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

Factored Value Functions for Graph-Based Multi-Agent Reinforcement LearningPoster
Factorized Scheduling Principle: Learning Interpretable and Transferable Policies via Structured Additive FunctionsPoster
Facts in Stats: Impacts of Pretraining Diversity on Language Model GeneralizationPoster
Failure is Feedback: History-Aware Backtracking for Agentic Traversal in Multimodal GraphsPoster
Failure-Driven Workflow RefinementSpotlight
Fair Classification with Efficient and Post-hoc Controllable Fairness-Accuracy Trade-offSpotlight
Fair Dataset Distillation via Cross-Group Barycenter AlignmentPoster
Fair Decisions from Calibrated Scores: Achieving Optimal Classification While Satisfying SufficiencyPoster
Fair Transit Stop Placement: A Clustering Perspective and BeyondPoster
Fair-FedMOE: Group-Fair One-Shot Federated Learning via Prototype-Guided Experts for Medical Imaging AnalysisPoster
FairGB: A Fair Granular-Ball Generation Method for Data ClassificationPoster
FairJudge : An Adaptive, Debiased, and Consistent LLM-as-a-JudgePoster
FairMerging: Rethinking Model Merging through the Lens of FairnessPoster
FairRARI: A Plug and Play Framework for Fairness-Aware PageRankPoster
FairSSL: Fair Multimodal Self-Supervised LearningPoster
Fairness in Aggregation: Optimal Top-$k$ and Improved Full RankingPoster
Faithful Mobile GUI Agents with Guided Advantage EstimatorPoster
Faithful Relational Reasoning with Region-based Embeddings: Expressivity of Convex Coordinate-wise ModelsPoster
FakeWorld 1.0: An Omni modal Benchmark for Fake Media and ContentPoster
Falsifying Sparse Autoencoder Reasoning Features in Language ModelsPoster
Fantastic Reasoning Behaviors and Where to Find Them: Unsupervised Discovery of the Reasoning ProcessPoster
Fast Autoregressive Video Diffusion and World Models with Temporal Cache Compression and Sparse AttentionPoster
Fast Byte Latent TransformerPoster
Fast Estimation for Forest Matrix of Signed GraphsPoster
Fast Inverse Lithography via GRPO Reinforced Flow MatchingPoster
Fast KV Compaction via Attention MatchingPoster
Fast Mixing Steady-State Control in Markov Decision ProcessesPoster
Fast Mixture of Curvature-Aware Experts for Diverse and Dynamic Graph TopologiesPoster
Fast Non-Episodic Finite-Horizon RL with K-Step Lookahead ThresholdingPoster
Fast Reconstruction of Mixtures of Bernoulli Product DistributionsPoster
Fast Spectrally Sparse Signal Reconstruction via Jacobi-Preconditioned Gradient DescentSpotlight
Fast and Accurate Causal Parallel Decoding using Jacobi ForcingPoster
Fast and Expressive Multi-Byte Prediction with Probabilistic CircuitsPoster
Fast and Highly Expressive Policy Learning for Offline Reinforcement Learning via Bootstrapped Flow Q-LearningPoster
Fast and Optimal Algorithms for Private Hypothesis SelectionPoster
Fast and Scalable Analytical DiffusionPoster
Fast k-means Seeding Under The Manifold HypothesisPoster
Fast kernel methods: Sobolev, physics-informed, and additive modelsPoster
Fast-SAM3D: 3Dfy Anything in Images but FasterPoster
FastSESR: Fast Scene-level Explicit Surface ReconstructionPoster
Faster Activation Functions at the Edge for Post-Training SpeedupsOral
Faster Query-Key Learning Sharpens Attention in Self-Attention ModelsPoster
Faster Than Flash: Exploiting Attention Sparsity for Efficient Long-Context DecodingPoster
FasterVAR: Plug-and-Play Acceleration for Visual Autoregressive ModelsPoster
Fault Tolerant Multi-Agent Learning with Adversarial Budget ConstraintsPoster
Faults in Our Formal Benchmarking: Dataset Defects and Evaluation Failures in Lean Theorem ProvingPoster
FeRA: Frequency-Energy Constrained Routing for Effective Diffusion Adaptation Fine-TuningPoster
Feasible Fusion: Constrained Joint Estimation under Structural Non-OverlapPoster
Feature Bagging Provides StabilityPoster
Feature Collapse Under Corruption: An Entropy Perspective on Robust Neural NetworksPoster
Feature Resemblance: Towards a Theoretical Understanding of Analogical Reasoning in TransformersPoster
Feature-aware (Hyper)graph Generation via Next-Scale PredictionPoster
FedARC: Anchor-Guided Residual Compensation for Data and Model Heterogeneous Federated LearningSpotlight
FedCDWA: Decoupled Federated Prototype Distillation with Hierarchical Wasserstein AggregationPoster
FedGain: Toward Negative-Gain-Free Client Collaboration in Federated LearningPoster
FedHPro: Federated Hyper-Prototype Learning via Gradient MatchingPoster
FedHera: Towards Drift-Resilient Federated Fine-tuning with Heterogeneous ResourcesPoster
FedLog: Personalized Federated Classification with Less Communication and More FlexibilityPoster
FedPAT: Federated Test-Time Adaptation via Prototype Affinity TopologyPoster
FedPDG: Prediction Discrepancy–Guided Data Generation for Heterogeneous Federated LearningPoster
FedPissa: Towards Federated Personalized Adaptation of Foundation Models via LoRA Subspace MappingSpotlight
FedQueue: Queue-Aware Federated Learning for Cross-Facility HPC TrainingPoster
FedRGL: Robust Federated Graph Learning under Label NoisePoster
FedReLa: Imbalanced Federated Learning via Re-LabelingPoster
FedRot-LoRA: Mitigating Rotational Misalignment in Federated LoRAPoster
FedSDR: Federated Self-Distillation with RectificationPoster
FedSSM: State Space Model-based Proactive Inference for Heterogeneous Multimodal Federated LearningPoster
FedScar: Correcting Geometric Bias for Flatness-Consistent Federated LearningPoster
FedTreeLoRA: Reconciling Statistical and Functional Heterogeneity in Federated LoRA Fine-TuningPoster
FedUSD: Unbiased Synthetic Data for Federated LearningPoster
FedVeer: Self-Adaptive Skew Estimation for Robust Federated LearningPoster
Federated Bilevel Performative PredictionPoster
Federated Causal Inference on Multi-Site Observational Data via Propensity Score AggregationPoster
Federated Data and Feature Selection by Generalized CUR DecompositionPoster
Federated Distillation for Whole Slide Image via Gaussian-Mixture Feature Alignment and Curriculum IntegrationPoster
Federated Graph Learning via Structure-Aware Fusion Using a Kalman Framework with Learnable DynamicsPoster
Federated Learning with Unlabeled Clients: Personalization Can Happen in Low DimensionsPoster
Federated Manifold Learning (FML): Tackling Domain Heterogeneity with Structural Knowledge TransferPoster
Federated Multi-view Clustering for Remote Sensing DataPoster
Federated Sketching LoRA: A Flexible Framework for Heterogeneous Collaborative Fine-Tuning of LLMsPoster
Federated Variational Preference Alignment with Gumbel-Softmax Prior for Personalized User PreferencesPoster
Fedfit: Federated dynamic pruning via Fisher Information scoringPoster
Feed-Forward Taylor-Gaussians-Flow: Towards Non-uniform Motion for Novel View Synthesis from Monocular VideoPoster
Feedback Control for Multi-Objective Graph Self-SupervisionPoster
FiGuRO - Intrinsic Dimension Estimation for Multi-Modal DataPoster
FiRE: Fine-grained Ranking Evaluation for Machine TranslationPoster
FiSeR: Fine-Grained Source Representations for Cross-Domain AI Image DetectionPoster
FiX: Introducing Fine-grained Forget Gate into Softmax AttentionPoster
Find, Fix, Reason: Context Repair for Video ReasoningPoster
Finding Differentially Private Second Order Stationary Points in Stochastic Minimax OptimizationPoster
Finding DoRI: Discovery of Retained Images in Diffusion ModelsPoster
Finding Most Influential SetsPoster
Finding Stationary Points by ComparisonsPoster
Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention DiscrepancyPoster
Finding the Minimal Parameter Budget for Implicit Reasoning: A Data Complexity Driven Scaling Law for Language ModelsPoster
Fine-Tune Once, Reuse Across Models: Bayesian Task-Update Factors and ApproximationsPoster
Fine-Tuning Masked Diffusion for Provable Self-CorrectionPoster
Fine-Tuning Without Forgetting In-Context Learning: A Theoretical Analysis of Linear Attention ModelsPoster
Fine-Tuning of Transformer models with FramesPoster
Fine-grained Analysis of Brain-LLM Alignment through Input AttributionPoster
Fine-to-Coarse Fairness-Informed Multi-View ClusteringPoster
FineFocus: Benchmarking and Improving Fine-Grained Text-to-Image Alignment via Paired Reinforcement LearningPoster
Fingerprinting Pre-trained Encoders under Arbitrary Downstream Fine-Tuning via Adversarial ShiftingPoster
Finite and Corruption-Robust Regret Bounds in Online Inverse Linear Optimization under M-Convex Action SetsPoster
Finite-Width Neural Tangent Kernels from Feynman DiagramsPoster
Finite-time Convergence Analysis of Actor-Critic with Evolving RewardPoster
Fisher-Preserving Guidance: Training-Free Manifold Constraints for Safe Diffusion ControlPoster
Fix Before Search: Benchmarking Agentic Visual Query Pre-processing in Multimodal Retrieval-augmented GenerationPoster
Fix the Loss, Not the Radius: Rethinking the Adversarial Perturbation of Sharpness-Aware MinimizationPoster
Fix the Mind, Not the Move: Interpretable AI Assistance via Knowledge-Gap LocalizationPoster
Fixed Aggregation Features Can Rival GNNsPoster
Fixed Budget is No Harder Than Fixed Confidence in Best-Arm Identification up to Logarithmic FactorsPoster
Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy OptimizationPoster
Flash-VAED: Plug-and-Play VAE Decoders for Efficient Video GenerationPoster
FlashBlock: Attention Caching for Efficient Long-Context Block DiffusionPoster
FlashOptim: Memory Efficient Optimizers for Large-Scale TrainingSpotlight
FlashSinkhorn: IO-Aware Entropic Optimal Transport on GPUOral
FlashSketch: Sketch-Kernel Co-Design for Fast Sparse Sketching on GPUsOral
Flat Minima and Generalization: Insights from Stochastic Convex OptimizationPoster
FlatLab: A Unified Methodology Framework and Simulation-Based Benchmark for Robotic Manipulation of Flat ObjectsPoster
FlatLand: Personalized Graph Federated Learning via Tailored Lorentz SpaceOral
Flatland: The Adventures of Gradient Descent with Large Step SizesPoster
Flatness-Aware Stochastic Gradient Langevin DynamicsPoster
Fleet: Few-Shots Lead Effective AIGI DetectionPoster
Flex-Forcing: Towards a Unified Autoregressive and Bidirectional Video Diffusion ModelSpotlight
FlexRank: Nested Low-Rank Knowledge Decomposition for Adaptive Model DeploymentSpotlight
FlexiFlow: decomposable flow matching for generation of flexible molecular ensemblePoster
Flexibility-Aware Geometric Latent Diffusion for Full-Atom Peptide DesignPoster
Flexible Kernels for Protein Property PredictionPoster
Float8@2bits: Entropy Coding Enables Data-Free Model CompressionPoster
Floating-Point Networks with Automatic Differentiation Can Represent Almost All Floating-Point Functions and Their GradientsPoster
FloorplanQA: A Benchmark for Spatial Reasoning in LLMs using Structured RepresentationsPoster
Flow Equivariant World Models: Structured Memory for Dynamic EnvironmentsPoster
Flow Inverse Reinforcement LearningPoster
Flow Matching Calibration for Simulation-Based Inference under Model MisspecificationPoster
Flow Sampling : Learning to Sample from Unnormalized Densities via Denoising Conditional ProcessesSpotlight
Flow for Future: Geometric SE(3)-Equivariant Flow Matching for 3D Trajectory PredictionPoster
Flow-Based Density Ratio Estimation for Intractable Distributions with Applications in GenomicsPoster
FlowCloud: Learning Continuous Spatiotemporal Dynamics from Unpaired Sparse Point Cloud SnapshotsPoster
FlowMAP: Flow Matching for Generalizable Agent PlanningPoster
FlowNar: Scalable Streaming Narration for Long-Form VideosPoster
FlowPET: Physics-Informed Symplectic Flow Matching for Low-Count PET ReconstructionPoster
FlowSeg: Dynamic Semantic Guidance for LLM-Conditioned SegmentationPoster
FlowState: Sampling-Rate‑Equivariant Time‑Series ForecastingPoster
Flowers: A Warp Drive for Neural PDE SolversSpotlight
FluxNet: Learning Capacity-Constrained Local Transport Operators for Conservative and Bounded PDE SurrogatesPoster
FocalPolicy: Frequency-Optimized Chunking and Locally Anchored Flow Matching for Coherent Visuomotor PolicyPoster
Focus and Dilution: The Multi-stage Learning Process of AttentionOral
Focus, Align, and Sustain: Counteracting Gradient Dilution in Incremental Object DetectionPoster
Focus-Then-Contact: Speeding Up Robotic Contact-Rich Task Learning with Affordance-Guided Real-World Residual Reinforcement LearningPoster
Focusing Where Vision Matters: Selective Training for Large Vision Language Models via Visual Information GainPoster
Focusing: View-Consistent Sparse Voxels for Efficient 3D VAEPoster
FoeGlass: When Simple In-Context Learning Is Enough for Red Teaming Audio Deepfake DetectorsPoster
Follow-the-Perturbed-Leader for Decoupled Bandits: Best-of-Both-Worlds and PracticalityPoster
ForceForget: Reinforcement Concept Removal for Enhancing Safety in Text-to-Image ModelsPoster
Foreground-Aware Token Routing Vision Transformer for Real-Time Satellite Video TrackingPoster
Forensic Prompting with Dual-Action Policy Optimization for Vision-Language Forgery Detection and LocalizationPoster
ForensicConcept:Transferable Forensic Concepts for AIGI DetectionPoster
Foresee-to-Ground: From Predictive Temporal Perception to Evidence-Driven Reasoning for Video Temporal GroundingPoster
ForesightKV: Optimizing KV Cache Eviction for Reasoning Models by Learning Long-Term ContributionPoster
Forget by Uncertainty: Orthogonal Entropy Unlearning for Quantized Neural NetworksPoster
Forget to Know, Remember to Use: Context-Aware Unlearning for Large Language ModelsPoster
Forget-It-All: Multi-Concept Machine Unlearning via Concept-Aware Neuron MaskingPoster
Forgetting Whenever You Want: A Decentralized Continual Learning Framework with On-Demand UnlearningPoster
FormAct: Agentic Source Editing for Rich-Format Document GenerationPoster
Formal Concept Lattices are Good Semantic Scaffolds for Concept-Based LearningPoster
FormalJudge: A Neuro-Symbolic Paradigm for Agentic OversightPoster
FormalRx: Rectify and eXamine Semantic Failures in AutoformalizationPoster
Formalizing Learning from Language Feedback with Provable GuaranteesPoster
Formalizing and Falsifying Causal Pathways of Rare EventsPoster
Formalizing the Binding ProblemPoster
Formally Exploring Visual Anomaly Detection Evaluation MetricsPoster
Forward-Chaining Temporal Point ProcessPoster
Forward-KL Convergence of Time-Inhomogeneous Langevin DiffusionsPoster
FoundObj: Self-supervised Foundation Models as Rewards for Label-free 3D Object SegmentationPoster
Foundation Inference Models for Ordinary Differential EquationsPoster
Foundation VAE for CT Reconstruction, Augmentation, and GenerationPoster
Foundations of Equivariant Deep Learning: Unifying Graph and Sheaf Neural NetworksOral
FourTune: Towards Fully 4-Bit Efficient Post-Training for Diffusion ModelsPoster
Fourier Features Let Agents Learn High Precision Policies with Imitation LearningPoster
Fox in the Henhouse: Supply-Chain Backdoor Attacks Against Reinforcement LearningPoster
Fractional is Better: Learnable Derivative Orders in Neural Operator LearningPoster
FrameOracle: Learning What to See and How Much to See in VideosPoster
FreeRet: MLLMs as Training-Free RetrieversPoster
FreeText: Training-Free Text Rendering via Attention Localization and Spectral Glyph InjectionPoster
Frequency Matching in Spiking Neural Networks for mmWave SensingPoster
Frequency-Aware Perceptual Optimization for Low-Complexity Implicit Image CompressionPoster
Frequentist Consistency of Prior-Data Fitted Networks for Causal EstimationPoster
Frictional Q-LearningPoster
From 2D Grids to 1D Tokens: Reforming Shared Representations for Multimodal Image FusionPoster
From Absolute to Relative: Rethinking Reward Shaping in Group-Based Reinforcement LearningPoster
From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action ModelOral
From Associations to Activations: Comparing Behavioral and Hidden-State Semantic Geometry in LLMsPoster
From Backward Spreading to Forward Replay: Revisiting Target Construction in LLM Parameter EditingPoster
From Basis to Basis: Gaussian Particle Representation for Interpretable PDE OperatorsPoster
From Bits to Rounds: Parallel Decoding with Exploration for Diffusion Language ModelsPoster
From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal ModelsPoster
From Coarse to Fine: Deep Prototype Refinement Network for Few-Shot Point Cloud Semantic SegmentationPoster
From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAGPoster
From Content to Knowledge: Lightning Fast Long-Video Understanding with Neural Knowledge RepresentationsPoster
From Correspondence to Actions: Human-Like Multi-Image Spatial Reasoning in Multi-modal Large Language ModelsPoster
From Denoising to De-Channeling: Integrating Physical Channel Priors into Diffusion Models for Radio Signal UnderstandingSpotlight
From Diagrams to Code: Multilingual Programming with Visual DesignPoster
From Directions to Regions: Decomposing Activations in Language Models via Local GeometryPoster
From Distribution to Geometry: Stable Graph Generalization via Invariant BarycentersSpotlight
From Drift to Coherence: Stabilizing Beliefs in LLMsPoster
From Evaluation to Design: Using Potential Energy Surface Smoothness Metrics to Guide ML Interatomic Potential ArchitecturesPoster
From Extraction to Deduction: Resolving Functional Misalignment in RAG via a Collaborative Critic-Reasoner FrameworkPoster
From Extrinsic to Intrinsic: Geodesic-Guided Representation Learning for 3D Geometric DataPoster
From Feasible to Practical: Pareto-Optimal Synthesis PlanningOral
From Flat Facts to Sharp Hallucinations: Detecting Stubborn Errors via Gradient SensitivityPoster
From Generalist to Specialist RepresentationPoster
From Generative to Episodic: Sample-Efficient Replicable RLPoster
From Growing to Looping: A Unified View of Iterative Computation in LLMsPoster
From Guessing to Placeholding: A Cost-Theoretic Framework for Uncertainty-Aware Code CompletionPoster
From Holo Pockets to Electron Density: GPT-style Drug Design with DensityPoster
From Human Labels to Literature: Semi-Supervised Learning of NMR Chemical Shifts at ScalePoster
From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot ManipulationPoster
From Individual Calibration to Reliable Classifiers: ALD Parameterization with mPAIC GuaranteesPoster
From Inpainting to Editing: Unlocking Robust Mask-Free Visual Dubbing via Generative BootstrappingPoster
From Intent to Solver Code: Semantic Alignment in Optimization ModelingPoster
From Interaction Trajectories to Prompt Rules: Credit Assignment for Multi-Agent Prompt OptimizationPoster
From Interactions to Principles: Experience-Driven Self-Distillation for Evolving LLM AgentsPoster
From Internal Diagnosis to External Auditing: A VLM-Driven Paradigm for Data-Free Online Backdoor DefensePoster
From Kepler to Newton: Inductive Biases Guide Learned World Models in TransformersPoster
From Knowledge to Inference: Formalizing Specialized Public Health Reasoning on GlobalHealthAtlasPoster
From LLM-Generated Conjectures to Lean Formalizations: Automated Polynomial Inequality Proving via Sum-of-Squares CertificatesPoster
From Lyapunov Analysis to Algorithm Design in two-sided PL Minimax OptimizationPoster
From Memorization to Parameter Interference: How Overtraining Experts Harms Model MergingPoster
From Moments to Models: Graphon-Mixture Learning for Mixup and Contrastive LearningPoster
From Muon to Gluon: Bridging Theory and Practice of LMO-based Optimizers for LLMsPoster
From Noise to Control: Parameterized Diffusion PoliciesPoster
From Noise to Intent: Anchoring Generative VLA Policies with Residual BridgesPoster
From Observations to States: Latent Time Series ForecastingPoster
From Optimization to Generalization under Heavy-Tailed Data: The Role of Gradient ClippingPoster
From Out-of-Distribution Detection to Hallucination Detection: A Geometric ViewPoster
From Outcomes to Actions: Leveraging Hindsight for Long-Horizon Language Agent TrainingPoster
From Pairwise Affinities to Functional Correspondences: Rethinking AttentionPoster
From Parameter Dynamics to Risk Scoring: Quantifying Sample-Level Safety Degradation in LLM Fine-tuningPoster
From Parameters to Data: A Task-Parameter-Guided Fine-Tuning Pipeline for Efficient LLM AlignmentPoster
From Parameters to Feature Space: Task Arithmetic for Backdoor Mitigation in Model MergingPoster
From Patches to Plans: Reasoning Distillation for Repository-Level Program RepairPoster
From Per-Image Low-Rank to Encoding Mismatch: Rethinking Feature Distillation in Vision TransformersPoster
From Perception to Planning: Evolving Ego-Centric Task-Oriented Spatiotemporal Reasoning via Curriculum LearningPoster
From Pixels to Tokens: A Systematic Study of Latent Action Supervision for Vision-Language-Action ModelsOral
From Player to Master: Enhancing Test-Time Learning of LLM Agents via Reinforcement Learning over MemoryPoster
From Poisoned to Aware: Fostering Backdoor Self-Awareness in LLMsSpotlight
From Prior to Pro: Efficient Skill Mastering via Distribution Contractive RL FinetuningPoster
From Prompts to Responses: Dual-Sided Data Leakage and Defense in Split Large Language ModelsPoster
From Prompts to Tokens: Internalizing Causal Supervision in Vision-Language Model for Multi-Image Causal ReasoningPoster
From Reasoning Traces to Reusable Modules: Reinforcement Learning for Compositional Generalization in Language Model ReasoningPoster
From Representation to Action: A Unified Laplacian Framework for Spatial Representation and Path PlanningPoster
From Retrieval to Translation: Translating Query into Graph-level Clues for Retrieval-Augmented GenerationPoster
From Reward-Free Representations to Preferences: Rethinking Offline Preference-Based Reinforcement LearningPoster
From Seeing to Thinking: Decoupling Perception and Reasoning Improves Post-Training of Vision-Language ModelsPoster
From Shortcuts to Reasoning: Robust Post-Training of Theory of Mind with Reinforcement LearningPoster
From Similarity to Vulnerability: Key Collision Attack on LLM Semantic CachingPoster
From Static Constraints to Dynamic Adaptation: Sample-Level Constraint Release for Offline-to-Online Reinforcement LearningPoster
From Statics to Dynamics: Physics-Aware Image Editing with Latent Transition PriorsPoster
From Talking to Singing: A New Challenge for Audio-Visual Deepfake DetectionPoster
From Teacher Pathways to Invariant Manifolds: Consensus Subspace Distillation for TSFMsPoster
From Text to Forecasts: Bridging Modality Gap with Temporal Evolution Semantic SpaceOral
From Token to Token Pair: Efficient Prompt Compression for Large Language Models in Clinical PredictionPoster
From Volume to Value: Preference-Aligned Memory Construction for On-Device RAGPoster
From Welfare to Utility: Generalized Objectives in Budget-Feasible ProcurementPoster
From Winning to Understanding: A Diagnostic Long-Horizon RTS Benchmark for LLMsPoster
From Zero to Hero: Advancing Zero-Shot Foundation Models for Tabular Outlier DetectionPoster
From geometry to dynamics: Learning overdamped Langevin dynamics from sparse observations with geometric constraintsPoster
Front-Loaded Robust Conformal Prediction: Heavy Calibration, Minimal Test-Time CostPoster
Frontier Models Can Take Actions at Low ProbabilitiesPoster
FrontierCS: Evolving Challenges for Evolving IntelligencePoster
Full-Batch Gradient Descent Outperforms One-Pass SGD: Sample Complexity Separation in Single-Index LearningPoster
Full-Spectrum Graph Neural Network: Expressive and ScalablePoster
FullStack-Agent: Enhancing Agentic Full-Stack Web Coding via Development-Oriented Testing and Repository Back-TranslationPoster
Fully Dynamic Coreset Spectral ClusteringPoster
Fully Zero-Shot Image DehazingPoster
FunCQNet: A Functional Censored Quantile Neural Network for Predicting Long-Term Post-Transplant Kidney SurvivalPoster
FunPhase: A Periodic Functional Autoencoder for Motion Generation via Phase ManifoldsPoster
Function-Valued Causal Influence in Nonlinear Time SeriesPoster
Functional Adjoint Sampler: Scalable Sampling on Infinite Dimensional SpacesPoster
Functional Cache Grafting: Robust and Rapid Code-Policy Synthesis for Embodied AgentsPoster
Functional Decomposition and Shapley Interactions for Interpreting Survival ModelsPoster
Functional Equivalence in Attention: A Comprehensive Study with Applications to Linear Mode ConnectivityPoster
Functional building blocks of neural networks: from network motifs to collective dynamicsPoster
Furina: Fragmented Uncertainty-Driven Refusal Instability AttackPoster
FuseFSS: Efficient Secure LLM Inference with Function Secret SharingPoster
FusionCell: Cross-Attentive Fusion of Layout Geometry and Netlist Topology for Standard-Cell Performance PredictionPoster
Future Dynamic 3D Reconstruction: A 3D World Model with Disentangled Ego-MotionPoster
Future-Gain Guided Test-Time Learning for Large Language ModelsPoster
FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMsPoster
G$^2$RPO: Geometric GRPO; Escaping LLM's Reasoning Rut to Break Accuracy--Entropy Trade-offPoster
G$^2$TAM: Geometry Grounded Track Anything ModelPoster
G-RANS: Generalizable Residual-Aware Neural Solvers for Sparse SystemsPoster
G2D2: Gradient-Guided Discrete Diffusion for Inverse Problem SolvingPoster
GAAVI: Global Asymptotic Anytime Valid Inference for the Conditional Mean FunctionPoster
GADA: Geometry-Aware Deformable Aggregation for Image-Based Gaussian SplattingPoster
GAE: Unleashing Physical Potential of VLM with Generalizable Action ExpertPoster
GAM-RAG: Gain-Adaptive Memory for Evolving Retrieval in Retrieval-Augmented GenerationPoster
GASS: Geometry-Aware Spherical Sampling for Disentangled Diversity Enhancement in Text-to-Image GenerationPoster
GAUSS: Graph-Assisted Uncertainty Quantification using Structure and Semantics for Long-Form Generation in LLMsPoster
GCIB: Graph Contrastive Information Bottleneck for Multi-Behavior RecommendationPoster
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL OptimizationPoster
GEM-FI: Gated Evidential Mixtures with Fisher ModulationPoster
GEM: Geometric Entropy Mixing for Optimal LLM Data CurationPoster
GEM: Geometric Erasure by Contrastive Velocity Matching in Rectified FlowsSpotlight
GEMQ: Global Expert-Level Mixed-Precision Quantization for MoE LLMsPoster
GENEB: Why Genomic Models Are Hard to ComparePoster
GEPC: Group-Equivariant Posterior Consistency for Out-of-Distribution Detection in Diffusion ModelsPoster
GFFMERGE: Efficient Merging of Graph Neural Force Fields and BeyondPoster
GFMate: Empowering Graph Foundation Models with Pre-training-agnostic Test-time Prompt TuningPoster
GFedCL: Graph-Based Federated Continual Learning with Spatial and Temporal AwarenessPoster
GHOST: Geometry-Guided Hallucination of Opaque Surface TexturesPoster
GHOST: Unmasking Phantom States in Mamba2 via Grouped Hidden-state Output-aware Selection & TruncationPoster
GI-GCN: Global Interacted Graph Convolutional Networks via Dominant Sets for Graph ClassificationPoster
GICDM: Mitigating Hubness for Reliable Distance-Based Generative Model EvaluationPoster
GIFT: Bootstrapping Image-to-CAD Program Synthesis via Geometric FeedbackPoster
GIPO: Gaussian Importance Sampling Policy OptimizationPoster
GIST: Targeted Data Selection for Instruction Tuning via Coupled Optimization GeometryPoster
GKD-Recruiter: Jointly Modeling Social and Task Heterogeneity for Spatial Crowdsourcing via Graph Knowledge DistillationPoster
GLAD: Bidirectional Structure-Attribute Alignment via Latent Graph Diffusion ModelsPoster
GLARE: Scalable Neuro-Symbolic Reward Shaping for LLM Agents via Group-Level AutomataPoster
GO-PRE：Goal-Oriented Next-Best-View Selection via Predictive Rendering Entropy for Active 3D ReconstructionPoster
GOCM: Single-Step Graph Outlier Synthesis via Origin Consistency ModelPoster
GOTabPFN: From Feature Ordering to Compact Tokenization for Tabular Foundation Models on High-Dimensional DataPoster
GP2F: Cross-Domain Graph Prompting with Adaptive Fusion of Pre-trained Graph Neural NetworksPoster
GPan-LoRA: Gaussian Process Amortized Networks for Bayesian Low-Rank Adaptation in Large Language ModelsPoster
GR-LoRA: Gradient-Recycling Low-Rank Adaptation for Class-Incremental LearningSpotlight
GRAPE: Let GRPO Supervise Query Rewriting by Ranking for RetrievalPoster
GRASP: Awakening Latent Spatial Reasoning in LVLMs via Training-free Geometric RectificationPoster
GRASP: Graph Reasoning via Agentic Solving and Probing of LLMsPoster
GRPO is Secretly a Process Reward ModelPoster
GRPO-based Cluster Decision Agent for Unknown-$\boldsymbol{K}$ Multi-view ClusteringPoster
GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion PriorsPoster
GSRQ: Gain-Shape Residual Quantization for Sub-1-bit KV CachePoster
GTPO and GRPO-S: Token and Sequence-Level Reward Shaping with Policy EntropyPoster
GUDA: Counterfactual Group-wise Training Data Attribution for Diffusion Models via UnlearningPoster
GUI-Spotlight: Adaptive Iterative Focus Refinement for Enhanced GUI Visual GroundingPoster
GXPO: Group Cross-Lingual Relative Policy Optimization for Code GenerationPoster
Game-Theoretic Co-Evolution for LLM-Based Heuristic DiscoveryPoster
GameDevBench: Evaluating Agentic Capabilities Through Game DevelopmentPoster
GameVerse: Can Vision-Language Models Learn from Video-based Reflection?Poster
Gaming Consensus: Coordinated Manipulation in Crowdsourced Fact-CheckingPoster
Gated Relational Alignment via Confidence-based Distillation for Efficient VLMsPoster
Gateways to Tractability for Satisfiability in Pearl’s Causal HierarchyPoster
Gauge-Equivariant Graph Networks via Self-Interference CancellationPoster
GaussTrace: Provenance Analysis of 3D Gaussian Splatting Models with Evidence-based LLM ReasoningPoster
Gaussian Mean Field Variational Inference can Overestimate Predictive VariancePoster
GePBench: Evaluating Fundamental Geometric Perception for Multimodal Large Language ModelsPoster
Gecko: A Simulation Environment with Stateful Feedback for Refining Agent Tool CallsPoster
GemDepth: Geometry-Embedded Features for 3D-Consistent Video DepthPoster
GenAlign: Towards Unified Alignment Framework of MLLMs via Generative Reward ModelPoster
GenCircuit-RL: Reinforcement Learning from Hierarchical Verification for Genetic Circuit DesignPoster
GenDA: Generative Data Assimilation on Complex Urban Areas via Classifier-Free Diffusion GuidancePoster
GenExam: A Multidisciplinary Text-to-Image ExamPoster
GenShield: Unified Detection and Artifact Correction for AI-Generated ImagesPoster
GenUnfold: Rapidly Predict Protein Mechanical Unfolding Trajectory via a Physics-Guided Diffusion ModelPoster
General Analysis of LMO-based Optimizers: Beyond Bounded VariancePoster
General Covariant Action Modeling: Constructing Generalized Manifolds via Spatio-Temporal DecouplingPoster
General Quantification of Covariate and Concept ShiftsPoster
General Synthetic-Powered InferencePoster
General and Efficient Steering of Unconditional Diffusion ModelsPoster
Generalist Graph Anomaly Detection via Prototype-Based DistillationPoster
Generalizable and Actionable Parts Pose Estimation with Symmetry Annotation-Free Learning StrategyPoster
Generalizable and Composable Multi-Model Embedding TranslationSpotlight
Generalization Bounds for Discrete Diffusion: Statistical Advantage of MaskingPoster
Generalization Bounds for Out-of-distribution GeneralizationPoster
Generalization and Scaling Laws for Mixture-of-ExpertsTransformersPoster
Generalization of Gibbs and Langevin Monte Carlo Algorithms in the Interpolation RegimePoster
Generalized Boundary FDR Control under Arbitrary Dependence: An Approach on Closure PrinciplePoster
Generalized Correctness Models: Learning Calibrated and Cross-Model Correctness Predictors from Historical PatternsPoster
Generalized Discrete Diffusion with Self-CorrectionPoster
Generalized Linear Bandits with MemoryPoster
Generalized Schrödinger Bridge on GraphsPoster
Generalizing Multi-Scale Time-Series Modeling with a Single OperatorPoster
Generalizing Stochastic Smoothing for Differentiation and Gradient EstimationPoster
Generation Enhances Understanding in Unified Multimodal Models via Multi-Representation GenerationPoster
Generation is Required for Data-Efficient PerceptionPoster
Generative Adaptation of Dynamics to Environmental Shifts via Weight-space DiffusionPoster
Generative Augmented InferencePoster
Generative Inverse Design with Abstention via Diagonal Flow MatchingPoster
Generative Large Neighborhood Search: Scalable Set Cover Optimization via Discrete DiffusionPoster
Generative Modeling of Discrete Latent Structures via Dynamic Policy GradientsPoster
Generative Modeling of Irregular Time Series via SDE-Induced Continuous-Discrete Variational InferenceSpotlight
Generative Modeling with Probabilistic ConstraintsPoster
Generative Neural Operators through Diffusion Last LayerPoster
Generative Online Reinforcement LearningPoster
Generative Representation Learning on Hyper-relational Knowledge Graphs via Masked Discrete DiffusionPoster
Generative Visual Code Mobile World ModelsPoster
Genome-Factory: A Library for Tuning, Deploying, and Interpreting Genomic Foundation ModelsPoster
GeoAlign: Geometric Rollout Curation for Robust LLM Reinforcement LearningPoster
GeoDM: Geometry-aware Distribution Matching for Dataset DistillationPoster
GeoEvo: Identity-Aware Potential Game with Geometric Evolution for Personalized Multimodal Federated LearningPoster
GeoFlow: Geo-Aware Modeling of Inter-Area Relationships in OD Flow Prediction and GenerationPoster
GeoLoom: High-quality Geometric Diagram Generation from Textual InputPoster
GeoMoLa: Geometry-Aware Motion Latents for Learning Robust Manipulation PoliciesPoster
GeoPT: Scaling Physics Simulation via Lifted Geometric Pre-TrainingPoster
GeoReward: Mitigating Contextual Variable Overestimation in Vision-Language Models for Cross-Market Preference PredictionPoster
GeoSense: Internalizing Geometric Necessity Perception for Multimodal ReasoningPoster
Geodesic Calculus on Implicitly Defined Latent ManifoldsPoster
Geodesic Flow Matching for Denoising High-Dimensional Structured RepresentationsPoster
Geometric Coherence Learning for Structuring Value Functions in Plain MDPsPoster
Geometric Collapse: When Vision Models Fail to Verify Physical CausalityPoster
Geometric Conformal Prediction with Spatial Ranks and Multivariate QuantilesPoster
Geometric Control of Out-of-Distribution Shift in Safe Offline RLPoster
Geometric Convergence of Gauss–Newton for Neural Networks: Riemannian Geometry and Adaptive DampingPoster
Geometric Decoupling: Diagnosing the Structural Instability of LatentPoster
Geometric Embedding Alignment via Curvature Matching in Transfer LearningPoster
Geometric Entropy and Retrieval Phase Transitions in Continuous Thermal Dense Associative MemoryPoster
Geometric Flow Grounding: A Unified Manifold Decoupling Framework for Dynamics Discovery and VerificationOral
Geometric Pocket-Centric Protein Encoding for Polypharmacology-Guided Multi-Target Drug DesignPoster
Geometric Rate–Distortion Invariance for Domain GeneralizationPoster
Geometric Reciprocity: Unlocking Self-Supervision for Stereoscopic Video GenerationPoster
Geometric and Stochastic Analysis of Discontinuities in Sparse Mixture-of-ExpertsSpotlight
Geometrically Constrained Outlier SynthesisPoster
Geometrically Constrained Stenosis Editing in Coronary Angiography via Entropic Optimal TransportPoster
Geometry of Reason: Spectral Signatures of Valid Mathematical ReasoningPoster
Geometry-Aware Contrastive Learning for Few-Shot Automatic Modulation RecognitionPoster
Geometry-Aware Dataset Condensation for Diffusion Model TrainingPoster
Geometry-Aware Decoding with Wasserstein-Regularized Truncation and Mass Penalties for Large Language ModelsSpotlight
Geometry-Aware Image Flow MatchingPoster
Geometry-Aware Neural Optimizer for Shape Optimization and InversionPoster
Geometry-Aware Probabilistic Circuits via Voronoi TessellationsPoster
Geometry-Aware Tabular DiffusionPoster
Geometry-Correct Diffusion Posterior Sampling with Denoiser-Pullback Curvature Guidance and Manifold-Aligned DampingPoster
Geometry-Guided Generative Representation for Functional Brain GraphsPoster
Geometry-Guided Modeling of Foundation Features Enables Generalizable Object Shape Deformation LearningPoster
Geometry-Misalignment in Distributional LearningPoster
Geometry-Preserving Orthonormal Initialization for Low-Rank Adaptation in Reinforcement LearningPoster
Geometry-Preserving Unsupervised Alignment for Heterogeneous Foundation ModelsPoster
Geometry-based Schrödinger Bridges for Trustworthy Multimodal FusionPoster
Giving Sensors a Voice: Multimodal JEPA for Semantic Time-Series EmbeddingsPoster
Glimpse: Geometry Learning of Multi-scale Structural Priors for 3D Pose EstimationPoster
Global Convergence of Adaptive Sensing for Principal Eigenvector EstimationPoster
Global Credit Assignment via Dynamical CriticalityPoster
Global Directional Priors with Local Statistical Validation for Scalable Causal DiscoveryPoster
Global Geometry Is Not Enough for Vision RepresentationsPoster
Global Merger-Arbitrage Forecasting with Language ModelsPoster
Global Plane Waves From Local Gaussians: Periodic Charge Densities in a BlinkPoster
Global Policy-Space Response Oracles for Two-Player Zero-Sum GamesPoster
Goal-Conditioned Agents that Learn Everything All at OncePoster
Goal-Oriented Lower-Tail Calibration of Gaussian Processes for Bayesian OptimizationPoster
Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet TextPoster
Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement LearningPoster
GoodDiffusion: Proactive Copyright Protection for Diffusion Generative Models via Learnable Sample-specific SignaturesOral
GradMem: Learning to Write Context into Memory with Test-Time Gradient DescentPoster
GradPower: Powering Gradients for Faster Language Model Pre-TrainingPoster
Gradient Descent as a Perceptron Algorithm: Understanding Dynamics and Implicit AccelerationPoster
Gradient Descent with Large Step Size Restores Symmetry in Deep Linear Networks with Multi-PathwayPoster
Gradient Flow Dynamics and Implicit Bias of Diagonal Linear Networks under Infinitesimal InitializationPoster
Gradient Flow Sampler-based Distributionally Robust OptimizationPoster
Gradient Flow Through Diagram Expansions: Learning Regimes and Explicit SolutionsSpotlight
Gradient Inversion Attacks Beyond SGDPoster
Gradient Regularization Prevents Reward Hacking in Reinforcement Learning from Human Feedback and Verifiable RewardsPoster
Gradient Smoothing: Coupling Layer-wise Updates for Improved OptimizationPoster
Gradient Transformer: Learning to Generate Updates for LLMsPoster
Gradient-Aware Scheduling: Coupling Curriculum and Staleness for Async Reinforcement LearningPoster
Gradient-Based Causal Tree Ensembles: A Backbone Architecture for Heterogeneous Treatment EffectsPoster
Gradient-Free Approaches is a Key to an Efficient Interaction with Markovian StochasticityPoster
GradientStabilizer: Fix the Norm, Not the GradientPoster
Gradients with Respect to Semantics Preserving Embeddings Tell the Uncertainty of Large Language ModelPoster
Gram2Token: Enabling Run-time GPU-Native Grammar-Constrained Decoding for LLMsPoster
Granularity-Aware Adaptive Classifier Expansion via Zero-Shot LearningPoster
Graph Alignment for Benchmarking Graph Neural Networks and Learning Positional EncodingsPoster
Graph Alignment via Dual-Pass Spectral Encoding and Latent Space CommunicationPoster
Graph Neural Dynamics via Learned Energy and Tangential FlowsPoster
Graph Neural Networks Are Not Continuous Across Graph ResolutionsPoster
Graph Rewiring based on Flow Alignment for Improving Fluid SimulationPoster
Graph is a Natural Regularization: Revisiting Vector Quantization for Graph Representation LearningPoster
Graph is a Substrate Across Data ModalitiesPoster
Graph of States: Solving Abductive Tasks with Large Language ModelsPoster
Graph-GRPO: Training Graph Flow Models with Reinforcement LearningPoster
Graph-Link: Bridging the Semantic-Structural Gap in Text-to-SQL via Constrained Subgraph InductionPoster
Graph-Preference Learning: Debiasing Network-Sampled Human Feedback for Target Welfare EstimationPoster
Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement LearningPoster
GraphFLEx: Unsupervised Structure Learning $\underline{\text{F}}$ramework for $\underline{\text{L}}$arge $\underline{\text{Ex}}$panding $\underline{\text{Graph}}$sPoster
GraphFlow: A Graph-Based Workflow Management for Efficient LLM-Agent ServingPoster
GraphP-FL: Personalized Federated Graph Learning via Dynamic Structure Awareness and Fisher Information Elastic AlignmentPoster
GraphPFN: A Prior-Data Fitted Network for Graph Node-Level TasksPoster
Great Minds Think Alike: Contextual Tacit Communication for Decentralized LLM-Agent CooperationPoster
Greedy Coordinate Diffusion: Effective and Semantically Coherent Adversarial Attacks via Diffusion GuidancePoster
Grokking Finite-Dimensional AlgebraPoster
Gromov-Wasserstein at Scale, Beyond Squared NormsPoster
Grounded in Reality: Learning and Deploying Proactive LLM from Offline LogsPoster
Grounding Functional Similarity by Invariance-Aware Model StitchingPoster
Grounding LLMs in Scientific Discovery via Embodied ActionsPoster
Grounding Multi-Hop Reasoning in Structural Causal Models via Group Relative Policy OptimizationPoster
Group Cognition Learning: Making Everything Better Through Controlled Two-Stage Agents CollaborationPoster
Group Distributionally Robust Optimization-Driven RL for LLM ReasoningPoster
Group-wise Data Ordering: Enhancing Instruction Tuning of Large Language Models via Embedding ProximityPoster
Grouter: Decoupling Routing from Representation for Accelerated MoE TrainingPoster
Guaranteed Optimal Compositional Explanations for NeuronsOral
Guidance: Sentence-Level Citation Enforcement via Prefix-Tail Guidance during LLM DecodingPoster
Guided Star-Shaped Masked DiffusionPoster
GuidedBridge: Training-freely Improving Bridge Models with Prior GuidancePoster
Guideline-Grounded Evidence Accumulation for High-Stakes Agent VerificationPoster
H$^2$CL: Heterogeneity-Aware Hypergraph Contrastive Learning for Robust RepresentationPoster
HALO: A Unified Vision-Language-Action Model for Embodied Multimodal Chain-of-Thought ReasoningPoster
HARD-KV: Head-Adaptive Regularization for Decoding-time KV CompressionPoster
HDFlow: Hierarchical Diffusion-Flow Planning for Long-horizon TasksSpotlight
HDTree: Generative Modeling of Cellular Hierarchies for Robust Lineage InferencePoster
HE-SNR: Uncovering Latent Logic via Entropy for Guiding Mid-Training on SWE-benchPoster
HEARTS: Benchmarking LLM Reasoning on Health Time SeriesPoster
HECTOR: Hybrid Editable Compositional Object References for Video GenerationPoster
HEDP: A Hybrid Energy-Distance Prompt-based Framework for Domain Incremental LearningPoster
HELIX: Hybrid Encoding with Learnable Identity and Cross-dimensional Synthesis for Time Series ImputationSpotlight
HERMES: Towards Efficient and Verifiable Mathematical Reasoning in LLMsPoster
HEXST: Hexagonal Shifted-Window Transformer for Spatial Transcriptomics Gene Expression PredictionPoster
HGMem: Hypergraph-based Working Memory to Improve Multi-step RAG for Long-Context Complex Relational ModelingPoster
HIAL: Towards Semantics-Aware Hypergraph Active Learning via Dual-Perspective Information MaximizationPoster
HIVE-3D: Hierarchical Voxel Enhancement for High-Quality 3D Scene GenerationPoster
HInT: Hypergraph Infusion at the Structural Layers Improves Table UnderstandingPoster
HO-SFL: Hybrid-Order Split Federated Learning with Backprop-Free Clients and Dimension-Free AggregationPoster
HOBIT: Hardness Optimized Batch Sampling for InfoNCE TrainingSpotlight
HOI-PAGE: Zero-Shot Human-Object Interaction Generation with Part Affordance GuidancePoster
HONet: Data-Efficient Learning for Exact Cover Problems via Hypergraph OptimizationPoster
HPS: Hyperspherical Parameter Sharing for Efficient Multi-Agent Reinforcement LearningPoster
HSGG: Training-Free Hierarchical Scene Graph Generation with Geometry-Guided Relation ReasoningPoster
HSMAD: Heterophily-Driven Spectral and Manifold Learning for Graph Anomaly DetectionPoster
HTAC: Hierarchical Task-Aware Composition for Continual Offline Reinforcement LearningPoster
HVAE: Hyperbolic Variational Autoencoder For Flexible Knowledge Transfer Across Multiple DomainsPoster
HVR-Met: A Hypothesis-Verification-Replaning Agentic System for Extreme Weather DiagnosisPoster
Hair-Trigger Alignment: Black-Box Evaluation Cannot Guarantee Post-Update AlignmentPoster
Hallucination Detection from Structural Reasoning ModelPoster
Hallucination is a Consequence of Space-Optimality: A Rate-Distortion Theorem for Membership TestingSpotlight
HaloProbe: Bayesian Detection and Mitigation of Object Hallucinations in Vision-Language ModelsPoster
Hamiltonian Asymmetric Fusion: One-Way Safe Directed Refinement under Modality ImbalancePoster
Hard Labels In! Rethinking the Role of Hard Labels in Mitigating Local Semantic DriftPoster
Hard-Constrained Graph Generation with Discrete-Projection DiffusionPoster
Hardware-Aware Dynamic Sparse Training for Large Output SpacesPoster
Harmful Overfitting in Sobolev SpacesPoster
Harmonized Dual Policy Improvement for Model-based Reinforcement LearningPoster
Harnessing Non-Adversarial Robustness in Large Language ModelsSpotlight
Harnessing Reasoning Trajectories for Hallucination Detection via Answer-agreement Representation ShapingPoster
Harnessing Spectrum Video for Subject-Level Few-Shot and Cross-Montage EEG GeneralizationPoster
Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM AgentsPoster
Head-in-Head in Linear AttentionPoster
Hearing Without Noticing? Attention-Aware Stealthy Black-box Adversarial Audio AttacksPoster
Heavy-tailed Physics-Informed Neural NetworksPoster
Hedging on the frontier: Learning new tasks with few samplesSpotlight
HelioX: A GPU-Native Framework for Simulation and Training of Biophysically Detailed NetworksPoster
Helpful to a Fault: Measuring Illicit Assistance in Multi-Turn, Multilingual LLM AgentsPoster
HeraSys: Collaborative Serving of Multiple LLM Workflows via Fine-Grained End-to-End OptimizationPoster
Hermes: An Evidence-Driven Agentic Framework for Trustworthy and Explainable AI-Generated Video DetectionPoster
Hermite-NGP: Gradient-Augmented Hash Encoding for Learning PDEsPoster
Heterogeneity-Aware Knowledge Sharing for Graph Federated LearningPoster
Heterogeneous Customizable Personalized Federated Fine-Tuning Approach for Large Language ModelsPoster
HexGen-3: A Fully Disaggregated LLM Serving Framework with Fine-Grained Heterogeneous Resource AutoscalingPoster
HiCI: Hierarchical Construction–Integration for Long-Context AttentionPoster
HiDe: Rethinking The Zoom-IN method in High Resolution MLLMs via Hierarchical DecouplingPoster
HiMAP-Travel: Hierarchical Multi-Agent Planning for Long-Horizon Constrained TravelPoster
HiMe: Hierarchical Embodied Memory for Long-Horizon Vision-Language-Action ControlPoster
HiPER: Hierarchical Plan–Execute RL for Multi-Turn LLM AgentsPoster
HiPPO Zoo: Making Implicit State Space Memory ExplicitPoster
HiPhO: How Far Are (M)LLMs from Humans in the Latest High School Physics Olympiad Benchmark?Poster
HiST: A Hierarchical Sparse Transformer for Cross-Modal Spatial Transcriptomics ModelingPoster
Hidden in Plain Sight -- Class Competition Focuses Attribution MapsPoster
Hidden in Plain Tokens: Simply Robust, Gradient-Free Watermark for Synthetic AudioPoster
Hide and Seek in Embedding Space: Geometry-based Steganography and Detection in Large Language ModelsPoster
Hide&Seek: Learning to explain in an end-to-end differentiable networkPoster
HieRD: Hierarchical Relational Distillation for Vision-Language Embedding ModelsPoster
HieraMAS: Optimizing Intra-Node LLM Mixtures and Inter-Node Topology for Multi-Agent SystemsPoster
HieraScaffold: Learning Compact Hierarchical Representations for Scalable 4D LiDAR GenerationPoster
Hierarchical Abstract Tree for Cross-Document Retrieval Augmented GenerationPoster
Hierarchical Anchor Graph Learning for Multi-View ClusteringPoster
Hierarchical Causal Abduction: A Foundation Framework for Explainable Model Predictive ControlPoster
Hierarchical Decision Making with Structured Policies: A Principled Design via Inverse OptimizationPoster
Hierarchical Filtering and Refinement Classification for Few-Shot Class-Incremental LearningPoster
Hierarchical Goal Abstractions via Learned Subset RelationsPoster
Hierarchical Image Tokenization for Multi-Scale Image Super ResolutionPoster
Hierarchical Multi Scale Graph Neural Networks: Scalable Heterophilous Learning with Oversmoothing and Oversquashing MitigationPoster
Hierarchical ODE: Learning Continuous-Time Physical Prototypes for Early Link Failure DetectionPoster
Hierarchical Policy Learning via Spectral DecompositionPoster
Hierarchical Procedural Meta-Reasoning for Generalizable Multimodal AgentsPoster
Hierarchical Reinforcement Learning for Sparse-Reward Search in Commutative AlgebraPoster
Hierarchical Representations for Cross-task Automated Heuristic Design using LLMsPoster
Hierarchical Retrieval at Scale: Bridging Transparency and EfficiencyPoster
Hierarchical Successor Representation for Robust TransferSpotlight
High-Dimensional Learning Dynamics of Quantized Models with Straight-Through EstimatorPoster
High-Dimensional Sensitivity Analysis for Genomic Studies: An Adversarial Framework for Learning Worst-Case Latent ConfoundersPoster
High-Fidelity ANN-to-SNN Conversion via Closed-Loop CKA DistillationPoster
High-Probability Convergence Guarantees of Decentralized SGDPoster
High-accuracy and dimension-free sampling with diffusionsOral
High-accuracy sampling for diffusion models and log-concave distributionsOral
Higher-Order Certified Robustness for RegressionPoster
HilbertA: Hilbert-Curve–Aligned Sparse Attention for 2D Structured DataPoster
Hista and Numca: Estimate State Value Effectively for Large Language Model Reinforcement LearningSpotlight
History-Bootstrapped Flow Matching for Inverse Boiling ReconstructionPoster
HodgeFlow Policy Search by Topologically Dissecting Temporal-Difference Signals in Non-Markovian EnvironmentsPoster
Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial IntelligenceOral
HoloFair: Unified T2I Fairness Evaluation and Fair-GRPO DebiasingPoster
Holonomy Grid Codes for Generalisation Under Directed ActionsPoster
Hom-PGD+: Fast Reparameterized Optimization over Non-convex Ball-Homeomorphic SetPoster
Homophily-Heterogeneity Gradient Surgery for Federated Graph LearningPoster
How (Not) to Hybridize Neural and Mechanistic Models for Epidemiological ForecastingPoster
How Can I Publish My LLM Benchmark Without Giving the True Answers Away?Poster
How Can Mamba Learn In Context with Outliers and Generalize Provably?Poster
How Chain of Thought Decomposes Complex TasksPoster
How Do Language Models Speak Languages? A Case Study on Unintended Code-SwitchingPoster
How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMsPoster
How Does the Lagrangian Guide Safe Reinforcement Learning through Diffusion Models?Poster
How Does the Pretraining Distribution Shape In-Context Learning? A Fundamental Trade-OffPoster
How Far Can LLM Agents Reason with Tables? Benchmarking Multi-Turn Agentic Table Question Answering in the WildPoster
How Few-Shot Examples Add Up: A Causal Decomposition of Function Vectors in In-Context LearningPoster
How Good is Post-Hoc Watermarking With Language Model Rephrasing?Poster
How Hard Can It Be? Hardness-Aware Multi-Objective UnlearningPoster
How Language Models Process NegationPoster
How Out-of-Distribution Detection Learning Theory Enhances Transformer: Learnability and ReliabilityPoster
How Powerful are LLMs in Generating Program Specifications?Poster
How RL Unlocks the Aha Moment in Geometric Interleaved ReasoningSpotlight
How RLHF Amplifies SycophancyPoster
How Reasoning Evolves from Post-Training Data: An Empirical Study Using ChessPoster
How Should Transformers Represent Numeric Values in Electronic Health Records?Poster
How Transformers Represent Hierarchies: A Local-to-Global MechanismPoster
How can embedding models bind concepts?Spotlight
How can we assess human-agent interactions? Case studies in software agent designPoster
How do Human Processes AI-generated Hallucination Contents: a Neuroimaging StudyPoster
How do LLMs Compute Verbal Confidence?Poster
How does Bayesian Sampling help Membership Inference Attacks?Poster
How does information access affect LLM monitors' ability to detect sabotage?Poster
How high is ‘high’? Rethinking the roles of dimensionality in topological data analysis and manifold learningPoster
How much can language models memorize?Oral
How to Avoid Debate: Scalable AI Safety via Doubly-Efficient Interactive ProofsPoster
How to Correctly Report LLM-as-a-Judge EvaluationsPoster
How to Fine-Tune a Reasoning Model? A Teacher–Student Cooperation Framework to Synthesize Student-Consistent SFT DataPoster
How to Price Data: A Market Equilibrium Based ApproachPoster
How to Train Your Advisor: Steering Black-Box LLMs with Advisor ModelsPoster
How to guide your flow: Steering flow maps for rapid test-time alignmentPoster
How2Everything: Mining the Web for How-to Procedures to Evaluate and Improve LLMsPoster
HugRAG: Hierarchical Causal Knowledge Graph Design for RAGPoster
Hugging Carbon: Quantifying the Training Carbon Emissions of AI Models at ScalePoster
Human-AI Collaborative Uncertainty QuantificationPoster
Human-in-the-Loop Policy Optimization for Preference-Based Multi-Objective Reinforcement LearningPoster
HumanLM: Simulating Users with State Alignment Beats Response ImitationPoster
Hunt Instead of Wait: Evaluating Deep Data Research on Large Language ModelsPoster
HyMTRL: A Hybrid Multi-Task Reinforcement Learning Framework via Phased Policy EvolutionPoster
HyPER: Bridging Exploration and Exploitation for Scalable LLM Reasoning with Hypothesis Path Expansion and ReductionPoster
HyPOLE: Hyperproperty-Guided Multi-Agent Reinforcement Learning under Partial ObservationPoster
Hybrid Policy Distillation for LLMsPoster
Hybrid Reinforcement Learning in Adversarial Markov Decision ProcessesPoster
Hybrid-Gym: Training Coding Agents to Generalize Across TasksPoster
HybridFlow: Resource-Adaptive Subtask Routing for Efficient Edge-Cloud LLM InferencePoster
HybridOM: Hybrid Physics-Based and Data-Driven Global Ocean Modeling with Efficient Regional DownscalingPoster
Hydra-Nav: Object Navigation via Adaptive Dual-Process ReasoningPoster
HypCL: Adapting CLIP in Hyperbolic Space for Continual LearningPoster
HypRAG: Hyperbolic Dense Retrieval for Retrieval Augmented GenerationPoster
Hyper-ICL: Attention Calibration with Hyperbolic Anchor Distillation for Multimodal In-Context LearningPoster
Hyper-LLaVA: Hyperbolic Uncertainty-aware Modality-Balanced Routing for Multimodal Continual Instruction TuningPoster
HyperMLP: An Integrated Perspective for Sequence ModelingPoster
HyperPotter: Spell the Charm of High-Order Interactions in Audio Deepfake DetectionPoster
Hyperbolic Associative Memory NetworksPoster
Hyperbolic Hierarchical Alignment for Video-Based Visible-Infrared Person Re-IdentificationPoster
Hyperbolic Multimodal Continual LearningPoster
Hyperbolic Neural OperatorPoster
Hyperbolic RQ-VAE enhanced Generative Recommendation with Differential-Length Codebook StrategyPoster
Hyperbolic neural population geometry benefits computationPoster
Hyperparameter Transfer Laws for Non-Recurrent Multi-Path Neural NetworksPoster
Hyperparameter Transfer with Mixture-of-Expert LayersPoster
Hyperspectral Image Fusion with Spectral-Band and Fusion-Scale AgnosticismPoster
HypoSpace: A Diagnostic Benchmark for Set-Valued Hypothesis Generation under Underdetermination and Sublinear Coverage BoundsSpotlight
Hölder++: Improving Quality-Coherence Trade-off in Multimodal VAEsPoster
IACW: Intent-Aware Controllable Watermarking for Scalable Authorial Intent AttributionPoster
IAPO: Information-Aware Policy Optimization for Token-Efficient ReasoningPoster
IBMA: Information Bottleneck-Based Multimodal AlignmentPoster
ICR-RL: Deep Reinforcement Learning via In-Context-RegressionPoster
IDLM: Inverse-distilled Diffusion Language ModelsPoster
IDRBench: Understanding the Capability of Large Language Models on Interdisciplinary ResearchPoster
IEC: When Information-Driven Exploration Meets Spectral Consensus via Primal–Dual Reward Regularization in Decentralized Multi-Agent RLPoster
IMPACT: Influence Modeling for Open-Set Time Series Anomaly DetectionPoster
INDEXGUARD: Index-only Backdoor Vetting for Secure Federated PEFT of Large Language ModelsPoster
INDUCTION: Finite-Structure Concept Synthesis in First-Order LogicSpotlight
INFER: Learning Implicit Neural Frequency Response Fields for Confined Acoustic EnvironmentsPoster
INT vs. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization FormatsPoster
IO-Adam: Rethinking Memory-Efficient Adaptive Optimizers from Gradient ComputationPoster
IPMark: A Sentence-Level Watermark for LLMs with Hierarchical Personalization and Efficient DetectionPoster
IQA-Spider: Unifying Reasoning, Grounding, and Referring for Multi-Granularity Image Quality AssessmentPoster
IRIS: Implicit Reward-Guided Internal Sifting for Mitigating Multimodal HallucinationPoster
IRPM: Intergroup Relative Preference Modeling for Pointwise Generative Reward ModelsPoster
ITSPACE: Monotone Gaussian Optimal Transport UpdatesPoster
IVQ: Structured and Lightweight Vector Quantization via Binary Hierarchical Composition Inspired by $\textit{IChing}$Poster
IVQA-LD: Inclusive Multimodal Understanding for Population with Limb-DeficiencyPoster
IdEst: Assessing Self-Supervised Learning Representations via Intrinsic DimensionPoster
Ideal Attribution and Faithful Watermarks for Language ModelsPoster
Identifiability of Causal Graphs under Non-Additive Conditionally Parametric Causal ModelsPoster
Identifiable Equivariant Networks are Layerwise EquivariantPoster
Identifiable Markov Switching Models with Instantaneous Effects and Exponential FamiliesPoster
Identifiable Nonlinear Differentiable Causal Discovery via Independence and Adaptive Group SparsityPoster
Identifiable Smooth Conjugacy Learning via Adversarial OrthogonalityPoster
Identifiable Token Correspondence for World ModelsPoster
Identifying Common Hubs in Multiple Gaussian Graphical ModelsPoster
Identifying Connectivity Distributions from Neural Dynamics Using FlowsPoster
Identifying Latent Concepts and Structures for Generalized Category DiscoveryPoster
Identifying Learnwares via Reduced Neural Conditional Mean EmbeddingPoster
Identifying Partially Observed Causal Models from Heterogeneous/Nonstationary DataPoster
Identifying and Correcting Label Noise for Robust GNNs via Influence ContradictionPoster
Identifying and Mitigating Errors in Gradient Aggregation of Distributed Data Parallel TrainingPoster
Identifying dependent components from multi-domain linear mixturesPoster
Image Restoration via Diffusion Models with Dynamic ResolutionPoster
Image-to-Brain Signal Generation for Visual Prosthesis with CLIP Guided Multimodal Diffusion ModelsPoster
Imagination Helps Visual Reasoning, But Not Yet in Latent SpacePoster
ImgCoT: Compressing Long Chain of Thought into Compact Visual Tokens for Efficient Reasoning of Large Language ModelPoster
Imitation Learning for Multi-turn LM Agents via On-policy Expert CorrectionsPoster
ImmersePro: End-to-End Stereo Video Synthesis Via Implicit Disparity LearningPoster
Immuno-VLM: Immunizing Large Vision-Language Models via Generative Semantic Antibodies for Open-World TrustworthinessPoster
ImpQuant: Fine-Grained Importance-Aware Quantization for Large Vision-Language ModelsPoster
ImpText: A Benchmark and Tool-Augmented Framework for Implicit Text ReasoningPoster
Impact of Connectivity on Laplacian Representations in Reinforcement LearningPoster
Implicit Action Chunking for Smooth Continuous ControlPoster
Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVRPoster
Implicit Intelligence - Evaluating Agents on What Users Don’t SayPoster
Implicit Preference Alignment for Human Image AnimationPoster
Implicit Safety Alignment from Crowd PreferencesPoster
Implicit Turn-Wise Policy Optimization for Proactive User-LLM InteractionPoster
Imposing Boundary Conditions on Neural Operators via Learned Function ExtensionsPoster
Improved Algorithms for Nash Welfare in Linear BanditsPoster
Improved Analysis of the Accelerated Noisy Power Method with Applications to Decentralized PCAPoster
Improved Bounds for Private and Robust AlignmentPoster
Improved Bounds for Reward-Agnostic and Reward-Free ExplorationPoster
Improved Convergence Analysis of Topology Dependence in Decentralized SGDPoster
Improved Convergence of Score-Based Diffusion Models via Prediction-CorrectionPoster
Improved Dimension Dependence for Bandit Convex Optimization with Gradient VariationsSpotlight
Improved Distribution Estimation in $\ell_\infty$Poster
Improved Dynamic Algorithm for Non-monotone Submodular Maximization under Cardinality ConstraintPoster
Improved Scaling Laws via Weak-to-Strong Generalization in Random Features Ridge RegressionPoster
Improved Stochastic Optimization of LogSumExpPoster
Improving Adversarial Robustness of Attribution via Implicit RegularizationPoster
Improving Backward Conformal Prediction via Non-Conformity Score TransformationPoster
Improving CLIP Adaptation by Breaking Tail Alignment for Source-Free Cross-Domain Few-Shot LearningPoster
Improving Classifier-Free Guidance of Flow Matching via Manifold ProjectionPoster
Improving Diffusion Planners by Self-Supervised Action Gating with EnergiesPoster
Improving Explicit Dynamic Gaussian Splatting Optimization via Update MixturePoster
Improving Few-Shot Design Optimization By Exploiting Auxiliary InformationPoster
Improving Graph Transformers via Global Structural PriorsPoster
Improving LLM-Based Recommenders with Conservative Generative Flow NetworksPoster
Improving ML attacks on LWE with data repetition and stepwise regressionPoster
Improving Neural Topic Modeling with Semantically-Grounded Soft Label DistributionsPoster
Improving Sampling for Masked Diffusion Models via Information GainPoster
Improving Visual Token Reduction via Rectifying Distortions for Efficient Multimodal LLM InferencePoster
Improving Zero-Shot Offline RL via Behavioral Task SamplingPoster
Improving the Performance and Learning Stability of Parallelizable RNNs Designed for Ultra-Low Power ApplicationsSpotlight
Improving the Robustness-Utility Trade-off in Decentralized Learning over Sparse NetworksPoster
Improving the Sensitivity of Backdoor Detectors via Class Subspace OrthogonalizationPoster
In-Context Generation with Regional Constraints for Instructional Video EditingPoster
In-Context Learning Is Provably Bayesian Inference: A Generalization Theory for Meta-LearningPoster
In-Context Learning as Rate–Distortion OptimizationPoster
In-Training Defenses Against Emergent Misalignment in Language ModelsPoster
Incentivized Exploration with Stochastic Covariates: A Two-Stage Mechanism Design for Recommender SystemPoster
Incentivizing Truthfulness and Collaborative Fairness in Bayesian LearningOral
Incomplete Multi-View Clustering via Neighborhood-Conditioned DiffusionPoster
Inconsistency-Aware Minimization: Improving Generalization with Unlabeled DataPoster
Incorporating Importance Weighting in Optimal Transport Based Domain AlignmentPoster
Incremental BPE TokenizationSpotlight
Incremental Learning of Sparse Attention Patterns in TransformersPoster
Incremental Transformer Neural ProcessesPoster
Independent Component Discovery in Temporal Count DataPoster
IndexMem: Learned KV-Cache Eviction with Latent Memory for Long-Context LLM InferencePoster
Inducing LLM Workflows with Bilevel Optimization and Textual GradientsPoster
Inducing Overthink: Hierarchical Genetic Algorithm-based DoS Attack on Black-Box Reasoning ModelsPoster
Induction Heads Interpolate N-GramsPoster
Induction Meets Biology: Mechanisms of Repeat Detection in Protein Language ModelsPoster
InertialAR: Autoregressive 3D Molecule Generation with Inertial FramesPoster
InfVSR: Toward Consistency-Driven Streaming Generative Video Super-ResolutionPoster
Inference Time Concept Removal Guidance for Text-to-Image Diffusion ModelsSpotlight
Inference Time Optimization with Confidence DynamicsPoster
Inference of Online Newton Methods with Nesterov's Accelerated SketchingPoster
Inference-Aware Meta-Alignment of LLMs via Non-Linear GRPOPoster
Inference-Time Conformal Reasoning with Valid Factuality Control for Large Language ModelsPoster
Inference-Time Forward-Process Alignment in Diffusion ModelsPoster
Inference-time Alignment with Rewards in Besov Spaces: Provable Advantages of Feature Learning and Multi-Step Policy UpdatesPoster
Inference-time optimization for experiment-grounded protein ensemble generationPoster
InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental TrainingPoster
Infinite Mask Diffusion for Few-Step DistillationPoster
Infinite-Precision Autoregressive Modeling for Vector Graphics and LayoutsPoster
Infinite-World: Scaling Interactive World Models to 1000-Frame Horizons via Pose-Free Hierarchical MemoryPoster
Infinite-dimensional generative diffusions via Doob's h-transformPoster
Influence-Disentangled Federated Training: Learning Models That Are Easy to UnlearnPoster
Influence-Guided Symbolic Regression: Scientific Discovery via LLM-Driven Equation Search with Granular FeedbackPoster
InfoDLM: an Information-Adaptive Framework for Discrete Diffusion Language Model PretrainingPoster
InfoFlow KV: Information-Flow-Aware KV Recomputation for Long ContextPoster
InfoGeo: Information-Theoretic Object-Centric Learning for Cross-View Generalizable UAV Geo-LocalizationPoster
InfoGlobe: Local-and-Global Information-Preserving Statistical Manifold Learning for Single-Cell TranscriptomicsPoster
InfoLaw: Information Scaling Laws for Large Language Models with Quality-Weighted Mixture Data and RepetitionPoster
InfoPO: Information-Driven Policy Optimization for User-Centric AgentsPoster
Information Flow Reveals When to Trust Language ModelsOral
Information Geometry Loss for Time Series ForecastingPoster
Information dynamics and Memory in Neural Networks through Fisher Information DiffusionSpotlight
Information-Geometric Adaptive Sampling for Graph DiffusionPoster
Information-Theoretic Disentangled Latent Modeling with Conditional Diffusion for Incomplete Multi-View ClusteringSpotlight
Information-Theoretic Generalization Bounds for VAEs: A Role of Encoder and Latent VariablePoster
Informed Asymmetric Actor-Critic: Leveraging Privileged Signals Beyond Full-State AccessPoster
InfraRL: A Benchmark for Constrained Resource Allocation in Large-Scale Infrastructure Asset ManagementPoster
InftyThink+: Effective and Efficient Infinite-Horizon Reasoning via Reinforcement LearningPoster
Initialization is Half the Battle: Generating Diverse Images from a Guidance Potential PosteriorSpotlight
Injecting Distributional Awareness into MLLMs via Reinforcement Learning for Deep Imbalanced RegressionPoster
Inner-layer Token Self-Modulation as Another Scaling Axis for LLMsPoster
InnoEval: On Research Idea Evaluation as a Knowledge-Grounded, Multi-Perspective Reasoning ProblemPoster
Innovation: An Almost Characterization of HallucinationPoster
Insertion Based Sequence Generation with Learnable Order DynamicsPoster
InstEmb: Instruction-Following Embeddings through Glimpses of the FuturePoster
Instance-Dependent Continuous-Time Reinforcement Learning via Maximum Likelihood EstimationPoster
Instance-Level Costs for Nuanced Classifier EvaluationPoster
Instance-Specific Approximation Ratios for Correlation Clustering and Max-CutPoster
Instruction Decomposition and Action Alignment for Vision-Language NavigationPoster
Instruction Lens Score: Your Instruction Contributes a Powerful Object Hallucination Detector for Multimodal Large Language ModelsPoster
IntentRL: Training Proactive User-intent Agents for Open-ended Deep Research via Reinforcement LearningPoster
Intentional Updates for Streaming Reinforcement LearningPoster
InteractBench: Benchmarking LLMs on Competitive Programming under Unrevealed InformationPoster
InteractComp: Evaluating Search Agents With Ambiguous QueriesPoster
InteractScience: Programmatic and Visually-Grounded Evaluation of Interactive Scientific Demonstration Code GenerationPoster
Interaction-Breaking Adversarial Learning Framework for Robust Multi-Agent Reinforcement LearningPoster
Interactive Person Retrieval via Multi-Turn Multimodal ConversationPoster
Interactive Segmentation with Elaborate Focus PriorPoster
Interleaved Selective State Space Models for Efficient WiFi-Based 3D Multi-Person Pose EstimationPoster
Internalizing Safety Understanding in Large Reasoning Models via VerificationPoster
Interpretability Transfer from Language to Vision via Sparse AutoencodersPoster
Interpretability and Generalization Bounds for Learning Spatial PhysicsPoster
Interpretable Discovery of One-parameter Subgroups: A Modular Framework for Elliptical, Hyperbolic, and Parabolic SymmetriesPoster
Interpretable Embeddings with Sparse Autoencoders: A Data Analysis ToolkitPoster
Interpretable Functional Koopman Learning with Non-Markovian Closure for Spatiotemporal SystemsSpotlight
Interpretable Neural ODEs for Gene Regulatory Network Discovery under PerturbationsPoster
Interpretable Self-Supervised Learning via Representer Landmarks and Nyström ApproximationPoster
Interpreting Genomic Language Models using Sparse AutoencodersPoster
Interpreting Physics in Video World ModelsPoster
Interpreting and Enhancing Emotional Circuits in Large Vision-Language Models via Cross-Modal Information FlowPoster
Interpreting and Steering State-Space Models via Activation Subspace BottlenecksPoster
Intervene When It Doubts: Conjunction-Guided Interactive ReasoningPoster
Interventional Processes For Causal Uncertainty QuantificationPoster
Intra-Modal Neighbors Never Lie: Rectifying Inter-Modal Noisy Correspondence via Graph-Based Intra-Modal ReasoningPoster
Intrinsic Credit Assignment for Long Horizon InteractionPoster
Intrinsic Gradient Suppression for Label-Noise Prompt Tuning in Vision–Language ModelsPoster
Intrinsic Task Symmetry Drives Generalization in Algorithmic TasksPoster
Introspection Adapters: Training LLMs to Report Their Learned BehaviorsPoster
InvGNN: Learning Invertible Node Representations on GraphsPoster
Invariant Representation Learning for Source-Free Time Series Forecasting with LLM-Centric Proxy DenoisingPoster
Inverse Depth Scaling From Most Layers Being SimilarPoster
Inverse Entropic Optimal Transport Solves Semi-supervised Learning via Data Likelihood MaximizationPoster
Inverting Data Transformations via Diffusion SamplingPoster
Investigating Advanced Reasoning of Large Language Models via Black-Box InteractionPoster
Investigating Component Contributions in Multi-Agent ML SystemsPoster
Investigating Continual Pretraining in Large Language Models: Insights and ImplicationsPoster
Investigating Memory in RL with POPGym ArcadeSpotlight
Is Code Better Than Language for Algorithmic Reasoning?Poster
Is Data Shapley Not Better than Random in Data Selection? Ask NASHSpotlight
Is Fixing Schema Graphs Necessary? Full-Resolution Graph Structure Learning for Relational Deep LearningPoster
Is Graph Mixup Beneficial? Investigating Interpolation And Empirical Performance of Graph Mixup MethodsPoster
Is One Layer Enough? Understanding Inference Dynamics in Tabular Foundation ModelsPoster
Is Spurious Correlation Removal Always Learnable?Poster
Is Training Necessary for Anomaly Detection?Poster
Is Vibe Coding Safe? Benchmarking Vulnerability of Agent-Generated Code in Real-World TasksPoster
Is Your Diffusion Sampler Actually Correct? A Sampler-Centric Evaluation of Discrete Diffusion Language ModelsPoster
Is Your LLM Overcharging You? Tokenization, Transparency, and IncentivesOral
Is the Last Layer Sufficient for Uncertainty Quantification?Poster
IsoCompute Playbook: Optimally Scaling Sampling Compute for LLM RLPoster
It's TIME: Towards the Next Generation of Time Series Forecasting BenchmarksPoster
It's a TRAP! Task-Redirecting Agent Persuasion Benchmark for Web AgentsPoster
Item Response Scaling Laws: A Measurement Theory Approach for Efficient and Generalizable Neural Scaling EstimationPoster
Iterated Population Based Training with Task-Agnostic RestartsPoster
Iterative Refinement Neural Operators are Learned Fixed-Point Solvers: A Principled Approach to Spectral Bias MitigationSpotlight
Iterative Robust Satisficing: Minimizing Performance Degradation Under Distribution ShiftPoster
JADAI: Jointly Amortizing Adaptive Design and Bayesian InferencePoster
JADE: Bridging the Strategic-Operational Gap in Dynamic Agentic RAGPoster
JADE: Expert-Grounded Dynamic Evaluation for Open-Ended Professional TasksPoster
JAEGER: Joint 3D Audio-Visual Grounding and Reasoning in Simulated Physical EnvironmentsPoster
JANUS-LORA: A Balanced Low-Rank Adaptation for Continual LearningPoster
Jailbreak Foundry: From Papers to Runnable Attacks for Reproducible BenchmarkingOral
Jailbreak to Protect: Buffering Harmful Fine-Tuning via Temporary Jailbreaking LoRA in Large Language ModelsSpotlight
Jailbreaking Vision-Language Models Through the Visual ModalityPoster
JanusPipe: Efficient Pipeline Parallel Training for Machine Learning Interatomic PotentialsPoster
Joint Enhancement and Classification using Coupled Diffusion Models of Signals and LogitsPoster
Joint Geometric and Trajectory Consistency Learning for One-Step Real-World Super-ResolutionPoster
Joint Learning in the Gaussian Single Index ModelOral
Joint Model and Data Sparsification via the Marginal LikelihoodPoster
Joint Navigation and Manipulation Planning with 3D Interaction ChainsPoster
Joint-Embedding Predictive Learning of Latent Market States in U.S. EquitiesPoster
Joint-Space Empowerment as a Theory of Dexterous Motor CoordinationSpotlight
Judging What We Cannot Solve: A Consequence-Based Approach for Oracle-Free Evaluation of Research-Level MathSpotlight
Judgment Operators: A Composition-Invariant Substrate for Multi-Agent Action SpacesPoster
Just Ask: Curious Code Agents Reveal System Prompts in Frontier LLMsPoster
Just Noticeable Difference Modeling for Deep Visual FeaturesSpotlight
Just Y-Prediction: Enabling Historical Cumulative Inconsistency in Label Diffusion for Learning with Noisy LabelPoster
Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient UpdatesSpotlight
KAGE-Bench: Fast Known-Axis Visual Generalization Evaluation for Reinforcement LearningPoster
KANFIS: A Neuro-Symbolic Framework for Interpretable and Uncertainty-Aware LearningPoster
KAST-BAR: Knowledge-Anchored Semantically-Dynamic Topology Brain Autoregressive Modeling for Universal Neural InterpretationPoster
KBQA-R1: Reinforcing Large Language Models for Knowledge Base Question AnsweringPoster
KFStego: Key-Free Secure Image Distribution via Bipartite Structural InvariantsPoster
KITE: Knowledge-Guided Probabilistic Modeling for Time Series Forecasting with Exogenous VariablesPoster
KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented ControlsPoster
KUMA: A Novel Framework with Koopman Separation and Efficient Multilevel Extraction in Time Series ForecastingPoster
Kalman Linear Attention: Parallel Bayesian Filtering For Efficient Language Modeling and State TrackingPoster
Keep Everyone Happy: Online Fair Division of Numerous Items with Few CopiesPoster
Keep It in Mind: User Centric Continual Spatial Intelligence Reasoning in Egocentric Video StreamsPoster
Keeping a Secret Requires a Good Memory: Space Lower-Bounds for Private AlgorithmsSpotlight
Kernel-based Maximum-of-difference Test for Two-sample ComparisonPoster
KernelBand: Steering LLM-based Kernel Optimization via Hardware-Aware Multi-Armed BanditsPoster
KernelCraft: Benchmarking for Agentic Close-to-Metal Kernel Generation on Emerging HardwarePoster
KernelFoundry: Hardware-Aware Evolutionary GPU Kernel OptimizationPoster
KineFlow: Kinematic Second-Order Flow Matching for Time-Series ForecastingPoster
Kinematics-Driven Gaussian Shape Deformation for Blurry Monocular Dynamic ScenesPoster
Klein Hyperbolic Metric LearningPoster
KnapSpec: Self-Speculative Decoding via Adaptive Layer Selection as a Knapsack ProblemPoster
Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget AllocationPoster
Knothe-Rosenblatt Quantile Regression for Risk-sensitive Multi-objective Reinforcement LearningPoster
Know More, Know Clearer: A Meta-Cognitive Framework for Knowledge Augmentation in Large Language ModelsSpotlight
Know Thyself, Know Thy User: Intrinsic Dual-Perspective Reasoning for Role-Playing LLMsPoster
Knowing Bias, Doing Better: Mitigating Social Bias in LLMs via Know-Bias Neuron EnhancementPoster
Knowing When to Quit: A Principled Framework for Dynamic Abstention in LLM ReasoningPoster
Knowing Who, Not How Much: Learning-Augmented Mechanisms for Consumer Utility MaximizationPoster
Knowing the Unknown: Interpretable Open-World Object Detection via Concept Decomposition ModelPoster
Knowledge Diversion for Efficient Morphology Control and Policy TransferPoster
Krause Synchronization TransformersPoster
KromHC: Manifold-Constrained Hyper-Connections with Kronecker-Product Residual MatricesPoster
Kronecker Generative Networks: A General Neural Architecture for Parameter-Efficient Learning Across Classification TasksPoster
Kuramoto Oscillatory Phase Encoding: Neuro-inspired Synchronization for Improved Learning EfficiencyPoster
L-CUBE: Isolating Long-Context Capacity from Knowledge with Controllable Mutual Information ScalingPoster
L-Drive: Beyond a Single Mapping—Latent Context Drives Time Series ForecastingPoster
L-SR1: Learned Symmetric-Rank-One PreconditioningPoster
L2G-NET: Local to Global Spectral Graph Neural Networks via Cauchy FactorizationsSpotlight
LABO: LLM-Accelerated Bayesian Optimization through Broad Exploration and Selective ExperimentationPoster
LAGEA: Language Guided Embodied Agents for Robotic ManipulationPoster
LALM-as-a-Judge: Benchmarking Large Audio-Language Models for Safety Evaluation in Multi-Turn Spoken DialoguesPoster
LAMP: Data-Efficient Linear Affine Weight-Space Models for Parameter-Controlled 3D Shape Generation and ExtrapolationPoster
LAPRAS : Learning-Augmented PRivate Answering for linear query Streams.Poster
LARA: Latent Action Representation Alignment for Vision-Language-Action ModelsPoster
LARFT: Closing the Cognition-Action Gap for Length Instruction Following in Large Language ModelsPoster
LASER: Learning Active Sensing for Continuum Field ReconstructionOral
LAST: Bridging Vision-Language and Action Manifolds via Gromov-Wasserstein AlignmentPoster
LATMiX: Learnable Affine Transformations for Microscaling Quantization of LLMsPoster
LATO: 3D Mesh Flow Matching with Structured TOpology Preserving LAtentsPoster
LAVA: A Unified Framework for Finetuning Language and Vision ModelsPoster
LC-QAT: Data-Efficient 2-Bit QAT for LLMs via Linear-Constrained Vector QuantizationPoster
LDARNet: DNA Adaptive Representation Network with Learnable Tokenization for Genomic ModelingPoster
LEAP: Zone-Aware MCTS for LLM Self-Speculative DecodingPoster
LECTOR: Joint Learning of Scientific Reasoning Graphs and Introduction GenerationPoster
LEGO-FL: Learning Heterogeneous Federated Models as a LEGO Assembly GamesPoster
LEGO: An LLM-Enabled Hierarchical Optimizer for Tensor Computation Graphs with Structure-Aware Search and Compositional SynthesisPoster
LEMUR: Learned Multi-Vector RetrievalPoster
LERD: Latent Event-Relational Dynamics for Neurodegenerative ClassificationPoster
LFQ: Logit-aware Final-block Quantization for Boosting the Generation Quality of Low-Bit Quantized LLMsPoster
LIF Recurrent Memory Enables Long-Horizon Spiking ComputationPoster
LIFT: A Novel Framework for Enhancing Long-Context Understanding of LLMs via Long Input Fine-TuningPoster
LILO: Bayesian Optimization with Natural Language FeedbackPoster
LIMMT: Less is More for Motion TrackingPoster
LIMSSR: LLM-Driven Sequence-to-Score Reasoning under Training-Time Incomplete Multimodal ObservationsSpotlight
LIVE: Long-horizon Interactive Video World ModelingPoster
LK Losses: Direct Acceptance Rate Optimization for Speculative DecodingPoster
LLM Priors for ERM over ProgramsPoster
LLM Self-Recognition: Steering and Retrieving Activation SignaturesPoster
LLM Watermark Evasion via Bias InversionPoster
LLM-Guided Communication for Cooperative Multi-Agent Reinforcement LearningPoster
LLM-Guided Diagnostic Evidence Alignment for Medical Vision–Language Pretraining under Limited PairingPoster
LLM-Guided Loop Bound Generation for Program Termination VerificationPoster
LLM-MatLogic: Executable Exchange Contracts for Knowledge-Graph Query Answering with Scoped NegationPoster
LLM-based Embeddings: Attention Values Encode Sentence Semantics Better Than Hidden StatesPoster
LLM4Branch: Large Language Model for Discovering Efficient Branching Policies of Integer ProgramsPoster
LLM4Cov: Execution-Grounded Agent Learning for High-Coverage Hardware VerificationPoster
LLMInertia: Adaptive Counter-Inertial Reasoning to Improve Evidence Faithfulness in Large Language ModelsPoster
LLMs as Noisy Channels: A Shannon Perspective on Model Capacity and Scaling LawsPoster
LLawCo: Learning Laws of Cooperation for Modeling Embodied Multi-Agent BehaviorPoster
LMCleaner: Efficient and Certified Online Unlearning via Influence Propagation TruncationPoster
LMM4-IC4K: A Large Multimodal Model Powered Integrated Circuit Footprint Geometry UnderstandingPoster
LO-BCQ: Locally Optimal Block Clustered Quantization for 4-bit (W4A4) LLM InferencePoster
LOCA-bench: Benchmarking Language Agents Under Controllable and Extreme Context GrowthPoster
LORD-GoF: A Robust Online Detection Approach for LLM Watermarks in Sparse and Mixed StreamsPoster
LOTTERY: Learning from Reference-Only Samples in Two-Sample Testing under Size AsymmetryPoster
LOVE: Benchmarking and Evaluating Text-to-Video Generation and Video-to-Text InterpretationPoster
LOZO+: Provably Efficient Zeroth-Order Fine-Tuning via Greedy Low-Rank Subspace SelectionPoster
LRAgent: Efficient KV Cache Sharing for Multi-LoRA LLM AgentsPoster
LS$^{2}$MC-GDA: A Smoothed Algorithm for Federated Stochastic Compositional Minimax OptimizationPoster
LSGQuant: Layer-Sensitivity Guided Quantization for One-Step Diffusion Real-World Video Super-ResolutionPoster
LUCID: Attention with Preconditioned RepresentationsPoster
LUGS: Latent-aware Guidance for Efficient Unmasking in Diffusion Large Language ModelsPoster
LUVE : Latent-Cascaded Ultra-High-Resolution Video Generation with Dual Frequency ExpertsPoster
LaRA-Fusion: Latent-Robust Adaptation via Dual-Loop Constraints for Infrared and Visible Image FusionPoster
LaRI: Layered Ray Intersections for Single-view 3D Geometric ReasoningPoster
LaST$_{0}$: Latent Spatio-Temporal Chain-of-Thought for Robotic Vision-Language-Action ModelSpotlight
LaTtE-Flow: Layerwise Timestep-Expert Flow-based TransformerPoster
LabBuilder: Protocol-Grounded 3D Layout Generation for Interactable and Safe LaboratoryPoster
Label-Guided Representation Learning for Incomplete Multi-View Multi-Label ClassificationPoster
LagLLM: LLM-empowered lead–lag dependency learning for spatial-temporal time series forecastingPoster
Lagrangian Perturbation Diffusion Steering: Latent Reinforcement Learning for Generative PoliciesPoster
LakeQA: A Benchmark for Complex Exploratory QA over a Million-Scale Data LakePoster
Landmark-Guided Policy Optimization for Multi-Objective Language Model SelectionPoster
LangForce: Bayesian Decomposition of Vision Language Action Models via Latent Action QueriesPoster
LangPrecip: Language-Aware Multimodal Precipitation NowcastingPoster
Langevin Rollout Optimization for Modelic Reinforcement LearningPoster
Language Bias in LVLMs: From In-Depth Analysis to Simple and Effective MitigationPoster
Language Generation in the Limit: Complexity Barriers and Implications for LearningSpotlight
Language Generation with Feedback: Queries and MistakesPoster
Language Generation with Replay: A Learning-Theoretic View of Model CollapsePoster
Language Model Augmented Semi-Supervised Statistical InferencePoster
Language Model Circuits Are Sparse in the Neuron BasisSpotlight
Language Models as Nodes: Constructing a High-Level Neural NetworkPoster
Language as a Wave Phenomenon: Semantic Phase Locking and Interference in Neural NetworksPoster
Language-based Trial and Error Falls Behind in the Era of ExperiencePoster
Laplacian Representations for Decision-Time PlanningPoster
Large Language Model Agents Are Not Always Faithful Self-EvolversPoster
Large Language Model Teaches Visual Students: Cross-Modality Transfer of Fine-Grained Conceptual KnowledgePoster
Large Language Models Develop Novel Social Biases Through Adaptive ExplorationOral
Large Language Models Explore by Latent DistillingPoster
Large Language Models as Topological Thinkers: A Benchmark on Graph Persistent HomologyPoster

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.