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

Large Scale Manifold Balanced ClusteringPoster
Large Vision–Language Models Get Lost in AttentionPoster
Large-Scale Molecular Dynamics Simulations: Direct Interatomic Modeling with Dilated Message PassingPoster
Large-Scale Notification Dispatch with Bundle Treatments and Multi-Outcome Uplift OptimizationPoster
Large-Scale Terminal Agentic Trajectory Generation from Dockerized EnvironmentsSpotlight
Large-capacity and Receiver Authenticable Generative Image SteganographyPoster
Large-scale Uncertainty Quantification for Latent Variable Models Using Subsampling Markov Chain Monte CarloPoster
LassoFlexNet: a Flexible Neural Architecture for Tabular DataPoster
Last-Iterate Convergence of Regularized Gradient Methods for Stochastic Monotone Variational InequalitiesPoster
Last-iterate Convergence of ADMM on Multi-affine Quadratic Equality Constrained ProblemPoster
Latent Collaboration in Multi-Agent SystemsSpotlight
Latent Diffusion Controller: Framework, Algorithms and ParameterizationPoster
Latent Diffusion Pretraining for Crystal Property PredictionPoster
Latent Forcing: Reordering the Diffusion Trajectory for Pixel-Space Image GenerationPoster
Latent Guided Sampling for Combinatorial OptimizationPoster
Latent Laplace Diffusion for Irregular Multivariate Time SeriesSpotlight
Latent Reasoning VLA: Latent Thinking and Prediction for Vision-Language-Action ModelsPoster
Latent Representation Alignment for Offline Goal-Conditioned Reinforcement LearningPoster
Latent Space Robust Optimization of Neural Processes with Aligned Stratified Order-Statistic Loss ReductionPoster
Latent Spherical Flow Policy for Reinforcement Learning with Combinatorial ActionsSpotlight
Latent Thoughts Tuning: Bridging Context and Reasoning with Fused Information in Latent TokensPoster
Latent-Guided Cooperative Energy-Based ModelsPoster
LatentChem: From Textual CoT to Latent Thinking in Chemical ReasoningPoster
LatentLens: Revealing Highly Interpretable Visual Tokens in LLMsPoster
Lavida-R1: Advancing Reasoning for Unified Multimodal Diffusion Language ModelsPoster
Layer-Centric Factors of Variation Disentanglement for Task- and Model-Agnostic GeneralizationPoster
Layer-wise Gradient Disentanglement: Decoupling Semantics and Preferences in Direct Preference OptimizationPoster
LayerT2V: A Unified Multi-Layer Video Generation FrameworkPoster
LazyAttention: Efficient Retrieval-Augmented Generation with Deferred Positional EncodingPoster
Leaderboard Incentives: Model Rankings under Strategic Post-TrainingPoster
Leak@$k$: Unlearning Does Not Make LLMs Forget Under Probabilistic DecodingPoster
LeakGFN: Robust Molecular Generation in Generative Flow Networks via Flow DecompositionPoster
Learn from A Rationalist: Distilling Intermediate Interpretable RationalesPoster
Learn from Your Mistakes: Tree-like Self-Play on Vulnerability Nodes for Secure Code LLMsPoster
Learn to Merge: Meta-Learning for Adaptive Multi-Task Model MergingPoster
Learn to Think: Improving Multimodal Reasoning through Vision-Aware Self-Improvement TrainingPoster
Learn to change the world: Multi-level reinforcement learning with model-changing actionsPoster
Learn-to-learn on Arbitrary Textual Conditioning: A Hypernetwork-Driven Meta-gated LLMPoster
Learnability-Driven Knowledge Assimilation for Class-Incremental Semantic SegmentationPoster
Learnability-Informed Fine-Tuning of Diffusion Language ModelsPoster
Learnable Kernel Density Estimation for Graphs and Its Application to Graph-Level Anomaly DetectionPoster
LearniBridge: Learnable Calibration of Feature Caching for Diffusion Models AccelerationPoster
Learning $U$-Statistics with Active InferencePoster
Learning 3D-Gaussian Simulators from RGB VideosPoster
Learning Adaptive Perturbation-Conditioned Contexts for Robust Transcriptional Response PredictionPoster
Learning Adaptive Topology with FiLM-Guided Distillation for Tertiary Structure-Based RNA DesignPoster
Learning Anisotropic Value Geometry with Finsler Reinforcement LearningPoster
Learning Attribute–Affordance Hierarchies in Hyperbolic Space for Open-Vocabulary 3D Object Affordance GroundingPoster
Learning Biophysical Models of Large-Scale Multineuronal Data To Enable Precise NeurostimulationSpotlight
Learning Cardiac Latent Representations in Vectorcardiogram SpacePoster
Learning Coherent Representations: A Topological Approach to InterpretabilityPoster
Learning Compressed Shape-Aware Molecular Representations for Virtual ScreeningPoster
Learning Context-Conditioned Predicate Semantics via Prototype FeedbackPoster
Learning Coupled Continuous-Time Latent Dynamics from Irregular EventsSpotlight
Learning Credal Ensembles via Distributionally Robust OptimizationSpotlight
Learning Decentralized LLM Collaboration with Multi-Agent Actor CriticPoster
Learning Discrete Diffusion on Graphs via Free-Energy Gradient FlowsPoster
Learning Discriminative and Generalizable Anomaly Detector for Dynamic Graph with Limited SupervisionPoster
Learning Disentangled Multi-Agent World Model for Decentralized ControlPoster
Learning Dynamics of Zeroth-Order Optimization: A Kernel PerspectivePoster
Learning Efficient Guardrails for CompliancePoster
Learning Fingerprints for Medical Time Series with Redundancy-Constrained Information MaximizationPoster
Learning Flexible Generalization in Video Quality Assessment by Bringing Device and Viewing Condition DistributionsPoster
Learning GUI Grounding with Spatial Reasoning from Visual FeedbackPoster
Learning Gaussian Graphical Models from a Glauber Trajectory Without MixingPoster
Learning Gaussian Mixture-distributed Prototypes for 3D Scene Graph Generation from RGB-D SequencesPoster
Learning General Causal Structures with Hidden Dynamic Process for Climate AnalysisPoster
Learning Generalizable Skill Policy with Data-Efficient Unsupervised RLPoster
Learning Generalized Label DistributionsPoster
Learning Generalized Trackers with Elastic Token BudgetsPoster
Learning Global Representation from Queries for Vectorized HD Map ConstructionPoster
Learning Graph Foundation Models on Riemannian Graph-of-GraphsPoster
Learning Hamiltonian Dynamics at Scale: A Differential-Geometric ApproachPoster
Learning Hamiltonian Flow Maps: Mean Flow Consistency for Large-Timestep Molecular DynamicsSpotlight
Learning High-Dimensional Parity Functions with Product Networks using Gradient DescentPoster
Learning High-Frequency Continuous Action Chunks in Latent SpacePoster
Learning Human-Robot Collaboration via Heterogeneous-Agent Lyapunov Policy OptimizationOral
Learning Interpretable Options by Identifying Reward Diffusion Bottlenecks in Reinforcement LearningPoster
Learning Junta Distributions, Quantum Junta States, and QAC$^0$ CircuitsPoster
Learning Latent Action World Models In The WildPoster
Learning Locally, Revising Globally: Global Reviser for Federated Learning with Noisy LabelsPoster
Learning Long Range Spatio-Temporal Representations over Continuous Time Dynamic Graphs with State Space ModelsPoster
Learning Manifold Data with Flow MatchingPoster
Learning Manifold and Itô Dynamics with Branched Neural Rough Differential EquationsPoster
Learning Molecular Semantic Invariant Representation with Prototype ConstraintPoster
Learning More from Less: Unlocking Internal Representations for Benchmark CompressionPoster
Learning Multi-Agent Coordination via Sheaf-ADMMPoster
Learning Multi-Scale Hypergraph for High-Order Brain Connectivity AnalysisPoster
Learning Multi-Timescale Abstractions for Hierarchical Combinatorial PlanningPoster
Learning Partial Concept Classes and Universal Rates Under Massart NoisePoster
Learning Permutation Distributions via Reflected Diffusion on RanksPoster
Learning Permutation from Structure Without SupervisionPoster
Learning Permutation-invariant Macroscopic DynamicsPoster
Learning Protein Structure-Function Relationships through Knowledge-guided Representation DecompositionPoster
Learning Query-Aware Budget-Tier Routing for Runtime Agent MemoryPoster
Learning Randomized ReductionsSpotlight
Learning Rate Annealing Improves Tuning Robustness in Stochastic OptimizationPoster
Learning Rate Scaling across LoRA Ranks and Transfer to Full FinetuningPoster
Learning Realistic Depth via Physics-Grounded Noise Disentanglement with Semantic-Geometric CollaborationPoster
Learning Reward Functions from Multiple Feedback Types with Amortized Variational InferencePoster
Learning Reward–Cost Balance in Safe RL via Score-Based World ModelsPoster
Learning Rewrite-Invariant Reasoning with Targeted Alternation TrainingPoster
Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label PairsPoster
Learning Situated Awareness in the Real WorldSpotlight
Learning Sparse Visual Representations via Spatial-Semantic FactorizationPoster
Learning Stochastic Bridges for Video Object Removal via Video-to-Video TranslationPoster
Learning Structured Reasoning via Tractable Trajectory ControlSpotlight
Learning Task-Sufficient World Models by Synergizing Agentic Exploration and Structured ModelingPoster
Learning Taxonomic Trees with Hierarchical Representation Regularization for Large Multimodal ModelsPoster
Learning Tight Rejection Boundaries without Negatives for Strict One-Class Audio Deepfake DetectionPoster
Learning Transferable Interaction Primitives from Game Videos for HumanoidsPoster
Learning Treatment Allocations with Risk Control Under Partial IdentifiabilityPoster
Learning Treatment Representations for Downstream Instrumental Variable RegressionPoster
Learning Unanimously Acceptable Lotteries via QueriesPoster
Learning Unmasking Policies for Diffusion Language ModelsOral
Learning Useful Supervision for Reinforcement Learning in Reasoning ModelsPoster
Learning What to Generate: A Reinforcement Learning-based Closed-Loop Augmentation Framework for Person Re-identificationPoster
Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool UsePoster
Learning When to Attend: Conditional Memory Access for Long-Context LLMsPoster
Learning a Generative Meta-Model of LLM ActivationsPoster
Learning a Zeroth-Order Optimizer for Fine-Tuning LLMsPoster
Learning from Comparison: Constrained Projection Policy Optimization for Pareto-Front ImprovementPoster
Learning from Fine-Grained Visual Discrepancies: Mitigating Multimodal Hallucinations via In-Context Visual Contrastive OptimizationPoster
Learning from Pairwise Preferences in Long-Term Decision ProblemsPoster
Learning in Bayesian Stackelberg Games With Unknown Follower's TypesPoster
Learning in Structured Stackelberg GamesSpotlight
Learning in the Fisher Subspace: A Guided Initialization for LoRA Fine-TuningPoster
Learning multi-modal generative models with permutation-invariant encoders and tighter variational objectivesPoster
Learning on Higher-Order Structures with Effective OperatorsPoster
Learning syntax without semantics: Disentangled tiny language modelsPoster
Learning the Best Under Constraints: A Duality-Based FrameworkPoster
Learning the ESG Geometry with Domain Aware Language ModelsPoster
Learning the Interaction Prior for Protein-Protein Interaction Prediction: A Model-Agnostic ApproachPoster
Learning the Minimum Action DistancePoster
Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph PretrainingPoster
Learning to Approximate Uniform Facility Location via Graph Neural NetworksPoster
Learning to Bet for Horizon-Aware Anytime-Valid TestingPoster
Learning to Correct: Reinforcement Learning for Multi-Attempt Chain-of-ThoughtPoster
Learning to Decode Against Compositional Hallucination in Video Multimodal Large Language ModelsPoster
Learning to Discover at Test TimeSpotlight
Learning to Emulate Chaos: Adversarial Optimal Transport RegularizationPoster
Learning to Evict from Key-Value CachePoster
Learning to Execute Graph Algorithms Exactly with Graph Neural NetworksSpotlight
Learning to Explore: Scaling Agentic Reasoning via Exploration-Aware Policy OptimizationPoster
Learning to Extrapolate to New Tasks: A Relational Approach to Task ExtrapolationPoster
Learning to Label: A Reinforced Self-Evolving Framework for Semi-supervised Referring Expression SegmentationPoster
Learning to Memorize with Attributive and Associative Memory for Online Test-Time Adaptation of Vision-Language ModelsPoster
Learning to Move Before Learning to Do: Task-Agnostic pretraining for VLAsPoster
Learning to Perceive the World Through Control: Empowerment-Based Representation LearningPoster
Learning to Rank by Directly Optimizing Full-Order ProbabilitiesPoster
Learning to Rank from Incomplete RankingsPoster
Learning to Reason for FactualityPoster
Learning to Reconfigure: Co-designing Reconfigurable robots for Heterogeneous LocomotionPoster
Learning to Refine: Spectral-Decoupled Iterative Refinement Framework for Precipitation NowcastingPoster
Learning to Remember, Learn, and Forget in Attention-Based ModelsPoster
Learning to Route Languages for Multilingual Preference OptimizationPoster
Learning to Search and Searching to Learn for Generalization in PlanningPoster
Learning to Self-Verify Makes Language Models Better ReasonersPoster
Learning to Share: Selective Memory for Efficient Parallel Agentic SystemsPoster
Learning to Theorize the World from ObservationOral
Learning to Think in Physics: Breaking Shortcut Learning in Scientific Diffusion via Representation AlignmentPoster
Learning to Watch: Active Video Anomaly Understanding via Interleaved Policy OptimizationPoster
Learning to Watermark in the Latent Space of Generative ModelsPoster
Learning with Admissibility: Robust Fuzzy Hashing for Cross-Modal Retrieval with Noisy LabelsSpotlight
Learning, Solving and Optimizing PDEs with TensorGalerkin: an efficient high-performance Galerkin assembly algorithmPoster
Learning-Augmented Online Covering ProblemsPoster
Learning-Augmented Online Minimization with Dual PredictionsPoster
Learning-Augmented Scalable Linear Assignment Problem Optimization via Neural Dual Warm-StartsPoster
Learning-Guided Integration Contours Construction for Fast Large-Scale Generalized EigensolversPoster
Learning-To-Measure: In-Context Active Feature AcquisitionPoster
Learning-augmented Rent-or-Buy with a SamplePoster
Learning-to-Optimize via Deep Unfolded FlowsSpotlight
Least-Loaded Expert Parallelism: Load Balancing An Imbalanced Mixture-of-ExpertsPoster
Left–Right Symmetry Breaking in CLIP-style Vision-Language Models Trained on Synthetic Spatial-Relation DataPoster
Length Generalization Bounds for TransformersPoster
Less Diverse, Less Safe: The Indirect But Pervasive Risk of Test-Time Scaling in Large Language ModelsPoster
Less Is More in Federated Continual Learning: RieSelect for Conflict-Aware Layer Selection in LLMsPoster
Less Is More: Elevating RAG via Performance-Driven Context CompressionPoster
Less Is More: Fast and Accurate Reasoning with Cross-Head Unified Sparse AttentionPoster
Less Precise Can Be More Reliable: A Systematic Evaluation of Quantization’s Impact on VLMs Beyond AccuracyPoster
Less Token, More Signal: MoE Expert Pruning via Critical Token SelectionPoster
Less is Enough: Synthesizing Diverse Data in Feature Space of LLMsOral
Less is More: Geometric Unlearning for LLMs with Minimal Data DisclosurePoster
Less is More: Neuroscience-Motivated Probing for Efficient Concept Circuits TracingPoster
Let EEG Models Learn EEGPoster
Let Language Constrain Geometry: Vision–Language Models as Semantic and Spatial Critics for 3D GenerationPoster
Let the Prototype Guide You: Robust Aggregation of Sparse Multi-Class Annotations via Annotator Prototype LearningPoster
Letting Trajectories Spread: Quality-Preserving Control for Diverse Flow MatchingPoster
Leveraging Evidence Priors for Robust Prompt Learning under Noisy Supervision in Vision-Language ModelsPoster
Leveraging Gauge Freedom for Learning Non-Gradient Population Dynamics of Stochastic SystemsPoster
Leveraging Lineage Barcodes as Natural Augmentations for Contrastive Learning of Cell Fate in scRNA-seq DataPoster
Leveraging Low-Rank Structures for High-Dimensional Score-Based SamplingPoster
Leveraging Machine Unlearning for Cost-Efficient Preference AlignmentPoster
LiME: Lightweight Mixture of Experts for Efficient Multimodal Multi-task LearningSpotlight
LiMuon: Light and Fast Muon Optimizer for Large ModelsPoster
Lie-Algebraic Neural Koopman DynamicsPoster
LieStoNet: Learning Lie Symmetries from Spatiotemporal Data for Stochastic Dynamical SystemsPoster
LieWarper: Geometry-Aware Motion Transfer via Lie AlgebraPoster
LiftQuant: Continuous Bit-Width Control for Pareto-Optimal LLM DeploymentSpotlight
Lifting Traces to Logic: Programmatic Skill Induction with Neuro-Symbolic Learning for Long-Horizon Agentic TasksPoster
Light Forcing: Accelerating Autoregressive Video Diffusion via Sparse AttentionPoster
Light Up Your Face: A Physically Consistent Dataset and Diffusion Model for Face Fill-Light EnhancementPoster
LightAVSeg: Lightweight Audio-Visual SegmentationPoster
Lightning Unified Video Editing via In-Context Sparse AttentionPoster
LightningRL: Breaking the Accuracy–Parallelism Trade-off of Block-wise dLLMs via Reinforcement LearningPoster
Lightweight Federated Incremental Learning via Decoupled ReplayPoster
Lightweight and Interpretable Transformer via Unrolling of Mixed Graph Algorithms for Traffic ForecastPoster
Likelihood Matching for Diffusion ModelsPoster
Likelihood over Estimation: Robust Quadratic Discriminant Analysis for Heavy-Tailed Distributions with Theory and EvidencePoster
LineageFlow: Flow Matching for High-Fidelity Family-Aware Protein Sequence GenerationPoster
Linear Bandits beyond Inner Product Spaces, the case of Bandit Optimal TransportPoster
Linear Causal Representation Learning by Topological Ordering, Pruning, and DisentanglementSpotlight
Linear Ensembles Wash Away Watermarks: On the Fragility of Distributional Perturbations in LLMsPoster
Linear Regression with Unknown Truncation Beyond Gaussian FeaturesPoster
Linear-Core Surrogates: Smooth Loss Functions with Linear Rates for Classification and Structured PredictionPoster
Linearizing Vision Transformer with Test-Time TrainingPoster
Linguistic Nepotism: Trading-off Quality for Language Preference in Multilingual RAGSpotlight
Linguistic Properties and Model Scale in Brain Encoding: From Small to Compressed Language ModelsSpotlight
Linguistic Relative Policy Optimization for Video Anomaly ReasoningPoster
Lions and Muons: Optimization via Stochastic Frank-WolfePoster
LipoPU: Pocket-level Prediction of Lipid-Protein Interactions via Positive-Unlabeled LearningPoster
Listening Through the Noise: Cauchy-Driven Diffusion Bridges for Robust Gastrointestinal Auscultation and Clinical BenchmarkingSpotlight
LitReview Arena: Evaluating Literature Review Agents with Battle-style Peer Review PlatformPoster
LiteVSR: Enabling Cross-Domain Fine-Grained Detail Generation in Light-Weight Transformers for Video Super-ResolutionPoster
LithoDreamer: A Physics-Informed World Model for Multi-Stage Computational LithographyPoster
Little By Little: Continual Learning via Incremental Mixture of Rank-1 Associative Memory ExpertsPoster
LiveFigure: Generating Editable Scientific Illustration with VLM AgentsPoster
LiveNewsBench: Evaluating LLM Web Search Capabilities with Freshly Curated NewsPoster
LiveOIBench: Can Large Language Models Outperform Human Contestants in Informatics Olympiads?Poster
LoBCD-GW: A Fast and Data-Dependent Algorithm for Computing Gromov-Wasserstein Distance via Localized Block Coordinate DescentPoster
LoCoT2V-Bench: Benchmarking Long-Form and Complex Text-to-Video GenerationPoster
LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model PretrainingPoster
LoPhyDA: Low-Rank Tensor and Physics Gradient Guided Diffusion for Atmospheric Data AssimilationPoster
LoRA-DA: Data-Aware Initialization for Low-Rank Adaptation via Asymptotic AnalysisPoster
LoRDO: Distributed Low-Rank Optimization with Infrequent CommunicationPoster
LoRe: Adaptive Interaction-Evaluation Routing with Per-step Interaction Budgets for Iterative Graph SolversPoster
LoSA: Locality Aware Sparse Attention in Diffusion Language ModelsPoster
Local Constrained Bayesian OptimizationPoster
Local Covariate Selection for Average Causal Effect Estimation without Pretreatment and Causal Sufficiency AssumptionsSpotlight
Local Hessian Spectral Filtering for Robust Intrinsic Dimension EstimationPoster
Local Intrinsic Dimension of Representations Predicts Alignment and Generalization in AI Models and Human BrainPoster
Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal ControlPoster
Local MAP Sampling for Diffusion ModelsPoster
Local Mechanisms of Compositional GeneralizationSpotlight
Local Minima in Quadratic-Penalty Relaxations of Binary Linear ProgramsPoster
Local Redundancy: An Information-Theoretic Measure of Plasticity from Synthetic MemorizationSpotlight
Local-Minima-Preserving Polynomial Relaxation of Ising ProblemsPoster
LocalV: Exploiting Information Locality for IP-level Verilog GenerationPoster
Localize and Neutralize: Gradient-Guided Token Suppression Against Visual Prompt Injection AttackPoster
Localize-and-Stitch: Efficient Model Merging via Sparse Task ArithmeticPoster
Localized, High-resolution Geographic Representations with Slepian FunctionsPoster
Localizing Memorized Regions in Diffusion Models via Coordinate-Wise Curvature DifferencesPoster
Locally Coherent Parallel Decoding in Diffusion Language ModelsPoster
Locate then Correct: Debiasing Attention Heads in CLIPPoster
Log-Normal Multiplicative Dynamics for Stable Low-Precision Deep LearningPoster
Logarithmic Switching Regret for Online Convex OptimizationPoster
LogicSAGE: Neuro-Symbolic Reasoning with Socratic-Guided EnhancementPoster
Logical Guidance for the Exact Composition of Diffusion ModelsPoster
Logit Distance Bounds Representational SimilarityPoster
Logit-Attention Divergence: Mitigating Position Bias in Multi-Image Retrieval via Attention-Guided CalibrationPoster
Long Grounded Thoughts: Synthesizing Grounded Visual Problems and Distilling Reasoning Chains at ScalePoster
Long Live The Balance: Information Bottleneck Driven Tree-based Policy OptimizationPoster
Long-Context Modeling with Dynamic Hierarchical Sparse Attention for Memory-Constrained LLM InferenceSpotlight
Long-Horizon Model-Based Offline Reinforcement Learning Without ConservatismPoster
Long-term Fairness with Selective LabelsPoster
LongCoT: Benchmarking Long-Horizon Chain-of-Thought ReasoningPoster
Look on Demand: A Cognitive Scheduling Framework for Visual Evidence Acquisition in Multimodal ReasoningPoster
Lookahead Path Likelihood Optimization for Diffusion LLMsPoster
Lookahead Sample Reward Guidance for Test-Time Scaling of Diffusion ModelsSpotlight
Lookahead Unmasking Elicits Reliable Decoding in Diffusion Language ModelsPoster
Lookahead-GCG: Improving Multi-Model Gradient-Based Jailbreaking Attacks via Nesterov MomentumPoster
Looking Locally: Object-Centric Vision Transformers as Foundation Models for Efficient SegmentationPoster
Loss-aware distributionally robust optimization via trainable optimal transport ambiguity setsSpotlight
Lost in Context: Discovering Context Anxiety in Large Language ModelsPoster
Lottery Prior: Randomized Neural Compression for Zero-Shot Inverse ProblemsOral
Low Kruskal-Rank AdaptationPoster
Low-Compute Watermark Removal via Dual-Domain Natural ProjectionPoster
Low-Rank and Sparsity Are All You Need: Exploring Robust Hierarchical Latent Subspaces for Transferable Adversarial AttackPoster
Low-cost Full Fine-tuning: Learning What to Update for LLMsPoster
Low-dimensional topology of deep neural networksPoster
Lower Bounds for Frank-Wolfe on Strongly Convex SetsPoster
Lower Complexity Bounds for Nonconvex-Strongly-Convex Bilevel Optimization with First-Order OraclesPoster
LumiNet: Perception-Driven Knowledge Distillation via Statistical Logit CalibrationPoster
LynX: Token Interface Alignment for Video+X LLMsPoster
M+Adam: Low-Precision Training via Mantissa–Exponent OptimizationPoster
M-IDoL: Information Decomposition for Modality-Specific and Diverse Representation Learning in Medical Foundation ModelPoster
MA$^3$S: Model-Agnostic Active Annotation Strategy for CrowdsourcingPoster
MAC-NeRF: Motion-Aware Curriculum Learning for Dynamic LiDAR NeRFsPoster
MACD: Model-Aware Contrastive Decoding via Counterfactual Data for Video-LLMsPoster
MAD: Manifold Attracted DiffusionPoster
MADA-Attack: Transferable Multi-modal Attention Distraction Adversarial Attack against Vision Language ModelsPoster
MADE: Benchmark Environments for Closed-Loop Materials DiscoveryPoster
MAFE: Enabling Equitable Algorithm Design in Multi-Agent Multi-Stage Decision-Making SystemsPoster
MAGIC: A Co-Evolving Attacker–Defender Adversarial Game for Robust LLM SafetyPoster
MAGIC: Multi-Granularity Language-Informed Image ClusteringPoster
MALICE: Memory-aware Loop Invariants Generation on Symbolic Execution TracesPoster
MAMBO-G: Magnitude-Aware Mitigation for Boosted GuidancePoster
MAPS: Memory-Aware Predictive Scheduling Framework for Large Language Models ServingPoster
MARS-SQL: A Multi-Agent Reinforcement Learning Framework For Text-To-SQLPoster
MARS: Modular Agent with Reflective Search for Automated AI ResearchPoster
MAS-Architect: Declarative Multi-Agent System Design via Separation of ConcernsPoster
MAS-Orchestra: Understanding and Improving Multi-Agent Reasoning Through Holistic Orchestration and Controlled BenchmarksPoster
MAS-ProVe: Understanding the Process Verification of Multi-Agent SystemsPoster
MASH: Modeling Abstention via Selective Help-SeekingPoster
MASPO: Joint Prompt Optimization for LLM-based Multi-Agent SystemsPoster
MASPOB: Bandit-Based Prompt Optimization for Multi-Agent Systems with Graph Neural NetworksSpotlight
MAST: Motif-Augmented Diffusion with Search Tree for Spectroscopic Molecular Structure ElucidationPoster
MAnchors: Memorization-Based Acceleration of Anchors via Rule Reuse and TransformationPoster
MC-HNN: Learning Latent Structural Semantics and High-Rank Representations for Hypergraph Neural NetworksPoster
MCCE: A Framework for Multi-LLM Collaborative Search in Discrete Spaces with Similarity-Filtered Preference LearningPoster
MCP-Persona: Benchmarking LLM Agents on Personalized MCP Tools and TasksPoster
MDGMIX: Boundary-Aware Subgraph Mixing for Multi-Domain Graph Pre-TrainingPoster
MDN: Parallelizing Stepwise Momentum for Delta Linear AttentionPoster
MEAL: A Benchmark for Continual Multi-Agent Reinforcement LearningPoster
MEC: Machine-Learning-Assisted Generalized Entropy Calibration for Semi-Supervised Mean EstimationPoster
MECAT: A Multi-Experts Constructed Benchmark for Fine-Grained Audio Understanding TasksPoster
MEDA: Medical-Oriented Activation Editing for Hallucination Mitigation in Medical Large Vision-Language ModelPoster
MEDUSA: Motion Elimination in Diffusion Using Spectral AttackPoster
MEG-XL: Data-Efficient Brain-to-Text via Long-Context Pre-TrainingPoster
MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM GamesPoster
MER-DG: Modality-Entropy Regularization for Multimodal Domain GeneralizationPoster
MESA: Improving MoE Safety Alignment via Decentralized ExpertisePoster
MET-Bench: Multimodal Entity Tracking for Evaluating the Limitations of Vision-Language and Reasoning ModelsPoster
MEnvAgent: Scalable Polyglot Environment Construction for Verifiable Software EngineeringSpotlight
MFCL Audio: An Audio Function Calling Evaluation for Large Language ModelsPoster
MFH-NAS:A Hybrid Neural Architecture Search Framework for Multimodal Fusion Object DetectionPoster
MGAL: A Multilingual Granularity-Aware Long-Context BenchmarkPoster
MICE-Bench: A Challenging and Comprehensive Benchmark for Multi-Reference Image Creation and EditingPoster
MIDSTEER: Optimal Affine Framework for Steering Generative ModelsPoster
MIMO-LP: A Multi-Input Multi-Output Framework for Subgraph-based Link PredictionPoster
MIMOMamba: From Scalar Duality to Matrix-Valued AttentionPoster
MIND: Decoupling Model-Induced Label Noise via Latent Manifold DisentanglementPoster
MIND: Multi-rationale INtegrated Discriminative Reasoning Framework for Multi-modal Large ModelsPoster
MINIF2F-DAFNY: LLM-Guided Mathematical Theorem Proving via Auto-Active VerificationPoster
MINIM: Privacy-Aware Minimal View for Agents via Trusted Local SanitizationPoster
MINT: Minimal Information Neuro-Symbolic Tree for Objective-Driven Knowledge-Gap Reasoning and Active ElicitationPoster
MIRA: A Score for Conditional Distribution Accuracy and Model ComparisonSpotlight
MIRO: MultI-Reward cOnditioned pretraining improves T2I quality and efficiencyPoster
MIST: Moment-Aligned Invariant Stability Transform for Robust Flow MatchingPoster
ML-Agent: Reinforcing LLM Agents for Autonomous Machine Learning EngineeringPoster
ML-Embed: Inclusive and Efficient Embeddings for a Multilingual WorldPoster
MLLM-4D: Towards Visual-based Spatial-Temporal IntelligencePoster
MLUBench: A Benchmark for Lifelong Unlearning Evaluation in MLLMsPoster
MM-DeepResearch: A Simple and Effective Multimodal Agentic Search BaselinePoster
MM-Snowball: Evaluating and Mitigating Hallucination Snowballing in Multimodal Multi-turn DialoguePoster
MM-Spectrum: Multimodal Multi-spectral Molecular Structural Elucidation with a Stable MoE FrameworkPoster
MMBench-Live: A Continuously Evolving Benchmark for Multimodal ModelsPoster
MMClima: A Framework for Multimodal Climate Science Data and EvaluationPoster
MME-Reasoning: A Broad-Spectrum Benchmark for Evaluating Logical Reasoning in MLLMsPoster
MMKU-Bench: A Multimodal Update Benchmark for Diverse Visual KnowledgePoster
MMPD-Bench: Bridging Multimodal Fission with Multi-Polarimetric Modalities DecompositionPoster
MN-Diff: Diffusion Parameterized MoE-NCDE for Continuous Time Series Generation with Irregular ObservationsPoster
MOC: Multi-Order Communication in LLM-based Multi-Agent SystemsPoster
MOD-SR: Unifying Multimodal Learning and Direct Optimization with Gradient-Guided Diffusion Model for Symbolic RegressionPoster
MODEL MERGING SCALING LAWS IN LARGE LANGUAGE MODELSPoster
MODEL SOUPS NEED ONLY ONE INGREDIENTPoster
MODUS: Decoder-only Any-to-Any Modeling of Diverse ModalitiesPoster
MOES-Pred: Molecular Structural Representation Learning by Adaptive Energy-Sentinel Vibration for Generalized Property PredictionPoster
MOOSE-Star: Unlocking Tractable Training for Scientific Discovery by Breaking the Complexity BarrierPoster
MORALISE: A Structured Benchmark for Moral Alignment in Visual Language ModelsPoster
MORE: A Multilingual Document Parsing Benchmark and EvaluationPoster
MPFM: Cross Multi-Domain Prototype Flow Matching for Log Anomaly DetectionPoster
MRPO: Magnitude-Regularized Policy Optimization via L1 ConstraintsPoster
MSP: Probabilistically Consistent Multi-Scale Action GenerationSpotlight
MTNL: A Unified Modeling Perspective for Enhancing Tensor Network LearningPoster
MUSA-PINN: Multi-scale Weak-form Physics-Informed Neural Networks for Fluid Flow in Complex GeometriesPoster
MUSE: Resolving Manifold Misalignment in Visual Tokenization via Topological OrthogonalityPoster
MV-FGAD: Towards Efficient and Effective Federated Graph Anomaly Detection via Multi-view LearningOral
MVI-Bench: A Comprehensive Benchmark for Evaluating Robustness to Misleading Visual Inputs in LVLMsPoster
MVISTA-4D: View-Consistent 4D World Model with Test-Time Action Inference for Robotic ManipulationPoster
MVP-LAM: Learning Action-Centric Latent Action via Cross-Viewpoint ReconstructionPoster
MVR-cache: Optimizing Semantic Caching via Multi-Vector Retrieval and Learned Prompt SegmentationPoster
MaMa: A Game-Theoretic Approach for Designing Safe Agentic SystemsPoster
MaMi-HOI: Harmonizing Global Kinematics and Local Geometry for Human-Object Interaction GenerationPoster
Machine Learning Hamiltonians are Accurate Energy-Force PredictorsPoster
MacroGuide: Topological Guidance for Macrocycle GenerationPoster
Magnitude Distance: A Geometric Measure of Dataset SimilarityPoster
Making Foundation Models Probabilistic via Singular Value EnsemblesPoster
Making Learner Weakness Actionable for Learning from Demonstration with Novice TeachersPoster
Making Models Unmergeable via Scaling-Sensitive Loss LandscapePoster
MalTree: Tracing Malware Evolution using Embeddings at ScalePoster
ManiSoft: Towards Vision-Language Manipulation for Soft RoboticsPoster
Manifold-Aligned Guided Integrated Gradients for Reliable Feature AttributionPoster
Manifold-Aware Perturbations for Constrained Generative ModelingSpotlight
Manifold-Optimal Guidance: A Unified Riemannian Control View of Diffusion GuidanceSpotlight
ManifoldKV: Training-Free KV Cache Compression via Euclidean Outlier DetectionPoster
Mantis: Lightweight Foundation Model for Time Series ClassificationPoster
Many Experiments, Few Repetitions, Unpaired Data, and Sparse Effects: Is Causal Inference Possible?Spotlight
Many Needles in a Haystack: Active Hit Discovery for Perturbation ExperimentsPoster
Many-Shot CoT-ICL: Making In-Context Learning Truly LearnPoster
MapDream: Task-Driven Map Learning for Vision-Language NavigationPoster
MapUQ: Map with Uncertainty Quantification for Robust BEV Vectorized ConstructionPoster
Margin-Adaptive Confidence Ranking for Reliable LLM JudgementPoster
MarketSim: Simulating Stock Markets with Large-Scale Generative AgentsPoster
Markov Chain Monte Carlo without Evaluating the Target: an Auxiliary Variable ApproachOral
Markovian Projection of Star-Shaped Diffusion for Exponential Family DistributionsPoster
Marrying Generative Model of Healthcare Events with Digital Twin of Human-Environment Interaction for Disease ReasoningPoster
Masked Multi-path Contrast with Confidence-Gated Semantic Imputation for Incomplete Multi-view ClusteringPoster
Masks Can Be Distracting: On Context Comprehension in Diffusion Language ModelsPoster
MatchFixAgent: Language-Agnostic Autonomous Repository-Level Code Translation Validation and RepairPoster
MathlibLemma: Folklore Lemma Generation and Benchmark for Formal MathematicsPoster
Matrix-Free GPU Semidefinite Programming for Quantum Ordered Search at the k=6 FrontierPoster
Matroid Algorithms Under Size-Sensitive Independence OraclesSpotlight
MaxSAT-Based Compression for Tsetlin MachinesPoster
Maximin Relative Improvement: Fair Learning as a Bargaining ProblemPoster
Maximizing mutual information between prompt and response improves LLM performance with no additional dataPoster
Maximizing the Spectral Energy Gain in Sub-1-Bit LLMs via Latent Geometry AlignmentPoster
Maximum Likelihood Reinforcement LearningOral
Maximum-Likelihood Learning of Latent Dynamics Without ReconstructionPoster
MePo: Meta Post-Refinement for Rehearsal-Free General Continual LearningPoster
Mean Flow Distillation: Robust and Stable Distillation for Flow Matching ModelsPoster
Mean Flow Policy OptimizationPoster
Mean-Shift PCA by Knockoﬀ MeanPoster
Measurement-Consistent Langevin Corrector for Stabilizing Latent Diffusion Inverse Problem SolversPoster
Measuring Intent Comprehension in LLMsPoster
Measuring Meta-Cultural Competency: A Spectral Framework for LLM Knowledge StructuresPoster
Measuring and Mitigating Post-hoc Rationalization in Reverse Chain-of-Thought GenerationPoster
MechVQA: Benchmarking and Enhancing Multimodal LLMs on Comprehensive Mechanical Drawing UnderstandingPoster
Mechanisms of Introspective AwarenessPoster
Mechanistic Anomaly Detection via Functional AttributionPoster
Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM UnitsOral
Mechanistic Interpretability as Statistical Estimation: A Variance AnalysisPoster
Med-Scout: Curing MLLMs' Geometric Blindness in Medical Perception via Geometry-Aware RL Post-TrainingPoster
Med-SegLens: Latent-Level Model Diffing for Interpretable Medical Image SegmentationPoster
MedCRP-CL: Continual Medical Image Segmentation via Bayesian Nonparametric Semantic Modality DiscoveryPoster
MedCoG: Maximizing LLM Inference Density in Medical Reasoning via Meta-Cognitive RegulationPoster
MedMamba: Multi-View State Space Models with Adaptive Graph Learning for Medical Time Series ClassificationPoster
MedMosaic: A Challenging Large Scale Benchmark of Diverse Medical AudioPoster
MedREK: Retrieval-Based Editing for Medical LLMs with Key-Aware PromptsPoster
MedSIGHT: Towards Grounded Visual Comprehension in Medical Large Vision-Language ModelsPoster
MedScope: Incentivizing "Think with Videos" for Clinical Reasoning via Coarse-to-Fine Tool CallingPoster
Meerkat-VL: Implicit Risk Safety Alignment in Multimodal LLMs via Perceptual Reasoning and Self-VerificationPoster
Mem-T: Densifying Rewards for Long-Horizon Memory AgentsPoster
MemCast: Memory-Driven Time Series Forecasting with Experience-Conditioned ReasoningPoster
MemDecoder: Enhancing Test-Time Compute for LLM Agents via Reinforced Memory DecodingPoster
MemEvolve: Meta-Evolution of Agent Memory SystemsPoster
MemIncept: Steering LLM Agents via Cooperative Stealthy Memory InjectionsPoster
MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon ReasoningPoster
Membership Inference Attacks for Unseen ClassesPoster
Memora: A Harmonic Memory Representation Balancing Abstraction and SpecificityPoster
Memoria-Bench: A Comprehensive Benchmark for Evaluating Memory in Long-Horizon Autonomous AgentsPoster
Memory Caching: RNNs with Growing MemoryPoster
Memory Savings at What Cost? A Study of Alternatives to BackpropagationPoster
Memory as Dynamics: Learning Reliability-Guided Predictive Models for Online Video PerceptionPoster
Memory as a Markov Matrix: Sample Efficient Knowledge Expansion via Token-to-Dictionary MappingPoster
Memory is Reconstructed, Not Retrieved: Graph Memory for LLM AgentsPoster
Memory-Distilled Selection for Noise-Robust Anomaly DetectionPoster
Memory-Efficient LLM Pretraining via Minimalist Optimizer DesignPoster
Memory-Efficient LLMs Training with Dynamic Sparsity: From Stability to Practical ScalingPoster
MemoryBench: A Benchmark for Memory and Continual Learning in LLM SystemsSpotlight
MemoryLLM: Plug-n-Play Interpretable Feed-Forward Memory for TransformersPoster
MentisOculi: Revealing the Limits of Reasoning with Mental ImageryPoster
Merge to Remember: Sharpness-Aware Isotropic Merging for Continual LearningPoster
MergeMix: Optimizing Mid-Training Data Mixtures via Learnable Model MergingPoster
Mesh Based Simulations with Spatial and Temporal awarenessPoster
Mesh Field Theory: Port–Hamiltonian Formulation of Mesh-Based PhysicsPoster
MeshTok: Efficient Multi-Scale Tokenization for Scalable PDE TransformersPoster
Message Passing on the Edge: Towards Scalable and Expressive GNNsPoster
Message Tuning Outshines Graph Prompt Tuning: A Prismatic Space PerspectivePoster
Meta Context Engineering via Agentic Skill EvolutionPoster
Meta Flow Maps enable scalable reward alignmentPoster
Meta-Black-Box Optimization Can Do Search Guidance for Expensive Constrained Multi-Objective OptimizationPoster
Meta-Learning with Generalized Ridge Regression: High-dimensional Asymptotics, Optimality and Hyper-covariance EstimationPoster
Meta-iLaD: Identifiable Latent Dynamics via Meta-Learning of Dynamics EnvironmentsPoster
Meta-learning Structure-Preserving DynamicsPoster
MetaBio: Learning from metadata for bioacoustics foundation modelsPoster
MetaDNS: Enhancing Exploration in Discrete Neural Samplers via MetadynamicsPoster
MetaMoE: Diversity-Aware Proxy Selection for Privacy-Preserving Mixture-of-Experts UnificationPoster
MetaOthello: A Controlled Study of Multiple World Models in TransformersPoster
MetaStreet: Semi-Supervised Multimodal Learning for Street-Level Socioeconomic PredictionPoster
MetaphorVU: Towards Metaphorical Video UnderstandingSpotlight
Metis: Learning to Jailbreak LLMs via Self-Evolving Metacognitive Policy OptimizationPoster
Metric–-Phase Fields: Decoupling Distance and Sign for Thin-Structure Reconstruction from Unoriented Point CloudsPoster
MiVE: Multiscale Vision-language features for reference-guided video EditingPoster
Midtraining Bridges Pretraining and Posttraining DistributionsOral
Milestone-Guided Policy Learning for Long-Horizon Language AgentsPoster
Mind Dreamer: Untethering Imagination via Active Counterfactual Reasoning on Latent ManifoldsPoster
Mind Your Entropy: From Maximum Entropy to Trajectory Entropy-Constrained RLPoster
Mind Your Margin and Boundary: Are Your Distilled Datasets Truly Robust?Oral
Mind the Gap: Catching Hallucinations via Evidence Drop on the Reasoning ManifoldPoster
Mind the Gap: Mixtures of Gaussians in Approximate Differential PrivacyPoster
Mind the Gap: Structure-Aware Consistency in Preference LearningPoster
Mind the budget: Accelerating Deep Reinforcement Learning using Early Exit Neural NetworksPoster
Mind-Omni: A Unified Multi-Task Framework for Brain-Vision-Language Modeling via Discrete DiffusionSpotlight
MindFlow: Mind Supernet Powered Thinking Flows for Research Idea InnovationPoster
MindZero: Learning Online Mental Reasoning With Zero AnnotationsPoster
MineDraft: A Framework for Batch Parallel Speculative DecodingPoster
MiniAppBench: Evaluating the Shift from Text to Interactive HTML Responses in LLM-Powered AssistantsSpotlight
MiniMax Learning of Interpretable Factored Stochastic Policies from Conjoint Data, with Uncertainty QuantificationPoster
MiniX: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation ModelsPoster
Minibatch Optimal Transport and Perplexity Bound Estimation in Discrete Flow MatchingPoster
Minibatch selection for Language Models via Partition Matroid Constrained Gradient MatchingPoster
Minimax Optimal Strategy for Delayed Observations in Online Reinforcement LearningOral
Minimax-Optimal Policy Regret in Partially Observable Markov GamesPoster
Minimizing Mismatch Risk: A Prototype-Based Routing Framework for Zero-shot LLM-generated Text DetectionPoster
Minimizing Upper Confidence Bounds: A Data-Driven Framework for Stochastic ProgrammingPoster
Minimum Distance Summaries for Robust Neural Posterior EstimationPoster
Mining Tensor/Neuron-Level Sparsity to Maximize Mixture-of-Experts Potential in Post-Training and InferencePoster
Mining Useful General Data for Low-Resource Domain AdaptationPoster
Mirror Descent Actor Critic via Bounded Advantage LearningPoster
Mirror Descent Policy Optimisation for Robust Constrained Markov Decision ProcessesPoster
Mirror Descent Under Generalized SmoothnessPoster
Mirror Mean-Field Langevin DynamicsPoster
Mitigating Bias in Locally Constrained Decoding via Tractable ProposalsPoster
Mitigating Conversational Inertia in Multi-Turn AgentsPoster
Mitigating Error Accumulation in Continuous Navigation via Memory-Augmented Kalman FilteringPoster
Mitigating Error Propagation in Low-Rank Approximation of Large Models via Distribution-Aware WhiteningPoster
Mitigating Gradient Pathology in PINNs through Aligned ConstraintPoster
Mitigating Hallucinations in Large Vision-Language Models via Causal Route GatingSpotlight
Mitigating Label Shift in Tabular In-Context Learning via Test-Time Posterior AdjustmentPoster
Mitigating Manifold Departure: Uncertainty-aware Subspace Rectification for Trustworthy MLLM DecodingPoster
Mitigating Mask Prior Drift and Positional Attention Collapse in Large Diffusion Vision-Language ModelsPoster
Mitigating Noise-Induced Layout Priors for Object Counting in Diffusion ModelsPoster
Mitigating Per-Sample Harm in Stochastic OptimizationPoster
Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward ModelingPoster
Mitigating Plasticity Loss through Architectural Design in Continual LearningPoster
Mitigating Premature Exploitation in Particle-based Monte Carlo for Inference-Time ScalingPoster
Mitigating Reward Hacking in LLM-based Recommendation: A Preference Optimization ApproachPoster
Mitigating Reward Hacking in RLHF via Bayesian Non-negative Reward ModelingOral
Mitigating Staleness in Asynchronous Pipeline Parallelism via Basis RotationPoster
Mitigating Surgical Data Imbalance with Dual-Prediction Video Diffusion ModelPoster
Mitigating Translationese Bias in Multilingual LLM-as-a-Judge via Disentangled Information BottleneckPoster
Mitigating Visual Hallucinations via Semantic Curriculum Preference Optimization in MLLMsPoster
Mitigating the Contractivity Trap in Diffusion ODEs via Stein StabilizationPoster
Mitigating the Modality Gap in Vision–Language Models with Fractal Spectral GeometryPoster
Mitigating the Safety–Utility Trade-off in LLM Alignment via Adaptive Safe Context LearningPoster
MixFP4: Extending NVFP4 to Mixed Micro-Format via Scale-Bit Reuse and Tensor Core Co-designPoster
MixQuant: Pushing the Limits of Block Rotations in Post-Training QuantizationPoster
MixReasoning: Switching Modes to ThinkPoster
Mixing Configurations for Downstream PredictionPoster
Mixing Expertise with Confidence: A Mixture of Expert Framework for Robust Multi-Modal Continual LearnerPoster
Mixture Prototype Flow Matching for Open-Set Supervised Anomaly DetectionPoster
Mixture of Concept Bottleneck ExpertsSpotlight
Mixture of Distributions Matters: Dynamic Sparse Attention for Efficient Video Diffusion TransformersPoster
Mixture of Horizons in Action ChunkingPoster
MixtureVitae: Open Web-Scale Pretraining Dataset With High Quality Instruction and Reasoning Data Built from Permissive-First Text SourcesPoster
Mixtures Closest To A Given Measure: A Semidefinite Programming ApproachOral
Mixtures of geodesic factor analyzers on Riemannian homogeneous spacesPoster
MoCL: Metabolic Optimization for Curvature-Aware Continual LearningPoster
MoCo-EA: Exploiting Adversarial Mode Connectivity for Efficient Evolutionary AttacksPoster
MoDA: Modulation Adapter for Fine-Grained Visual Understanding in Instructional MLLMsPoster
MoFO: Momentum-Filtered Optimizer for Mitigating Forgetting in LLM Fine-TuningPoster
MoLF: Mixture-of-Latent-Flow for Pan-Cancer Spatial Gene Expression Prediction from HistologyPoster
MoLoRA: Composable Specialization via Per-Token Adapter RoutingPoster
MoRGEN: Mixture-of-Resolutions Generative Forecasting for Irregularly Sampled Medical Time-Series DataPoster
MoSA: Motion-constrained Stress Adaptation for Mitigating Real-to-Sim Gap in Continuum Dynamics via Learning Residual AnisotropyPoster
MoSE: Mixture of Slimmable Experts for Efficient and Adaptive Language ModelsPoster
MoSSP: A Momentum-Based Single-Loop Stochastic Penalty Method for Nonconvex Constrained DC OptimizationPoster
MoST: Mixing Speech and Text with Modality-Aware Mixture of ExpertsPoster
MoVie: Multimodal Video Compression with Text GuidancePoster
MobileFusion: Mobile-Friendly Infrared and Visible Image Fusion via Structural Re-parameterizationPoster
Mobility-Embedded POIs: Learning What A Place Is and How It Is Used from Human MovementPoster
Modality-Decoupled Online Recursive EditingPoster
Mode Seeking meets Mean Seeking for Long Video GenerationPoster
Model Fusion via RetrofittingPoster
Model Monotonicity in Autobidding Auctions: When Do Better Predictions Lead to Better Outcomes?Poster
Model-Based Diffusion Sampling for Predictive Control in Offline Decision MakingPoster
Model-Dowser: Data-Free Importance Probing to Mitigate Catastrophic Forgetting in Multimodal Large Language ModelsPoster
Model-Free Robust Average-Reward Reinforcement Learning with Sample Complexity AnalysisPoster
Model-Preserving Adaptive RoundingPoster
Modeling Attributional Style at Scale: A Dataset and Analysis for Psychological Attribution Assessment and ReframingPoster
Modeling Covariate Transition for Efficient Estimation of Longitudinal Treatment Effects in Randomized ExperimentsPoster
Modeling Hierarchical Thinking in Large Reasoning ModelsOral
Modeling Long-Tail Relations in the Operating Room via In-Context Multimodal LearningPoster
Modeling Spectral Energy Shifts in Spatio-Temporal Graph Anomaly DetectionPoster
Modeling temporal scRNA-seq data with latent Gaussian process and optimal transportPoster
Modelling Attention with Aitchison Geometry: Token Distinguishability and Temperature ScalingPoster
Models Under SCOPE: Scalable and Controllable Routing via Pre-hoc ReasoningPoster
ModernVBERT: Towards Smaller Visual Document RetrieversPoster
Modular Pretraining Enables Access ControlSpotlight
MolAlign3D: Enhancing Fixed-Dimensional E(3)-Equivariant Latent Space for High-Fidelity 3D Molecular Reconstruction and EditingPoster
Moment Matching Q-LearningPoster
Momentum Further Constrains Sharpness at the Edge of Stochastic StabilityPoster
Monitorability as a Free Gift: How RLVR Spontaneously Aligns ReasoningPoster
Monitoring LLM-based Multi-Agent Systems Against Corruptions via Node EvaluationPoster
Monitoring MonitorabilityOral
MonoScale: Scaling Multi-Agent System with Monotonic ImprovementPoster
Monotonic Variational Gaussian Process for Efficient Data CollectionPoster
More Capable, Less Cooperative? When LLMs Fail at Zero-Cost CollaborationPoster
More Edits, More Stable: Understanding the Lifelong Normalization in Sequential Model EditingPoster
More Sail than Ballast: Addressing Harmful Knowledge Leakage in the Expansive Reasoning Space of LRMsPoster
Mosaic: Runtime-Efficient Multi-Agent Embodied PlanningPoster
Mosaic: Unlocking Over 30$\times$ Context Length for Diffusion LLMs Inference via Global Memory Planning and Dynamic Peak TamingPoster
MoshiRAG: Asynchronous Knowledge Retrieval for Full-Duplex Speech Language ModelsPoster
MotiMotion: Motion-Controlled Video Generation with Visual ReasoningPoster
Motion Attribution for Video GenerationOral
Motion Dynamics Learning for Few-Shot Embodied AdaptationPoster
Motion Planning in Compressed Representation SpacesPoster
Motion-Aware Caching for Efficient Autoregressive Video GenerationPoster
Motion-Residual Conflict-Aware Time Reversal for Generative InbetweeningPoster
MotionGRPO: Overcoming Low Intra-Group Diversity in GRPO-Based Egocentric Motion RecoveryPoster
MotionMAR: Multi-scale Auto-Regressive Human Motion Reconstruction from Sparse ObservationsPoster
Move-Then-Operate: Behavioral Phasing for Human-Like Robotic ManipulationPoster
Moving Beyond Sparse Grounding with Complete Screen Parsing SupervisionPoster
Moving Out: Physically-grounded Human-AI CollaborationPoster
MuCO: Generative Peptide Cyclization Empowered by Multi-stage Conformation OptimizationPoster
MuLoCo: Muon is a Practical Inner Optimizer for DiLoCoPoster
MulFCoder: Framework-conditioned Multi-agent for MLLM-based Multi-framework Front-end Code GenerationPoster
Multi-Accurate CATE is Robust to Unknown Covariate ShiftsPoster
Multi-Adapter Representation Interventions via Energy CalibrationPoster
Multi-Agent Reinforcement Learning with Submodular RewardPoster
Multi-Agent Teams Hold Experts BackPoster
Multi-Distribution Robust Conformal PredictionPoster
Multi-Head Attention as a Source of Catastrophic Forgetting in MoE TransformersPoster
Multi-Head LatentMoE and Head Parallel: Communication-Efficient and Deterministic MoE ParallelismPoster
Multi-Integration of Labels across Categories for Component Identification (MILCCI)Poster
Multi-Label Test-Time Adaptation with Bayesian Conditional PriorsPoster
Multi-Level Strategic Classification: Incentivizing Improvement through Promotion and Relegation DynamicsPoster
Multi-Objective Bayesian Optimization via Adaptive $\varepsilon$-Constraint DecompositionPoster
Multi-Objective Learning for Diffusion Models: A Statistical Theory under Semi-Supervised LearningPoster
Multi-Objective Preference Optimization: Improving Human Alignment of Generative ModelsPoster
Multi-Objective Protein Design via Memory-Aware Test-Time Scaling in Diffusion ModelsPoster
Multi-Round Human–AI Collaboration with User-Specified RequirementsPoster
Multi-Scale Wavelet Transformers for Operator Learning of Dynamical SystemsPoster
Multi-Task Bayesian In-Context LearningPoster
Multi-Task GRPO: Reliable LLM Reasoning Across TasksPoster
Multi-View Causal Discovery without Non-Gaussianity: Identifiability and AlgorithmsPoster
Multi-Way Representation AlignmentPoster
Multi-agent imitation learning with function approximation: linear Markov games and beyondPoster
Multi-label learning with contrastive cluster self-supervision for 3D hierarchical semantic segmentationPoster
Multi-marginal temporal Schrödinger Bridge Matching from unpaired dataPoster
Multi-scale Explainer for Graph Neural NetworksPoster
Multi-task Linear Regression without Eigenvalue Lower Bounds: Adaptivity, Robustness and SafetyPoster
Multi-timescale Reinforcement Learning by Value ReconstructionPoster
Multi-view Consistent Latent Action Learning for World Modeling and ControlPoster
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM SafetyPoster
MultiHal: Multilingual Dataset for Knowledge-Graph Grounded Evaluation of LLM HallucinationsPoster
MultiLoReFT: Decoupling Shared and Modality-Specific Subspaces in Multimodal Learning via Low-Rank Representation Fine-TuningPoster
MultiPriv: Benchmarking Individual-Level Privacy Reasoning in Vision-Language ModelsPoster
Multicalibration Yields Better MatchingsPoster
Multilingual Safety Alignment Via Sparse Weight EditingPoster
Multilingual Safety Alignment via Representation-Space SeparabilityPoster
Multilingual Unlearning in LLMs: Transfer, Dynamics, and ReversibilityPoster
Multimarginal flow matching with optimal transport potentialsPoster
Multimodal Crystal Flow: Any-to-Any Modality Generation for Unified Crystal ModelingPoster
Multimodal Function Vectors for Spatial RelationsPoster
Multimodal Fusion via Self-Consistent Task-Gradient FieldsPoster
Multimodal Latent Language Modeling with Next-Token DiffusionSpotlight
Multimodal Meta-Verifier with Explicit Structured RecalibrationPoster
Multimodal Nested Learning for Decoupled and Coordinated OptimizationOral
Multimodal Scaling Laws for Task & Data-Optimized Models of Visual CortexPoster
Multiple Choice Learning of Low-Rank Adapters for Language ModelingPoster
Multipole Semantic Attention: A Fast Approximation of Softmax Attention for PretrainingPoster
Multivariate distributional reinforcement learning using sliced divergencesPoster
Multiview Self-Representation Learning across Heterogeneous ViewsPoster
Muon in Associative Memory Learning: Training Dynamics and Scaling LawsPoster
MuonSSM: Orthogonalizing State Space Models for Sequence ModelingOral
MusicDET: Zero-Shot AI-Generated Music DetectionPoster
Must All Negatives Be Pushed Away Equally? Uncertainty-Aware Cross-View Geo-Localization via Normal Inverse Gamma DistributionPoster
MutAtlas: A PDB-Wide Energy-Guided Atlas of Protein Mutation EffectsPoster
N2M: Bridging Navigation and Manipulation by Learning Pose Preference from RolloutPoster
NAACA: Training-Free NeuroAuditory Attentive Cognitive Architecture with Oscillatory Working Memory for Salience-Driven Attention GatingPoster
NAVIGATE: Evaluating Visual-Guided Search Decision-Making on the Open WebPoster
NBCG: Nash-Bargained Causal Game for Long-Tailed Multi-Label NLPPoster
NEMO: Execution-Aware Optimization Modeling via Autonomous Coding AgentsPoster
NExT-Guard: Training-Free Streaming Safeguard without Token-Level LabelsPoster
NITP: Next Implicit Token Prediction for LLM Pre-trainingPoster
NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding AgentsPoster
NNiT: Width-Agnostic Neural Network Generation with Structurally Aligned Weight SpacesPoster
NOMAD: Lifelong Trajectory Planning via Non-Parametric Bayesian Memory-Adaptive Diffusion ExpertsPoster
NaRA: Noise-Aware LoRA for Parameter-Efficient Fine-Tuning of Diffusion LLMsPoster
Names Don’t Matter: Symbol-Invariant Transformer for Open-Vocabulary LearningPoster
NanoFLUX: Distillation-Driven Compression of Large Text-to-Image Generation Models for Mobile DevicesPoster
NanoQuant: Efficient Sub-1-bit Quantization of Large Language ModelsPoster
NanoSpec: Accelerating Speculative Decoding using Minimalist In-Context VocabulariesPoster
Narrowing the ANN–SNN Gap for 1D Signal Classification with Multi-Scale Temporal Encoding and Sparsity-Regularized Transform EncodingPoster
Nash Equilibria in Games with Playerwise Concave Coupling Constraints: Existence and ComputationOral
Native Active Perception as Reasoning for Omni-Modal UnderstandingPoster
Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement LearningPoster
Native Spatio-Temporal 4D Variational AutoencoderPoster
Natural Hypergradient Descent: Algorithm Design, Convergence Analysis, and Parallel ImplementationPoster
Natural Language Actor–Critic Is Bilevel: Learning to Reason with Textual FeedbackPoster
NavOL: Navigation Policy with Online Imitation LearningPoster
NaviAgent: Graph‑Driven Bilevel Planning for Scalable Tool OrchestrationPoster
NaviCache: Test-Time Self-Calibration Caching for Video GenerationPoster
Navigating the Energy Landscape of Collaboration: Multi-Agent Communication Graph Generation via Score-Based DiffusionPoster
Navigating the Flatlands: Dual Adaptive Sharpness-Aware Minimization for Domain GeneralizationPoster
Navigating the Pareto Frontier of Alignment:Spectrum-Adaptive Fine-Tuning for LLMsPoster
NeUQI: Near-Optimal Uniform Quantization Parameter Initialization for Low-Bit LLMsPoster
Near-Minimax Multi-Objective RL under Predictable Adversarial Preferences and Preference-Free Exploration in Linear MDPsPoster
Near-Optimal Convergence of Accelerated Gradient Methods under Generalized and $(L_0,L_1)$-SmoothnessPoster
Near-Optimal Dynamic Matching via Coarsening with Application to Heart TransplantationPoster
Near-Optimal Private Linear Regression via Iterative Hessian MixingSpotlight
Near-Optimal Regret for KL-Regularized Multi-Armed BanditsPoster
Near-Optimal Regret for Policy Optimization in Contextual MDPs with General Offline Function ApproximationPoster
Near-Universal Multiplicative Updates for Nonnegative Einsum FactorizationPoster
Near-optimal and Efficient First-Order Algorithm for Multi-Task Learning with Shared Linear RepresentationPoster
Necessary Conditions for Compositional Generalization of Embedding ModelsOral
Needles in the Haystack: Addressing Signal Dilution Improves scRNA-seq Perturbation Response Modeling and EvaluationPoster
Negative Sampling From the Ground Up: A Redesign for Graph-based RecommendationsPoster
Negatives-Dominant Contrastive Learning for Generalization in Imbalanced DomainsPoster
Nested Spatio-Temporal Time Series ForecastingPoster
Nested birth-death processes are competitive with parameter-heavy neural networks as time-dependent models of protein evolutionPoster
NetDiff: Graph Diffusion with Improved Global Capabilities to Generate and Update Mobile Network TopologiesPoster
Networked Information Aggregation for Binary ClassificationPoster
NeurIPS: Neuro-anatomical Inductive Priors for Sphere-based Brain DecodingPoster
NeurOCNN: A Neural-Operator-Based Model for Physiological Time SeriesPoster
NeurVLA: Unleashing Failure-Handling Capability of Vision-Language-Action Models via Neural-Symbolic ReasoningPoster
Neural Attention Search Linear: Towards Adaptive Token-Level Hybrid Attention ModelsPoster
Neural Collapse by Design: Learning Class Prototypes on the HyperspherePoster
Neural Concept Verifier: Scaling Prover-Verifier Games via Concept EncodingsSpotlight
Neural Control: Adjoint Learning Through Equilibrium ConstraintsPoster
Neural Dispersion on GraphsPoster
Neural Feature Geometry Evolves as Discrete Ricci FlowSpotlight
Neural Honeytrace: Plug&Play Watermarking Framework against Model Extraction AttacksPoster
Neural Implicit Action Fields: From Discrete Waypoints to Continuous Functions for Vision-Language-Action ModelsPoster
Neural Logistic BanditsPoster
Neural Low-Discrepancy SequencesPoster
Neural Minimum Weight Perfect Matching for Quantum Error CodesPoster
Neural Modular Physics for Elastic SimulationPoster
Neural QAOA$^2$: Differentiable Joint Graph Partitioning and Parameter Initialization for Quantum Combinatorial OptimizationPoster
Neural Quantum States in Mixed PrecisionPoster
Neural Thickets: Diverse Task Experts Are Dense Around Pretrained WeightsSpotlight
Neural Vector Lyapunov–Razumikhin Certificates for Delayed Interconnected SystemsPoster
Neural-HSS: Hierarchical Semi-Separable Neural PDE SolverPoster
Neural-Inspired Modeling of Auditory Selection and Compensation for Audio-Visual Speech SeparationPoster
NeuralFLoC: Neural Flow-Based Joint Registration and Clustering of Functional DataPoster
Neural–Evolutionary Symbolic Regression with Global Constraints: Constraint-Aware Decoding and Reward ShapingPoster
Neuro-Fuzzy Concept Learning for Interpretable Large Multimodal ModelsPoster
Neuro-Symbolic AI for Analytical Solutions of Differential EquationsPoster
Neuro-evolutionary Continual Reinforcement LearningSpotlight
NeuroCLUS: A Foundation Model with Functional Clustering for Intracranial Neural DecodingPoster
NeuroMamba: A Universal Spatiotemporal Module for Robust Perception in Degraded Sensory StreamsPoster
Neuromem: A Granular Decomposition of the Streaming Lifecycle in External Memory for LLMsPoster
NeuronCtrl: Geometry-Aware Safe Closed-Loop Generative Control for Neuronal Microenvironment DynamicsSpotlight
Neutral-Reference Prompting for Vision–Language ModelsPoster
New Algorithms for Fully-Dynamic k-center with OutliersPoster
New Bounds for Kernel Sums via Fast Spherical EmbeddingsPoster
New Wide-Net-Casting Jailbreak Attacks Risk Large ModelsPoster
Newton-coupled Dual-Teacher Semi-supervised Learning FrameworkPoster
Next-Gen CAPTCHAs: Leveraging the Cognitive Gap for Scalable and Diverse GUI-Agent DefensePoster
Next-Token Prediction and Regret MinimizationPoster
No Data? No Problem: Robust Vision-Tabular Learning with Missing ValuesPoster
No Free Lunch: Non-Asymptotic Analysis of Prediction-Powered InferencePoster
No Global Plan in Sight: Uncover the Myopic Planning Horizon of LLMsPoster
No More K-means: Single-Stage Sparse Coding for Efficient Multi-Vector RetrievalPoster
No More, No Less: Least-Privilege Language ModelsPoster
No Need to Train Your RDB Foundation ModelPoster
No Retraining at Edge: Efficient Resource-Aware Mixed-Precision Quantization via Federated Supernet LearningPoster
Noise Tectonics: Measuring the Stability of AI Benchmark EcosystemsPoster
Noise as a Natural Regularizer in Markov Decision Processes: Connecting Environmental Stochasticity and Policy SimplicityPoster
Noise-Guided Transport: Imitation Learning from Random PriorsPoster
Noise-Robust Density Estimation for Tabular Data Anomaly DetectionPoster
Noise-corrected GRPO: From Noisy Rewards to Unbiased GradientsPoster
NoiseSDF2NoiseSDF: Learning Clean Neural Fields from Noisy SupervisionPoster
Noisy Pairwise-Comparison Random Search for Smooth Nonconvex OptimizationPoster
Noisy-Channel Minimum Bayes Risk DecodingPoster
Noisy-Space Policy Gradient for Diffusion Policies in Offline Reinforcement LearningPoster
Non-Adversarial Imitation Learning Provably Free of Compounding Errors: The Role of Bellman ConstraintsPoster
Non-Euclidean Gradient Descent Operates at the Edge of StabilityOral
Non-Monotonic Autoregressive Sequence ModelPoster
Non-Parametric Optimization for Scalable Learning in Stochastic Decision ProblemsPoster
Non-Parametric Probabilistic Robustness: A Conservative Risk Estimator under Unknown Perturbation DistributionsPoster
Non-Stationary Online Structured Prediction with Surrogate LossesPoster
Non-Uniform Noise-to-Signal Ratio in the REINFORCE Policy-Gradient EstimatorPoster
NonZero: Interaction-Guided Exploration for Multi-Agent Monte Carlo Tree SearchSpotlight
Nonconvex Low-Rank Tensor Representation with Deep Priors for Multiview Subspace ClusteringPoster
Nonlinear Covariate Balance in Experimental DesignPoster
Nonparametric Data Attribution for Diffusion ModelsPoster
Nonparametric Distribution Regression Re-calibrationPoster
Nonparametric LLM Evaluation from Preference DataPoster
NorMuon: Making Muon more efficient and scalableSpotlight
Norm$\times$Direction: Restoring the Missing Query Norm in Vision Linear AttentionPoster
Normality Calibration in Semi-supervised Graph Anomaly DetectionPoster
Normalization Equivariance for Arbitrary Backbones, with Application to Image DenoisingPoster
Normalization-equivariant Diffusion Models: Learning Posterior Samplers From Noisy And Partial MeasurementsPoster
Normalized Energy Models for Linear Inverse ProblemsPoster
Normalized Rewards for Preference OptimizationPoster
Normalizing Diffusion Kernels with Optimal TransportPoster
Normalizing Flows with Iterative DenoisingPoster
Not All Answers Are Contextually Persuadable: Inference Dynamics in Large Language Models under Contextual InfluencePoster
Not All Frequencies Are Equal: Energy-Adaptive Diffusion for Time Series ForecastingPoster
Not All Invariants Are Equal: Curating Training Data to Accelerate Program Verification with SLMsPoster
Not All Prefills Are Equal: PPD Disaggregation for Multi-turn LLM ServingPoster
Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement LearningPoster
Numina-Lean-Agent: An Open and General Agentic Reasoning System for Formal MathematicsPoster
OBCache: Optimal Brain KV Cache Pruning for Efficient Long-Context LLM InferencePoster
OBJVanish: Prompt-Driven Generation of Physically Realizable 3D LiDAR-Invisible ObjectsPoster
OC-space: a Unifying Perspective on Verification of Tree EnsemblesSpotlight
OCNR: Stabilizing Self-Play by Mitigating Iteration-Collapse With One-Class Novelty RewardsPoster
OLion: Approaching the Hadamard Ideal by Intersecting Spectral and L inf Implicit BiasesPoster
OMAC: A Holistic Optimization Framework for LLM-Based Multi-Agent CollaborationOral
OMP: One-step Meanflow Policy with Directional AlignmentPoster
OOVDet: Low-Density Prior Learning for Zero-Shot Out-of-Vocabulary Object DetectionPoster
OPIC: Enhancing Language Model Merging via Optimizing In-Context CapabilityPoster
OPT-Engine: Benchmarking the Limits of LLMs in Optimization Modeling via Complexity ScalingPoster
OPTION: Optimal Transport–Guided Flow Matching for Incomplete and Unaligned Multi-View ClusteringPoster
OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every IterationOral
ORBIT: A Prognostic World Model for Ocular Reasoning Based on Imagined TrajectoriesPoster
OSAQ: Outlier Self-Absorption for Accurate Low-bit LLM QuantizationPoster
OSCS: Online Selection with Provable FAR Control for LLM SafetyPoster
OSF: On Pre-training and Scaling of Sleep Foundation ModelsPoster
OSM+: Billion-Level Open Street Map Dataset for City-wide ExperimentsSpotlight
OSNIP: Breaking the Privacy-Utility-Efficiency Trilemma in LLM Inference via Obfuscated Semantic Null SpacePoster
OServe: Accelerating LLM Serving via Spatial-Temporal Workload OrchestrationPoster
OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM AgentsPoster
OVLR: Efficient, Scalable, and Robust Training via Output-Level Variance-Reduced Likelihood RatioPoster
OXE-AugE: A Large-Scale Robot Augmentation of OXE for Scaling Cross-Embodiment Policy LearningSpotlight
ObjEmbed: Towards Universal Multimodal Object EmbeddingsPoster
Object-level Semantic and Spatial Distillation for Open Vocabulary DetectionPoster
Obliviate: Efficient Unlearning in Recommender SystemsPoster
OcclusionFormer: Arranging Z-Order for Layout-Grounded Image GenerationPoster
Off-Policy Evaluation Beyond Overlap under Network InterferencePoster
Off-Policy Evaluation for Missingness-Aware Policies in MDPs with Rewards Missing Not at RandomPoster
Off-Policy Evaluation with Strategic Agents via Local DisclosurePoster
Off-Policy Learning in Large Action Spaces: Optimization Matters More Than EstimationPoster
Offline Multi-Agent Reinforcement Learning via Sequential Score DecompositionPoster
Offline Multi-agent Continual Cooperation via Skill Partition and ReusePoster
Offline Preference Optimization for Rectified Flow with Noise-Tracked PairsPoster
Offline Reinforcement Learning of High-Quality Behaviors Under Robust Style AlignmentSpotlight
Offline Reinforcement Learning with Generative Trajectory PoliciesPoster
Offline Reinforcement Learning with Universal Horizon ModelsPoster
Offline Two-Player Zero-Sum Markov Games with KL RegularizationPoster
Olaf-World: Orienting Latent Actions for Video World ModelingPoster
Old Habits Die Hard: How Conversational History Geometrically Traps LLMsPoster
Olivia: Harmonizing Time Series Foundation Models with Power Spectral DensityPoster
Olmix: A Framework for Data Mixing Throughout LM DevelopmentPoster
Omitted Variable Bias in Language Models Under Distribution ShiftPoster
Omni-Perception Policy Optimization for Multimodal Emotion ReasoningPoster
Omni-fMRI: A Universal Atlas-Free fMRI Foundation ModelPoster
OmniAID: Decoupling Semantic and Artifacts for Universal AI-Generated Image Detection in the WildPoster
OmniDenseCap: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual CaptionsPoster
OmniFit: Bridging Modalities via Layer-Adaptive Token Compression for Omnimodal Large Language ModelsSpotlight
OmniMoE: An Efficient MoE by Orchestrating Atomic Experts at ScalePoster
OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language ModelsPoster
OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy OptimizationPoster
OmniShow: Orchestrating Multimodal Conditions for Human-Object Interaction Video GenerationPoster
OmniVL-Guard: Towards Unified Vision-Language Forgery Detection and Grounding via Balanced RLPoster
OmniVideo-R1: Reinforcing Audio-visual Reasoning with Query Intention and Modality AttentionPoster
On Computation and Reinforcement LearningOral
On Contraction of Sequential and Offset Rademacher ComplexitiesPoster
On Densest $k$-Subgraph Mining and Diagonal Loading: Optimization Landscape and Finite-Step Exact Convergence AnalysisPoster
On Effectiveness and Efficiency of Agentic Tool-calling and RL TrainingPoster
On Efficient Scaling of GNNs via IO-Aware Layers ImplementationsSpotlight
On Expressive Power of Floating-Point TransformersPoster
On Group Relative Policy Optimization Collapse in Agent Search: The Lazy Likelihood-DisplacementPoster
On Information Self-Locking in Reinforcement Learning for Active ReasoningPoster
On Learnability and Disambiguation of Multiclass Partial Concept ClassesPoster
On Local Policies for Graph-Structured Markov Decision ProcessesPoster
On Minimum Depth and Width of Floating-Point Neural Networks for Representing Floating-Point FunctionsOral
On Multi-Step Theorem Prediction via Non-Parametric Structural PriorsPoster
On Path to Multimodal Historical Reasoning: HistBench and HistAgentPoster
On Regret Bounds of Thompson Sampling for Bayesian OptimizationPoster
On Revisiting Entropy for Identifying Mislabeled Medical ImagesPoster
On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMsPoster
On Stable Long-Form Generation: Benchmarking and Mitigating Length VolatilityPoster
On Structured State-Space DualityPoster
On Testing Conditional Mean Independence for Manifold-Valued DataPoster
On The Variability Of Concept Activation VectorsPoster
On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon LengthPoster
On Uniform Error Bounds for Kernel Regression under Non-Gaussian NoisePoster
On the "Induction Bias" in Sequence ModelsPoster
On the Ability of Transformers to Verify PlansPoster
On the Accuracy of Newton Step and Influence Function Data AttributionsSpotlight
On the Adversarial Robustness of Large Vision-Language Models under Visual Token CompressionPoster
On the Anisotropy of Score-Based Generative ModelsPoster
On the Collapse of Generative Paths: A Criterion and Correction for Diffusion SteeringPoster
On the Computational Complexity of Performative PredictionPoster
On the Convergence Rate of LoRA Gradient DescentOral
On the Convergence of Adaptive Gradient Methods for Nonconvex OptimizationPoster
On the Convergence of Decentralized Stochastic Minimax Optimization Algorithm with Compressed CommunicationPoster
On the Convergence of Steepest Descent and Adaptive Gradient Methods under Non-Uniform SmoothnessPoster
On the Coordination of Value-Maximizing BiddersPoster
On the Difficulty of Learning a Meta-network for Training Data SelectionOral
On the Effect of Misspecifying the Embedding Dimension in Low-rank Network ModelsPoster
On the Entropy Dynamics in Reinforcement Fine-Tuning of Large Language ModelsPoster
On the Epistemic Uncertainty of Overparametrized Neural NetworksPoster
On the Expressive Power of GNNs to Solve Linear SDPsPoster
On the Expressive Power of Permutation-Equivariant Weight-Space NetworksSpotlight
On the Fragility of Data Attribution When Learning Is DistributedPoster
On the Generalization Gap in Self-Evolving Language Model ReasoningPoster
On the Generalization in Topology Optimization via Sensitivity-Conditioned Bernoulli Flow MatchingPoster
On the Identifiability of Poisson Branching Structural Causal Model Under Latent ConfoundingOral
On the Infinite Width and Depth Limits of Predictive Coding NetworksPoster
On the Interaction of Batch Noise, Adaptivity, and Compression, under $(L_0,L_1)$-Smoothness: An SDE ApproachPoster
On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language ModelsSpotlight
On the Intrinsic Limits of Transformer Image Embeddings in Non-Solvable Spatial ReasoningPoster
On the Learnability of Test-Time Adaptation: A Recovery Complexity PerspectivePoster
On the Learning Dynamics of RLVR at the Edge of CompetencePoster
On the Limits of LLM Adaptability: Impact of LLM Pre-Training on Annotation Task PerformanceOral
On the Limits of Test-Time Compute: Sequential Reward Filtering for Better InferencePoster
On the Optimization Trajectory of DeepWalk EmbeddingsSpotlight
On the Plasticity and Stability for Post-Training Large Language ModelsPoster
On the Power of (Approximate) Reward Models for Inference-Time ScalingPoster
On the Power of Source Screening for Learning Shared Feature ExtractorsSpotlight
On the Power of Statistics in Class-Incremental Learning with Pretrained ModelsPoster
On the Provable Suboptimality of Momentum SGD in Nonstationary Stochastic OptimizationPoster
On the Relationship Between Activation Outliers and Feature Death in Sparse AutoencodersPoster
On the Robustness of Langevin Dynamics to Score Function ErrorPoster
On the Role of Batch Size in Stochastic Conditional Gradient MethodsPoster
On the Salience of Low-Probability Tokens for AI-Generated Text Detection: A Multiscale Uncertainty PerspectivePoster
On the Sample Efficiency of Inverse Dynamics Models for Semi-Supervised Imitation LearningPoster
On the Separability of Information in Diffusion ModelsPoster
On the Sharp Input-Output Analysis of Nonlinear Systems under Adversarial AttacksSpotlight
On the Theoretical Limitations of Embedding-based Link PredictionPoster
On the Theory of Continual Learning with Gradient Descent for Neural NetworksPoster
On the existence of consistent adversarial attacks in high-dimensional linear classificationSpotlight
On the origin of neural scaling laws: from random graphs to natural languageSpotlight
Once-for-All: Scalable Simultaneous Forecasting via Equilibrium State EstimationPoster
One Batch Is Enough: A Unified Dataset Condensation Framework for General Time Series AnalysisPoster
One Bias After Another: Mechanistic Reward Shaping and Persistent Biases in Language Reward ModelsPoster
One Bug, Hundreds Behind: LLMs for Large-Scale Bug DiscoveryPoster
One Coin Has Two Sides: Single Poistive Multi Label Learning from Salient AnnotationsPoster
One Intervention per Component is Enough: Towards Identifiability in Linear Stochastic Dynamics from Steady StateSpotlight
One LR Doesn’t Fit All: Heavy-Tail Guided Layerwise Learning Rates for LLMsPoster
One Model to Translate Them All: Universal Any-to-Any Translation for Heterogeneous Collaborative PerceptionPoster
One Step Forward and K Steps Back: Better Reasoning with Denoising Recursion ModelsPoster
One Tool Is Enough: Reinforcement Learning of LLM Agents for Repository-Level Code NavigationPoster
One-Shot Weighted Ensemble Estimation for Federated Quantile Regression: Optimal Statistical Guarantees under Heterogeneous Structured DataPoster
One-Step Gradient Delay is Not a Barrier for Large-Scale Asynchronous Pipeline Parallel LLM PretrainingPoster
One-Step Graph-Structured Neural Flows for Irregular Multivariate Time Series ClassificationPoster
One-Step Residual Shifting Diffusion for Image Super-Resolution via DistillationPoster
One-Way Policy Optimization for Self-Evolving LLMsPoster
One-shot Conditional Sampling: MMD meets Nearest NeighborsPoster
One-shot Entropy Minimization for Language Model ReasoningPoster
One-step Latent-free Image Generation with Pixel Mean FlowsPoster
One-step Optimal Transport via Regularized Distribution Matching DistillationPoster
OnePO: Direct One-stage Policy Optimization for SFT-free Domain AdaptationPoster
OneSearch: A Preliminary Exploration of the Unified End-to-End Generative Framework for E-commerce SearchPoster
Online Bayesian Experimental Design for Partially Observed Dynamical SystemsPoster
Online Change Point Detection for Multivariate Inhomogeneous Poisson Processes Time SeriesPoster
Online Compatible Reward Identification from Preference FeedbackPoster
Online Conformal Prediction via Universal Portfolio AlgorithmsSpotlight
Online Continual Learning with Dynamic Label HierarchiesPoster
Online Contract Design With Unknown TechnologyPoster
Online Fair Division with Additional InformationPoster
Online Learning and Inference for Cox Proportional Hazards Model Using Renewable Sieve EstimationPoster
Online Learning with Recency: Algorithms for Sliding-window Streaming Multi-armed BanditsPoster
Online Linear Programming for Multi-Objective Routing in LLM ServingPoster
Online Packet Scheduling with Deadlines and LearningPoster
Online Robust Reinforcement Learning with General Function ApproximationPoster
Online Rubrics Elicitation from Pairwise ComparisonsPoster
Online Social Welfare Function-based Resource AllocationPoster
Online Tensor Learning: Computational and Statistical Trade-offs, Adaptivity and Optimal RegretPoster
Op-CAD: Benchmarking and Investigating Operation-oriented CAD GenerationPoster
Open Materials Generation with Inference-Time Reinforcement LearningPoster
Open-Text Aerial Detection: A Unified Framework For Aerial Visual Grounding And DetectionPoster
Open-o3-Video: Grounded Video Reasoning with Explicit Spatio-Temporal EvidencePoster
OpenDeception: Learning Deception and Trust in Human–AI Interaction via Multi-Agent SimulationPoster
OpenGPT-4o-Image: A Comprehensive Dataset for Advanced Image Generation and EditingPoster
OpenHA: A Series of Open-Source Hierarchical Agentic Models in MinecraftPoster
OpenIKLR: Bridging the Reasoning Gap in Open-World Scenarios via Iterative Premise CompletionPoster
OpenMAG: A Comprehensive Benchmark for Multimodal-Attributed GraphPoster
OpenSage: Self-programming Agent Generation EnginePoster
OpenTSLM: Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series DataPoster
Operationalizing the Superficial Alignment Hypothesis via Task ComplexityPoster
Operator Splitting with Hamilton-Jacobi-based ProximalsPoster
Ophiuchus: Incentivizing Tool-augmented ''Think with Images'' for Joint Medical Segmentation, Understanding and ReasoningPoster
Opportunistic Expert Activation: Batch-Aware Expert Routing for Faster Decode Without RetrainingPoster
Opt-Miner: Empowering Information-Seeking Agent with Tree-Guided Data Synthesis for Optimization ModelingPoster
Opt-Verifier: Unleashing the Power of LLMs for Optimization Modeling via Dual-Side VerificationPoster
OptMaster: A DAG-Based Framework for Formulation and Heuristic Discovery in OptimizationPoster
OptProver: Bridging Olympiad and Optimization through Continual Training in Formal Theorem ProvingPoster
OptiFluence: Principled Design of Privacy CanariesPoster
Optimal Anytime Algorithms for Online Convex Optimization with Adversarial ConstraintsPoster
Optimal Attention Temperature Improves the Robustness of In-Context Learning under Distribution Shift in High DimensionsPoster
Optimal Bayesian Stopping for Efficient Inference of Consistent LLM AnswersPoster
Optimal Classical and Quantum Algorithms for Gradient Testing and Estimation by ComparisonsPoster
Optimal Decision-Making Based on Prediction SetsOral
Optimal Design for Multinomial Logit Model with Applications to Best Assortment IdentificationPoster
Optimal Domain-Aware Privacy Mechanisms for Synthetic Data GenerationPoster
Optimal Estimation of Continuous Treatment Effects with Kernel Ridge RegressionPoster
Optimal Fair Aggregation of Crowdsourced Noisy Labels using Demographic Parity ConstraintsPoster
Optimal Learning from Label Proportions with General Loss FunctionsPoster
Optimal Pricing for Data-Augmented AutoML MarketplacesPoster
Optimal Quantum Speedups for Repeatedly Nested Expectation EstimationPoster
Optimal Rates for Feasible Payoff Set Estimation in GamesSpotlight
Optimal Regret for Policy Optimization in Contextual BanditsPoster
Optimal Regularization for Performative LearningPoster
Optimal Self-Consistency for Efficient Reasoning with Large Language ModelsPoster
Optimal Splitting of Language Models from Mixtures to Specialized DomainsPoster
Optimal Statistical Guarantees for Diffusion Models on Low-Dimensional, Multi-Modal DataPoster
Optimal Stopping in Latent Diffusion ModelsPoster
Optimal Top-$k$ Identification from Pairwise ComparisonsPoster
Optimal Transport Group Counterfactual ExplanationsPoster
Optimal Transport for Reward Modeling from Noisy FeedbackPoster
Optimal Transport under Group Fairness ConstraintsSpotlight
Optimal Transport with Symmetry GroupsPoster
Optimal Transport–Guided Stochastic Control for Graph Combinatorial OptimizationPoster
Optimal Unconstrained Self-Distillation in Ridge Regression: Strict Improvements, Precise Asymptotics, and One-Shot TuningPoster
Optimal and Scalable MAPF via Multi-Marginal Optimal Transport and Schrödinger BridgesOral
Optimal conversion from Rényi Differential Privacy to $f$-Differential PrivacyPoster
Optimal structure learning and conditional independence testingSpotlight
Optimality of FSQ tokens for continuous diffusion for categorical data with application to text-to-speechPoster
Optimization Dynamics of Equivariant and Augmented Neural NetworksPoster
Optimization with Access to Auxiliary InformationPoster
Optimization, Generalization and Differential Privacy Bounds for Gradient Descent on Kolmogorov–Arnold NetworksPoster
Optimized Deferral for Imbalanced SettingsPoster
Optimizing Agentic Reasoning with Retrieval via Synthetic Semantic Information Gain RewardPoster
Optimizing Diversity and Quality through Base-Aligned Model CollaborationPoster
Optimizing Few-Step Generation with Adaptive Matching DistillationPoster
Optimizing Inference-Time Compute for Medical Reasoning via Uncertainty QuantificationPoster
Optimizing KV Cache Eviction from an Output Perturbation PerspectivePoster
Optimizing Language Models for Crosslingual Knowledge ConsistencyPoster
Optimizing Network Simulation: Enhancing Performance Prediction Accuracy via Neural Architecture SearchPoster
Optimizing Rank for High-Fidelity Implicit Neural RepresentationsPoster
Optimizing Return Distributions with Distributional Dynamic ProgrammingPoster
Optimizing Visual Generative Models via Distribution-wise RewardsPoster
OrchJail: Jailbreaking Tool-Calling Text-to-Image Agents by Orchestration-Guided FuzzingPoster
Orchestrating Spatial Semantics via a Zone-Graph Paradigm for Intricate Indoor Scene GenerationPoster

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.