ICML 2025 Accepted Papers

The full list of 3,333 papers accepted at ICML 2025 (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: 2,988Spotlight: 225Oral: 120

TMetaNet: Topological Meta-Learning Framework for Dynamic Link PredictionPoster
TOPLOC: A Locality Sensitive Hashing Scheme for Trustless Verifiable InferencePoster
TRACE Back from the Future: A Probabilistic Reasoning Approach to Controllable Language GenerationPoster
TRUST-VLM: Thorough Red-Teaming for Uncovering Safety Threats in Vision-Language ModelsPoster
TS-SNN: Temporal Shift Module for Spiking Neural NetworksPoster
TSP: A Two-Sided Smoothed Primal-Dual Method for Nonconvex Bilevel OptimizationPoster
TTFSFormer: A TTFS-based Lossless Conversion of Spiking TransformerPoster
TUMTraf VideoQA: Dataset and Benchmark for Unified Spatio-Temporal Video Understanding in Traffic ScenesPoster
TabFSBench: Tabular Benchmark for Feature Shifts in Open EnvironmentsPoster
TabNAT: A Continuous-Discrete Joint Generative Framework for Tabular DataPoster
TabSDS: a Lightweight, Fully Non-Parametric, and Model Free Approach for Generating Synthetic Tabular DataPoster
Tackling Dimensional Collapse toward Comprehensive Universal Domain AdaptationPoster
Tackling View-Dependent Semantics in 3D Language Gaussian SplattingPoster
Taming Diffusion for Dataset Distillation with High RepresentativenessPoster
Taming Knowledge Conflicts in Language ModelsSpotlight
Targeted Low-rank Refinement: Enhancing Sparse Language Models with PrecisionPoster
Targeted Unlearning with Single Layer Unlearning GradientPoster
Targeted control of fast prototyping through domain-specific interfacePoster
Task Generalization with Autoregressive Compositional Structure: Can Learning from $D$ Tasks Generalize to $D^T$ Tasks?Poster
Task-Agnostic Pre-training and Task-Guided Fine-tuning for Versatile Diffusion PlannerPoster
Task-Aware Virtual Training: Enhancing Generalization in Meta-Reinforcement Learning for Out-of-Distribution TasksPoster
Task-Gated Multi-Expert Collaboration Network for Degraded Multi-Modal Image FusionPoster
TeDS: Joint Learning of Diachronic and Synchronic Perspectives in Quaternion Space for Temporal Knowledge Graph CompletionPoster
TeLoGraF: Temporal Logic Planning via Graph-encoded Flow MatchingPoster
Teaching Physical Awareness to LLMs through SoundsPoster
Telling Peer Direct Effects from Indirect Effects in Observational Network DataPoster
Temporal Difference FlowsOral
Temporal Distance-aware Transition Augmentation for Offline Model-based Reinforcement LearningPoster
Temporal Misalignment in ANN-SNN Conversion and its Mitigation via Probabilistic Spiking NeuronsPoster
Temporal Query Network for Efficient Multivariate Time Series ForecastingPoster
Tensor Decomposition Based Memory-Efficient Incremental LearningPoster
Tensor Product Neural Networks for Functional ANOVA ModelPoster
Tensor-Var: Efficient Four-Dimensional Variational Data AssimilationPoster
Tensorized Multi-View Multi-Label Classification via Laplace Tensor RankPoster
Test-Time Adaptation for Online Vision-Language Navigation with Feedback-based Reinforcement LearningPoster
Test-Time Adaptation with Binary FeedbackPoster
Test-Time Canonicalization by Foundation Models for Robust PerceptionPoster
Test-Time Graph Neural Dataset Search With Generative ProjectionPoster
Test-Time Learning for Large Language ModelsPoster
Test-Time Multimodal Backdoor Detection by Contrastive PromptingPoster
Test-Time Selective Adaptation for Uni-Modal Distribution Shift in Multi-Modal DataPoster
Test-time Adaptation on Graphs via Adaptive Subgraph-based Selection and Regularized PrototypesPoster
Test-time Adapted Reinforcement Learning with Action Entropy RegularizationPoster
Test-time Correlation AlignmentPoster
Testing Conditional Mean Independence Using Generative Neural NetworksPoster
Testing the Limits of Fine-Tuning for Improving Visual Cognition in Vision Language ModelsPoster
Text-to-LoRA: Instant Transformer AdaptionPoster
TextCenGen: Attention-Guided Text-Centric Background Adaptation for Text-to-Image GenerationPoster
Textural or Textual: How Vision-Language Models Read Text in ImagesPoster
The Batch Complexity of Bandit Pure ExplorationPoster
The Berkeley Function Calling Leaderboard (BFCL): From Tool Use to Agentic Evaluation of Large Language ModelsPoster
The Butterfly Effect: Neural Network Training Trajectories Are Highly Sensitive to Initial ConditionsPoster
The Canary’s Echo: Auditing Privacy Risks of LLM-Generated Synthetic TextPoster
The Case for Learned Provenance-based System Behavior BaselinePoster
The Complexity of Learning Sparse Superposed Features with FeedbackPoster
The Courage to Stop: Overcoming Sunk Cost Fallacy in Deep Reinforcement LearningPoster
The Diffusion DualityPoster
The Elicitation Game: Evaluating Capability Elicitation TechniquesPoster
The Emperor's New Clothes in Benchmarking? A Rigorous Examination of Mitigation Strategies for LLM Benchmark Data ContaminationPoster
The Empirical Mean is Minimax Optimal for Local Glivenko-CantelliPoster
The Energy Loss Phenomenon in RLHF: A New Perspective on Mitigating Reward HackingPoster
The Four Color Theorem for Cell Instance SegmentationPoster
The Generalized Skew Spectrum of GraphsPoster
The Geometry of Refusal in Large Language Models: Concept Cones and Representational IndependencePoster
The Global Convergence Time of Stochastic Gradient Descent in Non-Convex Landscapes: Sharp Estimates via Large DeviationsPoster
The Harder Path: Last Iterate Convergence for Uncoupled Learning in Zero-Sum Games with Bandit FeedbackPoster
The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety DirectionsPoster
The Hidden Joules: Evaluating the Energy Consumption of Vision Backbones for Progress Towards More Efficient Model InferencePoster
The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models Via Visual Information SteeringPoster
The Illusion of Role Separation: Hidden Shortcuts in LLM Role Learning (and How to Fix Them)Poster
The Impact of On-Policy Parallelized Data Collection on Deep Reinforcement Learning NetworksPoster
The Importance of Being Lazy: Scaling Limits of Continual LearningPoster
The Jailbreak Tax: How Useful are Your Jailbreak Outputs?Spotlight
The Limits of Predicting Agents from BehaviourPoster
The Limits of Tractable MarginalizationPoster
The Lock-in Hypothesis: Stagnation by AlgorithmPoster
The Logical Implication Steering Method for Conditional Interventions on Transformer GenerationPoster
The Missing Alignment Link of In-context Learning on SequencesPoster
The Noisy Laplacian: a Threshold Phenomenon for Non-Linear Dimension ReductionPoster
The Number of Trials Matters in Infinite-Horizon General-Utility Markov Decision ProcessesSpotlight
The Panaceas for Improving Low-Rank Decomposition in Communication-Efficient Federated LearningPoster
The Polynomial Stein Discrepancy for Assessing Moment ConvergencePoster
The Power of Random Features and the Limits of Distribution-Free Gradient DescentPoster
The Price of Freedom: Exploring Expressivity and Runtime Tradeoffs in Equivariant Tensor ProductsPoster
The Price of Linear Time: Error Analysis of Structured Kernel InterpolationPoster
The Relationship Between No-Regret Learning and Online Conformal PredictionPoster
The Ripple Effect: On Unforeseen Complications of Backdoor AttacksPoster
The Role of Sparsity for Length Generalization in LLMsPoster
The Sample Complexity of Online Strategic Decision Making with Information Asymmetry and Knowledge TransportabilityPoster
The Sparse-Plus-Low-Rank Quasi-Newton Method for Entropic-Regularized Optimal TransportPoster
The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model TrainingPoster
The Synergy of LLMs & RL Unlocks Offline Learning of Generalizable Language-Conditioned Policies with Low-fidelity DataSpotlight
The Underlying Universal Statistical Structure of Natural DatasetsPoster
The Value of Prediction in Identifying the Worst-OffOral
The impact of uncertainty on regularized learning in gamesPoster
The underlying structures of self-attention: symmetry, directionality, and emergent dynamics in Transformer trainingPoster
Theoretical Limitations of Ensembles in the Age of OverparameterizationOral
Theoretical Performance Guarantees for Partial Domain Adaptation via Partial Optimal TransportPoster
Theoretically Unmasking Inference Attacks Against LDP-Protected Clients in Federated Vision ModelsPoster
Thickness-aware E(3)-Equivariant 3D Mesh Neural NetworksPoster
Think Twice, Act Once: A Co-Evolution Framework of LLM and RL for Large-Scale Decision MakingPoster
Three-Dimensional Trajectory Prediction with 3DMoTraj DatasetPoster
Tight and Fast Bounds for Multi-Label LearningPoster
Tightening Causal Bounds via Covariate-Aware Optimal TransportPoster
Tilted Sharpness-Aware MinimizationPoster
Time Series Representations with Hard-Coded InvariancesPoster
Time to Spike? Understanding the Representational Power of Spiking Neural Networks in Discrete TimePoster
Time-Aware World Model for Adaptive Prediction and ControlPoster
TimeBase: The Power of Minimalism in Efficient Long-term Time Series ForecastingSpotlight
TimeDART: A Diffusion Autoregressive Transformer for Self-Supervised Time Series RepresentationPoster
TimePoint: Accelerated Time Series Alignment via Self-Supervised Keypoint and Descriptor LearningPoster
TimePro: Efficient Multivariate Long-term Time Series Forecasting with Variable- and Time-Aware Hyper-statePoster
TimeStacker: A Novel Framework with Multilevel Observation for Capturing Nonstationary Patterns in Time Series ForecastingPoster
TimeStep Master: Asymmetrical Mixture of Timestep LoRA Experts for Versatile and Efficient Diffusion Models in VisionPoster
TinyMIG: Transferring Generalization from Vision Foundation Models to Single-Domain Medical ImagingPoster
To Each Metric Its Decoding: Post-Hoc Optimal Decision Rules of Probabilistic Hierarchical ClassifiersPoster
To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language ModelsPoster
ToMA: Token Merge with Attention for Diffusion ModelsPoster
Token Cleaning: Fine-Grained Data Selection for LLM Supervised Fine-TuningPoster
Token Coordinated Prompt Attention is Needed for Visual PromptingPoster
Token Signature: Predicting Chain-of-Thought Gains with Token Decoding Feature in Large Language ModelsPoster
TokenSwift: Lossless Acceleration of Ultra Long Sequence GenerationPoster
Tokenized Bandit for LLM Decoding and AlignmentPoster
TopInG: Topologically Interpretable Graph Learning via Persistent Rationale FiltrationPoster
Topological Signatures of Adversaries in Multimodal AlignmentsPoster
Topology-Aware Dynamic Reweighting for Distribution Shifts on GraphPoster
Topology-aware Neural Flux Prediction Guided by PhysicsPoster
Toward Data-centric Directed Graph Learning: An Entropy-driven ApproachPoster
Towards Better-than-2 Approximation for Constrained Correlation ClusteringSpotlight
Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement LearningPoster
Towards Escaping from Class Dependency Modeling for Multi-Dimensional ClassificationPoster
Towards Global-level Mechanistic Interpretability: A Perspective of Modular Circuits of Large Language ModelsPoster
Towards Graph Foundation Models: Learning Generalities Across Graphs via Task-TreesPoster
Towards Learning to Complete Anything in LidarPoster
Towards Lifelong Model Editing via Simulating Ideal EditorPoster
Towards Memorization Estimation: Fast, Formal and FreePoster
Towards Practical Defect-Focused Automated Code ReviewSpotlight
Towards Rationale-Answer Alignment of LVLMs via Self-Rationale CalibrationPoster
Towards Robust Influence Functions with Flat Validation MinimaPoster
Towards Robustness and Explainability of Automatic Algorithm SelectionSpotlight
Towards Theoretical Understanding of Sequential Decision Making with Preference FeedbackPoster
Towards Trustworthy Federated Learning with Untrusted ParticipantsPoster
Towards Understanding Catastrophic Forgetting in Two-layer Convolutional Neural NetworksPoster
Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit AnalysisPoster
Towards Understanding Gradient Dynamics of the Sliced-Wasserstein Distance via Critical Point AnalysisPoster
Towards Understanding Parametric Generalized Category Discovery on GraphsPoster
Towards Universal Offline Black-Box Optimization via Learning Language Model EmbeddingsPoster
Towards a Formal Theory of Representational CompositionalityPoster
Towards a General Time Series Forecasting Model with Unified Representation and Adaptive TransferPoster
Towards a Mechanistic Explanation of Diffusion Model GeneralizationSpotlight
Towards a Unified Framework of Clustering-based Anomaly DetectionPoster
Towards an Explainable Comparison and Alignment of Feature EmbeddingsPoster
Towards the Causal Complete Cause of Multi-Modal Representation LearningPoster
Towards the Efficient Inference by Incorporating Automated Computational Phenotypes under Covariate ShiftPoster
TraceGrad: a Framework Learning Expressive SO(3)-equivariant Non-linear Representations for Electronic-Structure Hamiltonian PredictionPoster
Tracking Most Significant Shifts in Infinite-Armed BanditsPoster
Tracking The Best Expert PrivatelyPoster
Tractable Transformers for Flexible Conditional GenerationPoster
Training Diffusion-based Generative Models with Limited DataPoster
Training Flexible Models of Genetic Variant Effects from Functional Annotations using Accelerated Linear AlgebraPoster
Training High Performance Spiking Neural Network by Temporal Model CalibrationPoster
Training a Generally Curious AgentOral
Trajectory World Models for Heterogeneous EnvironmentsPoster
TransPL: VQ-Code Transition Matrices for Pseudo-Labeling of Time Series Unsupervised Domain AdaptationPoster
Transfer Learning for Nonparametric Contextual Dynamic PricingPoster
Transfer Q-Learning with Composite MDP StructuresPoster
Transformative or Conservative? Conservation laws for ResNets and TransformersOral
Transformer-Based Spatial-Temporal Counterfactual Outcomes EstimationPoster
Tree-Sliced Wasserstein Distance with Nonlinear ProjectionPoster
Tree-Sliced Wasserstein Distance: A Geometric PerspectivePoster
TreeLoRA: Efficient Continual Learning via Layer-Wise LoRAs Guided by a Hierarchical Gradient-Similarity TreePoster
Triple-Optimistic Learning for Stochastic Contextual Bandits with General ConstraintsPoster
Trust-Region Twisted Policy ImprovementPoster
Trusted Multi-View Classification with Expert Knowledge ConstraintsSpotlight
Trustworthy Machine Learning through Data-Specific IndistinguishabilityPoster
TruthFlow: Truthful LLM Generation via Representation Flow CorrectionPoster
TtBA: Two-third Bridge Approach for Decision-Based Adversarial AttackPoster
TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMsPoster
Tuning Sequential Monte Carlo Samplers via Greedy Incremental Divergence MinimizationPoster
Two Tickets are Better than One: Fair and Accurate Hiring Under Strategic LLM ManipulationsPoster
TypyBench: Evaluating LLM Type Inference for Untyped Python RepositoriesPoster
UDora: A Unified Red Teaming Framework against LLM Agents by Dynamically Hijacking Their Own ReasoningPoster
UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and InteractionPoster
Ultra Lowrate Image Compression with Semantic Residual Coding and Compression-aware DiffusionPoster
UltraTWD: Optimizing Ultrametric Trees for Tree-Wasserstein DistancePoster
UnHiPPO: Uncertainty-aware Initialization for State Space ModelsPoster
Unbiased Evaluation of Large Language Models from a Causal PerspectivePoster
Unbiased Recommender Learning from Implicit Feedback via Weakly Supervised LearningPoster
UncertainSAM: Fast and Efficient Uncertainty Quantification of the Segment Anything ModelPoster
Uncertainty Estimation for Heterophilic Graphs Through the Lens of Information TheoryPoster
Uncertainty-Based Extensible Codebook for Discrete Federated Learning in Heterogeneous Data SilosPoster
Unconstrained Robust Online Convex OptimizationPoster
Underestimated Privacy Risks for Minority Populations in Large Language Model UnlearningPoster
Understanding Bias Reinforcement in LLM Agents DebatePoster
Understanding Complexity in VideoQA via Visual Program GenerationPoster
Understanding Fixed Predictions via Confined RegionsPoster
Understanding Input Selectivity in Mamba: Impact on Approximation Power, Memorization, and Associative Recall CapacityPoster
Understanding Model Reprogramming for CLIP via Decoupling Visual PromptsPoster
Understanding Nonlinear Implicit Bias via Region Counts in Input SpacePoster
Understanding Overadaptation in Supervised Fine-Tuning: The Role of Ensemble MethodsPoster
Understanding Sharpness Dynamics in NN Training with a Minimalist Example: The Effects of Dataset Difficulty, Depth, Stochasticity, and MorePoster
Understanding Synthetic Context Extension via Retrieval HeadsPoster
Understanding and Improving Length Generalization in Recurrent ModelsPoster
Understanding and Mitigating Memorization in Diffusion Models for Tabular DataPoster
Understanding and Mitigating Memorization in Generative Models via Sharpness of Probability LandscapesSpotlight
Understanding the Forgetting of (Replay-based) Continual Learning via Feature Learning: Angle MattersPoster
Understanding the Kronecker Matrix-Vector Complexity of Linear AlgebraPoster
Understanding the Logic of Direct Preference Alignment through LogicPoster
Understanding the Statistical Accuracy-Communication Trade-off in Personalized Federated Learning with Minimax GuaranteesPoster
Understanding the Unfairness in Network QuantizationPoster
Understanding the difficulties of posterior predictive estimationPoster
UniDB: A Unified Diffusion Bridge Framework via Stochastic Optimal ControlSpotlight
UniMC: Taming Diffusion Transformer for Unified Keypoint-Guided Multi-Class Image GenerationPoster
UniMate: A Unified Model for Mechanical Metamaterial Generation, Property Prediction, and Condition ConfirmationPoster
UniMoMo: Unified Generative Modeling of 3D Molecules for De Novo Binder DesignPoster
UniSim: A Unified Simulator for Time-Coarsened Dynamics of BiomoleculesPoster
Unifews: You Need Fewer Operations for Efficient Graph Neural NetworksPoster
Unified Analysis of Continuous Weak Features Learning with Applications to Learning from Missing DataPoster
Unified K-Means Clustering with Label-Guided Manifold LearningPoster
Unified Screening for Multiple DiseasesPoster
Uniform Mean Estimation for Heavy-Tailed Distributions via Median-of-MeansPoster
Unifying Knowledge from Diverse Datasets to Enhance Spatial-Temporal Modeling: A Granularity-Adaptive Geographical Embedding ApproachPoster
Unisolver: PDE-Conditional Transformers Towards Universal Neural PDE SolversPoster
Unisoma: A Unified Transformer-based Solver for Multi-Solid SystemsPoster
Universal Approximation of Mean-Field Models via TransformersPoster
Universal Biological Sequence Reranking for Improved De Novo Peptide SequencingPoster
Universal Neural Optimal TransportPoster
Unlocking Post-hoc Dataset Inference with Synthetic DataPoster
Unlocking the Capabilities of Large Vision-Language Models for Generalizable and Explainable Deepfake DetectionPoster
Unlocking the Power of Rehearsal in Continual Learning: A Theoretical PerspectivePoster
Unlocking the Power of SAM 2 for Few-Shot SegmentationPoster
Unnatural Languages Are Not Bugs but Features for LLMsPoster
Unpaired Point Cloud Completion via Unbalanced Optimal TransportPoster
Unraveling the Interplay between Carryover Effects and Reward Autocorrelations in Switchback ExperimentsPoster
Unsupervised Learning for Class Distribution MismatchPoster
Unveiling Markov heads in Pretrained Language Models for Offline Reinforcement LearningPoster
Upcycling Text-to-Image Diffusion Models for Multi-Task CapabilitiesPoster
Update Your Transformer to the Latest Release: Re-Basin of Task VectorsPoster
VCT: Training Consistency Models with Variational Noise CouplingPoster
VIP: Vision Instructed Pre-training for Robotic ManipulationPoster
VTGaussian-SLAM: RGBD SLAM for Large Scale Scenes with Splatting View-Tied 3D GaussiansPoster
Validating Mechanistic Interpretations: An Axiomatic ApproachPoster
Value-Based Deep RL Scales PredictablyPoster
Variance as a Catalyst: Efficient and Transferable Semantic Erasure Adversarial Attack for Customized Diffusion ModelsPoster
Variance-Reduced Forward-Reflected-Backward Splitting Methods for Nonmonotone Generalized EquationsPoster
Variational Control for Guidance in Diffusion ModelsPoster
Variational Counterfactual Intervention Planning to Achieve Target OutcomesPoster
Variational Learning of Fractional PosteriorsPoster
Variational Phylogenetic Inference with Products over BipartitionsPoster
Vector Grimoire: Codebook-based Shape Generation under Raster Image SupervisionPoster
VerbalTS: Generating Time Series from TextsPoster
Verification Learning: Make Unsupervised Neuro-Symbolic System FeasiblePoster
Video-Enhanced Offline Reinforcement Learning: A Model-Based ApproachPoster
VinePPO: Refining Credit Assignment in RL Training of LLMsPoster
Vision Graph Prompting via Semantic Low-Rank DecompositionPoster
Vision-Language Model Selection and Reuse for Downstream AdaptationPoster
Vision-Language Models Create Cross-Modal Task RepresentationsPoster
Visual Abstraction: A Plug-and-Play Approach for Text-Visual RetrievalPoster
Visual Attention Never Fades: Selective Progressive Attention ReCalibration for Detailed Image Captioning in Multimodal Large Language ModelsPoster
Visual Generation Without GuidancePoster
Visual Graph Arena: Evaluating Visual Conceptualization of Vision and Multimodal Large Language ModelsPoster
Visual and Domain Knowledge for Professional-level Graph-of-Thought Medical ReasoningSpotlight
Volume Optimality in Conformal Prediction with Structured Prediction SetsPoster
Volume-Aware Distance for Robust Similarity LearningPoster
Voronoi-grid-based Pareto Front Learning and Its Application to Collaborative Federated LearningPoster
Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-TuningPoster
WATCH: Adaptive Monitoring for AI Deployments via Weighted-Conformal MartingalesPoster
WAVE: Weighted Autoregressive Varying Gate for Time Series ForecastingPoster
WGFormer: An SE(3)-Transformer Driven by Wasserstein Gradient Flows for Molecular Ground-State Conformation PredictionPoster
WILTing Trees: Interpreting the Distance Between MPNN EmbeddingsPoster
WMarkGPT: Watermarked Image Understanding via Multimodal Large Language ModelsPoster
WOMD-Reasoning: A Large-Scale Dataset for Interaction Reasoning in DrivingPoster
Wait-Less Offline Tuning and Re-solving for Online Decision MakingPoster
Wasserstein Policy OptimizationPoster
Watch Out Your Album! On the Inadvertent Privacy Memorization in Multi-Modal Large Language ModelsPoster
WeGeFT: Weight‑Generative Fine‑Tuning for Multi‑Faceted Efficient Adaptation of Large ModelsPoster
Weak-to-Strong Generalization Even in Random Feature Networks, ProvablyPoster
Weak-to-Strong Jailbreaking on Large Language ModelsPoster
Weakly Supervised Anomaly Detection via Dual-Tailed KernelPoster
Weakly-Supervised Contrastive Learning for Imprecise Class LabelsSpotlight
Weight matrices compression based on PDB model in deep neural networksPoster
Weisfeiler and Leman Go Gambling: Why Expressive Lottery Tickets WinPoster
What Do Learning Dynamics Reveal About Generalization in LLM Mathematical Reasoning?Poster
What Has a Foundation Model Found? Inductive Bias Reveals World ModelsPoster
What Limits Bidirectional Model's Generative Capabilities? A Uni-Bi-Directional Mixture-of-Expert Method For Bidirectional Fine-tuningPoster
What Limits Virtual Agent Application? OmniBench: A Scalable Multi-Dimensional Benchmark for Essential Virtual Agent CapabilitiesOral
What Makes In-context Learning Effective for Mathematical ReasoningPoster
What Makes a Good Feedforward Computational Graph?Poster
What can large language models do for sustainable food?Poster
What makes an Ensemble (Un) Interpretable?Poster
When Bad Data Leads to Good ModelsPoster
When Can Proxies Improve the Sample Complexity of Preference Learning?Poster
When Data-Free Knowledge Distillation Meets Non-Transferable Teacher: Escaping Out-of-Distribution Trap is All You NeedPoster
When Diffusion Models Memorize: Inductive Biases in Probability Flow of Minimum-Norm Shallow Neural NetsPoster
When Do LLMs Help With Node Classification? A Comprehensive AnalysisPoster
When Dynamic Data Selection Meets Data Augmentation: Achieving Enhanced Training AccelerationPoster
When Every Millisecond Counts: Real-Time Anomaly Detection via the Multimodal Asynchronous Hybrid NetworkSpotlight
When Maximum Entropy Misleads Policy OptimizationPoster
When Model Knowledge meets Diffusion Model: Diffusion-assisted Data-free Image Synthesis with Alignment of Domain and ClassPoster
When Will It Fail?: Anomaly to Prompt for Forecasting Future Anomalies in Time SeriesPoster
When and How Does CLIP Enable Domain and Compositional Generalization?Spotlight
When can in-context learning generalize out of task distribution?Poster
When do neural networks learn world models?Poster
When to Forget? Complexity Trade-offs in Machine UnlearningPoster
When to retrain a machine learning modelPoster
When, Where and Why to Average Weights?Poster
Whitened CLIP as a Likelihood Surrogate of Images and CaptionsPoster
Whoever Started the interference Should End It: Guiding Data-Free Model Merging via Task VectorsPoster
Widening the Network Mitigates the Impact of Data Heterogeneity on FedAvgPoster
WikiBigEdit: Understanding the Limits of Lifelong Knowledge Editing in LLMsPoster
WildChat-50M: A Deep Dive Into the Role of Synthetic Data in Post-TrainingPoster
Winner-takes-all for Multivariate Probabilistic Time Series ForecastingPoster
Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement LearningPoster
World Model Implanting for Test-time Adaptation of Embodied AgentsPoster
Wrapped Gaussian on the manifold of Symmetric Positive Definite MatricesPoster
WyckoffDiff -- A Generative Diffusion Model for Crystal SymmetryPoster
X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIPPoster
XAttention: Block Sparse Attention with Antidiagonal ScoringPoster
You Always Recognize Me (YARM): Robust Texture Synthesis Against Multi-View CorruptionPoster
Zero Shot Generalization of Vision-Based RL Without Data AugmentationPoster
Zero-Shot Adaptation of Parameter-Efficient Fine-Tuning in Diffusion ModelsPoster
Zero-Shot Cyclic Peptide Design via Composable Geometric ConstraintsPoster
Zero-Shot Offline Imitation Learning via Optimal TransportPoster
ZipAR: Parallel Autoregressive Image Generation through Spatial LocalityPoster
am-ELO: A Stable Framework for Arena-based LLM EvaluationSpotlight
any4: Learned 4-bit Numeric Representation for LLMsPoster
e-GAI: e-value-based Generalized $\alpha$-Investing for Online False Discovery Rate ControlPoster
iDPA: Instance Decoupled Prompt Attention for Incremental Medical Object DetectionPoster
iN2V: Bringing Transductive Node Embeddings to Inductive GraphsPoster
polybasic Speculative Decoding Through a Theoretical PerspectivePoster
scSSL-Bench: Benchmarking Self-Supervised Learning for Single-Cell DataSpotlight
sciLaMA: A Single-Cell Representation Learning Framework to Leverage Prior Knowledge from Large Language ModelsPoster
unMORE: Unsupervised Multi-Object Segmentation via Center-Boundary ReasoningPoster

ICML accepted papers in other years

ICML 2026 (6,634)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.