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

Order Matters in Retrosynthesis: Structure-aware Generation via Reaction-Center-Guided Discrete Flow MatchingPoster
Order Matters: Unveiling the Hidden Impact of Macro Placement Sequences via Proxy-Guided LLM EvolutionPoster
Order within Chaos: Capturing Intrinsic Energy Anomalies for AI-Manipulated Image Forgery LocalizationPoster
Origo: Physically Interpretable Multi-Physics PDE Pre-training through Neural Operator SplittingPoster
Orthogonal Concept Erasure for Diffusion ModelsOral
Orthogonal Hierarchical Decomposition for Structure-Aware Table Understanding with Large Language ModelsPoster
Orthogonal Model MergingPoster
Out-of-Distribution Evaluation of Rule-Based and Strategic Reasoning in Chess TransformersPoster
Outcome-Aware Spectral Feature Learning for Instrumental Variable RegressionPoster
Outcome-Based Rewards Do Not Guarantee Faithful and Verifiable ReasoningPoster
Outrunning LLM Cutoffs: A Live Kernel Crash Resolution Benchmark for AllPoster
Over-Alignment vs Over-Fitting: The Role of Feature Learning Strength in GeneralizationPoster
Overclocking Electrostatic Generative ModelsPoster
Overcoming PINNs Failure Modes In High Dimension With Low-Rank Fourier SumSpotlight
Overcoming the Incentive Collapse ParadoxPoster
Overcoming the Modality Gap in Context-Aided ForecastingPoster
Overthinking: Amplifying Reasoning Weights to Extract Learned SecretsPoster
OvisOCR: End-to-End Document Parsing via Aligning Specialized Perception with General ReasoningPoster
PAC-Bayesian Reinforcement Learning Trains Generalizable PoliciesPoster
PACE: Parameter Change for Unsupervised Environment DesignPoster
PACE: Post-Causal Entropy Modeling for Learned LiDAR Point Cloud CompressionPoster
PACE: Proactive Agent-Level Admission Control for Efficient Agentic Batch InferencePoster
PACEAttention: Principled and Adaptive Feature Compression-Expansion Grounded in the Geometry of $\text{MCR}^2$Poster
PACER: Acyclic Causal Discovery from Large-scale Interventional DataPoster
PACT: Self-Evolving Physical Safety Alignment for Diffusion Policies in Embodied ManipulationSpotlight
PADA-Coder: Improving Plan-Following Code Generation via Perturbation-Verified Attention Distillation and Dynamic AlignmentPoster
PADD: Path-Aligned Decompression Distillation for Non-Router Teacher to Guide MoE Student LearningPoster
PADS-TAL: Padding-Annealed Diffusion Sampling in Text-Aware Latent Space for Robust and Diverse Text-to-Music GenerationPoster
PAMD: Structured Adaptive Distances for Bisimulation Representations in Visual Reinforcement LearningPoster
PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant AttacksPoster
PASO: Step Parallel Stochastic OptimizationPoster
PATCHCODE: Discrete Latent Predictive Learning for EEG Foundation ModelPoster
PATRA: Pattern-Aware Alignment and Balanced Reasoning for Time Series Question AnsweringPoster
PAWS: Preference Learning with Advantage-Weighted SegmentsPoster
PCA of Probability Measures: Sparse and Dense Sampling RegimesPoster
PCGS: Deblurring 3D Gaussian Splatting with Patch ComparisonPoster
PCRNet: Phase-aware Complex Refinement Network for EEG-based Auditory Attention DecodingPoster
PDAgent: An LLM-Driven Autonomous Agent Framework Towards *In Silico* Protein Design via Directed MutationPoster
PDFBench: A Benchmark for De Novo Protein Design from FunctionPoster
PEARL: Differentially Private and Entropy-Aware Regulated Language GenerationPoster
PESD-TSF: A Period-Aware and Explicit Structured Decomposition Framework for Long-Term Time Series ForecastingPoster
PETS: A Principled Framework Towards Optimal Trajectory Allocation for Efficient Test-Time Self-ConsistencyPoster
PFT: Phonon Fine-tuning for Machine Learned Interatomic PotentialsPoster
PGC: Peak-Guided Calibration for Generalizable AI-Generated Image DetectionPoster
PGD-NO: A Neural Operator with Precomputed Geometry Decomposition for 3D Million-Scale physics simulationsPoster
PGS: Effective LLM Code Refinement via Property-Oriented and Structurally Minimal FeedbackPoster
PGT: Procedurally Generated Tasks for improving fine-grained understanding in MLLMsPoster
PHALAR: Phasors for Learned Musical Audio RepresentationsPoster
PICACO: Pluralistic In-Context Value Alignment via Total Correlation OptimizationPoster
PINE: Pruning Boosted Tree Ensembles with Conformal In-Distribution Prediction EquivalencePoster
PINNfluence: Interpreting PINNs through Influence FunctionsPoster
PISA: Privacy-Preserving Split Adaptation with Model IP ProtectionPoster
PISCES: Annotation-free Text-to-Video Post-Training via Optimal Transport-Aligned RewardsPoster
PLANTAIN: Plan-Answer Interleaved ReasoningSpotlight
PLASH: Provably Linear-Time Attention with Selective Higher-Order Feature SketchingPoster
PLATE: Plasticity-Tunable Efficient Adapters for Geometry-Aware Continual LearningPoster
PLSemanticsBench: A Formal Semantics Reasoning Benchmark for CodePoster
PLaID++: A Preference Aligned Language Model for Targeted Inorganic Materials DesignPoster
PLoRA: Efficient Concurrent LoRA Training for Large Language ModelsPoster
PMSPO: Progressive Matching and Semantic-Aware Policy Optimization for Camouflaged Object DetectionPoster
PODiff: Latent Diffusion in Proper Orthogonal Decomposition Space for Scientific Super-ResolutionPoster
POET-X: Memory-efficient LLM Training by Scaling Orthogonal TransformationOral
POLCA: Stochastic Generative Optimization with LLMPoster
POLIA: Policy Optimization with Visual-Object-Level Intrinsic Advantage for Multimodal ReasoningPoster
PPDL: LLM-Based Flows as Probabilistic ProgramsPoster
PPI Candidate Ranking: Large-Scale Evaluation of a Domain Knowledge–Guided PipelinePoster
PPT-Eval: A Benchmark for Computer-Use Agents on PowerPoint TasksPoster
PRAC: Principal-Random Subspace for LLM Activation Compression and Memory-Efficient TrainingPoster
PRIM：Cooperative Dynamic Token Compression for Efficient Large Multimodal ModelsPoster
PRISM: Demystifying Retention and Interaction in Mid-TrainingSpotlight
PRISM: Distribution-free Adaptive Computation of Matrix Functions for Accelerating Neural Network TrainingPoster
PRISM: Gauge-Invariant Tangent-Space Differentially Private LoRAOral
PRISM: Perception Reasoning Interleaved for Sequential Decision Making.Poster
PRISM: Sequence Modeling as Parallel Residual IterationPoster
PRISM: Synergizing Vision Foundation Models via Self-organized Expert SpecializationPoster
PRISM: Training-Free Video Anomaly Detection via Intrinsic Statistical ModelingPoster
PRM-PBE: Process Reward Model for Reinforcement Learning in Programming-by-ExamplePoster
PRPO: Paragraph-level Policy Optimization for Vision-Language Deepfake DetectionPoster
PS-PPO : Prefix-Sampling PPO for Critic-Free RLHFPoster
PSBench: Editing Image via GUI Agents in PhotoshopPoster
PSG-Nav: Probabilistic Scene Graph Navigation via Multiverse Decision MakingPoster
PSMix: Robust Point Cloud Recognition through Spectral Domain MixingPoster
PULSE: Generative Phase Evolution for Non-Stationary Time Series ForecastingPoster
PVDepth: Panoramic Video Depth Estimation via Geometry-Aware Spatiotemporal AdaptationPoster
Pair2Scene: Learning Local Object Relations for Procedural Scene GenerationPoster
Panini: Continual Learning in Token Space via Structured MemoryPoster
PanoWorld-X: Generating Explorable Panoramic Worlds via Sphere-Aware Video DiffusionSpotlight
PaperBanana: Automating Academic Illustration for AI ScientistsSpotlight
ParEVO: Synthesizing Code for Irregular Data: High-Performance Parallelism through Agentic EvolutionPoster
ParaTool: Shifting Tool Representations from Context to ParametersPoster
ParalESN: Enabling parallel information processing in Reservoir ComputingPoster
Parallel Stochastic Gradient-Based Planning for World ModelsPoster
Parallel-Probe: Towards Efficient Parallel Thinking via 2D ProbingPoster
ParamMem: Augmenting Language Agents with Parametric Reflective MemoryPoster
Parameter Decorrelation via Transition-Variance Alignment for Multivariate Time-series ForecastingPoster
Parameter Manifold PurificationPoster
Parameter-Masked Decoupled Optimization for Cross-Domain Class-Incremental LearningPoster
Parameter-free Dynamic Regret: Time-varying Movement Costs, Delayed Feedback, and MemoryPoster
Parameters as Experts: Adapting Vision Models with Dynamic Parameter Routing for Dense PredictionsPoster
Parametric Prior Mapping Framework for Non-stationary Probabilistic Time Series ForecastingPoster
Parametrized Power-Iteration Clustering for Directed GraphsPoster
Pareto-Guided Optimal Transport for Multi-Reward AlignmentPoster
ParisKV: Fast and Drift-Robust KV-Cache Retrieval for Long-Context LLMsPoster
Parsimonious Learning-Augmented Online Metric MatchingPoster
PartCo: Part-Level Correspondence Priors Enhance Category DiscoveryPoster
Partial Fusion of Neural Networks: Efficient Tradeoffs Between Ensembles and Weight AggregationPoster
Partial Identification under High-Dimensional Potential Outcomes and Confounders via Optimal TransportPoster
Partial Ring Scan: Revisiting Scan Order in Vision State Space ModelsPoster
Particle Flow for Learning from Label ProportionsPoster
Particle-Guided Diffusion Models for Partial Differential EquationsPoster
Particles Don’t Care About Z: Towards Scaling Entropy Estimation of Unnormalized DensitiesPoster
Partitioning for Intrinsic Model Inversion Resistance in Collaborative InferencePoster
Path-Coupled Bellman Flows for Distributional Reinforcement LearningPoster
Path-Decoupled Hyperbolic Flow Matching for Few-Shot AdaptationPoster
Path-conditioned training: a principled way to rescale ReLU neural networksPoster
Path-dependent Discrete Amortized InferenceOral
PathWise: Planning through World Model for Automated Heuristic Design via Self-Evolving LLMsPoster
PathwayLLM: Explainable Clinical Trajectory Modeling with Structured Pathways for Sepsis PredictionPoster
PatternKV: Flattening KV Representation Expands Quantization HeadroomPoster
Patterning: The Dual of InterpretabilityPoster
Peer-Preservation in Frontier ModelsPoster
PepCompass: Navigating Peptide Embedding Spaces Using Riemannian GeometryPoster
Per-example Gradients: a New Frontier for Understanding and Improving OptimizersPoster
PerceptOS: Semantic-Aware Kernel Optimization for OS-Intensive Workloads via Hardware-Software AlignmentPoster
PerceptionRubrics: Calibrating Multimodal Evaluation to Human PerceptionPoster
Perceptrons and Localization of Attention’s Mean-Field LandscapeSpotlight
Perceptual Flow Network for Visually Grounded ReasoningPoster
Performative Learning TheoryPoster
Performative Policy Gradient: Optimality in Performative Reinforcement LearningPoster
Periodic Bayesian Flow Networks with Additive AccuracyPoster
PersistBench: When Should Long-Term Memories Be Forgotten by LLMs?Poster
Persistent Backdoor Attacks in Class-Incremental Learning via Structural Invariant AnchoringPoster
Persistent Semantic Entities in Tool-Augmented LLM SystemsPoster
Persona-Pruner: Sculpting Lightweight Models for Role-PlayingPoster
Persona2Web: Benchmarking Personalized Web Agents for Contextual Reasoning with User HistoryPoster
Personalized Additive Modeling for Multi-level Federated LearningPoster
Personalized Image Generation via Human-in-the-loop Bayesian OptimizationPoster
Personalized Policy Learning through Discrete ExperimentationPoster
Persuasive PrivacyPoster
PerturbDiff: Functional Diffusion for Single-Cell Perturbation ModelingPoster
Pessimistic Verification for Open-Ended Math QuestionsPoster
Phase-Aware Mixture of Experts for Agentic Reinforcement LearningPoster
Phase-Type Variational Autoencoders for Heavy-Tailed DataPoster
PhaseAlign: Complex Phase Alignment for Stable Open-Vocabulary Semantic SegmentationPoster
PhaseCoder: Microphone Geometry-Agnostic Spatial Audio Understanding for Multimodal LLMsPoster
PhenoBrain: Phenotype-Conditioned Long-Range Communication for Multi-Modal Brain Network AnalysisOral
PhoStream: Benchmarking Real-World Streaming for Omnimodal Assistants in Mobile ScenariosPoster
PhotoAgent: Exploratory Visual Aesthetic Planning with Large Vision ModelsOral
Phy-CoSF: Physics-Guided Continuous Spectral Fields Reconstruction and Spectral Super-Resolution for Snapshot Compressive ImagingPoster
PhyScene3D: Physically Consistent 3D Interactive Tabletop Scene GenerationPoster
PhysForge: Generating Physics-Grounded 3D Assets for Interactive Virtual WorldPoster
PhysHanDI: Physics-Based Reconstruction of Hand-Deformable Object InteractionsPoster
Physically-Guided Data-Space Rectified Flow for Precipitation NowcastingPoster
Physics from Video: Identifiability of Time-Invariant Second-Order ODEs under Minimal Trajectory ConditionsPoster
Physics in 2-Steps: Locking Motion Priors Before Visual Refinement Erases ThemPoster
Physics-Aware Spatiotemporal Causal Graph Network for Forecasting with Limited DataPoster
Physics-Guided Motion Loss for Video Generation ModelPoster
Physics-Informed Distillation of Diffusion Models for PDE-Constrained GenerationPoster
Physics-Informed Residual FlowsPoster
Physics-Informed Self-Supervised Learning on Efficient Electron-Density Images for Organic Material Property PredictionPoster
Physics-informed Neural Operator Learning for Nonlinear Grad-Shafranov EquationPoster
Physics-informed coarsening for multigrid graph neural networks surrogatesPoster
Physics-informed diffusion models in spectral spacePoster
Physiology as Language: Translating Nocturnal Breathing to EEGPoster
Physiology-Aware Masked Cross-Modal Reconstruction for Biosignal Representation LearningPoster
Pianist Transformer: Towards Expressive Piano Performance Rendering via Scalable Self-Supervised Pre-TrainingPoster
PinTok: Tokenizers Deserve Dedicated Pinned CPU-Compute and MemoryPoster
PipeSD: An Efficient Cloud-Edge Collaborative Pipeline Inference Framework with Speculative DecodingPoster
Pix2Key: Controllable Open-Vocabulary Retrieval with Semantic Decomposition and Self-Supervised Visual Dictionary LearningPoster
PixCLIP: Towards Fine-grained Vision-Language Understanding via Any-granularity Pixel-Text AlignmentPoster
Plain Transformers are Surprisingly Powerful Link PredictorsPoster
Plan Then Action: High-Level Planning Guidance Reinforcement Learning for LLM ReasoningPoster
Plan for Speed: Dilated Scheduling for Masked Diffusion Language ModelsPoster
Plan in Sandbox, Navigate in Open Worlds: Learning Physics-Grounded Abstracted Experience for Embodied NavigationPoster
Plan, Decouple, Assimilate: Physics-Aware Object Insertion in Remote Sensing ImageryPoster
Planar Symmetric Pattern GenerationPoster
Plasticity Activation via Polar Operator: A Plug-in Method for Balancing Stability and PlasticityPoster
Platonic Transformers: A Solid Choice For EquivariancePoster
PlotCraft: Pushing the Limits of LLMs for Complex and Interactive Data VisualizationPoster
PluRel: Synthetic Data unlocks Scaling Laws for Relational Foundation ModelsPoster
Plug-and-Play Benchmarking of Reinforcement Learning Algorithms for Large-Scale Flow ControlPoster
Plug-and-Play Diffusion Meets ADMM: Dual-Variable Coupling for Robust Medical Image ReconstructionPoster
Plug-and-Play Guidance for Discrete Diffusion Models via Gradient-Informed Logit CorrectionPoster
Plug-and-Play Label Map Diffusion for Universal Goal-Oriented NavigationPoster
Plug-and-Play Spiking Operators: Breaking the Nonlinearity Bottleneck in Spiking TransformersPoster
PlugGuard: A Streaming Safeguard for Large Models via Latent Dynamics-Guided Risk DetectionPoster
PlugMem: A Task-Agnostic Plugin Memory Module for LLM AgentsPoster
Pluralistic LeaderboardsPoster
PnP-Corrector: A Universal Correction Framework for Coupled Spatiotemporal ForecastingPoster
PoMtVRS: Preference-Optimized Multi-Task Vehicle Routing Solver with Preference GatingPoster
PointCHR: Point Cloud Analysis via Curvature-Aware Hyperbolic RectificationPoster
PointDiT: Pixel-Space Diffusion for Monocular Geometry EstimationPoster
Poison with Style: A Practical Poisoning Attack on Code Large Language ModelsPoster
PolarDepth: Monocular Transparent Object Depth from Polar-Physics PriorsPoster
Polaris: Coupled Orbital Polar Embeddings for Hierarchical Concept LearningPoster
Policy Search via Bayesian Optimization with Temporal Difference Gaussian ProcessesPoster
Policy-Driven World Model Adaptation for Robust Offline Model-based Reinforcement LearningPoster
PolicyGuard: Towards Test-time and Step-level Backdoor Defense for Reinforcement Learning AgentPoster
Polishing-Only Policies in Peer Reviews are Currently Not EnforceablePoster
PolyFlow: Safe and Efficient Polytope-Constrained Flow Matching with Constraint Embedding and Projection-free UpdatePoster
PolySAE: Modeling Feature Interactions in Sparse Autoencoders via Polynomial DecodingPoster
Polyphonia: Training-Free Context-Aware Music Editing with Acoustic-Informed Attention CalibrationPoster
PonderLM-2: Pretraining LLM with Latent Thoughts in Continuous SpaceSpotlight
Population-Aware Imitation Learning in Mean-field Games with Common NoisePoster
Population-Free Pareto Tracking for Sample-Efficient Multi-Policy MORLPoster
PortraitRL: Reinforcement Learning for Personalized Portrait Pose Transfer with Multi-Objective Reward ModelingPoster
Pose-ICL: 3D-Aware In-Context Learning for Pose-Controllable Subject CustomizationPoster
Position Is All You Need: A Free Lunch Token Compression Strategy for MLLM-based Referring Expression SegmentationPoster
Position: *Beyond Text* The Text-Centric Bias in Foundation Models Must Be Revisited for a Speech-First FutureSpotlight
Position: AGI Requires a Coordination Layer on Top of Pattern RepositoriesPoster
Position: AI Capabilities Are Not Increasing ExponentiallyPoster
Position: AI Evaluation Should Work With HumansPoster
Position: AI Evaluations Should be Grounded on a Theory of CapabilityPoster
Position: AI Governance Needs ISO-like Interoperability Protocols, Not Just LawsSpotlight
Position: AI Leaderboards Are Underserving the Global South: A Case Study from IndiaPoster
Position: AI Lock-In Is in Progress, and We Must Be PreparedSpotlight
Position: AI Must Become Planet-Centered, Not Human-CenteredPoster
Position: AI Researchers Must Lead Arms Control to Mitigate Military AI RisksPoster
Position: AI Should Facilitate Democratic Deliberation at ScaleOral
Position: AI Usage Policies Should Be Aligned with International Human Rights LawPoster
Position: AI Welfare Is BullshitPoster
Position: AI for Science Should Treat Measurement-to-Dataset Pipelines as Inference ComponentsPoster
Position: AI/ML Deepfake Research is Misaligned with AI Generated Non-Consensual Intimate Imagery (AIG-NCII)Oral
Position: Academic Conferences are Potentially Facing Denominator Gaming Caused by Fully Automated Scientific AgentsPoster
Position: Accountable Deployment of Agentic AI Demands Layered, System-Level InterpretabilityPoster
Position: Adopting AI in Practice Does Not Guarantee the Productivity BoostPoster
Position: Adversarial ML for LLMs Is Not Making Any ProgressPoster
Position: Age Estimation Models Do Not Process Biometric DataPoster
Position: Agent Evaluation Should Be Agentified for Openness, Standardization, and ReproducibilityPoster
Position: Agent Security Needs Redefinition through a Holistic FrameworkPoster
Position: Agent Should Invoke External Tools ONLY When Epistemically NecessaryPoster
Position: Agentic AI Is a Foreseeable Pathway to AGIPoster
Position: Agentic AI systems should be making Bayes-consistent decisionsPoster
Position: Agentic Safety is an Epistemic Property, Not a Behavioral OnePoster
Position: Agentic Systems Should be GeneralPoster
Position: Anthropomorphic Misalignment Research Needs Stronger EvidenceOral
Position: Artificial Intelligence Needs Meta Intelligence - the Case for Metacognitive AIPoster
Position: Assistive AI requires Personalized Specialists, not GeneralistsPoster
Position: Assistive Agents Need Accessibility AlignmentSpotlight
Position: Behavioral Systems Require Behavioral TestsPoster
Position: Benchmarks Do Not Measure Deployment Readiness in Clinical AIPoster
Position: Benchmarks for Vision–Language Models in Urban Perception Should Be Reliability-Aware and NegotiatedPoster
Position: Beyond Prediction: Toward Verifiable Physiological Waveform Reasoning with Foundation Models and Agentic LLMsPoster
Position: Beyond Reasoning Zombies — AI Reasoning Requires Process ValidityPoster
Position: Beyond Sensitive Attributes, ML Fairness Should Quantify Structural Injustice via Social DeterminantsPoster
Position: Breaking the Dual Curse of Multilingual AI Requires Socio-Technical Guardrails, Not Post-Hoc AlignmentPoster
Position: Bridge Human Interpretation and Machine Representation With Explicit Specification For Qualitative Data Analysis In LLM EraPoster
Position: Bridge the Gaps between AI Development and RegulationPoster
Position: Carbon Footprint Reporting Should Be Routine in Machine Learning ResearchPoster
Position: Causality is Key for Interpretability Claims to GeneralisePoster
Position: Certified Correctness in Neural Constraint Reasoning Requires Symbolic IntegrationPoster
Position: Child Safety Necessitates New Approaches to AI SafetySpotlight
Position: Code Benchmarks Should Prioritize Rigor, Reliability, and ReproducibilityPoster
Position: Collaborative Agentic AI Needs Interoperability Across EcosystemsPoster
Position: Collusion Risks Among AI Reasoning Agents Justify Certification Requirements for Making Market DecisionsPoster
Position: Comprehensive AI governance requires addressing non-model capability gainsPoster
Position: Creating High-Fidelity Synthetic Training Data Should Employ Multi-level OptimizationPoster
Position: Current Benchmarking Hinders Real Progress in Deep Learning for Time Series ForecastingPoster
Position: Current Model Cards Are Insufficient for Downstream Governance of Open-Weight Foundation ModelsPoster
Position: Deciphering the Functions of DNAs, RNAs, and Proteins Should Consider Multi-Modal Large Language ModelsSpotlight
Position: Deployed Reinforcement Learning should be ContinualPoster
Position: Digital Agents Require Unified Agent-Native EnvironmentsPoster
Position: Don't Just "Fix it in Post'': A Science of AI Must Study Learning DynamicsOral
Position: EU AI Act's Research Exemptions Can Break the Publication Norms of Major AI ConferencesSpotlight
Position: Early-Stage Quality Assurance in Annotation Pipelines Is More Cost-Effective Than Late-Stage ValidationPoster
Position: Embodied AI Requires a Privacy-Utility TradeoffPoster
Position: Enabling Fair Revenue Sharing for Data Providers in GenAI SystemsPoster
Position: Epistemic uncertainty estimation methods are fundamentally incompletePoster
Position: Evaluating LLMs in Finance Requires Explicit Bias ConsiderationPoster
Position: Evaluation of ECG Representations Must Be FixedPoster
Position: Evaluation of ML Resource Utilization Requires Model Life Cycle AssessmentPoster
Position: Every Ground Truth is a Human Construction, not an Objective TruthPoster
Position: Evidence and Implications of Texture Bias in Deep Neural NetworksPoster
Position: Explainability Research Must Prioritize Foundations over Ad-hoc MethodsPoster
Position: Explanation Stability Is a Property of the Model–Method Pair, Not the ModelPoster
Position: Express Your Doubts — Probabilistic World Modeling Should not be Based on Token *logprobs*Poster
Position: Fairness Failure in Generative Models is an Evaluation ProblemPoster
Position: Federated Learning is a Lens towards a Democratized Future for the Scaling Law EraPoster
Position: From Crowdsourcing to Crowd-LLM-Sourcing and LLM-SourcingPoster
Position: Generative Distributional Integrity against Backdoor AttacksPoster
Position: Generative Engine Optimization Creates Underexamined Risks, Governance Must Target Concentration, Disclosure, and Academic Blind SpotsPoster
Position: Generative Models Erode Temporal Learning Through Market SelectionPoster
Position: Genomic Model Research Must Move Beyond Anecdotal Evaluation of Interpretability MethodsSpotlight
Position: Good Embodied Reward Models Need Bad Behavior DataSpotlight
Position: Graph Condensation Needs a Reset—Move Beyond Full-dataset Training and Model-DependenceSpotlight
Position: Hallucinations Undermine Trust; Metacognition is a Way ForwardPoster
Position: Hippocampal Explicit Memory Is a Cornerstone to Human-Level AIPoster
Position: Human-Centric Vision Requires Topological Generalization Beyond Fixed Skeletal TopologiesPoster
Position: ICML Should Treat Hosted LLM APIs as Versioned Dependencies and Require Drift-Audit ArtifactsPoster
Position: Ideas Should be the Center of Machine Learning ResearchSpotlight
Position: If open source is to win, it must go publicSpotlight
Position: Improved Documentation is Necessary for Benchmarking AI Systems in GeometryPoster
Position: In Defense of Information Leakage in Concept-based ModelsPoster
Position: Interestingness is an Inductive Heuristic for Future Compression ProgressPoster
Position: Interpretability Can Be ActionablePoster
Position: Interpretability in Deep Time Series Models Demands Semantic AlignmentPoster
Position: Invisible Tokens, Visible Bills: The Urgent Need to Audit Hidden Operations in Opaque LLM ServicesPoster
Position: Irresponsible AI: big tech’s influence on AI research and associated impactsOral
Position: It is Time to Virtualize Foundation Models with a Self-evolving Operating System LayerPoster
Position: It’s Time to Optimize for Self-ConsistencyPoster
Position: Knowing Isn’t Understanding: Re-grounding Generative Proactivity with Epistemic and Behavioral InsightPoster
Position: LLM Agents Are the Antidote to Walled GardensPoster
Position: LLM Benchmark Datasets should be Contamination-ResistantPoster
Position: LLM Serving Needs Mathematical Optimization and Algorithmic Foundations, Not Just HeuristicsPoster
Position: LLM for Physics Research Requires Domain-Specialized Training and ToolingPoster
Position: LLM-Based Social Simulations Require a BoundaryPoster
Position: LLM-Safety Evaluations Lack RobustnessPoster
Position: LLMs Should Incorporate Explicit Mechanisms for Human EmpathyPoster
Position: LLMs can't jumpPoster
Position: Large Language Models Should Learn Personalized Rather Than Aggregated Human PreferencesPoster
Position: Let's Develop Data Probes to Fundamentally Understand How Data Affects LLM PerformancePoster
Position: Let’s Build a Trustworthy Model Context Protocol!Poster
Position: Machine Learning Research Should Be Guided by Explicit, Pluralistic Models of Human PurposePoster
Position: Machine Learning for Heart Transplant Allocation Policy Optimization Should Account for IncentivesSpotlight
Position: Make Planning Research Rigorous Again!Poster
Position: Measuring Human Preferences in RLHF is a Social Science ProblemSpotlight
Position: Mechanisms for Aggregated Individual Reporting Should be Established for Post-Deployment EvaluationPoster
Position: Medical AI Neglects Real Treatment OutcomesPoster
Position: Metaphysical Concepts in AI Should Be Judged by Their ConsequencesPoster
Position: Model identity in machine learning is a convention, not a propertyPoster
Position: Modular Memory is the Key to Continual Learning AgentsSpotlight
Position: Modular Safety Guardrails Are Necessary for Foundation-Model-Enabled Robots in the Real WorldPoster
Position: Multi-Agent Explainability Needs Contracts Before MethodsPoster
Position: Multi-Agent Systems Should Prioritize Concurrency ControlPoster
Position: Multiple Definitions & Unrealistic Assumptions of Model Collapse Distract from Real World ThreatsPoster
Position: Multiplicity is an Inevitable and Inherent Challenge in Multimodal LearningPoster
Position: Natural Language Should Not Fully Replace Formal LanguagesPoster
Position: Neglecting the Sustainability of AI is Fuelling a Global AI Arms RacePoster
Position: Neural Approximation Is Rarely Justified for Hard Combinatorial ProblemsPoster
Position: No Retroactive Cure for Infringement during TrainingSpotlight
Position: Peer Review Should Be Calibrated via LLM ScoringPoster
Position: Peer Review in ML/AI Conferences Should Separate Publication from Presentation and Offer Non-Anonymous Review TracksPoster
Position: Predicting AI’s Impact on Labor Is a Core Machine Learning ProblemPoster
Position: Predictive Uncertainty Is Not Enough -- Joint Distribution for Full Uncertainty RepresentationPoster
Position: Preparing for AI Systems That Deceive DevelopersPoster
Position: Preregister Experiments with AI AgentsSpotlight
Position: Prioritize Identifying Structure, Not Complex Models, for Scientific DiscoveryPoster
Position: Privacy Is a Claim, Not a Property of Synthetic DataPoster
Position: Profiling Game Worlds by Transition ComplexityPoster
Position: Prompting Intent Should Be Audited in LLM-Assisted Peer ReviewPoster
Position: Prompts for Public-Sector LLMs Should Be Governed as CommonsPoster
Position: Quantum Deep Learning Still Needs a Quantum LeapPoster
Position: Quantum Kernel Machines Should Move Beyond Scalar-Valued Kernels to Realize Their PotentialPoster
Position: Quantum Program Generation Must Prioritize Validity Over Probabilistic ScalingPoster
Position: RL Researchers Need to Distinguish Between Solving Simulators and Using Simulators as a ProxyPoster
Position: RL Should Be Used to Adjust Foundation Models, NOT AbusedPoster
Position: Reasoning After Perception Means Reasoning Without VisionPoster
Position: Reframing Hallucination: Latent Space Geodesics as a Pathway for Generative DiscoveryPoster
Position: Regulating Algorithms Is Not Enough. A Study of Content Discovery in Online PlatformsPoster
Position: Reliable AI Needs to Externalize Implicit Knowledge: A Human–AI Collaboration PerspectivePoster
Position: Responsible AI for AI companions must actively combat violence toward intimate partnersSpotlight
Position: Responsible Practices and Model Performance are Not Competing GoalsPoster
Position: Retire the "Positive Backdoor" Label—Secret Alignment Requires Strict and Systematic EvaluationPoster
Position: Robust AI Personalization Will Require a Human Context ProtocolPoster
Position: Safe AI Should be Resistant and Resilient in an Evolving WorldPoster
Position: Safe Models Do Not Guarantee Safe Societies: The Case for Sociopolitical RiskSpotlight
Position: Safety Must Precede the Deployment of Open-Ended AI AgentsPoster
Position: Scale is a False Promise for Endangered LanguagesPoster
Position: Self-Play Only Evolves When Self-Synthetic Pipeline Ensures Learnable Information GainPoster
Position: Significant impact of numerical precision in scientific machine learningPoster
Position: Solipsistic superintelligence is unlikely to be cooperativePoster
Position: Spatial Fairness: Foundations, Pitfalls, and a Path ForwardPoster
Position: State-of-the-Art Claims Require State-of-the-Art EvidencePoster
Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!Poster
Position: Stop Automating Peer Review Without Rigorous EvaluationOral
Position: Stop Chasing the C-index when Evaluating Survival Analysis ModelsSpotlight
Position: Stop Preaching and Start Practising Data Frugality for Responsible Development of AIPoster
Position: Stop Reactively Patching Your Model Every Time and Start Proactive Test-Driven AI DevelopmentPoster
Position: Stop Using Culturally Biased Human Cognitive Benchmarks to Evaluate LLMsPoster
Position: Stop evaluating AI with human tests, develop principled, AI-specific tests insteadPoster
Position: Sustainable Open-Source AI Requires Tracking the Cumulative Footprint of DerivativesSpotlight
Position: Sycophancy is an Educational Safety Risk: Why LLM Tutors Need Sycophancy BenchmarksPoster
Position: Temporal Measurement Interval Determines Computational and Model Complexity in Single-Cell Perturbation AnalysisSpotlight
Position: Text Embeddings Should Capture Implicit Semantics, Not Just Surface MeaningPoster
Position: The AI Imperative: Scaling High-Quality Peer Review in Machine LearningOral
Position: The Age of AI Agents Demands A New Scientific Paradigm To Sustain Trustworthy SciencePoster
Position: The Alignment Community is Unintentionally Building a Censor’s ToolkitOral
Position: The Case for Theory-Level AutoformalizationSpotlight
Position: The Data Provenance–Parametric Divide in Large Language ModelsPoster
Position: The Inevitable Transition to Machine Learning in Quantum ChemistryPoster
Position: The Open Benchmark Paradox Must Be Resolved through Sovereign Medical EvaluationPoster
Position: The Privacy-Auditability Paradox in Federated Learning: Why We Need Controllable Secure AggregationPoster
Position: The Systemic Lack of Agency in Visual ReasoningPoster
Position: The Term “Machine Unlearning” Is Overused in LLMsPoster
Position: The Time for Sampling Is Now! Charting a New Course for Bayesian Deep LearningSpotlight
Position: The Turing-Completeness of Real-World Autoregressive Transformers Relies Heavily on Context ManagementPoster
Position: There are futures that benchmark-driven AI cannot seeOral
Position: Time to Close The Validation Gap in LLM Social SimulationsPoster
Position: Time-Series Foundation Models Require Explicit Domain-Level BenchmarksPoster
Position: To Defend Against Cyber Attacks, We Must Teach AI Agents to HackPoster
Position: Token Taxes Can Mitigate AI's Economic RisksPoster
Position: Topological Machine Learning Cannot Progress without Experimental StandardsPoster
Position: Towards Responsible Evaluation for Text-to-SpeechPoster
Position: Trustworthy AI Suffers from Invariance Conflicts and Causality is The SolutionPoster
Position: Uncertainty Quantification in LLMs is Just Unsupervised ClusteringPoster
Position: Uncertainty is a Strategic Signal in Human–AI Decision MakingPoster
Position: Universal Aesthetic Alignment Narrows Artistic ExpressionSpotlight
Position: Unlabeled ≠ No Human Supervision in Visual LearningPoster
Position: Unplugging a Seemingly Sentient Machine Is the Rational Choice — A Metaphysical PerspectiveSpotlight
Position: Use Sparse Autoencoders to Discover UnknownsPoster
Position: VLM Causal Reasoning Benchmarks Should Probe Temporal Understanding, Not Presume ItSpotlight
Position: Vector Prompt Interfaces Should Be Exposed to Enable Customization of Large Language ModelsPoster
Position: Verifiable Data Minimization is a Prerequisite for Responsible, Privacy-Preserving Industrial VisionPoster
Position: Video LLMs Must Not Ignore the Pixel Dynamics in Plain SightPoster
Position: Virtual Cells Need Context, Not Just ScalePoster
Position: Vision encoders should be image size agnostic and task drivenPoster
Position: Want Better ML Reviews? Stop Asking Nicely and Start Incentivizing with a Credit SystemPoster
Position: We Need A Unified Definition of Hallucination (It’s The World Model, Stupid!)Poster
Position: We Need AI Efficiency Incentives for Accessibility and SustainabilityPoster
Position: We Need Large Language Models Optimized For Our Well-BeingPoster
Position: We Need Practical AI Alignment Methods that Mirror Human ReasoningPoster
Position: We need to re-think the concept of “real” images.Poster
Position: Web Agents Should Use Typed Actions Instead of Click-Based BrowsingPoster
Position: Weight Space Should Be a First-Class Generative AI ModalityPoster
Position: When AI Decides Who Gets an Organ: Multi-Agentic AI Systems in Transplant Medicine Risk Amplifying Disparities Without Targeted Explainability and Deployment StrategiesPoster
Position: Why a Dynamical Systems Perspective is Needed to Advance Time Series ModelingPoster
Position: World Models as an Intermediary between Agents and the Real WorldPoster
Position: Your VLM May Not Be Thinking with Interleaved ImagesPoster
Position: Zeroth-Order Optimization in Deep Learning Is Underexplored, Not UnderpoweredSpotlight
Position: `AI Alignment' Encompasses Competing Technical PrioritiesPoster
Position: the Stochastic Parrot in the Coal Mine. Model Collapse is a Threat to Low-Resource CommunitiesSpotlight
Positional Encoding for Spiking TransformersPoster
Positive Distribution Shift as a Framework for Understanding Tractable LearningPoster
Positive-Unlabeled Learning with Extreme Scarcity of Labeled PositivesPoster
Positive–Unlabeled Reinforcement Learning Distillation for On-Premise Small ModelsPoster
Possibilistic Predictive Uncertainty for Deep LearningPoster
Post-Hoc Merging is Not Enough: Many-Shot Model Merging with Loss-Gap BalancingPoster
Post-Training LLMs as Better Decision-Making Agents: A Regret-Minimization ApproachPoster
Post-Training with Policy Gradients: Optimality and the Base Model BarrierSpotlight
PostTrainBench: Can LLM Agents Automate LLM Post-Training?Poster
PosterAgent: Agentic Poster Generation via Stage-Aware Reinforcement LearningPoster
Posterior Behavioral Cloning: Pretraining BC Policies for Efficient RL FinetuningSpotlight
Posterior Concentration of Physics-Informed Neural Networks for Elliptic PDEsPoster
Posterior Mismatch Matters: Adversarial Training for Long-Tailed RobustnessPoster
Posterior Sampling Reinforcement Learning with Gaussian Processes for Continuous Control: Sublinear Regret Bounds for Unbounded State SpacesPoster
Power-Boosted Granger-Causal Discovery for Large Heterogeneous Panel DataPoster
Power-Calibrated LLM Watermarking: A Statistical FrameworkPoster
PowerFlow: Unlocking the Dual Nature of LLMs via Principled Distribution MatchingPoster
Powerful and Theoretically Guaranteed Independence Testing on Heterogeneous Federated ClientsPoster
Practical Mechanism for Fault-Tolerant Spiking Neural Networks via Simple Input Control Based on Learnable FragmentationPoster
Practical and Optimal Algorithm for Linear Contextual Bandits with Rare Parameter UpdatesSpotlight
Practical and Scalable Hamiltonian Monte Carlo Without the Metropolis TestPoster
PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable PromptsPoster
Precise Asymptotics of Bagging Regularized M-estimatorsPoster
Precision-Induced Miscalibration: Understanding and Correcting Confidence Distortion in Quantized Neural NetworksPoster
Preconditioned DeltaNet: Curvature-aware Sequence Modeling for Linear RecurrencesPoster
Preconditioning Neural Tangent Kernel for Adaptive OptimizationPoster
Predictable Compression Failures: Order Sensitivity and Information Budgeting for Evidence-Grounded Binary AdjudicationPoster
Predicting Dynamic Stability Landscapes in Synchronization NetworksPoster
Predicting Future KV Utility: Global Combinatorial Optimization for Task-Agnostic KV Cache EvictionPoster
Predicting Large Model Test Losses with a Noisy Quadratic SystemPoster
Predicting What Matters: Robust Generalist Robot Policy Learning via Future Semantic MaskPoster
Predicting evolutionary rate as a pretraining task improves genome language model representationsPoster
Predicting the Emergence of Induction Heads in Language Model PretrainingPoster
Predicting the Order of Upcoming Tokens Improves Language ModelingPoster
Prediction-Powered Adaptive Inference with Pretrained AI Models for Contextual BanditsPoster
Prediction-Powered Risk Monitoring of Deployed Models for Detecting Harmful Distribution ShiftsPoster
Predictive Prefetching for Retrieval-Augmented GenerationPoster
Predictive variational inference: Learn the predictively optimal posterior distributionPoster
Preference Goal Tuning: Post-Training as Latent Control for Frozen PoliciesPoster
Preference-Calibrated Optimization with Score-Level Distribution Alignment for Text-to-Image Diffusion Model UnlearningPoster
Preference-Enhanced Reinforcement Learning for Pluralistic Image InpaintingPoster
Preference-Modulated Structural Attention for Multi-Objective Combinatorial OptimizationPoster
Preference-based Antibody Expression Ranking: Scaling with Large-scale Weak SupervisionPoster
Prefix cache aware data reordering for LLM augmented database analyticsPoster
Prescriptive Scaling Reveals the Evolution of Language Model CapabilitiesOral
Preserve-Then-Quantize: Balancing Rank Budgets for Quantization Error Reconstruction in LLMsPoster
Preserving Expert-Level Privacy in Offline Reinforcement LearningPoster
Preserving Plasticity in Continual Learning via Dynamical IsometryPoster
Pressure Reveals Character: Behavioural Alignment Evaluation at DepthSpotlight
PretrainZero: Reinforcement Active PretrainingPoster
Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual LearningOral
Primal-Spectral Generative Modeling: Fast Analytical Generation via Pseudoinverse Lévy InversionPoster
Principle-Evolvable Scientific Discovery via Uncertainty MinimizationPoster
Principled RL for Flow Matching Emerges From the Chunk-level Policy OptimizationPoster
Principled SVD-based Delta Compression via Quantization Error MinimizationPoster
Principled Synthetic Data Enables the First Scaling Laws for LLMs in RecommendationPoster
Principled Zero-shot Ranking Agents with Tournament GraphsSpotlight
Prior Diffusiveness and Regret in the Linear-Gaussian BanditPoster
Prioritize the Process, Not Just the Outcome: Rewarding Latent Thought Trajectories Improves Reasoning in Looped Language ModelsPoster
Prioritized Model Experience ReplayPoster
Priority-Aware Shapley ValuePoster
Prism-MoE: Efficient Dense-to-MoE Conversion for Visual Autoregressive GenerationPoster
Prism: Spectral-Aware Block-Sparse AttentionPoster
PrivAct: Internalizing Contextual Privacy Preservation via Multi-Agent Preference TrainingPoster
PrivCode++ : Latent-Conditioned Differentially Private Code Generation for Comprehensive GuaranteesPoster
PrivGate: Steering Contextual Integrity in LLMs via Latent Space GeometryPoster
Privacy Amplification in Differentially Private Zeroth-Order Optimization with Hidden StatesPoster
Privacy Risks of Agentic Inferential Capabilities in Data Linkage AttacksPoster
Privacy-Aware Data Integration for Enhanced Quantile Inference under HeterogeneityPoster
Privacy-Aware Video Anomaly Detection: Guided Orthogonal Projection and a Comprehensive Evaluation FrameworkOral
Privasis: Synthesizing the Largest "Public" Private Dataset from ScratchPoster
Private Learning with Public Feature ConditioningPoster
Private and Stable Test-time Adaptation with Differential PrivacyPoster
Privately Fine-Tuned LLMs Preserve Temporal Dynamics in Tabular DataPoster
Privileged Information Distillation for Language ModelsPoster
ProAct: A Benchmark and Multimodal Framework for Structure-Aware Proactive ResponsePoster
ProConMV: Provenance-Enabled Conceptual Framework for Interpretable Multi-View Diabetic Retinopathy DiagnosisPoster
ProEval: Proactive Failure Discovery and Efficient Performance Estimation for Generative AI EvaluationPoster
ProMeCD: Unifying Long-Tailed and Noisy Label Learning via White-Box ControlPoster
ProMiSE: Protein Multi-state Structure Evaluation Benchmark in Biological ContextsPoster
ProOPF: Benchmarking and Improving LLMs for Professional-Grade Power Systems Optimization ModelingPoster
ProRL: Effective Reinforcement Learning for Proactive Recommendation via Rectified Policy Gradient EstimationPoster
ProSAR: Prototype-Guided Semantic Augmentation and Refinement for Time Series Contrastive LearningPoster
Proact-VL: A Proactive VideoLLM for Real-Time AI CompanionsPoster
Proactive Defense Benchmark against Deepfake GenerationPoster
ProactiveLLM: Learning Active Interaction for Streaming Large Language ModelsPoster
Probabilistic Bisection Algorithm Provably Achieves Exponential ConvergencePoster
Probabilistic Modeling of Latent Agentic Substructures in Deep Neural NetworksPoster
Probabilistic Performance Guarantees for Multi-Task Reinforcement LearningPoster
Probabilistic Pretraining for Improved Neural RegressionPoster
Probabilistic Retrofitting of Learned SimulatorsPoster
Probabilistic Robustness Certificates against Adversarial AttacksPoster
Probabilistic Salient Object RankingPoster
Probabilistically-routed Bayesian Additive Spanning Trees for Learning on Constrained DomainsPoster
Probability of Matching for Batch Multi-Objective Bayesian OptimizationPoster
Probability-Entropy Calibration: An Elastic Indicator for Adaptive Fine-tuningPoster
Probably Approximately Correct LabelsPoster
ProbeLLM: Automating Principled Diagnosis of LLM FailuresPoster
Probing Cross-modal Information Hubs in Audio-Visual LLMsPoster
Probing How Scalable Table Data Enhances General Long-Context ReasoningPoster
Probing Newtonian Mechanics in Video Generative Models with Real Physical SystemsPoster
Probing RLVR Training Instability through the Lens of Objective-Level HackingPoster
Probing the Geometry of Diffusion Models with the String MethodPoster
Probing the Inductive Bias of Neural Networks through Learning Random Cellular AutomataPoster
Probing the Knowledge Boundary: An Interactive Agentic Framework for Deep Knowledge ExtractionPoster
Problem Distributions as Tasks: Repurposing Meta Learning for Generative Combinatorial Optimization towards Multi-task Pretrain and AdaptationPoster
ProcMEM: Learning Reusable Procedural Memory from Experience via Non-Parametric PPO for LLM AgentsSpotlight
Procedural Generation Of Algorithm Discovery Tasks in Machine LearningPoster
Procedural Pretraining: Warming Up Language Models with Abstract DataOral
Process Reward Agents for Steering Knowledge-Intensive ReasoningPoster
Process Reward Models That ThinkPoster
Profiling the Irrational Agent: Cognitive Modeling of LLM Behaviors in Sequential JailbreaksPoster
Progressive Cramming: Reliable Token Compression and What It RevealsPoster
Progressive Graph Structure Adjustment for Homophily Shift AdaptationSpotlight
ProjQ: Project-and-Quantize for Adapter-Aware LLM CompressionPoster
Projected Gradient Ascent for Efficient Reward-Guided Updates with One-Step Generative ModelsPoster
Projection-Free Algorithms for Minimax ProblemsPoster
Prompt Estimation from Prototypes for Federated Prompt Tuning of Vision TransformersPoster
Prompt Injection as Role ConfusionPoster
Prompt Optimization with Minimal Unlabeled Input via Meta-ReasoningPoster
Prompt Reinjection: Alleviating Prompt Forgetting in Multimodal Diffusion TransformersPoster
Prompt Tuning for CLIP on the Pretrained ManifoldPoster
PromptDyG: Test-Time Prompt Adaptation on Dynamic GraphsPoster
PromptPilot: Game-Theoretic Multi-Agent Prompt Optimization for Segment AnythingPoster
PromptRL: Prompt Matters in RL for Flow-Based Image GenerationPoster
ProphetKV: User-Query-Driven Selective Recomputation for Efficient KV Cache Reuse in Retrieval-Augmented GenerationPoster
Propose, Solve, Verify: Self-Play Through Formal VerificationPoster
ProtDBench: A Unified Benchmark of Protein Binder Design and EvaluationPoster
Protein Autoregressive Modeling via Multiscale Structure GenerationOral
Protein Circuit Tracing via Cross-layer TranscodersPoster
Protein Design with Agent Rosetta: A Case Study for Specialized Scientific AgentsPoster
Protein Fold Classification at Scale: Benchmarking and PretrainingOral
Protein Language Model Embeddings Improve Generalization of Implicit Transfer OperatorsPoster
Proteo-R1: Thinking Foundation Models for De Novo Protein Binder DesignPoster
Proteus: Lookup-Free Trellis-Coded Quantization by Lattice-Breaking Compute Codes for 2-Bit LLMsPoster
ProtoKV: Streaming Video Understanding under Delayed Evidence with Summary-State MemoryPoster
ProtoVAR: Efficient Dataset Distillation via Prototype-Guided Visual Autoregressive ModelingPoster
Prototype Transformer: Towards Language Model Architectures Interpretable by DesignPoster
Prototype-Based Test-Time Adaptation of Vision-Language ModelsPoster
Prototype-Grounded Concept Models for Verifiable Concept AlignmentPoster
Prototype-guided Bilateral Alignment Multimodal Federated LearningSpotlight
Provable Accuracy Collapse of Embedding-Based Representations under Dimensionality MismatchSpotlight
Provable Benefits of RLVR over SFT for Reasoning Models: Learning to Backtrack EfficientlyPoster
Provable Bounds for the Learnability of Sample-Compressible Families from Noisy SamplesSpotlight
Provable Sample Efficiency of Curriculum Post-Training for Transformer ReasoningPoster
Provable Training Data Identification for Large Language ModelsPoster
Provably Adaptive Linear Approximation for the Shapley Value and BeyondPoster
Provably Convergent Actor-Critic in Risk-averse MARLSpotlight
Provably Data-driven Lagrangian Relaxation for Mixed Integer Linear ProgrammingPoster
Provably Data-driven Multiple Hyper-parameter Tuning with Structured Loss FunctionPoster
Provably Efficient Policy-Reward Co-Pretraining for Adversarial Imitation LearningPoster
Provably Label-Efficient Conformal PredictionPoster
Provably Learning Attention with QueriesPoster
Provably Protecting Fine-Tuned LLMs from Training Data ExtractionPoster
Provably Valid Uncertainty Quantification for Deep Computed TomographyPoster
Proximal Decoding: Provably Reducing Copyright Risk for Any Language ModelPoster
Proximal Splitting Methods for Hybrid Differentiable ModelsPoster
Proximal-Based Generative Modeling for Bayesian Inverse ProblemsPoster
Proximal-IMH: Proximal Posterior Proposals for Independent Metropolis–Hastings with Approximate OperatorsPoster
Proxy Compression for Language ModelingPoster
PruneFuse: Efficient Data Selection via Weight Pruning and Network FusionPoster
Pruning at Initialisation through the lens of Graphon Limit: Convergence, Expressivity, and GeneralisationPoster
Pseudo-Mallows for Efficient Probabilistic Preference LearningPoster
PsumQuant: In-line Post-training Partial Sum Quantizer for Energy Efficient NPU InferencePoster
Pull Requests as a Training Signal for Repo-Level Code EditingPoster
Push, Pop, Parallelize: Stack-Augmented Linear Attention via the Delta RulePoster
Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic OptimizationPoster
Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic VerificationPoster
PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inferencePoster
PyHealth 2.0: A Comprehensive Open-Source Toolkit for Accessible and Reproducible Clinical Deep LearningPoster
PyPop7: A Pure-Python Library for Population-Based Black-Box OptimizationPoster
PyVision-RL: Forging Open Agentic Vision Models via RLPoster
Q-CLIP: Unleashing the Power of Vision-Language Models for Video Quality Assessment through Unified Cross-Modal AdaptationPoster
Q-Delta: Beyond Key–Value Associative State EvolutionPoster
Q-DiT4SR: Exploration of Detail-Preserving Diffusion Transformer Quantization for Real-World Image Super-ResolutionPoster
Q-Flow: Stable and Expressive Reinforcement Learning with Flow-based PolicyPoster
Q-SAM: Unlocking Sharpness-Aware Minimization for Generalization in Offline Reinforcement LearningPoster
Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware SchedulingPoster
Q-Tab: Quantized Tabular Data GeneratorPoster
QEDBench: Quantifying the Alignment Gap in Automated Evaluation of University-Level Mathematical ProofsPoster
QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RLPoster
QPKO: Differentiable QP-Embedded Deep Koopman Framework for Modeling Nonlinear SystemsPoster
QPoint: End-to-End Lightweight Point Cloud Processing via Robust Quaternion Feature LearningPoster
QTALE: Quantization-Robust Token-Adaptive Layer Execution for LLMsPoster
QUATRO: Query-Adaptive Trust Region Policy Optimization for LLM Fine-tuningPoster
QuArch: A Benchmark for Evaluating LLM Reasoning in Computer ArchitecturePoster
QuITE: Query-based Irregular Time-series EmbeddingPoster
Quadratically Regularized Optimal Transport: Localization Bounds and Affine Case AnalysisPoster
Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache QuantizationPoster
QuantWear: Quantum-scale Wear Particle Detection for Jet Engine DiagnosisPoster
Quantifying Biases in LLM-as-a-Judge EvaluationsPoster
Quantifying Frontier LLM Capabilities for Container Sandbox EscapeOral
Quantifying LLM Attention-Head Stability: Implications for Circuit UniversalityPoster
Quantifying Temperature Scaling in Discrete Sequence (Language) ModelsPoster
Quantifying and Optimizing Simplicity via Polynomial RepresentationsPoster
Quantifying the Effect of Noise in Language GenerationPoster
Quantifying the Generalization Gap in Seizure Detection: A Large-Scale Empirical Benchmark via the SzCORE ChallengePoster
Quantifying the noise sensitivity of the Wasserstein metric for imagesPoster
Quantile-Free Uncertainty Quantification in Graph Neural NetworksPoster
Quantitative Estimation of Target Task Performance from Unsupervised Pretext Task in Semi/Self-Supervised LearningPoster
Quantized Maximum Likelihood Estimation under Normal Mean-Variance Mixture ModelPoster
Quantum Algorithms for Triangle Cut SparsificationPoster
Quantum Robust Inner Minimization for Reinforcement Learning with Quadratic Speed-Up in Query ComplexityPoster
Quantum latent distributions in deep generative modelsPoster
QuantumBoost: A lazy, yet fast, quantum algorithm for learning with weak hypothesesPoster
Quaternion Self-Attention with Shared ScoresPoster
Query Circuits: Explaining How Language Models Answer User PromptsPoster
Query Lens: Interpreting Sparse Key-Value Features with Indirect EffectsPoster
Query-Based Asymmetric Modeling with Decoupled Input–Output Rates for Speech RestorationPoster
Query-efficient model evaluation using cached responsesPoster
Questioning the Coverage-Length Metric in Conformal Prediction: When Shorter Intervals Are Not BetterPoster
R$^3$L: Reasoning 3D Layouts from Relative Spatial RelationsPoster
R-Diverse: Mitigating Diversity Illusion in Self-Play LLM TrainingPoster
R1-SyntheticVL: Is Synthetic Data from Generative Models Ready for Multimodal Large Language Model?Poster
R2-Router: A New Paradigm for LLM Routing with ReasoningPoster
R2R2: Robust Representation for Intensive Experience Reuse via Redundancy Reduction in Self-Predictive LearningPoster
RA-Det: Towards Universal Detection of AI-Generated Images via Robustness AsymmetryPoster
RA-VLA: Retrieval-Augmented VLA for Test-Time AdaptationPoster
RACER: Risk-Aware Calibrated Efficient Routing for Large Language ModelsPoster
RAD: Retrieval High-quality Demonstrations to Enhance Decision-makingPoster
RADAR: Defending RAG Dynamically against Retrieval CorruptionPoster
RADAR: Redundancy-Aware Diffusion for Multi-Agent Communication Structure GenerationPoster
RADE: Unbiased Random Add-Drop Edge as a RegularizerPoster
RADIO1D: Elastic Representations for Condensed Vision ModelingPoster
RAG without Forgetting: Continual Query-Infused Key MemoryPoster
RAIGen: Rare Attribute Identification in Text-to-Image Generative ModelsPoster
RAMAC: Multimodal Risk-Aware Offline Reinforcement Learning and the Role of Behavior RegularizationPoster
RAPNet: Accelerating Algebraic Multigrid with Learned Sparse CorrectionsPoster
RAST-MoE-RL: A Regime-Aware Spatio-Temporal MoE Framework for Deep Reinforcement Learning in Ride-HailingPoster
RAT+: Train Dense, Infer Sparse - Recurrence Augmented Attention for Dilated InferencePoster
RBCBF: Decoding Time Safety Alignment via Risk Guided Rollback and Barrier ControlPoster
RC-FCL: Combating Asynchronous Concept Drift in Federated Continual Learning via Retrospective CalibrationPoster
RDT2: Exploring the Scaling Limit of UMI Data Towards Zero-Shot Cross-Embodiment GeneralizationPoster
RE-TRAC: REcursive TRAjectory Compression for Deep Search AgentsPoster
REAL: Regression-Aware Reinforcement Learning for LLM-as-a-JudgePoster
REAL: Resolving Knowledge Conflicts in Knowledge-Intensive Visual Question Answering via Reasoning-Pivot AlignmentPoster
REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM HallucinationsPoster
REAR: Test-time Preference Realignment through Reward DecompositionPoster
RECAST: Model Reconstruction via Counterfactual-Aware Wasserstein Geometry under Limited DataPoster
RECOVER:Reliable Detection of Unauthorized Data Usage in Text-to-Image Diffusion Models via Inversion RobustnessPoster
RECTOR: Masked Region-Channel-Temporal Modeling for Affective and Cognitive Representation LearningPoster
RED-HDP-HMM: Observation-Dependent Durations for Bayesian Nonparametric Sequential ModelsSpotlight
REG: In-Sample RL via Regularizing the Evaluation GapPoster
RELO: Reinforcement Learning to Localize for Visual Object TrackingPoster
RESIDUAL-GUIDED MULTI-RESOLUTION REFINEMENT OF FOUNDATION MODELS - A CASE STUDY IN DROUGHT FORECASTINGPoster
REST: Diffusion-based Real-time End-to-end Streaming Talking Head Generation via ID-Context Caching and Asynchronous Streaming DistillationPoster
REVIS: Sparse Latent Steering to Mitigate Object Hallucination in Large Vision-Language ModelsPoster
REViT: Roto-reflection Equivariant Convolutional Vision TransformerPoster
RGGT: A Generative-Prior-Guided Transformer for Unified Rigid and Non-Rigid Point Cloud RegistrationPoster
RGMem: Renormalization Group–inspired Memory Evolution for Language AgentsPoster
RL-SPH: Learning to Achieve Feasible Solutions for Integer Linear ProgramsPoster
RL4RLA: Teaching ML to Discover Randomized Linear Algebra Algorithms through Curriculum Design and Graph-based SearchPoster
RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL SystemPoster
RLCracker: Evaluating the Worst-Case Vulnerability of LLM Watermarks with Adaptive RL AttacksPoster
RLIE: Rule Generation with Logistic Regression, Iterative Refinement, and Evaluation for Large Language ModelsPoster
RLSF-V: Mitigating Hallucinations in MLLMs via Fuzzy Semantic Self-FeedbackPoster
RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable EnvironmentsPoster
RMNP: Row-Momentum Normalized Preconditioning for Scalable Matrix-Based OptimizationPoster
RN-D: Discretized Categorical Actors with Regularized Networks for On-Policy Reinforcement LearningPoster
RNA-FM: Flow-Matching Generative Model for Genome-wide RNA-Seq PredictionPoster
ROAMM: A Benchmark Dataset for Multimodal Human Attention Decoding and EEG-to-Text Modeling During Naturalistic ReadingPoster
RQ-MoE: Residual Quantization via Mixture of Experts for Efficient Input-Dependent Vector CompressionPoster
RSA-CP: Efficient Conformal Prediction in Small-Sample Regimes via Random Score AlignmentPoster
RSAgent: Learning to Reason and Act via Multi-Turn Tool Invocations for Text-Guided SegmentationPoster
RSF-GLLM: Bridging the Semantic Gap in Multi-Hop Knowledge Graph QA via Recurrent Soft-Flow and Decoupled LLM GenerationPoster
RSPO: Regularized Self-Play Alignment of Large Language ModelsPoster
RSTR: Reducing SpatioTemporal Redundancy in Diffusion TransformersPoster
RT-Lynx: Putting the GEMM Sparsity In a Right Way for Diffusion ModelsPoster
RTInfer: Exploiting Concurrency for Multiple Real-Time DNN Inference on Edge GPUsPoster
RTPrune: Reading-Twice Inspired Token Pruning for Efficient DeepSeek-OCR InferencePoster
RVAS: Referring Video Active Exploration and SegmentationPoster
RaBiT: Residual Aware Binarization Training for Accurate and Efficient LLMsPoster
RaBitQCache: Rotated Binary Quantization for KVCache in Long Context LLM InferencePoster
RaGEP: Rank-aware Geometric Expert Pruning for Mixture-of-Experts Language ModelsPoster
Radial Scaling Voxelization for Accurate Small Object 3D DetectionPoster
Ramba: Selective State-Space Models for Relational Deep LearningPoster
Random Erasing vs. Model Inversion: A Promising Defense or a False Hope?Poster
Random Process Flow Matching: Generative Implicit Representations of Multivariate Random FieldsPoster
Random Scaling of Emergence CapabilitiesPoster
Random Selection Reveals Implicit Knowledge Consensus in Code GenerationPoster
Randomized Advantage Transformation (RAT): Computing Natural Policy Gradients via Direct BackpropagationPoster
Randomized Feasibility Methods for Constrained Optimization with Adaptive Step SizesPoster
Rank-Aware Spectral Bounds on Attention Logits for Stable Low-Precision TrainingPoster
Rank-guided Diffusion for Noise Few-Shot LearningPoster
Ranking Free RAG: Replacing Re-ranking with Selection in RAG for Sensitive DomainsPoster
Ranking Time Series using a Time Warping Ideal Point ModelSpotlight
RapTB: Rooted Absorbed Trajectory Balance with Submodular Replay for Stable Autoregressive GFlowNet TrainingPoster
Rapid Poison: Practical Poisoning Attacks Against the Rapid Response FrameworkSpotlight
Rare Event Analysis of Large Language ModelsOral
Rashomon Sets of Falling TreesSpotlight
Rate or Fate? RLV$^{\varepsilon}$R: Reinforcement Learning with Verifiable Noisy RewardsSpotlight
Ratio-Variance Regularized Policy OptimizationSpotlight
Rational Neural Networks have Expressivity AdvantagesPoster
Rational TransductorsOral
Rationality Measurement and Theory for Reinforcement Learning AgentsPoster
Rays as Pixels: Learning A Joint Distribution of Video and Camera TrajectoriesPoster
Re-FORC: Adaptive Reward Prediction for Efficient Chain-of-Thought ReasoningPoster
ReAugment: Targeted Few-Shot Time Series Augmentation via Model Zoo-Guided Reinforcement LearningPoster
ReCoG: Relational and Compact Context Graph Learning for Few-shot Molecular Property PredictionPoster
ReGen: Hierarchical Multi-Prompt Representation Generation for Efficient Waveform Diffusion ModelsPoster
ReJump: A Tree-Jump Representation for Analyzing and Improving LLM ReasoningPoster
ReLAM: Learning Anticipation Model for Rewarding Visual Robotic ManipulationPoster
ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM InferencePoster
ReNF: Rethinking the Principles of Neural Long-Term Time Series ForecastersPoster
RePack then Refine: Efficient Diffusion Transformers with Vision Foundation ModelsPoster
RePo: Language Models with Context Re-PositioningPoster
RePro: Training Language Models to Faithfully Recycle the Web for PretrainingPoster
ReQAT: Achieving Full-Precision Reasoning Accuracy with 4-bit Floating-Point Quantization-Aware TrainingOral
ReSeek: A Self-Correcting Framework for Search Agents with Instructive RewardsPoster
ReSpinQuant: Efficient Layer-Wise LLM Quantization via Subspace Residual Rotation ApproximationPoster
ReTabSyn: Realistic Tabular Data Synthesis via Reinforcement LearningPoster
ReVSI: Rebuilding Visual Spatial Intelligence Evaluation for Accurate Assessment of VLM 3D ReasoningPoster
ReViT: Rotational-equivariant Vision Transformers for Neural PDE SolversOral
ReaForest: Fostering Generative Video Reasoning for Spatial PlanningPoster
Reading Between the Tokens: Improving Preference Predictions through Mechanistic ForecastingPoster
Reading the Cell, Designing the Cure: Perturbation-Conditioned Molecular Diffusion for Function-Oriented Drug DesignPoster
Real Data Lies: Unveiling and Closing the Quality Shortcut in Generalizable AI-Generated Video DetectionPoster
Real-Time Aligned Reward Model beyond SemanticsPoster
Real-Time Monitoring and Calibration of Chain-of-Thought Sycophancy in Large Reasoning ModelsPoster
Real-Time Visual Attribution Streaming in Thinking ModelSpotlight
Real-Time and Lightweight Diffusion Image CompressionPoster
Real-World Unsupervised Models Generalize to Predict Brain Responses to Out-of-Distribution StimuliSpotlight
RealisMotion: Decomposed Human Motion Control and Video Generation in the World SpacePoster
Realistic Adaptive MergingPoster
Realizable Bayes-Consistency for General Metric LossesPoster
RealtimeTool: Parallel Decoding for Real-Time LLM Function CallingPoster
Reason with Thumbnails, Answer with Focus: An Efficient and Effective Paradigm for Multimodal Grounded Visual ReasoningPoster
Reason, Then Re-reason: Cross-view Revisiting Improves Spatial ReasoningPoster
ReasonEdit: Editing Vision--Language Models using Human ReasoningPoster
Reasoning Cache: Learning to Extrapolate to Long Lengths via Short-Length RLPoster
Reasoning Can Be Restored by Correcting a Few Decision TokensPoster
Reasoning Compartmentalization: Bridging the Concretization Gap via Abstraction-based RoutingPoster
Reasoning Is Not Free: Robust Adaptive Cost-Efficient Router for LLM-as-a-JudgePoster
Reasoning LLM Improves Speaker Recognition in Long-form TV DramasPoster
Reasoning Models Are Test Exploiters: Rethinking Multiple ChoicePoster
Reasoning Models Struggle to Control their Chains of ThoughtPoster
Reasoning Structure of Large Language ModelsPoster
Reasoning about Reasoning: BAPO Bounds on Chain-of-Thought Token Complexity in LLMsPoster
Reasoning as an Attack Surface: Adaptive Evolutionary CoT Jailbreaks for LLMsPoster
Reasoning on the Manifold: Bidirectional Consistency for Self-Verification in Diffusion Language ModelsPoster
Reasoning over Boundaries: Enhancing Specification Alignment via Test-time DeliberationPoster
Reasoning to Edit: Hypothetical Instruction-Based Image Editing with Visual ReasoningPoster
Reasoning-Driven Synthetic Data Generation and EvaluationPoster
Reasoning-VLA: An Efficient and Spatial-Guided General Vision-Language-Action Reasoning Model for Autonomous DrivingPoster
Reasoning-preserved Efficient Distillation of Large Language Models via Activation-aware InitializationPoster
Recognize Your Orchestrator: An Entropy Dynamics Perspective for LLM Multi-Agent SystemsPoster
Reconstructing Template-Memorized Images from Natural PromptsPoster
Reconstruction Outcomes Look Similar but Processes Differ: Improving Context Consistency and Coverage in Graph Masked Auto-EncoderPoster
Recontextualization Mitigates Specification Gaming Without Modifying the SpecificationPoster
Recovering Hidden Reward in Diffusion-Based PoliciesPoster
Recovering Policy-Induced Errors: Benchmarking and Trajectory Synthesis for Robust GUI AgentsSpotlight
Rectified LpJEPA: Joint-Embedding Predictive Architectures with Sparse and Maximum-Entropy RepresentationsPoster
Rectifying Gradient Trajectories: A Hierarchical Geometric Framework with Structural Constraints for Few-Shot EEG AdaptationPoster
Recurrent Equivariant Constraint Modulation: Learning Per-Layer Symmetry Relaxation from DataSpotlight
Recurrent Structural Policy Gradient for Partially Observable Mean Field GamesSpotlight
Recursive Binding on a Budget: Subspace Carving in Order-$p$ Tensor MemoriesPoster
Recursive Models for Long-Horizon ReasoningPoster
Recursive Monte-Carlo Tree SearchPoster
RedDebate: Safer Responses Through Multi-Agent Red Teaming DebatesPoster
RedVisor: Reasoning-Aware Prompt Injection Defense via Zero-Copy KV Cache ReusePoster
Reduction of Probabilistic Chemical Reaction NetworksPoster
RefChess: Monte-Carlo Move Selection for Zero-Shot Referring Image SegmentationPoster
Reference-Free Meta-Learning for Generalized Implicit Neural Representation in Efficient MRI ReconstructionPoster
Referring Multiple Regions with Large Multimodal Models via Contextual Latent SteeringPoster
RefineEvo: Planning-Guided Heuristic Evolution with Bidirectional ExperiencePoster
Refined Analysis of Entropy-Regularized Actor-CriticPoster
Refining Context-Entangled Content Segmentation via Curriculum Selection and Anti-Curriculum PromotionPoster
Refining Dual Spectral Sparsity in Transformed Tensor Singular ValuesPoster
ReflFlow: Learning Geometry-Guided Ray Tracing for Dynamic Specular ReconstructionPoster
Reflect-then-Correct: Rebalancing Task Optimization for Generalizable Meta-Reinforcement Learning via Distributional Value Error ReductionPoster
Reflective Hamiltonian Monte Carlo: Mixing Analysis and Application to Sampling on Stiefel ManifoldPoster
Reflector: Internalizing Step-wise Reflection against Indirect JailbreaksPoster
Reflex: Real-Time Vision-Language-Action Control through Streaming InferencePoster
Regime-Adaptive Bayesian Optimization via Dirichlet Process Mixtures of Gaussian ProcessesPoster
Regression Language Models for CodePoster
Regret Minimization With a Crowd of Awakening ExpertsPoster
Regret Pre-training: Bridging Prior and Posterior Views for Enhanced Knowledge GroundingPoster
Regret-Based Federated Causal Discovery with Unknown InterventionsPoster
Regularization in the Axiomatic Approach to Learning from Human PreferencesSpotlight
Regularized Discriminative Alignment for Deep Representations under Label ShiftPoster
Regularized Offline Policy Optimization with Posterior Hybrid Bayesian BeliefPoster
Regulating Anatomy-Aware Rewards via Trajectory-Integral Feedback for Volumetric Computed Tomography AnalysisPoster
Reinforced Sequential Monte Carlo for Amortised SamplingSpotlight
Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-TrainingPoster
Reinforcement Learning for Non-Verifiable ProblemsPoster
Reinforcement Learning for Reachability: Guaranteeing Asymptotic OptimalityPoster
Reinforcement Learning for Tool-Calling Agents in Fast Healthcare Interoperability Resources (FHIR)Poster
Reinforcement Learning from Bagged RewardPoster
Reinforcement Learning from Human Feedback with Active QueriesPoster
Reinforcement Learning via Self-DistillationPoster
Reinforcement Learning with Action-Triggered ObservationsPoster
Reinforcement Learning with Discrete Diffusion Policies for Combinatorial Action SpacesPoster
Reinforcement Learning with Evolving Rubrics for Deep ResearchOral
Reinforcement Learning with Verifiable Rewards: GRPO's Loss, Dynamics, and Success AmplificationPoster
Reinforcement-aware Knowledge Distillation for LLM ReasoningPoster
Reinforcing Real-world Service Agents: Balancing Utility and Cost in Task-oriented DialoguePoster
Rel-MOSS: Towards Imbalanced Relational Deep Learning on Relational DatabasesPoster
Relational In-Context Learning via Synthetic Pre-training with Structural PriorPoster
Relational Structural Causal ModelsPoster
Relative Entropy Estimation in Function Space: Theory and Applications to Trajectory InferencePoster
RelaxFlow: Text-Driven Amodal 3D GenerationSpotlight
RelayCaching: Accelerating LLM Collaboration via Decoding KV Cache ReusePoster
Relevance-Based Embeddings: Lightweight Candidate Selection via Heavy Ranker CallsPoster
Reliability-Aware LLM Alignment from Inconsistent Human FeedbackPoster
Reliable Confidence Alignment for Generalized Category DiscoveryPoster
Reliable Neighborhood-Aware Multi-View Outlier DetectionPoster
Reliable Thinking with ImagesPoster
Remove the Ambiguity: Few-shot Multimodal Anomaly Detection Using Crossmodal Feature ReplacersPoster
Removing Noise, not Finding Gold: Quality Filtering for Large-Scale PretrainingPoster
Removing Sandbagging in LLMs by Training with Weak SupervisionPoster
Reparameterization Flow Policy OptimizationPoster
Reparameterization Proximal Policy OptimizationPoster
RepetitionCurse: Measuring and Understanding Router Imbalance in Mixture-of-Experts LLMs under DoS StressPoster
Replay Failures as Successes: Sample-Efficient Reinforcement Learning for Instruction FollowingPoster
Repositioning the Subject within ImagePoster
Representation Drift Compensation: A Zero-Cost Enhancement for LLM DecompositionPoster
Representation Learning for Equivariant Inference with GuaranteesPoster
Representation Unlearning: Forgetting through Information CompressionPoster
Representational Curvature Shapes Behavioral Uncertainty in Large Language ModelsPoster
Representational Similarity and Model Behavior in Multi-Agent InteractionPoster
Required Spine Optional Limbs: Heterogeneous Federated Learning via Backbone-sharing and Activation-guided SelectionSpotlight
Reranker Helps, but Not Enough: Towards Strong Poisoning Attacks Against Retrieval-Augmented GenerationPoster
ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement LearningPoster
Residual Context Diffusion Language ModelsPoster
Resilient Coresets and Consistent ClusteringPoster
Resolution as a Direction: Vector-Panning Feature Alignment for Cross-Resolution Re-IdentificationPoster
Resolving Blind Inverse Problems under Dynamic Range Compression via Structured Forward Operator ModelingPoster
Resolving the Timestep Scaling Paradox in Spiking Neural Networks with a Timestep-Scalable Neuron ModelPoster
Resource-Efficient Reinforcement for Reasoning Large Language Models via Dynamic One-Shot Policy RefinementPoster
Respecting Modality Gap in Post-hoc Out-of-distribution Detection with Pre-trained Vision-Language ModelsPoster
Responsible Text-to-Image Diffusion: Interpretable and Linearly Controllable Semantics for Fair and Safe GenerationPoster
Resting Neurons, Active Insights: Robustify Activation Sparsity for Large Language ModelsPoster
Restoring Exploration after Post-Training: Latent Exploration Decoding for Large Reasoning ModelsPoster
Restoring Initial Noise Sensitivity in Text-to-Image Distillation through Geometric AlignmentPoster
Retaining by Doing: The Role of On-Policy Data in Mitigating ForgettingPoster
Rethink the Role of Neural Decoders in Quantum Error CorrectionPoster
Rethinking 1-bit Optimization Leveraging Pre-trained Large Language ModelsPoster
Rethinking 3D Shape Generation: Diffusion over SuperquadricsPoster
Rethinking Attention in Spiking Transformers: Overcoming Density Bias with Set SimilarityPoster
Rethinking Calibration for Early-Exit Neural NetworksPoster
Rethinking Code Complexity Through the Lens of Large Language ModelsPoster
Rethinking Contrastive Learning for Graph Collaborative Filtering: Limitations and A Simple RemedyPoster
Rethinking Convergence in MoE Training: The Role of Routing SparsityPoster
Rethinking Depth Pruning for Vision Transformers: A Heterogeneity-Aware PerspectivePoster
Rethinking Efficient Graph Coarsening via a Non-Selfishness PrinciplePoster
Rethinking Evaluation Paradigms in IBP-based Certified TrainingPoster
Rethinking Feature Alignment in Generalist Graph Anomaly Detection: A Relational Fingerprint-based ApproachPoster
Rethinking Federated Prompt Learning for Medical Images: From Textual Tuning to Visual Manifold AnchoringPoster
Rethinking Forgery Attacks on Semantic Watermarks in Black-Box Settings: A Geometric Distortion PerspectivePoster
Rethinking GNNs and Missing Features: Challenges, Evaluation and a Robust SolutionPoster
Rethinking Gating Mechanism in Sparse MoE: Handling Arbitrary Modality Inputs with Confidence-Guided GatePoster
Rethinking Genomic Modeling Through Optical Character RecognitionPoster
Rethinking Human Intent to CAD: Parametric CAD Model Generation via Cooperative Multi-Task Alignment and Spatial-Aware Reinforcement LearningPoster
Rethinking KV Cache Eviction via a Unified Information-Theoretic ObjectivePoster
Rethinking LLM Ensembling from the Perspective of Mixture ModelsSpotlight
Rethinking Loss Reweighting for Imbalance Learning as an Inverse Problem: A Neural Collapse Point of ViewPoster
Rethinking Low-Confidence Pseudo Labels: Influence-Aware Semi-Supervised Fine-Tuning for Hyperspectral Change DetectionPoster
Rethinking Memory in Continual Learning: Beyond a Monolithic Store of the PastPoster
Rethinking Multimodal Time-Series Forecasting EvaluationPoster
Rethinking Neural Network Learning Rates: A Stackelberg PerspectivePoster
Rethinking Parameter Sharing as Graph Coloring for Structured CompressionPoster
Rethinking Personalization in Large Language Models at the Token LevelPoster
Rethinking Pretraining Data Detection for LLMs: From Local to GlobalPoster
Rethinking Serialization in Linear 3D Vision: Decoupling Anisotropic Geometry from Isotropic SemanticsPoster
Rethinking Sparse Mixture of Experts from a Unified PerspectivePoster
Rethinking Temporal Consistency in Video Object-Centric Learning: From Prediction to CorrespondencePoster
Rethinking Thinking Tokens: LLMs as Improvement OperatorsPoster
Rethinking Time-Series Imputation as Conditional Inference along Temporal EvolutionPoster
Rethinking Video Generation Model for the Embodied WorldPoster
Rethinking Visual Autoregressive Sampling with Information-Grounding GuidancePoster
Rethinking Visual Intelligence: Insights from Video PretrainingPoster
Rethinking generative image pretraining: How far are we from scaling up next-pixel prediction?Poster
Rethinking the Design Space of Reinforcement Learning for Diffusion Models: On the Importance of Likelihood Estimation Beyond Loss DesignPoster
Rethinking the Flow-based Gradual Domain Adaption: A Semi-Dual Optimal Transport PerspectivePoster
Rethinking the Hardness of PbRL: A Provable General Regret BoundPoster
Rethinking the Reranker: Boundary-Aware Evidence Selection for Robust Retrieval-Augmented GenerationPoster
Rethinking the Trust Region in LLM Reinforcement LearningPoster
RetrOrchestrator: A Multi-Step Retrosynthesis Agent Dynamically Orchestrating Single-Step Transition ModelsPoster
Retrieval-Aware Distillation for Transformer-SSM HybridsPoster
Retriever Portfolios: A Principled Approach to Adaptive RAGPoster
Retro-Expert: Collaborative Reasoning for Interpretable RetrosynthesisPoster
Retrospective Feature Estimation for Continual LearningPoster
Return of Frustratingly Easy Unsupervised Video Domain AdaptationPoster
Return-Aligned Decision TransformerPoster
Return-Critic: Bridging Goal Discrepancy for Efficient Visual Reinforcement LearningPoster
Return-to-Go Is More Than a Number: Q-Guided Alignment for Return-Conditioned Supervised LearningPoster
Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy PrefixesPoster
Reusing Trajectories in Policy Gradients Enables Fast ConvergencePoster
RevealLayer: Disentangling Hidden and Visible Layers via Occlusion-Aware Image DecompositionPoster
Revealing Behavioral Plasticity in Large Language Models: A Token-Conditional PerspectivePoster
Revealing Differences in Multi-Modal Embeddings via Constrained Kernel AnalysisPoster
Revealing Long-context Potential of Attention Heads via Frequency KernelsPoster
Revealing Scaling Behavior in Large-scale Time Series Models: Implications for More Efficient and Accurate ForecastingPoster
Revenue Efficiency of Correlated Equilibria in First Price AuctionsOral
Reverse Flow Matching: A Unified Framework for Online Reinforcement Learning with Diffusion and Flow PoliciesSpotlight
Reverse-Engineering Model Editing on Language ModelsPoster
Revisiting Anisotropy in Language Transformers: The Geometry of Learning DynamicsPoster
Revisiting Asymmetries in Black-box Link Stealing against Graph Neural NetworksPoster
Revisiting Coding-Based Approaches to Overcome the Curse of Dimensionality in Learning-Based WatermarkingPoster
Revisiting Distribution Correction Estimation for Offline Imitation Learning with Suboptimal DatasetPoster
Revisiting Efficiency–Accuracy Scaling in Mixture-of-Experts ArchitecturesPoster
Revisiting ML Training under Fully Homomorphic Encryption: Convergence Guarantees, Differential Privacy, and Efficient AlgorithmsPoster
Revisiting Neural Processes via Fourier Transform and Volterra SeriesPoster
Revisiting OOD Generalization in Programmatic RLPoster
Revisiting Padded Transformer Expressivity: Which Architectural Choices Matter and Which Don'tPoster
Revisiting Parameter-Based Knowledge Editing in Large Language Models: Theoretical Limits and Empirical EvidencePoster
Revisiting Photometric Ambiguity for Accurate Gaussian-Splatting Surface ReconstructionPoster
Revisiting Positive Samples in Graph Contrastive Learning: From the Perspective of Message PassingPoster
Revisiting Pre-Propagation GNNs: Robust Diffusion Operators and Hidden-State Re-PropagationPoster
Revisiting Regularized Policy Optimization for Stable and Efficient Reinforcement Learning in Two-Player GamesPoster
Revisiting Robustness for LLM Safety Alignment via Selective Geometry ControlPoster
Revisiting Spectral Representations in Generative Diffusion ModelsPoster
Revisiting Uncertainty: On Evidential Learning for Partially Relevant Video RetrievalPoster
Revisiting Zeroth-Order Hessian Approximation: A Single-Step Policy Optimization LensPoster
Revisiting the Bertrand Paradox via Equilibrium Analysis of No-regret LearnersPoster
Revisiting the Platonic Representation Hypothesis: An Aristotelian ViewPoster
Revisiting the Role of Pretrained Weights in Model Merging: On Near-Optimality within the Core SubspacePoster
Revisiting the Volume HypothesisPoster
Reviving Error Correction in Modern Deep Time-Series ForecastingPoster
Reward Auditor: Inference on Reward Modeling Suitability in Real-World Perturbed ScenariosPoster
Reward Hacking Benchmark: Measuring Exploits in LLM Agents with Tool UsePoster
Reward Learning through Ranking Mean Squared ErrorPoster
Reward Modeling from Natural Language Human FeedbackPoster
Reward Redistribution for CVaR MDPs using a Bellman Operator on L-infinitySpotlight
Reward Shaping Control Variates for Off-Policy Evaluation Under Sparse RewardsPoster
Reward Shaping for Inference-Time Alignment: A Stackelberg Game PerspectivePoster
Reward Under Attack: Analyzing the Robustness and Hackability of Process Reward ModelsPoster
Reward and Guidance through Rubrics: Promoting Exploration to Improve Multi-Domain ReasoningSpotlight
Reward-Preserving Counterfactual State Editing for Offline Reinforcement LearningPoster
Reward-free Alignment for Conflicting ObjectivesOral
Rewiring Experts on the Fly: Continuous Rerouting for Better Online Adaptation in Mixture-of-Expert modelsPoster
Rex: A Family of Reversible Exponential (Stochastic) Runge-Kutta SolversOral
Rh-3DGS: Robust Open-Vocabulary Scene Understanding via Riemannian Huber Distillation and Manifold-Aware SamplingPoster
RiboSphere: Learning Unified and Efficient Representations of RNA StructuresPoster
Richer Bayesian Last Layers with Subsampled NTK FeaturesPoster
Riemannian Diffusion Models on General Manifolds via Physics-Informed Neural NetworksPoster
Riemannian Dueling OptimizationPoster
Riemannian Generative DecoderPoster
Riemannian MeanFlowPoster
Riemannian MeanFlow for One-Step Generation on ManifoldsPoster
Riemannian Metric Matching for Scalable Geometric Modeling of DistributionsOral
Riemannian Networks over Full-Rank Correlation MatricesPoster
Riemannian Neural Optimal TransportPoster
Riemannian Optimization for Fair Spectral ClusteringPoster
Riemannian stochastic optimization for sufficient dimension reductionPoster
Ripple Perturbations Through Structure: Likelihood-Constrained Adversarial Attacks on Heterogeneous Tabular DataPoster
Risk Awareness Injection: Calibrating Vision-Language Models for Safety without Compromising UtilityPoster
Risk-Averse and Optimistic Advertiser Incentive Compatibility in Auto-biddingPoster
Risk-Bounded Distribution Reconstruction: Stable Statistic Calibration for Long-Tailed RecognitionPoster
RiskZero: Plan More to Risk Less with a Learned ModelPoster
RoCA: Robust Cross-Domain End-to-End Autonomous DrivingPoster
RoboFlow4D: A Lightweight Flow World Model Toward Real-Time Flow-Guided Robotic ManipulationPoster
RoboMME: Benchmarking and Understanding Memory for Robotic Generalist PoliciesOral
RoboOmni: Actions Are Just Another Modality for Your Vision-Language ModelsPoster
RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic ManipulationPoster
RobuQ: Pushing DiTs to W1.58A2 via Robust Activation QuantizationPoster
Robust AI Evaluation through Maximal LotteriesPoster
Robust Bayes-Assisted Conformal PredictionPoster
Robust Bayesian Optimisation with Unbounded CorruptionsPoster
Robust Causal Discovery in Real-World Time Series with Power-LawsSpotlight
Robust Contextual Optimization with Missing CovariatesOral
Robust Cross-Modal Retrieval via Generative Semantic Refinement and Exclusion-Guided AdaptationPoster
Robust Federated Learning Against Adaptive CompressionPoster
Robust Filter Attention: Self-Attention as a Parallel State EstimatorSpotlight
Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language ModelsOral
Robust In-Context Reinforcement Learning Under Reward Poisoning AttacksPoster
Robust Inter-Series Dependency Modeling for Time Series Forecasting via Information-Theoretic AlignmentPoster
Robust Learning via Nested Distributionally Robust OptimizationPoster
Robust Linear Dueling Bandits with Post-serving Context under Unknown Delays and Adversarial CorruptionsPoster
Robust Multi-View Fusion via Prototype-Anchored Unbalanced Optimal TransportPoster
Robust Parallel Diffusion Sampling via Dynamic Jacobian BandwidthPoster
Robust Reinforcement Learning in a Sample-Efficient SettingPoster
Robust Self-reflective Hashing for Cross-modal Retrieval with Noisy LabelPoster
Robust Sequential Experimental Design for A/B TestingPoster
Robust Signal Enhancement via Fractional Detail Views and Knowledge Guided Multi-view FusionPoster
Robust Stochastic Gradient Posterior Sampling with Lattice Based DiscretisationPoster
Robust Strategic Classification under Decision-Dependent Cost UncertaintyPoster
Robust Vision-Language Models via Manifold-Adversarial AdaptersPoster
Robust and Consistent Ski Rental with Distributional AdvicePoster

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.