early PredictionPoster
DITRON: Distributed Multi-level Tiling Compiler for Parallel Tensor ProgramsPoster
DIVA: Harnessing the Representation Divergence in Unified Multimodal Models for Mutual ReinforcementPoster
DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool UsePoster
DIVER: Diving Deeper into Distilled Data via Expressive Semantic RecoveryPoster
DIYHealth Suite: Dataset, Model, and Benchmark for Health Management at HomePoster
DLEBench: Evaluating Small-scale Object Editing Ability for Instruction-based Image Editing ModelPoster
DLLMQuant: A Post-Training Quantization Framework Tailored for Diffusion-Based Large Language ModelsPoster
DLM-Scope: Mechanistic Interpretability of Diffusion Language Models via Sparse AutoencodersPoster
DLM: Unified Decision Language Models for Offline Multi-Agent Sequential Decision MakingSpotlight
DLO-Lab: Benchmarking Deformable Linear Object Manipulations with Differentiable PhysicsPoster
DMCO: Budget-Aware Co-Optimization of Data Cleaning and AutoMLPoster
DNA: Uncovering Universal Latent Forgery KnowledgePoster
DNACHUNKER: Learnable Tokenization for DNA Language ModelsPoster
DOCKSMITH: Scaling Reliable Coding Environments via an Agentic Docker BuilderPoster
DOT-MoE: Differentiable Optimal Transport for MoEficationPoster
DOUBT: Decoupled Object-level Understanding and Bridging via vMF-based Trustworthiness for Hallucination Detection in MLLMsOral
DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep LearningPoster
DPO Unchained: Your Training Algorithm is Secretly Disentangled in Human Choice Theory (and Its Loss' Convexity is Dispensable)Oral
DPsurv: Dual-Prototype Evidential Fusion for Uncertainty-Aware and Interpretable Whole Slide Image Survival PredictionPoster
DR$^2$Seg: Decomposed Two-Stage Rollouts for Efficient Reasoning Segmentation in Multimodal Large Language ModelsPoster
DR-MMSearchAgent: Deepening Reasoning in Multimodal Search AgentsPoster
DREAM-R: Multimodal Speculative Reasoning with RL-Based Refined Drafting, Precise Verification, and Fully Parallel ExecutionPoster
DREAM: A Unified Framework for Drift-Corrected Federated Multi-Objective LearningPoster
DREAM: Dual-Standard Semantic Homogeneity with Dynamic Optimization for Graph Learning with Label NoisePoster
DRFusion: Drift-Resilient Temporally Consistent Infrared–Visible Video FusionPoster
DRIFT-BENCH: Diagnosing CoopeRative Breakdowns in LLM Agents under Input Faults via Multi-Turn InteractionPoster
DRIFT: Decoupled Rollouts and Importance-Weighted Fine-Tuning for Efficient Multi-Turn OptimizationPoster
DRIVE: Best Data Scheduling Practices for Reinforcement Learning with Verifiable Reward in Competitive Code GenerationPoster
DRIVE: Distributional and Retrieval-Augmented Bidding with Value EvaluationPoster
DRL-STAF: A DRL Framework for State-aware Forecasting of Complex Multivariate Hidden Markov ProcessPoster
DRPBench: Evaluating LLMs in Concurrent Code Comprehension via Fine-grained Data Race PredictionSpotlight
DSB: Dynamic Sliding Block Scheduling for Diffusion LLMsPoster
DSENet: A Novel Dual-Stream Enhancement Network for Multi-Scale Non-Stationary Time Series ForecastingPoster
DSGCR: Decomposed Spectral Geometry-Aware Cross-Modal Semantic Representation for 3D Visual GroundingPoster
DSGym: A Standardized and Holistic Framework for Advancing Data Science AgentsPoster
DTKG: Dual-Track Knowledge Graph-Verified Reasoning Framework for Multi-Hop QAPoster
DTS: Enhancing Large Reasoning Models via Decoding Tree SketchingPoster
DTop-p MoE: Sparsity-Controlled Dynamic Top-p MoE for Foundation Model Pre-trainingPoster
DV-World: Benchmarking Data Visualization Agents in Real-World ScenariosPoster
Darwinian Memory: A Training-Free Self-Regulating Memory System for GUI Agent EvolutionPoster
Data Agent: Learning to Select Data via End-to-End Dynamic OptimizationPoster
Data Augmentation of Contrastive Learning is Estimating Positive-incentive NoisePoster
Data Difficulty and the Generalization–Extrapolation Tradeoff in LLM Fine-TuningPoster
Data Provenance Auditing of Fine-Tuned Large Language Models with a Text-Preserving TechniquePoster
Data Reconstruction: Identifiability and Optimization with Sample SplittingPoster
Data Selection for Fine-tuning Vision Language Models via Cross Modal Alignment TrajectoriesPoster
Data- and Variance-dependent Regret Bounds for Online Tabular MDPsPoster
Data-Source Adaptive Online Learning under Heteroscedastic NoisePoster
Data-driven Mixed Integer Optimization through Probabilistic Multi-variable BranchingPoster
DataGuard: A Non-intrusive Dataset Auditing Framework via Differential Information ForensicsPoster
Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear TasksPoster
De-Linearizing Agent Traces: Bayesian Inference of Latent Partial Orders for Efficient ExecutionPoster
De-attribute to Forget for LLM UnlearningPoster
De4D-SLAM: Gradient-Isolated Static-Dynamic Decoupling for Monocular SLAM in Dynamic EnvironmentsPoster
DeCoDe: Decoupling Binding Position and Molecular Conformation in 3D Ligand Diffusion for Structure-Based Drug DesignSpotlight
DeFacto: Counterfactual Thinking with Images for Enforcing Evidence-Grounded and Faithful ReasoningPoster
Debate with Images: Detecting Deceptive Behaviors in Multimodal Large Language ModelsPoster
Debate2Create: Robot Co-design via Multi-Agent LLM DebatePoster
Debiased Model-based Representations for Sample-efficient Continuous ControlPoster
DecAEvolve: Decompose, Adapt, and Evolve, or, Three Pillars of Effective LLM-based Scientific Equation DiscoveryPoster
DecFus: Decentralized Layer-wise Fusion with Dynamic Exploration and ExploitationPoster
Decentralized Bandits without Global Clock for Dynamic Matching MarketPoster
Decentralized Instruction Tuning: Conflict-Aware Splitting and Weight MergingPoster
Decentralized Online Convex Optimization with Efficient Communication: Improved Algorithm and Lower BoundsPoster
Decentralized and Disentangled Task–Role Representation Learning for Generalizable Offline Multi-Agent Meta Reinforcement LearningPoster
DecepChain: Inducing Deceptive Reasoning in Large Language ModelsPoster
Decision Transformers As Zero-Shot Learners via Text-Behavior AlignmentSpotlight
Decision Tree Learning on Product SpacesPoster
Decision-Focused Learning via Tangent-Space Projection of Prediction ErrorPoster
Decision-focused Sparse Tangent Portfolio OptimizationPoster
DecoVer: A Decompose-and-Verify Neuro-Symbolic Framework for Embodied Task Planning with BC+Poster
DecodeShare: Tracing the Shared Pathways of LLM Decode-Time DecisionsSpotlight
DecoderTCR: Compositional Pretraining and Entropy-Guided Decoding for TCR-pMHC InteractionsPoster
Decoding Safety Feedback from Diverse Raters: A Data-driven Lens on Responsiveness to SeverityPoster
DecomPose: Disentangling Cross-Category Optimization Contention for Category-Level 6D Object Pose EstimationPoster
Decompose and Recompose: Reasoning New Skills from Existing Abilities for Cross-Task Robotic ManipulationPoster
Decompose, Structure, and Repair: A Neuro-Symbolic Framework for Autoformalization via Operator TreesPoster
Decomposed On-Policy Distillation for Vision-Language Reasoning: Steering Gradients for Visual GroundingSpotlight
Decomposing Out-of-Distribution Error in Conditional Flow Matching via Wasserstein GeometryPoster
Decomposing Query-Key Feature Interactions Using Contrastive CovariancesPoster
Decomposing the Basic Abilities of Large Language Models: Mitigating Cross-Task Interference in Multi-Task Instruct-TuningPoster
Decomposition-Based Modular Conformal Prediction for Two-Stage ModelingPoster
Decouple Searching from Training: Scaling Data Mixing via Model Merging for Large Language Model Pre-trainingPoster
Decouple and Cache: KV Cache Construction for Streaming Video UnderstandingPoster
Decoupled Low-Rank Adaptation for Robust Federated Fine-TuningPoster
Decoupled Training with Local Reinforcement Fine-Tuning in Federated LearningPoster
Decoupling Reasoning and Confidence: Resurrecting Calibration in Reinforcement Learning from Verifiable RewardsPoster
Decoupling Regularization and Privacy in Differentially Private Ridge Regression and ERMPoster
Decoupling Skeleton and Flesh: Efficient Multimodal Table Reasoning with Disentangled Alignment and Structure-aware GuidanceSpotlight
Decoupling The "What" and "Where" With Polar Coordinate Positional EmbeddingSpotlight
Decoupling Universal Laws and Environmental Heterogeneity: A Physics-Inspired Framework for Robust Spatio-Temporal ForecastingPoster
Decoupling Variance and Scale-Invariant Updates in Adaptive Gradient Descent for Unified Vector and Matrix OptimizationPoster
Decoy for the Judge: Disrupting Multi-Turn Jailbreaks using Semantics-Preserving Output RewritingPoster
Deep Coupling Learning for Solving PDEsPoster
Deep Discriminative Structure Proxy Hashing for Cross-modal RetrievalPoster
Deep Ensemble Clustering for Visual Representation LearningPoster
Deep Flow NetworksSpotlight
Deep Forcing: Training-Free Long Video Generation with Deep Sink and Participative CompressionPoster
Deep Incentive Design with Differentiable Equilibrium BlocksPoster
Deep Learning for Bioimaging: What are we actually learning?Poster
Deep Multi-view Graph Clustering via Attribute-aware Bidirectional Structural Refinement and Pseudo-label Guided Multi-level FusionPoster
Deep Networks Learn Deep Hierarchical ModelsPoster
Deep Neural Network Regression with Functional CovariatesPoster
Deep Pre-Alignment for VLMsPoster
Deep Progressive Training: scaling up depth capacity of zero/one-layer modelsPoster
Deep Reinforcement Learning Finds Bayes-Nash Equilibrium in Competitive Newsvendor ProblemsPoster
Deep Residual Injection for Full-Spectrum Forensic Signal Perception in Multimodal Large Language ModelsPoster
Deep Scientific Reasoning under Physical Constraints: Structure-Aware Spectrum Prediction for Electronic Density of StatesPoster
Deep Single-Index Fréchet RegressionPoster
Deep Trajectory Supervision: Deep Supervision Strikes BackPoster
Deep networks learn to parse uniform-depth context-free languages from local statisticsPoster
Deep neural networks divide and conquer dihedral multiplicationPoster
Deep sequence models tend to memorize geometrically; it is unclear why.Poster
DeepAnalyze: Agentic Large Language Models for Autonomous Data SciencePoster
DeepBlip: Estimating Conditional Average Treatment Effects Over TimePoster
DeepHA: Scaling Action Chains Elicits Deep Hierarchical AgentsPoster
DeepImageSearch: Benchmarking Multimodal Agents for Context-Aware Image Retrieval in Visual HistoriesPoster
DeepSight: Long-Horizon World Modeling via Latent States Prediction for End-to-End Autonomous DrivingPoster
Deformba: Vision State Space Model with Adaptive State FusionPoster
Degradation-Aware Metric Prompting for Hyperspectral Image RestorationPoster
Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial ParticipationPoster
Delegation and Verification under AIPoster
Deliberate Evolution for Sample-Efficient Symbolic Regression with LLMPoster
DeltaEvolve: Accelerating Scientific Discovery through Momentum-Driven EvolutionPoster
Delving into Muon and Beyond: Deep Analysis and ExtensionsSpotlight
Delving into Non-Exchangeability for Conformal Prediction in Graph-Structured Multivariate Time SeriesPoster
Demystifying Action Space Design for Robotic Manipulation PoliciesPoster
Demystifying Entropy Control in LLM RL Training: Theoretical Analysis and Dynamic SchedulingSpotlight
Demystifying LLM-as-a-Judge: Analytically Tractable Model for Inference-Time ScalingPoster
Demystifying MaskGIT Sampler and Beyond: Adaptive Order Selection in Masked DiffusionPoster
Demystifying Mergeability: Interpretable Properties to Predict Model Merging SuccessPoster
Demystifying Multimodal Biomolecular Co-design With Intrinsic Geodesic CouplingPoster
Demystifying Scientific Problem-Solving in LLMs by Probing Knowledge and ReasoningPoster
Demystifying When Pruning Works via Representation HierarchiesPoster
Demystifying the Optimal Fair Classifier in Multi-Class ClassificationPoster
Denoising without Diffusion: Fixed-Noise Denoiser Anomaly Detection in Tabular DataPoster
Dense associative memory for Gaussian distributionsPoster
DenseMLLM: Standard Multimodal LLMs are Intrinsic Dense PredictorsPoster
DenseSteer: Steering Small Language Models towards Dense Math ReasoningPoster
Density-Aware Translation of Spurious Correlations in Zero-Shot VLMsPoster
Density-Guided Continuous Flow for Robust Counterfactual ExplanationsPoster
Dependence-Aware Label Aggregation for LLM-as-a-Judge via Ising ModelsPoster
Dependency-Aware Parallel Decoding via Attention for Diffusion LLMsPoster
Depth over Fidelity in Fixed-Budget Noisy Evolution StrategiesPoster
Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive ExplorationPoster
Depth-Progressive Monotonic Learning without BackpropagationPoster
Derivative Informed Learning of Exchange-Correlation FunctionalsPoster
Deriving Neural Scaling Laws from the Statistics of Natural LanguagePoster
Design Linear Constrained Neural Layers with Implicit Convex OptimizationPoster
Designing Observation and Action Models for Efficient Reinforcement Learning with LLMsPoster
Designing a Conditional Prior Distribution for Flow-Based Generative ModelsPoster
Designing noise schedules for diffusion models with spectral analysisPoster
Desirable Effort Fairness and Optimality Trade-offs in Strategic LearningPoster
Detached Skip-Links and $R$-Probe: Decoupling Feature Aggregation from Gradient Propagation for MLLM OCRPoster
DetailMaster: Can Your Text-to-Image Model Handle Long Prompts?Poster
Detecting Contextual Hallucinations in Large Language Models with Frequency-Aware AttentionPoster
Detecting Errors in AI-Generated Annotations: When and Why Semantic Neighbors HelpPoster
Detecting Fluent Optimization Based Adversarial Prompts via Sequential Entropy ChangesPoster
Detecting Perspective Shifts in Multi-Agent SystemsPoster
Detecting and Filtering Unsafe Training Data via Data Attribution with Denoised RepresentationPoster
Detecting the Semantic Fixed Point: A Geometric Framework for Efficient InferenceOral
Deterministic Component Mining for Multi-framework UI2Code GenerationPoster
Deterministic Differentiable Structured Pruning for Large Language ModelsPoster
Deterministic Inference across Tensor Parallel Sizes That Eliminates Training-Inference MismatchPoster
DevEvol: Benchmarking LLM Agents on Continuous Software EvolutionPoster
DexMachina: Functional Retargeting for Bimanual Dexterous ManipulationPoster
Di-BiLPS: Denoising induced Bidirectional Latent-PDE-Solver under Sparse ObservationsPoster
DiL: Discrete-anchored Representation Alignment for Semi-Supervised Continual LearningPoster
DiLA: Disentangled Latent Action World ModelsPoster
DiP-G: Discrete Prompting for Graph Neural NetworksPoster
DiScoFormer: Plug-In Density and Score Estimation with TransformersOral
Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence AttributionPoster
Diagnosing and Correcting Concept Omission in Multimodal Diffusion TransformersPoster
Diagnosing the Reliability of LLM-as-a-Judge via Item Response TheoryPoster
Diamond Maps: Efficient Reward Alignment via Stochastic Flow MapsPoster
DiasR: Dual-Modal Identity-Anchored Sparse Routing for Efficient Multi-Subject Video GenerationPoster
Dichotomy of Feature Learning and Unlearning: Fast-Slow Analysis on Neural Networks with Stochastic Gradient DescentPoster
Didactic to Constructive: Turning Expert Solutions into Learnable ReasoningPoster
DiffCrossGait: Trajectory-Level Alignment for 2D-3D Cross-Modal Gait Recognition via Latent DiffusionPoster
DiffStyle3D: Consistent 3D Gaussian Stylization via Attention OptimizationPoster
DiffThinker: Towards Generative Multimodal Reasoning with Diffusion ModelsPoster
Diffeomorphism-Equivariant Neural NetworksPoster
Difference-Aware Decision Learning for Multimodal Image FusionPoster
Different Usage of Shared Components Explains Behavioral Variance in LLMsPoster
Differentiable Conformal Training for LLM Reasoning FactualityPoster
Differentiable Optimization Layers for Guaranteed Fairness in Deep LearningPoster
Differentiable Weightless Controllers: Learning Logic Circuits for Continuous ControlPoster
Differential Smoothing Mitigates Sharpening and Improves LLM ReasoningPoster
Differential syntactic and semantic encoding in LLMsPoster
Differentially Private Continual Release with Relative ErrorPoster
Differentially Private Cross-Silo Recommendation from Implicit FeedbackPoster
Differentially Private Geodesic RegressionPoster
Differentially Private Preference Data Synthesis for Large Language Model AlignmentPoster
Differentially Private Range Subgraph CountingPoster
Differentially Private Submodular Maximization with a Knapsack ConstraintPoster
Differentially Private Synthetic Tabular Data via Private EvolutionPoster
Differentially Private and Scalable Estimation of the Network Principal ComponentPoster
Diffract: Spectral View of LLM Domain AdaptationOral
DiffuMamba: High-Throughput Diffusion LMs with Mamba BackbonePoster
DiffuReason: Enhancing Reasoning Ability for Diffusion Language Models via Monte Carlo Tree SearchPoster
Diffuse to Detect: Bi-Level Sample Rebalancing with Pseudo-Label Diffusion for Point-Supervised Infrared Small-Target DetectionSpotlight
Diffusing to Coordinate: Efficient Online Multi-Agent Diffusion PoliciesPoster
Diffusion Bridge or Flow Matching? A Unifying Framework and Comparative AnalysisPoster
Diffusion Flow Matching: Dimension-Improved KL Bounds and Wasserstein GuaranteesSpotlight
Diffusion Language Model Parallel Decoding via Product-of-Experts BridgePoster
Diffusion Models Preferentially Memorize Prototypical Examples or: Why Does My Diffusion Model Love Slop?Poster
Diffusion differentiable resamplingPoster
Diffusion posterior sampling for simulation-based inference in tall data settingsPoster
Diffusion-based learning framework for Constrained Nonconvex Optimization with Weighted Bootstrapped RefinementPoster
Dimension-Free Multimodal Sampling via Preconditioned Annealed Langevin DynamicsPoster
Dimension-Independent Convergence of Underdamped Langevin Monte Carlo in KL DivergencePoster
Dimension-free convergence of diffusion models for approximate Gaussian mixturesPoster
Dimensional Collapse in Transformer Attention Outputs: A Challenge for Sparse Dictionary LearningPoster
Dimensionality Reduction with Point-distributions Similarity InvariantPoster
Direct 3D-Aware Object Insertion via Decomposed Visual ProxiesPoster
Direct Flow Q-LearningPoster
DirectEdit: Step-Level Accurate Inversion for Flow-Based Image EditingPoster
Directional Neural Collapse for Self-Supervised Visual Representation LearningPoster
Directly Optimizing Natural Language Explanations for Behavioral Faithfulness: Simulatability and RecoverabilityPoster
Dirichlet-Prior Shaping: Guiding Expert Specialization in Upcycled MoEsPoster
DisPOSE: Projected Polystochastic Diffusion for Self-Supervised Multi-View 3D Human Pose EstimationPoster
DisPPO: Quantile-Based Distributional Reinforcement Learning for Large Language ModelsPoster
DiscoForcing: A Unified Framework for Real-Time Audio-Driven Character Control with Diffusion ForcingPoster
Discontinuous Galerkin Neural Operator for Pathology Defocus DeblurringPoster
Discounted Beta-Bernoulli Reward Estimation for Sample-Efficient Reinforcement Learning with Verifiable RewardsPoster
DiscoverLLM: From Executing Intents to Discovering ThemPoster
Discovering Differences in Strategic Behavior between Humans and LLMsPoster
Discovering Implicit Large Language Model Alignment ObjectivesPoster
Discovering Interpretable Algorithms by Decompiling Transformers to RASPPoster
Discovering Ordinary Differential Equations with LLM-Based Qualitative and Quantitative EvaluationPoster
Discovering Scaling Exponents with Physics-Informed Müntz-Szász NetworksPoster
Discovering Symmetry Groups with Flow MatchingPoster
Discrete Adjoint Schrödinger Bridge SamplerPoster
Discrete Diffusion Samplers and Bridges: Off-Policy Algorithms and Applications in Latent SpacesPoster
Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action PoliciesPoster
Discrete Diffusion with Physical Mass Constraints for \emph{De Novo} Peptide SequencingPoster
Discrete Survival Knowledge Distillation for Competing Risks AnalysisPoster
Discrete Tilt MatchingPoster
Discretely-Refined Multi-view Clustering via Aligned Anchor LearningPoster
Discretized Density-Guided Source-Free Adaptation for Continuous TargetsSpotlight
Discriminative Attribute Graph Clustering Through Topology-Guided Contrastive LearningPoster
Discriminative Mixture-of-Experts on Graphs with Reliable Expert FusionPoster
Discriminative Visual Process Rewards for Scaling Thinking at Test-Time with ImagesPoster
Disease-Centric Vision-Language Pretraining with Hybrid Visual Encoding for 3D Computed TomographyPoster
Disentangling Consensus and Value-Specific Representations for Controllable Pluralistic Value Alignment of LLMsPoster
Disentangling Geometry, Performance, and Training in Language ModelsSpotlight
Disentangling Intent from Role: Adversarial Self-Play for Persona-Invariant Safety AlignmentPoster
Disentangling Latent Risk Pathways via Bayesian Hypergraph InferenceOral
Disentangling a Large Language Model’s Computation from its Chain-of-ThoughtPoster
Disentangling meaning from language in LLM-based machine translationPoster
DisjunctiveNet: Neural Symbolic Learning via Differentiable Convexified Optimization LayersPoster
Dismantling Pathological Shortcuts: A Causal Framework for Faithful LVLM DecodingPoster
Dismantling the Illusion of Vision-Language-Action Models Competence via Explicit Distributional ShiftsPoster
Dispersion Loss Counteracts Embedding Condensation and Improves Generalization in Small Language ModelsPoster
Dissect and Prune: Enhancing Robustness in AI-Generated Image DetectionPoster
Dissecting Causal Mechanism Shifts via FANS: Function And Noise SeparationPoster
Dissecting Embodied Abilities in Multimodal Language Models through Skill-level Evaluation and DiagnosisPoster
Dissecting Multimodal In-Context Learning: Modality Asymmetries and Circuit Dynamics in modern TransformersSpotlight
Dissecting Post-Training: Uncovering the Complementary Roles of SFT and RL for Document ParsingPoster
Dissecting Quantization Error: A Concentration-Alignment PerspectivePoster
Dissecting the Safety Circuit: Neuronal Intervention for Transferable Adversarial Attacks on VLMsPoster
DistFlow: A Fully Distributed RL Framework for Scalable and Efficient LLM Post-TrainingPoster
DistMatch: Adaptive Binning via Distribution Matching for Robust Sequential Conformal PredictionPoster
Distillation Models are Good Samplers for Diffusion Reinforcement LearningPoster
Distilling Geometry Priors for 3D-Consistent Video GenerationPoster
Distilling Linearized Behavior into Non-linear Fine-Tuning for Effective Task ArithmeticPoster
Distilling Neuro-Symbolic Programs into 3D Multi-modal LLMsPoster
Distilling Task-Level Coordination Policies for Generalizable Multi-Agent CooperationPoster
Distinguishable Deletion: Unifying Knowledge Erasure and Refusal for Large Language Model UnlearningPoster
Distinguishing Imitation Error from Intrinsic Motion Learning DifficultyPoster
Distortion of AI Alignment Revisited: RLHF is a Decent Utilitarian AlignerPoster
Distributed Direct Preference OptimizationPoster
Distributed Stochastic $K$-Level Optimization Over NetworksPoster
Distribution Alignment for One-Shot Federated Learning via Optimal TransportPoster
Distribution Matching Variational AutoEncoderPoster
Distribution Transformers: Fast Approximate Bayesian Inference With On-The-Fly Prior AdaptationSpotlight
Distribution-Calibrated Inference Time Compute for Thinking LLM-as-a-JudgePoster
Distributional Active InferencePoster
Distributional Alignment Games for Answer-Level Fine-TuningPoster
Distributional Inverse Reinforcement LearningOral
Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value CodebookPoster
Distributionally Robust Causal AbstractionsPoster
Distributionally Robust Markov Games with Average RewardPoster
Distributionally Robust Reinforcement Learning with Human FeedbackPoster
Distributionally Robust Set Representation Learning Under Inference-Time Element CorruptionPoster
Dive into the Scene: Breaking the Perceptual Bottleneck in Vision-Language Decision Making via Focus Plan GenerationPoster
Divergence Decoding: Targeted Unlearning via Auxiliary ModelsPoster
Diversity Matters: Revisiting Test-Time Compute in Vision-Language ModelsPoster
Diversity Over Frequency: Rethinking Tool Use in Visual Chain-of-Thought AgentsPoster
Diversity-Aware Recursive Feature Multiple Kernel LearningPoster
Diversity-Driven Offline Multi-Objective Optimization via Bi-Level Pareto Set LearningPoster
Diversity-Preserved Distribution Matching Distillation for Fast Visual SynthesisPoster
Diversity-aware Weight Perturbation Promotes Robust AdaptationPoster
Divide and Conquer: Reliable Multi-View Evidential Learning for Deepfake DetectionPoster
Divide and Contrast: Learning Robust Temporal Features without AugmentationPoster
Divide and Learn: Multi-Objective Combinatorial Optimization at ScalePoster
Divide-and-Denoise: A Game-Theoretic Method for Fairly Composing Diffusion ModelsSpotlight
Diving into Kronecker Adapters: Component Design MattersPoster
Divisiveness-Consistent Label Distribution LearningPoster
Do Audio LLMs Listen or Read? Analyzing and Mitigating Paralinguistic Failures with VoxParadoxPoster
Do LLMs Signal When They’re Right? Evidence from Neuron AgreementSpotlight
Do LLMs “Feel”? Emotion Circuits Discovery and ControlPoster
Do Language Models Track Entities Across State Changes?Poster
Do Natural Language Interpretability Methods Convey Privileged Information?Poster
Do Neural Operators Forget Geometry? The Forgetting Hypothesis in Deep Operator LearningPoster
Do Text Edits Generalize to Visual Generation? Benchmarking Cross-Modal Knowledge Editing in UMMsPoster
Do Transformers Need Three Projections? Systematic Study of QKV VariantsPoster
Do Vision and Text Cues Exhibit Evidential Coupling? UFO: A Benchmark for Compositional Multimodal Reasoning in Unified ModelsPoster
Do We Need Adam? Surprisingly Strong and Sparse Reinforcement Learning with SGD in LLMsOral
Do You Want to Know if Two Distributions Are Close to Each Other?Testing the Closeness With Statistical SignificancePoster
Do-Prompt: Causal Interventions Meet Variational Prompt BottlenecksPoster
Doc-to-LoRA: Learning to Instantly Internalize ContextsPoster
DocHop: Benchmarking Out-of-domain Multi-hop Reasoning in Information-Dense DocumentsPoster
DocOS: A Benchmark for Proactive Document-Guided Actions in GUI AgentsPoster
DocVAL: Validated Chain-of-Thought Distillation for Grounded Document VQAPoster
Does AI Reviewer See the Full Picture? Attacking and Defending Multimodal Peer ReviewPoster
Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM ReasoningPoster
Does Reasoning Improve Seeing? Understanding When Vision-Language Models Benefit from ThinkingPoster
Does Reinforcement Fine-Tuning Improve Generalization of LLM Agents? An Empirical StudyPoster
Does Your Reasoning Model Implicitly Know When to Stop Thinking?Poster
Does a Hybrid Space-Aware Randomized Defense Improve Empirical and Certified Adversarial Robustness?Poster
DomED: Redesigning Ensemble Distillation for Domain GeneralizationPoster
Domain Adaptation with Adaptive $f$-Divergence: Tighter Variational Representation and Generalization BoundsPoster
Domain Adaptive Object Detection via Dynamic Causal RefinementPoster
Domain Restriction via SAE Multi-Layer TransitionsPoster
Domain Transfer Becomes Identifiable via a Single AlignmentPoster
Domain-Shift-Aware Conformal Prediction for Large Language ModelsPoster
Don't Drop Dropout: Optimizing Layer Sparsity for Efficient LLM Training and InferencePoster
Don't Force the Fit: Bounded Log-Likelihood Loss for Enhanced Reasoning in Large Language ModelsOral
Don't Forget Why You Started: Tackling Dual Forgetting in Vision-Language Continual LearningPoster
Don't Ignore the Tail: Decoupling top-K Probabilities for Efficient Language Model DistillationPoster
Don't Overthink with Pixels: Efficient Reasoning for SegmentationPoster
Don't Reinvent the Wheel, Just Realign the Spokes: Resource-Efficient Federated Fine-Tuning via Rank-Wise Expert AssemblySpotlight
Don't Walk the Line: Boundary Guidance for Filtered GenerationPoster
Doppler Prompting for Stable mmWave-based Human Pose EstimationPoster
Doubly Outlier-Robust Online Infinite Hidden Markov ModelPoster
Doubly Regularized Markov Decision Processes for Robust Reinforcement LearningPoster
Doubly Robust Distributionally Robust Offline Contextual PricingPoster
Dr. Kernel: Reinforcement Learning Done Right for Triton Kernel GenerationsPoster
Draft-Conditioned Constrained Decoding for Structured Generation in LLMsPoster
Draft-and-Audit Reinforcement Learning for Optimization ModelingPoster
Dream-MPC: Gradient-Based Model Predictive Control with Latent ImaginationPoster
DreamDojo: A Real-Time Robot World Model from Large-Scale Human VideosSpotlight
DreamID-Omni: Unified Framework for Controllable Human-Centric Audio-Video GenerationPoster
Dreaming in Code for Curriculum Learning in Open-Ended WorldsPoster
Drift is a Sampling Error: SNR-Aware Power Distributions for Long-Horizon Robotic PlanningPoster
DriveWorld-VLA: Unified Latent-Space World Modeling with Vision–Language–Action for Autonomous DrivingPoster
DroneDINO: Towards Heterogeneous Routed Mixture of Experts for Drone-based Unified Object DetectionOral
Drop-in Circulant Structural Priors for Transformer Decoding of Cyclic CodesPoster
Dropout Universality: Scaling Laws and Optimal Scheduling at the Edge-of-ChaosPoster
DropoutTS: Sample-Adaptive Dropout for Robust Time Series ForecastingPoster
DuFal: Dual-Frequency-Aware Learning for High-Fidelity Extremely Sparse-view CBCT ReconstructionPoster
DuRP: Dual-Stage Physics-Embedded Learning for Joint Radiance and Polarization RestorationPoster
Dual Latent Memory for Visual Multi-agent SystemPoster
Dual Mechanisms of Value Expression: Intrinsic vs. Prompted Values in Large Language ModelsPoster
Dual Optimal Transport for Multi-Concept Composition: Structural Alignment and Texture Injection in Diffusion ModelsPoster
Dual Quaternion SE(3) Synchronization with Recovery GuaranteesPoster
Dual-Calibration Multi-View Clustering via Compact Anchor LearningPoster
Dual-Latent Memory Routing for Vision-Language ReasoningSpotlight
Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action ModelPoster
Dual-View Predictive Diffusion: Lightweight Speech Enhancement via Spectrogram-Image SynergyPoster
Dual-branch Robust Unlearnable ExamplesPoster
Dual-channel Dynamic Graph Neural Networks with Adaptive Adjacency Learning and Multi-scale Representation FusionPoster
Dual-stage Contrastive Learning-enhanced Multi-view Variational ClusteringPoster
DualCOIL: Offline Imitation Learning from Contrasting DemonstrationsPoster
DualOptim+: Bridging Shared and Decoupled Optimizer States for Better Machine Unlearning in Large Language ModelsPoster
DualTimesField: Rethinking Time Series as Continuous-Time Trends and EventsPoster
DuetServe: Harmonizing Prefill and Decode for LLM Serving via Adaptive GPU MultiplexingPoster
Dustin: Draft-Augmented Sparse Verification for Efficient Long-Context Generation with Speculative DecodingPoster
DyCon: Dynamic Reasoning Control via Evolving Difficulty ModelingPoster
DyGRO-VLA: Cross-Task Scaling of Vision–Language–Action Models via Dynamic Grouped Residual OptimizationPoster
DyLLM: Efficient Diffusion LLM inference via saliency-based token selection and partial attentionPoster
DyPE: Dynamic Position Extrapolation for Ultra High Resolution DiffusionPoster
Dyn-VPP: Video Prediction Policy Optimization for Improved Visual DynamicsPoster
DynVLA: Learning World Dynamics for Action Reasoning in Autonomous DrivingPoster
DynaMem: Consistent Long Video Generation via Hierarchical Memory and Motion PriorsPoster
DynaSchedBench: Calibrated Dynamic Scheduling Benchmarks and Observability Paradox in LLM-based Scheduling AgentsPoster
DynaTok: Token-Based 4D Reconstruction from Partial Point CloudsPoster
Dynamic Compression Flows for Neuroscience DataPoster
Dynamic Decision Learning: Test-Time Evolution for Abnormality Grounding in Rare DiseasesPoster
Dynamic Fractal Mamba: A Neural Renormalization Group Flow for Scale-Invariant Sequence ModelingPoster
Dynamic High-Dimensional Facility Location with Low RecoursePoster
Dynamic Linear AttentionPoster
Dynamic Multimodal Evaluation via Knowledge-Enhanced Benchmark EvolutionPoster
Dynamic Optimizations of LLM Ensembles with Two-Stage Reinforcement Learning AgentsPoster
Dynamic Programming for Epistemic Uncertainty in Markov Decision ProcessesSpotlight
Dynamic Regret via Discounted-to-Dynamic Reduction with Applications to Curved Losses and Adam OptimizerPoster
Dynamic Relational Priming Improves Transformer in Multivariate Time SeriesPoster
Dynamic Stratified Contrastive Learning with Upstream Augmentation for MILP BranchingSpotlight
Dynamic Symmetric Point Tracking: Tackling Non-ideal Reference in Analog In-memory TrainingPoster
Dynamic TMoE: A Drift-Aware Dynamic Mixture of Experts Framework for Non-Stationary Time Series ForecastingPoster
Dynamic Thinking-Token Selection for Efficient Reasoning in Large Reasoning ModelsPoster
Dynamics Are Learned, Not Told: Semi-Supervised Discovery of Latent Dynamics Geometries For Zero-Shot Policy AdaptationPoster
Dynamics Reveals Structure: Challenging the Linear Propagation AssumptionSpotlight
Dynamics Within Latent Chain-of-Thought: An Empirical Study of Causal StructurePoster
Dynamics and representation structure of local approximations to gradient-based learning in linear recurrent neural networksPoster
Dynamics of neural scaling laws in random feature regression with powerlaw-distributed kernel eigenvaluesPoster
Dywave: Event-Aligned Dynamic Tokenization for Heterogeneous IoT Sensing SignalsPoster
D²Evo: Dual Difficulty-Aware Self-Evolution for Data-Efficient Reinforcement LearningPoster
E-VAds: An E-commerce Short Videos Understanding Benchmark for MLLMsPoster
E-mem: Multi-Agent Based Episodic Context Reconstruction for LLM Agent MemoryPoster
E2Former-V2: On-the-Fly Equivariant Attention with Linear Activation MemoryPoster
EAGer: Entropy-Aware GEneRation for Adaptive Inference-Time ScalingPoster
EAKV: An Entropy-Driven Adaptive KV Compression Framework for Long Video UnderstandingPoster
EAPO: Enhancing Policy Optimization with On-Demand Expert AssistancePoster
EARL: Towards a Unified Analysis-Guided Reinforcement Learning Framework for Egocentric Interaction Reasoning and Pixel GroundingPoster
ECA: Efficient Continual Alignment for Open-Ended Image-to-Text Generation.Poster
ECCO: Evidence-Driven Causal Reasoning for Compiler OptimizationPoster
ECG-R1: Protocol-Guided and Modality-Agnostic MLLM for Reliable ECG InterpretationPoster
ECHO: Elastic Speculative Decoding with Sparse Gating for High-Concurrency ScenariosOral
ECHO: Entropy-Confidence Hybrid Optimization for Test-Time Reinforcement LearningPoster
ECO: Quantized Training without Full-Precision Master WeightsPoster
ECSEL: Explainable Classification via Signomial Equation LearningPoster
EDCO: Dynamic Curriculum Orchestration for Domain-specific Large Language Model Fine-tuningPoster
EEG-Based Multimodal Learning via Hyperbolic Mixture-of-Curvature ExpertsPoster
EEG-FM-Bench: A Comprehensive Benchmark for the Systematic Evaluation and Diagnostic Analyses of EEG Foundation ModelsPoster
EEmo-Logic: A Unified Dataset and Multi-Stage Framework for Comprehensive Image-Evoked Emotion AssessmentSpotlight
EGG: An Expert-Guided Agent Framework for Kernel GenerationPoster
EMBGUARD: Constructing Hazard-Aware Guardrails for Safe Planning in Embodied AgentsPoster
EMFormer: Efficient Multi-Scale Transformer for Accumulative Context Weather ForecastingPoster
EPS3D: End-to-End Feed-Forward 3D Panoptic SegmentationPoster
EPSVec: Efficient and Private Synthetic Text Generation via Dataset VectorsPoster
EPiC: Efficient Video Camera Control Learning with Precise Anchor-Video GuidancePoster
ERAlign: Energy-based Representation Alignment of GNNs and LLMs on Text-attributed GraphsPoster
ERGeoBench: A Comprehensive Benchmark for Embodied Reasoning and Geo-localization in Multimodal Large Language ModelsPoster
ETS: Energy-Guided Test-Time Scaling for Training-Free RL AlignmentPoster
EVMbench: Evaluating AI Agents on Smart Contract SecurityPoster
EVOLVING ROLLOUTS: Harnessing Historical Experience for Web Agent Evolution in Reinforcement LearningPoster
EXVERUS: Verus Proof Repair via Counterexample ReasoningPoster
Early Decisions Matter: Proximity Bias and Initial Trajectory Shaping in Non-Autoregressive Diffusion Language ModelsPoster
Early Directional Convergence in Deep Homogeneous Neural Networks for Small InitializationsPoster
Easier to Judge than to Find: Predicting In-Context Learning Success for Demonstration SelectionPoster
EasyBalance: Cross-Layer Load Balancing in Distributed MoE InferencePoster
Eating for a Sustainable Planet: Personalized Sustainable Diet Recommendation via Constraint-Aware Decision-Making ModelingPoster
EchoAttention: Exploiting Token-Pair Redundancy and Frame-Block Similarity for Efficient Long Video GenerationPoster
EchoRL: Reinforcement Learning via Rollout EchoingPoster
Echoes within the Reasoning: Stealth and Effective Watermarking via Chain of ThoughtPoster
EchoingPixels: Aliasing-Resistant Joint Token Reduction for Audio-Visual LLMsPoster
EcoVLA: Environment-Aware Adaptive Pruning with Interleaved Inference Orchestration for Vision-Language-Action ModelsSpotlight
Edge-colored Clustering in Hypergraphs: A MaxECC ApproximationPoster
Edit-Based Refinement for Parallel Masked Diffusion Language ModelsPoster
Editable Proof Sketch for Automated Theorem ProvingPoster
EduMirror: Modeling Educational Social Dynamics with Value-driven Multi-agent SimulationPoster
Effective MoE-based LLM Compression by Exploiting Heterogeneous Inter-Group Experts Routing Frequency and Information DensityPoster
Effective Model Pruning : Measuring the Redundancy of Model ComponentsSpotlight
Effective Reasoning Chains Reduce Intrinsic DimensionalitySpotlight
Efficient Adaptive Testing via Gradient Path Matching Subset Selection for AI EducationPoster
Efficient Bayesian Inference from Noisy Pairwise ComparisonsPoster
Efficient Bilevel Optimization for CKA-Guided MoE UpcyclingPoster
Efficient Code Analysis via Graph-Guided Large Language ModelsPoster
Efficient Continuous-Depth Modeling with GRU EquivalentsPoster
Efficient DP-SGD for LLMs with Randomized ClippingPoster
Efficient Diffusion LLMs via Temporal-Spatial Parallel Decoding and Confidence ExtrapolationPoster
Efficient Diffusion Models under Nonconvex Equality and Inequality constraints via LandingSpotlight
Efficient Diffusion Models via Time Step Optimization with Consistent Training and Inference ConstraintsPoster
Efficient Distributed MLLM Training with ModalGluePoster
Efficient Distributionally Robust Assortment Optimization in MNL BanditsPoster
Efficient Equivariant High-Order Crystal Tensor Prediction via Cartesian Local-Environment Many-Body CouplingPoster
Efficient Generative Modeling beyond Memoryless Diffusion via Adjoint Schrödinger Bridge MatchingPoster
Efficient Hallucination Detection for LLMs Using Uncertainty-Aware Attention HeadsPoster
Efficient Inference for Noisy LLM-as-a-Judge EvaluationPoster
Efficient LLM Moderation with Multi-Layer Latent PrototypesPoster
Efficient Learned Image Compression without Entropy CodingPoster
Efficient Learning of Compositional Targets with Hierarchical Spectral MethodsPoster
Efficient Learning of Deep State Space Models via Importance SmoothingPoster
Efficient Mismatch-Tolerant Coding for Model-Driven CompressionPoster
Efficient Multi-Agent Reasoning via Confidence-Guided Adaptive DebatePoster
Efficient Multi-modal Dataset Distillation via Analytic Parameter MatchingPoster
Efficient Multi-round LLM Inference over Disaggregated ServingPoster
Efficient Neural Controlled Differential Equations via Attentive Kernel SmoothingPoster
Efficient Online Influence Maximization under the Independent Cascade Model with Node-Level FeedbackPoster
Efficient Online Variational Estimation via Monte Carlo SamplingPoster
Efficient Parallel Samplers for Recurrent-Depth ModelsSpotlight
Efficient Prediction of SO(3)-Equivariant Hamiltonian Matrices via SO(2) Local FramesPoster
Efficient Preference Poisoning Attack on Offline RLHFPoster
Efficient Public Verification of Private ML via RegularizationPoster
Efficient RL Training for LLMs with Experience ReplayPoster
Efficient Rashomon Set Approximation for Decision TreesPoster
Efficient Reasoning with Hidden ThinkingPoster
Efficient Skill Grounding via Code Refactoring with Small Language ModelsPoster
Efficient Stochastic Optimisation via Sequential Monte CarloPoster
Efficient Synthetic Network Generation via Latent Embedding ReconstructionPoster
Efficient Tail-Aware Generative Optimization via Flow Model Fine-TuningPoster
Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language ModelsPoster
Efficient Test-time Inference for Generative Planning Models with OCL SearchPoster
Efficient Training of Boltzmann Generators Using Off-Policy Log-Dispersion RegularizationPoster
Efficient Training-Free Multi-Token Prediction via Embedding-Space ProbingPoster
Efficient Transformer Attention for SNNs via Hadamard SimplificationPoster
Efficient and Minimax-optimal In-context Nonparametric Regression with TransformersPoster
Efficient and Safe Molecular Assembly via Reinforcement Learning and Constraint SolvingPoster
Efficient and Unbiased Sampling from Boltzmann Distributions via Variance-Tuned Diffusion ModelsPoster
Efficient and Uncertainty-Aware Diffusion Framework for Offline-to-Online Reinforcement LearningPoster
Efficient numeracy in language models through single-token number embeddingsSpotlight
Efficient privacy loss accounting for subsampling and random allocationPoster
Efficient, Property-Aligned Fan-Out Retrieval via RL-Amortized DiffusionPoster
Efficient, Validation-Free Intrinsic Quality Estimation for Large-Scale Face Recognition DatasetsPoster
Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in SpeedPoster
Efficiently Learning Drifting Halfspaces with Massart NoisePoster
Efficiently Solving Discounted MDPs via Predictions with Unknown Prediction ErrorsPoster
Efficiently Training Time-to-First-Spike Spiking Neural Networks from ScratchSpotlight
Ego3S: Select, Strengthen, and Synchronize for Efficient Egocentric ReasoningPoster
EgoTactile: Learning Grasp Pressure for Everyday Objects from Egocentric VideoSpotlight
EigenCache: Rethinking Diffusion Acceleration as Covariance-Optimal Forecasting and Submodular Information AllocationPoster
Eigenvectors of Experts are Training-free Non-collapsing RoutersSpotlight
Ekka: Automated Diagnosis of Silent Errors in LLM InferencePoster
Elastic Attention: Test-time Adaptive Sparsity Ratios for Efficient TransformersPoster
Elastic Diffusion TransformerPoster
ElicitR: Unlocking Latent Reasoning in Dense Retrievers via Generative RegularizationPoster
Elign: Equivariant Diffusion Model Alignment from Foundational Machine Learned Force FieldsPoster
Eliminating Solution Bias in Differentially Private OptimizationPoster
Ellipsoidal Time Series ForecastingPoster
EmBrace: A Collective Knowledge Fusion Framework Toward Unified EEG Foundation ModelsPoster
EmWorld: Emotion World Model with Latent State Evolution for Scenario-Incremental Dynamic Facial Expression RecognitionPoster
Embedding Hybrid Systems into Continuous Latent Vector FieldsPoster
Embedding Trust: Semantic Isotropy Predicts Nonfactuality in Long-Form Text GenerationPoster
Embodied Interpretability: Linking Causal Understanding to Generalization in Vision-Language-Action ModelsPoster
Embodied Task Planning via Graph-Informed Action Generation with Large Lanaguage ModelPoster
Embodied-DETR: End-to-End Temporal 3D Object Detection in Egocentric ViewsPoster
Embodiment-Conditioned Mixture of Experts Increases the Evolvability of RobotsPoster
Emergence of Biased Consensus in Multi-Agent LLM DebatesPoster
Emergence of Exploration in Policy Gradient Reinforcement Learning via RetryingPoster
Emergence of Hierarchical Emotion Organization in Large Language ModelsPoster
Emergent Alignment via CompetitionPoster
Emergent Analogical Reasoning in TransformersSpotlight
Emergent Biological Realism in RL-Trained DNA Language ModelsPoster
Emergent Communication Under MisinformationPoster
Emergent Visual Representations through Unsupervised Spiking Networks with Synaptic PruningPoster
Empirical Gaussian ProcessesPoster
Empty Shelves or Lost Keys? Recall Is the Bottleneck for Parametric FactualityPoster
Enabling Faithful Camera Control in Video Diffusion through Geometry-Flow-Guided Noise WarpingPoster
End-to-End Autoregressive Image Generation with 1D Semantic TokenizerSpotlight
End-to-End Compression for Tabular Foundation ModelsSpotlight
End-to-end Graph-structured Brain Representation LearningPoster
Endogenous Resistance to Activation Steering in Language Models: Evidence for Internal Consistency Monitoring in Llama-3.3-70BPoster
EnerGS: Energy-Based Gaussian Splatting under Partial Geometric ObservabilityPoster
Energy-Structured Low-Rank Adaptation for Continual LearningPoster
Energy-based Compositional Diffusion PlanningPoster
EngiAgent: Fully Connected Coordination of LLM Agents for Solving Open-ended Engineering Problems with Feasible SolutionsPoster
Enhanced Latent-Space Adversarial Training for Super-ResolutionPoster
Enhanced Multi-Instance Partial Label Learning via Average Gradient Outer ProductPoster
Enhancing Affine Maximizer Auctions with Correlation-Aware PaymentPoster
Enhancing Conformal Prediction via Class SimilarityPoster
Enhancing Cross-subject Emotion Recognition via Heterogeneous Distribution Augmentation and Collaborative LearningPoster
Enhancing LLM Training via Spectral ClippingPoster
Enhancing LLMs for Graph Tasks via Graph-aware LoRA GenerationPoster
Enhancing Membership Inference Attacks on Diffusion Models from a Frequency-Domain PerspectivePoster
Enhancing Multi-Modal LLMs Reasoning via Difficulty-Aware Group NormalizationPoster
Enhancing Neural Theorem Proving via High-Quality Proof Selection and Verifier FeedbackPoster
Enhancing Numerical Prediction in LLMs via Smooth MMD AlignmentPoster
Enhancing Protein-Protein Interaction Prediction with Hierarchical Motif-based Multimodal Protein EmbeddingPoster
Enhancing Reasoning for Diffusion LLMs via Distribution Matching Policy OptimizationSpotlight
Enhancing Train-Free Infinite-Frame Generation for Consistent Long VideosPoster
EnsembleVLA: Ensemble Learning for Vision-Language Action ModelsPoster
Ensembling Sparse AutoencodersPoster
EntRAG: Entity-Centric Retrieval-Augmented Generation for Knowledge-based Visual Question AnsweringPoster
Entangled No More: Multi-Domain Decoupling for Robust Dynamic Graph Neural NetworksPoster
EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise SettingsPoster
EntroKV: Entropy-Guided Dynamic Budget Allocation for KV-Cache CompressionSpotlight
Entropic Mirror Monte CarloPoster
Entropy-Aware Dynamic KV Cache Sparsification for Autoregressive Image Generation and EditingPoster
Entropy-Aware On-Policy Distillation of Language ModelsPoster
Entropy-aware Span-Constrained Optimal Transport for Robust Cross-Tokenizer Knowledge DistillationPoster
Entropy-informed Decoding: Adaptive Information-Driven BranchingPoster
Envisioning Beyond the Few: Disentangled Semantics and Primitives for Few-Shot Atypical Layout-to-Image GenerationPoster
Envy-Free Allocation of Indivisible Goods via Noisy QueriesPoster
EpiCache: Episodic KV Cache Management for Long-Term Conversation on Resource-Constrained EnvironmentsPoster
EpiCoCo: De Novo Epitope Generation via MHC-Context Co-Modeling and Contrastive Affinity GuidancePoster
EpiTwin: Spatiotemporal Graph Transformers for Epileptic sEEG Signal ReconstructionPoster
Episodic Memory-Guided Controllable Experience Synthesis for Reinforcement LearningPoster
Epistemic Gain, Aleatoric Cost: Uncertainty Decomposition in Multi-Agent Debate for Math ReasoningPoster
Epistemic Uncertainty Quantification for Pre-trained VLMs via Riemannian Flow MatchingPoster
EqGINO: Equivariant Geometry-Informed Fourier Neural Operators for 3D Partial Differential EquationsPoster
Equalized Generative Treatment: Matching f-divergences for Fairness in Generative ModelsPoster
EquiCAD: A Geometric Equivariant Neural Network for 3D Shape ClassiﬁcationPoster
Equilibrium Pricing in Oligopolistic Data MarketsOral
Equilibrium Propagation for Non-Conservative SystemsPoster
Equilibrium Reasoners: Learning Attractors Enables Scalable ReasoningPoster
Equivalence of Context and Parameter Updates in Modern Transformer BlocksOral
Equivariant Covariance Tensors: Guaranteed SPD Uncertainty for Tensor-Valued Geometric LearningPoster
Equivariant Latent Alignment via Flow Matching under Group SymmetriesPoster
Equivariant Neural Networks for General Linear Symmetries on Lie AlgebrasPoster
Erased but Not Forgotten: How Backdoors Compromise Concept ErasurePoster
Error Amplification Limits ANN-to-SNN Conversion in Continuous ControlPoster
Error Analysis of Discrete Flow with Generator MatchingPoster
Error Propagation Mechanisms and Compensation Strategies for Quantized Diffusion ModelsOral
Error Propagation and Model Collapse in Diffusion Models: A Theoretical StudyPoster
Error Propagation in Dynamic Programming: From Stochastic Control to American Option PricingPoster
Error-Driven Graph Augmentation for Mesh-Based PDE SurrogatesPoster
Escaping Mode Collapse in LLM GenerationPoster
Escaping Whack-a-Mole: Code Documentation Optimization via Dependency-Guided Bi-level SearchPoster
Escaping the Diversity Trap in Robotic Manipulation via Anchor-Centric AdaptationPoster
Escaping the Likelihood Trap: Geometric Diversity Optimization for Long-Form Image CaptioningPoster
Escaping the Mode: Multi-Answer Reinforcement Learning in LMsPoster
Escaping the Subspace Trap: The Role of Optimizer Geometry in Model Width ExpansionPoster
Escaping the Verifier: Learning to Reason via DemonstrationsPoster
Esoteric Language ModelsPoster
Estimating Correlation Clustering Cost in Node-Arrival StreamPoster
Estimating Tail Risks in Language Model Output DistributionsSpotlight
Estimating the Empowerment of Language Model AgentsPoster
Estimation of Treatment Effects Under Nonstationarity via the Truncated Policy Gradient EstimatorPoster
Euclean: Automated Geometry Problem Formalization with Unified Verification in LeanPoster
Euler–Poincaré Neural Dynamics: A Geometric-Mechanics Framework for Scientific SimulationPoster
EvReflection: Event-Driven Micro-Dynamics for Reflection RemovalPoster
Evaluating AI Grading on Real-World Handwritten College Mathematics: A Large-Scale Study Toward a BenchmarkPoster
Evaluating Agentic Optimization on Large CodebasesPoster
Evaluating Contextual Illegality: AI Compliance in Corporate Law ScenariosPoster
Evaluating LLM Uncertainty in Long-Form Generation Using Deterministic Ground TruthPoster
Evaluating LLMs When They Do Not Know the Answer: Statistical Evaluation of Mathematical Reasoning via Comparative SignalsPoster
Evaluating Language Models in Realistic Conversational ContextsPoster
Evaluating Object-Centric Models beyond Object DiscoveryPoster
Evaluating Parameter Efficient Methods for RLVRPoster
Evaluating Robustness of Reasoning Models on Parameterized Logical ProblemsOral
Evaluating Sample Utility for Efficient Data Selection by Mimicking Model WeightsPoster
Evaluating and Explaining Prompt Sensitivity of LLMs Using InteractionsPoster
Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-ProbabilityPoster
Evaluating and Steering Modality Preferences in Multi-modal LLMsPoster
Evaluating bivariate causal statements based on mutual compatibilityPoster
Evaluating the Representation Space of Diffusion Models via Self-Supervised PrinciplesPoster
Even Faster Kernel Matrix Linear Algebra via Density EstimationSpotlight
Event2Vec: Processing neuromorphic events directly by representations in vector spacePoster
Every Step Counts: Decoding Trajectories as Authorship Fingerprints of dLLMsPoster
Evidential Copula Concept Embedding ModelsPoster
Evidential Reasoning Advances Interpretable Real-World Disease ScreeningPoster
EvoC2F: Compiling Tool Orchestration for Efficient and Evolvable LLM AgentsPoster
EvoCF: Multi-Agent Collaboration via Agentic Memory-Driven Evolutionary Counterfactual PlanningPoster
EvoEGF-Mol: Evolving Exponential Geodesic Flow for Structure-based Drug DesignPoster
EvoGM: Learning to Merge LLMs via Evolutionary Generative OptimizationPoster
EvoMAS: Heuristics in the Loop—Evolving Smarter Agentic WorkflowsPoster
Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement LearningPoster
Evolution Strategies at the HyperscalePoster
Evolution of Benchmark: Black-Box Optimization Benchmark Design through Large Language ModelPoster
Evolutionary Generation of Multi-Agent SystemsPoster
Evolutionary Multi-View Classification with Label Noise via Gradient and Feature Dual-PerceptionSpotlight
Evolving Interdependent Operators with Large Language Models for Multi-Objective Combinatorial OptimizationPoster
Evolving Interpretable Constitutions for Multi-Agent CoordinationPoster
Evolving Quantitative Reasoning through Self-Play in Digital Twin MarketsPoster
ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat InvestigationPoster
ExPLAIND: Unifying Model, Data, and Training Attribution to Study Model BehaviorPoster
ExSkill: Continual Learning from Experience and Skills in Multimodal AgentsPoster
Exact Functional ANOVA Decomposition for Categorical InputsOral
Exact Unlearning in Reinforcement LearningSpotlight
Exact and Approximate Algorithms for Polytree LearningPoster
Exactly Computing do-Shapley ValuesPoster
Excited Pfaffians: Generalized Neural Wave Functions Across Structure and StateSpotlight
Executable Agentic Memory for GUI AgentPoster
ExpAlign: Expectation-Guided Vision–Language Alignment for Open-Vocabulary GroundingPoster
ExpWeaver: LLM Agents Learn from Experience via Latent RAGPoster
Expand Neurons, Not ParametersPoster
Expandable, Compressible, Mineable: Open-World Thermal Infrared Image RestorationPoster
Expanding the AI Evaluation Toolbox with Statistical ModelsPoster
Expanding the Chaos: Neural Operator for Stochastic (Partial) Differential EquationsPoster
Expectation Alignment of Language Models for Real-World User ExpectationsPoster
Expectation Consistency Loss: Rethink Confidence Calibration under Covariate ShiftPoster
Expected Return Causes Outcome-Level Mode Collapse in Reinforcement Learning and How to Fix It with Inverse Probability ScalingPoster
Expected Returns and Policy Inconsistency-Aware Offline Federated Deep Reinforcement LearningPoster
Experience Augmented Policy Optimization for LLM ReasoningPoster
Experience is the Best Teacher: Motivating Effective Exploration in Reinforcement Learning for LLMsPoster
Experience-Evolving Multi-Turn Tool-Use Agent with Hybrid Episodic–Procedural MemoryPoster
Expert Routing with Synthetic Data for Domain Incremental LearningPoster
Expert-guided Clinical Text Augmentation via Query-Based Model CollaborationPoster
Expert-level Leaf Cell Layout Generation via Preference-Optimized LLMPoster
ExpertWeaver: Unlocking the Inherent MoE in Dense LLMs with GLU Activation PatternsPoster
Explainable Federated Learning via Global–Local Attribution AlignmentPoster
Explainable Forensics of Manipulated Segments in Untrimmed Long VideosPoster
Explaining Concept Shift with Interpretable Feature AttributionPoster
Explaining Data Mixing Scaling LawsPoster
Explanations are a Means to an End: A Value of Information Framework for Validating ExplanationsPoster
Explicit representation of germline and non-germline residues improves antibody language modelingPoster
Explicitly Modeling Censoring Produces Superior Survival PredictorsPoster
Exploiting Hankel-Toeplitz Structures for Fast Computation of Kernel Precision MatricesPoster
Exploiting weight-space symmetries for approximating curvaturePoster
Exploration Hacking: LLMs Can Learn to Resist RL TrainingPoster
Exploration-free Algorithms for Multi-group Mean EstimationPoster
Exploring 3D Dataset PruningPoster
Exploring Accurate and Transparent Domain Adaptation in Predictive Healthcare via Concept-Grounded Orthogonal InferencePoster
Exploring Data-Free LoRA Transferability for Video Diffusion ModelsPoster
Exploring More to Solve More: Boosting Diversity in Text Diffusion Models via Entropy-Based GuidancePoster
Exploring Motif-based Heterogeneous Graph Learning for ReDoS DetectionPoster
Exploring Nonlinear Pathway in Parameter Space for Machine UnlearningPoster
Exploring Relational Reasoning Capabilities in LLMs with RELPoster
Exploring and Exploiting Stability in Latent Flow MatchingPoster
Expo-GS: Exposure-Aware Signed Distance Function in Gaussian Splatting for High Dynamic RangePoster
Exposing Hidden Biases in Text-to-Image Models via Automated Prompt SearchPoster
Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target AttacksPoster
Expressive Graph Neural Networks via Equivariant Use of NoiseSpotlight
Expressivity-Efficiency Tradeoffs for Hybrid Sequence ModelsOral
Extending Fair Null-Space Projections for Continuous Attributes to Kernel MethodsPoster
Extending Mean-Field Variational Inference via Entropic Regularization: Theory and ComputationPoster
Extending Prediction-Powered Inference through Conformal PredictionPoster
Extra-Merge: Tracing the Rank-1 Subspace of Model Merging in Language Model Pre-TrainingPoster
Extracting alignment data in open modelsPoster
Eyes-on-Me: Scalable RAG Poisoning through Transferable Attention-Steering AttractorsPoster
E²I-VRWKV: Explicit EPI-Representation and Interaction-Aware Vision-RWKV for Light Field Semantic SegmentationPoster
FAB: A First-Order AB-based Gradient Algorithm for Distributed Bilevel Optimization over Time-Varying Directed GraphsPoster
FACT: Fuzzy Alignment with Comorbidity Topology for Reliable Multi-Label Medical Image DiagnosisPoster
FAFO: Lossy KV Cache Compression for Lossless Inference Acceleration via Draftless Fumble DecodingPoster
FAIL: Flow Matching Adversarial Imitation Learning for Image GenerationPoster
FAIR-Calib: Frontier-Aware Instability-Reweighted Calibration for Post-Training Quantization of Diffusion Large Language ModelsPoster
FEDEMOE: IMPROVING PERSONALIZATION ON HET- EROGENEOUS FEDERATED LEARNING VIA ELASTIC MIXTURE OF EXPERTS ARCHITECTUREPoster
FG-CLIP 2: A Bilingual Fine-grained Vision-Language Alignment ModelPoster
FHAIM: Fully Homomorphic AIM for Private Synthetic Data GenerationPoster
FIBER: A Differentially Private Optimizer with Filter-Aware Innovation Bias CorrectionPoster
FIDIA: Function-Informed Sequence Design via Inference-Aligned Policy OptimizationSpotlight
FIPN: Forward Self-Organizing Interpretable Polynomial Networks for Time Series ForecastingPoster
FIRE-Bench: Evaluating Agents on the Rediscovery of Scientific InsightsPoster
FIRE: Learning to Navigate and Act on Real-World Files via Stateful Reinforcement LearningPoster
FIRE: Multi-fidelity Regression with Distribution-conditioned In-context Learning using Tabular Foundation ModelsSpotlight
FLAC: Maximum Entropy RL via Kinetic Energy Regularized Bridge MatchingPoster
FLAG: Foundation model representation with Latent diffusion Alignment via Graph for spatial gene expression predictionPoster
FLARE-AI: Flaw Reporting for AIPoster
FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning ApplicationsOral
FLIPS: Instance-Fingerprinting for LLMs via Pseudo-random SequencesPoster
FOAM: Blocked State Folding for Memory-Efficient LLM TrainingPoster
FOAM: Frequency and Operator-Error Based Adaptive Damping Method for Reducing Staleness-Oriented Error for ShampooPoster
FOCA: Future-Oriented Conditioning for Data-Efficient Vision-Language-Action AdaptationPoster
FOCUS & RePAIR: Mitigating Text Degeneration via Token-Level Guidance For Pruned Large Language ModelsSpotlight
FOCUS: DLLMs Know How to Tame Their Compute BoundPoster
FOCUS: Forcing In-Context Object Localization through Visual Support Constraints and Policy OptimizationPoster
FOVI: A biologically-inspired foveated interface for deep vision modelsPoster
FPTQuant: Function-Preserving Transforms for LLM QuantizationPoster
FRACTAL: State Space Model with Fractional Recurrent Architecture for Computational Temporal Analysis of Long SequencesPoster
FRIGID: Scaling Diffusion-Based Molecular Generation from Mass Spectra at Training and Inference TimePoster
FRISM: Fine-Grained Reasoning Injection via Subspace-Level Model Merging for Vision–Language ModelsPoster
FS-I2P: A Hierarchical Focus–Sweep Registration Network with Dynamically Allocated DepthPoster
FT-Dojo: Towards Autonomous LLM Fine-Tuning with Language AgentsPoster
FUSE: Ensembling Verifiers with Zero Labeled DataPoster
FUSE: FK-Steered Multi-Modal Flow Matching for Efficient Simulation-Based Posterior EstimationPoster
FUSE: Frequency-domain Unification and Spectral Energy Alignment for Multi-modal Object Re-IdentificationPoster
FUSE: Full‑spectrum Unlearnable Examples via Spectral EqualizationPoster
FUSE: Quantifying Uncertainty in Multimodal LLMs by Bayesian Fusing Epistemic and Aleatoric UncertaintyPoster
FaPS: A General and Fast Training Method for Diffusion ModelsPoster
FactGuard: Agentic Video Misinformation Detection via Reinforcement LearningPoster
Factor-Wise Homogeneity of Slot-Attention for Continual Object-Centric LearningPoster
Factored Causal Representation Learning for Robust Reward Modeling in RLHFPoster
Factored Classifier-Free GuidancePoster
Factored Gossip DiLoCo: Reducing Blocking Communication within DiLoCoPoster
Factored Latent Action World ModelsPoster

ICML accepted papers in other years

ICML 2025 (3,333)ICML 2024 (2,610)ICML 2023 (1,828)ICML 2022 (1,228)ICML 2021 (1,181)ICML 2020 (1,082)ICML 2019 (773)ICML 2018 (620)ICML 2017 (433)ICML 2016 (322)ICML 2015 (270)

Looking for submission deadlines instead? See the conference deadline calendar.