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

Latent Variable Estimation in Bayesian Black-Litterman ModelsPoster
Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language ModelsSpotlight
Layer-wise Quantization for Quantized Optimistic Dual AveragingPoster
Lean and Mean Adaptive Optimization via Subset-Norm and Subspace-Momentum with Convergence GuaranteesPoster
Learn Beneficial Noise as Graph AugmentationPoster
Learn Singularly Perturbed Solutions via Homotopy DynamicsPoster
Learn to Vaccinate: Combining Structure Learning and Effective Vaccination for Epidemic and Outbreak ControlPoster
Learnable Spatial-Temporal Positional Encoding for Link PredictionPoster
Learngene Tells You How to Customize: Task-Aware Parameter Initialization at Flexible ScalesPoster
Learning Adaptive Lighting via Channel-Aware GuidancePoster
Learning Along the Arrow of Time: Hyperbolic Geometry for Backward-Compatible Representation LearningPoster
Learning Attribute-Aware Hash Codes for Fine-Grained Image Retrieval via Query OptimizationPoster
Learning Bayesian Nash Equilibrium in Auction Games via Approximate Best ResponsePoster
Learning Cascade Ranking as One NetworkPoster
Learning Changes in Graphon Attachment Network ModelsPoster
Learning Classifiers That Induce MarketsPoster
Learning Compact Semantic Information for Incomplete Multi-View Missing Multi-Label ClassificationPoster
Learning Condensed Graph via Differentiable Atom Mapping for Reaction Yield PredictionPoster
Learning Configurations for Data-Driven Multi-Objective OptimizationPoster
Learning Curves of Stochastic Gradient Descent in Kernel RegressionPoster
Learning Distribution-wise Control in Representation Space for Language ModelsPoster
Learning Dynamics in Continual Pre-Training for Large Language ModelsOral
Learning Dynamics under Environmental Constraints via Measurement-Induced Bundle StructuresSpotlight
Learning Efficient Robotic Garment Manipulation with StandardizationPoster
Learning Event Completeness for Weakly Supervised Video Anomaly DetectionPoster
Learning Extrapolative Sequence Transformations from Markov ChainsPoster
Learning Fused State Representations for Control from Multi-View ObservationsPoster
Learning Gaussian DAG Models without Condition Number BoundsPoster
Learning Imbalanced Data with Beneficial Label NoisePoster
Learning Imperfect Information Extensive-form Games with Last-iterate Convergence under Bandit FeedbackPoster
Learning In-context $n$-grams with Transformers: Sub-$n$-grams Are Near-Stationary PointsPoster
Learning Initial Basis Selection for Linear Programming via Duality-Inspired Tripartite Graph Representation and Comprehensive SupervisionPoster
Learning Input Encodings for Kernel-Optimal Implicit Neural RepresentationsPoster
Learning Invariant Causal Mechanism from Vision-Language ModelsPoster
Learning Joint Interventional Effects from Single-Variable Interventions in Additive ModelsPoster
Learning Likelihood-Free Reference PriorsPoster
Learning Mean Field Control on Sparse GraphsPoster
Learning Minimum-Size BDDs: Towards Efficient Exact AlgorithmsPoster
Learning Mixtures of Experts with EM: A Mirror Descent PerspectivePoster
Learning Monotonic Probabilities with a Generative Cost ModelPoster
Learning Optimal Multimodal Information Bottleneck RepresentationsPoster
Learning Parametric Distributions from Samples and PreferencesSpotlight
Learning Policy Committees for Effective Personalization in MDPs with Diverse TasksPoster
Learning Progress Driven Multi-Agent CurriculumPoster
Learning Robust Neural Processes with Risk-Averse Stochastic OptimizationPoster
Learning Safe Control via On-the-Fly Bandit ExplorationPoster
Learning Safe Strategies for Value Maximizing Buyers in Uniform Price AuctionsPoster
Learning Safety Constraints for Large Language ModelsSpotlight
Learning Single Index Models with Diffusion PriorsPoster
Learning Soft Sparse Shapes for Efficient Time-Series ClassificationSpotlight
Learning State-Based Node Representations from a Class Hierarchy for Fine-Grained Open-Set DetectionPoster
Learning Survival Distributions with the Asymmetric Laplace DistributionPoster
Learning Time-Aware Causal Representation for Model Generalization in Evolving DomainsPoster
Learning Time-Varying Multi-Region Brain Communications via Scalable Markovian Gaussian ProcessesOral
Learning Vision and Language Concepts for Controllable Image GenerationPoster
Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient AligningPoster
Learning from Sample Stability for Deep ClusteringPoster
Learning from Suboptimal Data in Continuous Control via Auto-Regressive Soft Q-NetworkPoster
Learning from True-False Labels via Multi-modal Prompt RetrievingPoster
Learning the Electronic Hamiltonian of Large Atomic StructuresPoster
Learning to Generate Projections for Reducing Dimensionality of Heterogeneous Linear Programming ProblemsPoster
Learning to Incentivize in Repeated Principal-Agent Problems with Adversarial Agent ArrivalsPoster
Learning to Keep a Promise: Scaling Language Model Decoding Parallelism with Learned Asynchronous DecodingPoster
Learning to Match Unpaired Data with Minimum Entropy CouplingPoster
Learning to Quantize for Training Vector-Quantized NetworksPoster
Learning to Reuse Policies in State Evolvable EnvironmentsPoster
Learning to Route LLMs with Confidence TokensPoster
Learning to Steer Learners in GamesPoster
Learning to Stop: Deep Learning for Mean Field Optimal StoppingPoster
Learning to Trust Bellman Updates: Selective State-Adaptive Regularization for Offline RLPoster
Learning with Exact Invariances in Polynomial TimeSpotlight
Learning with Expected Signatures: Theory and ApplicationsOral
Learning with Selectively Labeled Data from Multiple Decision-makersPoster
Learning without Isolation: Pathway Protection for Continual LearningPoster
Learning-Augmented Algorithms for MTS with Bandit Access to Multiple PredictorsPoster
Learning-Augmented Hierarchical ClusteringPoster
Learning-Order Autoregressive Models with Application to Molecular Graph GenerationPoster
Learnware Specification via Dual AlignmentPoster
Lego Sketch: A Scalable Memory-augmented Neural Network for Sketching Data StreamsPoster
LensLLM: Unveiling Fine-Tuning Dynamics for LLM SelectionPoster
Less is More: Federated Graph Learning with Alleviating Topology Heterogeneity from A Causal PerspectivePoster
Let LLM Tell What to Prune and How Much to PrunePoster
Leveraging Diffusion Model as Pseudo-Anomalous Graph Generator for Graph-Level Anomaly DetectionSpotlight
Leveraging Model Guidance to Extract Training Data from Personalized Diffusion ModelsPoster
Leveraging Offline Data in Linear Latent Contextual BanditsPoster
Leveraging Per-Instance Privacy for Machine UnlearningPoster
Leveraging Predictive Equivalence in Decision TreesPoster
Leveraging Randomness in Model and Data Partitioning for Privacy AmplificationPoster
Leveraging Skills from Unlabeled Prior Data for Efficient Online ExplorationPoster
Leveraging Sparsity for Sample-Efficient Preference Learning: A Theoretical PerspectivePoster
LieRE: Lie Rotational Positional EncodingsPoster
Liger: Linearizing Large Language Models to Gated Recurrent StructuresPoster
LightGTS: A Lightweight General Time Series Forecasting ModelPoster
Lightweight Protocols for Distributed Private Quantile EstimationSpotlight
Lightweight-Mark: Rethinking Deep Learning-Based WatermarkingPoster
LineFlow: A Framework to Learn Active Control of Production LinesPoster
Linear $Q$-Learning Does Not Diverge in $L^2$: Convergence Rates to a Bounded SetPoster
Linear Bandits with Partially Observable FeaturesPoster
Linear Mode Connectivity between Multiple Models modulo Permutation SymmetriesPoster
Linear Transformers as VAR Models: Aligning Autoregressive Attention Mechanisms with Autoregressive ForecastingPoster
Linear convergence of Sinkhorn's algorithm for generalized static Schrödinger bridgePoster
LipsNet++: Unifying Filter and Controller into a Policy NetworkSpotlight
LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and ModelsPoster
LoRA-Gen: Specializing Large Language Model via Online LoRA GenerationPoster
LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and EfficientlyOral
Local Identifying Causal Relations in the Presence of Latent VariablesSpotlight
Local Manifold Approximation and Projection for Manifold-Aware Diffusion PlanningPoster
Local Pan-privacy for Federated AnalyticsPoster
Locality Preserving Markovian Transition for Instance RetrievalPoster
Log-Sum-Exponential Estimator for Off-Policy Evaluation and LearningSpotlight
Logits are All We Need to Adapt Closed ModelsPoster
Long-Short Alignment for Effective Long-Context Modeling in LLMsPoster
LongRoPE2: Near-Lossless LLM Context Window ScalingPoster
Loss Functions and Operators Generated by f-DivergencesPoster
LotteryCodec: Searching the Implicit Representation in a Random Network for Low-Complexity Image CompressionSpotlight
Low-Rank Adapting Models for Sparse AutoencodersPoster
Low-Rank Tensor Transitions (LoRT) for Transferable Tensor RegressionPoster
Low-Rank ThinningPoster
Low-distortion and GPU-compatible Tree Embeddings in Hyperbolic SpacePoster
LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 BitsPoster
M+: Extending MemoryLLM with Scalable Long-Term MemoryPoster
M2PDE: Compositional Generative Multiphysics and Multi-component PDE SimulationPoster
M3-JEPA: Multimodal Alignment via Multi-gate MoE based on the Joint-Embedding Predictive ArchitecturePoster
MA-LoT: Model-Collaboration Lean-based Long Chain-of-Thought Reasoning enhances Formal Theorem ProvingPoster
MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spacesPoster
MAPLE: Many-Shot Adaptive Pseudo-Labeling for In-Context LearningPoster
MARGE: Improving Math Reasoning with Guided ExplorationPoster
MASS: Mathematical Data Selection via Skill Graphs for Pretraining Large Language ModelsPoster
MATS: An Audio Language Model under Text-only SupervisionPoster
MCU: An Evaluation Framework for Open-Ended Game AgentsSpotlight
MDDM: Practical Message-Driven Generative Image Steganography Based on Diffusion ModelsPoster
MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI AgentsPoster
MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch TrainingPoster
MF-LAL: Drug Compound Generation Using Multi-Fidelity Latent Space Active LearningPoster
MGD$^3$ : Mode-Guided Dataset Distillation using Diffusion ModelsOral
MIB: A Mechanistic Interpretability BenchmarkPoster
MIPT: Multilevel Informed Prompt Tuning for Robust Molecular Property PredictionPoster
MIRROR: Make Your Object-Level Multi-View Generation More Consistent with Training-Free RectificationPoster
MITIGATING OVER-EXPLORATION IN LATENT SPACE OPTIMIZATION USING LESPoster
ML$^2$-GCL: Manifold Learning Inspired Lightweight Graph Contrastive LearningPoster
MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and EfficiencyPoster
MMInference: Accelerating Pre-filling for Long-Context Visual Language Models via Modality-Aware Permutation Sparse AttentionPoster
MODA: MOdular Duplex Attention for Multimodal Perception, Cognition, and Emotion UnderstandingSpotlight
MODULI: Unlocking Preference Generalization via Diffusion Models for Offline Multi-Objective Reinforcement LearningPoster
MOGIC: Metadata-infused Oracle Guidance for Improved Extreme ClassificationPoster
MP-Nav: Enhancing Data Poisoning Attacks against Multimodal LearningPoster
MPO: An Efficient Post-Processing Framework for Mixing Diverse Preference AlignmentPoster
MTL-UE: Learning to Learn Nothing for Multi-Task LearningPoster
MTSTRec: Multimodal Time-Aligned Shared Token RecommenderPoster
MUDDFormer: Breaking Residual Bottlenecks in Transformers via Multiway Dynamic Dense ConnectionsPoster
MVA: Linear Attention with High-order Query-Keys Integration and Multi-level Vocabulary DecompositionPoster
Machine Learning meets Algebraic Combinatorics: A Suite of Datasets Capturing Research-level Conjecturing Ability in Pure MathematicsOral
Mahalanobis++: Improving OOD Detection via Feature NormalizationPoster
Maintaining Proportional Committees with Dynamic Candidate SetsPoster
Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization AlignmentPoster
Making Hard Problems Easier with Custom Data Distributions and Loss Regularization: A Case Study in Modular ArithmeticPoster
MapEval: A Map-Based Evaluation of Geo-Spatial Reasoning in Foundation ModelsSpotlight
Mask-Enhanced Autoregressive Prediction: Pay Less Attention to Learn MorePoster
MaskTwins: Dual-form Complementary Masking for Domain-Adaptive Image SegmentationPoster
Masked Generative Nested Transformers with Decode Time ScalingPoster
Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision TransformerPoster
Mastering Multiple-Expert Routing: Realizable $H$-Consistency and Strong Guarantees for Learning to DeferPoster
Matrix Completion with Incomplete Side Information via Orthogonal Complement ProjectionPoster
Maximizing Intermediate Checkpoint Value in LLM Pretraining with Bayesian OptimizationPoster
Maximum Coverage in Turnstile Streams with Applications to Fingerprinting MeasuresPoster
Maximum Entropy Reinforcement Learning with Diffusion PolicyPoster
Maximum Total Correlation Reinforcement LearningPoster
Maximum Update Parametrization and Zero-Shot Hyperparameter Transfer for Fourier Neural OperatorsPoster
Measuring Diversity in Synthetic DatasetsPoster
Measuring In-Context Computation Complexity via Hidden State PredictionPoster
Measuring Representational Shifts in Continual Learning: A Linear Transformation PerspectivePoster
Measuring Variable Importance in Heterogeneous Treatment Effects with ConfidencePoster
MemFreezing: A Novel Adversarial Attack on Temporal Graph Neural Networks under Limited Future KnowledgePoster
Memorization Sinks: Isolating Memorization during LLM TrainingPoster
Merge-Friendly Post-Training Quantization for Multi-Target Domain AdaptationPoster
Meta Optimality for Demographic Parity Constrained Regression via Post-ProcessingPoster
Meta-Reinforcement Learning with Adaptation from Human Feedback via Preference-Order-Preserving Task EmbeddingPoster
MetaAgent: Automatically Constructing Multi-Agent Systems Based on Finite State MachinesPoster
MetricEmbedding: Accelerate Metric Nearness by Tropical Inner ProductPoster
Mind the Gap: A Practical Attack on GGUF QuantizationPoster
Mind the Gap: a Spectral Analysis of Rank Collapse and Signal Propagation in Attention LayersPoster
MindAligner: Explicit Brain Functional Alignment for Cross-Subject Visual Decoding from Limited fMRI DataPoster
MindCustomer: Multi-Context Image Generation Blended with Brain SignalPoster
MindLLM: A Subject-Agnostic and Versatile Model for fMRI-to-text DecodingPoster
Minerva: A Programmable Memory Test Benchmark for Language ModelsPoster
Minimalist Concept Erasure in Generative ModelsPoster
Minimax Optimal Regret Bound for Reinforcement Learning with Trajectory FeedbackPoster
Minimum Width for Universal Approximation using Squashable Activation FunctionsPoster
Mirror, Mirror of the Flow: How Does Regularization Shape Implicit Bias?Poster
MissScore: High-Order Score Estimation in the Presence of Missing DataPoster
Mitigating Local Cohesion and Global Sparseness in Graph Contrastive Learning with Fuzzy BoundariesPoster
Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded GuidanceSpotlight
Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving SparsificationPoster
Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing ChurnPoster
MixBridge: Heterogeneous Image-to-Image Backdoor Attack through Mixture of Schrödinger BridgesPoster
MixMin: Finding Data Mixtures via Convex MinimizationPoster
Mixture of Experts Made Intrinsically InterpretablePoster
Mixture of Experts Provably Detect and Learn the Latent Cluster Structure in Gradient-Based LearningPoster
Mixture of Hidden-Dimensions: Not All Hidden-States’ Dimensions are Needed in TransformerPoster
Mixture of Lookup ExpertsOral
MoEQuant: Enhancing Quantization for Mixture-of-Experts Large Language Models via Expert-Balanced Sampling and Affinity GuidancePoster
MoMa: Modulating Mamba for Adapting Image Foundation Models to Video RecognitionPoster
MoRAgent: Parameter Efficient Agent Tuning with Mixture-of-RolesPoster
Modalities Contribute Unequally: Enhancing Medical Multi-modal Learning through Adaptive Modality Token Re-balancingPoster
Model Immunization from a Condition Number PerspectiveOral
Model Steering: Learning with a Reference Model Improves Generalization Bounds and Scaling LawsSpotlight
Model Uncertainty Quantification by Conformal Prediction in Continual LearningPoster
Modeling All-Atom Glycan Structures via Hierarchical Message Passing and Multi-Scale Pre-trainingPoster
Models of Heavy-Tailed Mechanistic UniversalityPoster
Modified K-means Algorithm with Local Optimality GuaranteesPoster
Modularized Self-Reflected Video Reasoner for Multimodal LLM with Application to Video Question AnsweringPoster
Modulated Diffusion: Accelerating Generative Modeling with Modulated QuantizationPoster
Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of ExpertsPoster
Momentum-Driven Adaptivity: Towards Tuning-Free Asynchronous Federated LearningPoster
More Than Meets the Eye: Enhancing Multi-Object Tracking Even with Prolonged OcclusionsPoster
Morse: Dual-Sampling for Lossless Acceleration of Diffusion ModelsPoster
Multi-Armed Bandits with Interference: Bridging Causal Inference and Adversarial BanditsPoster
Multi-Marginal Stochastic Flow Matching for High-Dimensional Snapshot Data at Irregular Time PointsPoster
Multi-Modal Object Re-identification via Sparse Mixture-of-ExpertsPoster
Multi-Stage Manipulation with Demonstration-Augmented Reward, Policy, and World Model LearningPoster
Multi-Timescale Dynamics Model Bayesian Optimization for Plasma Stabilization in TokamaksPoster
Multi-Turn Code Generation Through Single-Step RewardsSpotlight
Multi-View Graph Clustering via Node-Guided Contrastive EncodingPoster
Multi-band Frequency Reconstruction for Neural Psychoacoustic CodingPoster
Multi-objective Linear Reinforcement Learning with Lexicographic RewardsPoster
MultiPDENet: PDE-embedded Learning with Multi-time-stepping for Accelerated Flow SimulationPoster
Multiaccuracy and Multicalibration via Proxy GroupsPoster
Multidimensional Adaptive Coefficient for Inference Trajectory Optimization in Flow and DiffusionPoster
Multilayer Matrix Factorization via Dimension-Reducing Diffusion Variational InferencePoster
Multinoulli Extension: A Lossless Yet Effective Probabilistic Framework for Subset Selection over Partition ConstraintsPoster
Multiobjective distribution matchingPoster
Multivariate Conformal SelectionPoster
MuseControlLite: Multifunctional Music Generation with Lightweight ConditionersPoster
Mutual Learning for SAM Adaptation: A Dual Collaborative Network Framework for Source-Free Domain TransferPoster
MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-DesignPoster
M³HF: Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed QualityPoster
N2GON: Neural Networks for Graph-of-Net with Position AwarenessPoster
NEAR: Neural Electromagnetic Array ResponsePoster
NICE Data Selection for Instruction Tuning in LLMs with Non-differentiable Evaluation MetricPoster
NMA-tune: Generating Highly Designable and Dynamics Aware Protein BackbonesPoster
NTK-DFL: Enhancing Decentralized Federated Learning in Heterogeneous Settings via Neural Tangent KernelPoster
NTPP: Generative Speech Language Modeling for Dual-Channel Spoken Dialogue via Next-Token-Pair PredictionPoster
Natural Perturbations for Black-box Training of Neural Networks by Zeroth-Order OptimizationPoster
Navigating Conflicting Views: Harnessing Trust for LearningPoster
Navigating Semantic Drift in Task-Agnostic Class-Incremental LearningOral
Navigating the Social Welfare Frontier: Portfolios for Multi-objective Reinforcement LearningPoster
Near Optimal Best Arm Identification for Clustered BanditsPoster
Near Optimal Non-asymptotic Sample Complexity of 1-IdentificationPoster
Near-Optimal Consistency-Robustness Trade-Offs for Learning-Augmented Online Knapsack ProblemsPoster
Near-Optimal Decision Trees in a SPLIT SecondOral
Near-optimal Sketchy Natural Gradients for Physics-Informed Neural NetworksPoster
Nearly Optimal Sample Complexity for Learning with Label ProportionsPoster
NegMerge: Sign-Consensual Weight Merging for Machine UnlearningPoster
Neighbour-Driven Gaussian Process Variational Autoencoders for Scalable Structured Latent ModellingPoster
Nemotron-CORTEXA: Enhancing LLM Agents for Software Engineering Tasks via Improved Localization and Solution DiversityPoster
NestQuant: nested lattice quantization for matrix products and LLMsPoster
Nesterov Method for Asynchronous Pipeline Parallel OptimizationPoster
Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement LearningOral
Neural Collapse Beyond the Unconstrained Features Model: Landscape, Dynamics, and Generalization in the Mean-Field RegimeSpotlight
Neural Event-Triggered Control with Optimal SchedulingPoster
Neural Graph Matching Improves Retrieval Augmented Generation in Molecular Machine LearningPoster
Neural Guided Diffusion BridgesPoster
Neural Interpretable PDEs: Harmonizing Fourier Insights with Attention for Scalable and Interpretable Physics DiscoveryPoster
Neural Representational Consistency Emerges from Probabilistic Neural-Behavioral Representation AlignmentPoster
Neural Solver Selection for Combinatorial OptimizationPoster
NeuralCohort: Cohort-aware Neural Representation Learning for Healthcare AnalyticsPoster
NeuroTree: Hierarchical Functional Brain Pathway Decoding for Mental Health DisordersPoster
NeuronTune: Towards Self-Guided Spurious Bias MitigationPoster
Neurosymbolic World Models for Sequential Decision MakingPoster
Neutral residues: revisiting adapters for model extensionPoster
New Bounds for Sparse Variational Gaussian ProcessesSpotlight
NextCoder: Robust Adaptation of Code LMs to Diverse Code EditsPoster
No Free Lunch from Random Feature Ensembles: Scaling Laws and Near-Optimality ConditionsPoster
No Metric to Rule Them All: Toward Principled Evaluations of Graph-Learning DatasetsPoster
No Soundness in the Real World: On the Challenges of the Verification of Deployed Neural NetworksSpotlight
Noise Conditional Variational Score DistillationPoster
Noise-Guided Predicate Representation Extraction and Diffusion-Enhanced Discretization for Scene Graph GenerationPoster
Noisy SIGNSGD Is More Differentially Private Than You (Might) ThinkPoster
Non-Asymptotic Length GeneralizationPoster
Non-Asymptotic and Non-Lipschitzian Bounds on Optimal Values in Stochastic Optimization Under Heavy TailsPoster
Non-Stationary Predictions May Be More Informative: Exploring Pseudo-Labels with a Two-Phase Pattern of Training DynamicsPoster
Non-asymptotic Error Bounds in $\mathcal{W}_2$-Distance with Sqrt(d) Dimension Dependence and First Order Convergence for Langevin Monte Carlo beyond Log-ConcavityPoster
Non-stationary Diffusion For Probabilistic Time Series ForecastingSpotlight
Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via MixabilityPoster
Nonconvex Theory of $M$-estimators with Decomposable RegularizersPoster
Nonlinear transformers can perform inference-time feature learningPoster
Nonparametric Identification of Latent ConceptsPoster
Not All Tokens Matter All The Time: Dynamic Token Aggregation Towards Efficient Detection TransformersPoster
Not All Wrong is Bad: Using Adversarial Examples for UnlearningSpotlight
Not all solutions are created equal: An analytical dissociation of functional and representational similarity in deep linear neural networksSpotlight
Novelty Detection in Reinforcement Learning with World ModelsSpotlight
O-MAPL: Offline Multi-agent Preference LearningPoster
OV-MER: Towards Open-Vocabulary Multimodal Emotion RecognitionPoster
OW-VAP: Visual Attribute Parsing for Open World Object DetectionPoster
Occult: Optimizing Collaborative Communications across Experts for Accelerated Parallel MoE Training and InferencePoster
Of Mice and Machines: A Comparison of Learning Between Real World Mice and RL AgentsPoster
Off-Policy Actor-Critic for Adversarial Observation Robustness: Virtual Alternative Training via Symmetric Policy EvaluationPoster
Off-Policy Evaluation under Nonignorable Missing DataPoster
Offline Model-based Optimization for Real-World Molecular DiscoveryPoster
Offline Opponent Modeling with Truncated Q-driven Instant Policy RefinementPoster
Offline-to-Online Reinforcement Learning with Classifier-Free Diffusion GenerationPoster
Olica: Efficient Structured Pruning of Large Language Models without RetrainingPoster
OmiAD: One-Step Adaptive Masked Diffusion Model for Multi-class Anomaly Detection via Adversarial DistillationPoster
Omni-Angle Assault: An Invisible and Powerful Physical Adversarial Attack on Face RecognitionPoster
OmniArch: Building Foundation Model for Scientific ComputingPoster
OmniAudio: Generating Spatial Audio from 360-Degree VideoPoster
OmniBal: Towards Fast Instruction-Tuning for Vision-Language Models via Omniverse Computation BalancePoster
On Differential Privacy for Adaptively Solving Search Problems via SketchingOral
On Efficient Estimation of Distributional Treatment Effects under Covariate-Adaptive RandomizationPoster
On Exact Bit-level Reversible Transformers Without Changing ArchitecturePoster
On Explaining Equivariant Graph Networks via Improved Relevance PropagationPoster
On Fine-Grained Distinct Element EstimationPoster
On Learning Parallel Pancakes with Mostly Uniform WeightsSpotlight
On Measuring Long-Range Interactions in Graph Neural NetworksPoster
On Mitigating Affinity Bias through Bandits with Evolving Biased FeedbackPoster
On Path to Multimodal Generalist: General-Level and General-BenchOral
On Teacher Hacking in Language Model DistillationPoster
On The Concurrence of Layer-wise Preconditioning Methods and Provable Feature LearningPoster
On Understanding Attention-Based In-Context Learning for Categorical DataPoster
On the Adversarial Robustness of Multi-Kernel ClusteringPoster
On the Alignment between Fairness and Accuracy: from the Perspective of Adversarial RobustnessPoster
On the Clean Generalization and Robust Overfitting in Adversarial Training from Two Theoretical Views: Representation Complexity and Training DynamicsPoster
On the Convergence of Continuous Single-timescale Actor-criticPoster
On the Diversity of Adversarial Ensemble LearningPoster
On the Duality between Gradient Transformations and AdaptersPoster
On the Dynamic Regret of Following the Regularized Leader: Optimism with History PruningPoster
On the Emergence of Position Bias in TransformersPoster
On the Generalization Ability of Next-Token-Prediction PretrainingPoster
On the Guidance of Flow MatchingSpotlight
On the Impact of Performative Risk Minimization for Binary Random VariablesPoster
On the Importance of Gaussianizing RepresentationsPoster
On the Interplay between Graph Structure and Learning Algorithms in Graph Neural NetworksPoster
On the Learnability of Distribution Classes with Adaptive AdversariesPoster
On the Out-of-Distribution Generalization of Self-Supervised LearningPoster
On the Power of Learning-Augmented Search TreesPoster
On the Private Estimation of Smooth Transport MapsPoster
On the Provable Separation of Scales in Maximal Update ParameterizationPoster
On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty AgentsPoster
On the Robustness of Reward Models for Language Model AlignmentPoster
On the Role of Label Noise in the Feature Learning ProcessPoster
On the Similarities of Embeddings in Contrastive LearningPoster
On the Statistical Mechanisms of Distributional Compositional GeneralizationPoster
On the Tension between Byzantine Robustness and No-Attack Accuracy in Distributed LearningSpotlight
On the Training Convergence of Transformers for In-Context Classification of Gaussian MixturesPoster
On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention for Long-Context LLM ServingPoster
One Arrow, Two Hawks: Sharpness-aware Minimization for Federated Learning via Global Model TrajectoryPoster
One Diffusion Step to Real-World Super-Resolution via Flow Trajectory DistillationPoster
One Image is Worth a Thousand Words: A Usability Preservable Text-Image Collaborative Erasing FrameworkPoster
One Leaf Reveals the Season: Occlusion-Based Contrastive Learning with Semantic-Aware Views for Efficient Visual RepresentationPoster
One Stone, Two Birds: Enhancing Adversarial Defense Through the Lens of Distributional DiscrepancyPoster
One Wave To Explain Them All: A Unifying Perspective On Feature AttributionPoster
One-Pass Feature Evolvable Learning with Theoretical GuaranteesPoster
One-Shot Heterogeneous Federated Learning with Local Model-Guided Diffusion ModelsPoster
One-Step Generalization Ratio Guided Optimization for Domain GeneralizationOral
One-dimensional Path ConvolutionPoster
Online Clustering of Dueling BanditsPoster
Online Conformal Prediction via Online OptimizationPoster
Online Curvature-Aware Replay: Leveraging $\mathbf{2^{nd}}$ Order Information for Online Continual LearningPoster
Online Detection of LLM-Generated Texts via Sequential Hypothesis Testing by BettingPoster
Online Differentially Private Conformal Prediction for Uncertainty QuantificationPoster
Online Episodic Convex Reinforcement LearningPoster
Online Laplacian-Based Representation Learning in Reinforcement LearningPoster
Online Learning in Risk Sensitive constrained MDPPoster
Online Learning in the Random-Order ModelPoster
Online Linear Classification with Massart NoisePoster
Online Pre-Training for Offline-to-Online Reinforcement LearningPoster
Online Robust Reinforcement Learning Through Monte-Carlo PlanningPoster
Online Sparsification of Bipartite-Like Clusters in GraphsPoster
Open Materials Generation with Stochastic InterpolantsPoster
Open Your Eyes: Vision Enhances Message Passing Neural Networks in Link PredictionPoster
Open-Det: An Efficient Learning Framework for Open-Ended DetectionPoster
OpenworldAUC: Towards Unified Evaluation and Optimization for Open-world Prompt TuningPoster
Optimal Algorithm for Max-Min Fair BanditPoster
Optimal Auction Design in the Joint AdvertisingPoster
Optimal Decision Tree Pruning Revisited: Algorithms and ComplexityPoster
Optimal Fair Learning Robust to Adversarial Distribution ShiftPoster
Optimal Information Retention for Time-Series ExplanationsPoster
Optimal Sensor Scheduling and Selection for Continuous-Discrete Kalman Filtering with Auxiliary DynamicsPoster
Optimal Survey Design for Private Mean EstimationPoster
Optimal Transfer Learning for Missing Not-at-Random Matrix CompletionPoster
Optimal and Practical Batched Linear Bandit AlgorithmPoster
Optimistic Algorithms for Adaptive Estimation of the Average Treatment EffectPoster
Optimization Proxies using Limited Labeled Data and Training Time -- A Semi-Supervised Bayesian Neural Network ApproachPoster
Optimization for Neural Operators can Benefit from WidthPoster
Optimization over Sparse Support-Preserving Sets: Two-Step Projection with Global Optimality GuaranteesPoster
Optimizing Language Models for Inference Time Objectives using Reinforcement LearningPoster
Optimizing Noise Distributions for Differential PrivacyPoster
Optimizing Robustness and Accuracy in Mixture of Experts: A Dual-Model ApproachPoster
Optimizing Social Network Interventions via Hypergradient-Based Recommender System DesignPoster
Oracle-MoE: Locality-preserving Routing in the Oracle Space for Memory-constrained Large Language Model InferencePoster
Organize the Web: Constructing Domains Enhances Pre-Training Data CurationPoster
Origin Identification for Text-Guided Image-to-Image Diffusion ModelsPoster
OrthoRank: Token Selection via Sink Token Orthogonality for Efficient LLM inferencePoster
Orthogonal Subspace Decomposition for Generalizable AI-Generated Image DetectionOral
Otter: Generating Tests from Issues to Validate SWE PatchesPoster
Outlier-Aware Post-Training Quantization for Discrete Graph Diffusion ModelsPoster
Outsourced Diffusion Sampling: Efficient Posterior Inference in Latent Spaces of Generative ModelsPoster
Overcoming Multi-step Complexity in Multimodal Theory-of-Mind Reasoning: A Scalable Bayesian PlannerSpotlight
Overcoming Non-monotonicity in Transducer-based Streaming GenerationPoster
Overcoming Spurious Solutions in Semi-Dual Neural Optimal Transport: A Smoothing Approach for Learning the Optimal Transport PlanPoster
Overcoming Vocabulary Mismatch: Vocabulary-agnostic Teacher Guided Language ModelingPoster
Overestimation in LLM Evaluation: A Controlled Large-Scale Study on Data Contamination’s Impact on Machine TranslationPoster
PAC Learning with ImprovementsPoster
PAC-Bayes Analysis for Recalibration in ClassificationPoster
PANDAS: Improving Many-shot Jailbreaking via Positive Affirmation, Negative Demonstration, and Adaptive SamplingSpotlight
PARM: Multi-Objective Test-Time Alignment via Preference-Aware Autoregressive Reward ModelPoster
PARQ: Piecewise-Affine Regularized QuantizationPoster
PASS: Private Attributes Protection with Stochastic Data SubstitutionSpotlight
PCEvolve: Private Contrastive Evolution for Synthetic Dataset Generation via Few-Shot Private Data and Generative APIsSpotlight
PDE-Transformer: Efficient and Versatile Transformers for Physics SimulationsPoster
PDUDT: Provable Decentralized Unlearning under Dynamic TopologiesPoster
PEAKS: Selecting Key Training Examples Incrementally via Prediction Error Anchored by Kernel SimilarityPoster
PEINR: A Physics-enhanced Implicit Neural Representation for High-Fidelity Flow Field ReconstructionPoster
PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting for Novel View SynthesisPoster
PIGDreamer: Privileged Information Guided World Models for Safe Partially Observable Reinforcement LearningPoster
PINNsAgent: Automated PDE Surrogation with Large Language ModelsPoster
PIPA: Preference Alignment as Prior-Informed Statistical EstimationPoster
PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by Watching Stuff DropPoster
POQD: Performance-Oriented Query Decomposer for Multi-vector retrievalPoster
PPDiff: Diffusing in Hybrid Sequence-Structure Space for Protein-Protein Complex DesignPoster
PRIME: Deep Imbalanced Regression with ProxiesPoster
PROTOCOL: Partial Optimal Transport-enhanced Contrastive Learning for Imbalanced Multi-view ClusteringPoster
PROXSPARSE: REGULARIZED LEARNING OF SEMI-STRUCTURED SPARSITY MASKS FOR PRETRAINED LLMSPoster
PTTA: Purifying Malicious Samples for Test-Time Model AdaptationPoster
Pairwise Maximum Likelihood For Multi-Class Logistic Regression Model With Multiple Rare ClassesPoster
Parallel Simulation for Log-concave Sampling and Score-based Diffusion ModelsSpotlight
ParallelComp: Parallel Long-Context Compressor for Length ExtrapolationPoster
Pareto Merging: Multi-Objective Optimization for Preference-Aware Model MergingPoster
Pareto-Optimal Fronts for Benchmarking Symbolic Regression AlgorithmsPoster
Pareto-Optimality, Smoothness, and Stochasticity in Learning-Augmented One-Max-SearchPoster
Pareto-frontier Entropy Search with Variational Lower Bound MaximizationPoster
Partially Observable Reinforcement Learning with Memory TracesPoster
Partition First, Embed Later: Laplacian-Based Feature Partitioning for Refined Embedding and Visualization of High-Dimensional DataOral
Patch-wise Structural Loss for Time Series ForecastingPoster
PatchPilot: A Cost-Efficient Software Engineering Agent with Early Attempts on Formal VerificationPoster
Penalizing Infeasible Actions and Reward Scaling in Reinforcement Learning with Offline DataSpotlight
Perceptual-GS: Scene-adaptive Perceptual Densification for Gaussian SplattingPoster
Perceptually Constrained Precipitation Nowcasting ModelPoster
Peri-LN: Revisiting Normalization Layer in the Transformer ArchitecturePoster
Peripheral Memory for LLMs: Integration of Sequential Memory Banks with Adaptive QueryingPoster
Permutation-Free High-Order Interaction TestsPoster
Permutation-based Rank Test in the Presence of Discretization and Application in Causal Discovery with Mixed DataPoster
Pessimism Principle Can Be Effective: Towards a Framework for Zero-Shot Transfer Reinforcement LearningPoster
Pfeife: Automatic Pipeline Parallelism for PyTorchPoster
Phase and Amplitude-aware Prompting for Enhancing Adversarial RobustnessPoster
Phase transitions for the existence of unregularized M-estimators in single index modelsPoster
PhySpec: Physically Consistent Spectral Reconstruction via Orthogonal Subspace Decomposition and Self-Supervised Meta-Auxiliary LearningSpotlight
Physics Aware Neural Networks for Unsupervised Binding Energy PredictionPoster
Physics-Informed DeepONets for drift-diffusion on metric graphs: simulation and parameter identificationPoster
Physics-Informed Weakly Supervised Learning For Interatomic PotentialsPoster
Physics-informed Temporal Alignment for Auto-regressive PDE Foundation ModelsPoster
PiD: Generalized AI-Generated Images Detection with Pixelwise Decomposition ResidualsPoster
PieClam: A Universal Graph Autoencoder Based on Overlapping Inclusive and Exclusive CommunitiesPoster
Piloting Structure-Based Drug Design via Modality-Specific Optimal SchedulePoster
PipeOffload: Improving Scalability of Pipeline Parallelism with Memory OptimizationPoster
Pivoting Factorization: A Compact Meta Low-Rank Representation of Sparsity for Efficient Inference in Large Language ModelsPoster
Pixel-level Certified Explanations via Randomized SmoothingPoster
Pixel2Feature Attack (P2FA): Rethinking the Perturbed Space to Enhance Adversarial TransferabilityPoster
Plan-and-Act: Improving Planning of Agents for Long-Horizon TasksPoster
Plausible Token Amplification for Improving Accuracy of Differentially Private In-Context Learning Based on Implicit Bayesian InferencePoster
Playmate: Flexible Control of Portrait Animation via 3D-Implicit Space Guided DiffusionPoster
Point Cloud Dataset DistillationPoster
Pointwise Information Measures as Confidence Estimators in Deep Neural Networks: A Comparative StudyPoster
PoisonBench: Assessing Language Model Vulnerability to Poisoned Preference DataPoster
PoisonedEye: Knowledge Poisoning Attack on Retrieval-Augmented Generation based Large Vision-Language ModelsPoster
PokéChamp: an Expert-level Minimax Language AgentSpotlight
Policy Filtration for RLHF to Mitigate Noise in Reward ModelsPoster
Policy Gradient with Tree ExpansionPoster
Policy Optimization for CMDPs with Bandit Feedback: Learning Stochastic and Adversarial ConstraintsPoster
Policy Regularization on Globally Accessible States in Cross-Dynamics Reinforcement LearningSpotlight
Policy-Regret Minimization in Markov Games with Function ApproximationPoster
Policy-labeled Preference Learning: Is Preference Enough for RLHF?Spotlight
Poly2Vec: Polymorphic Fourier-Based Encoding of Geospatial Objects for GeoAI ApplicationsPoster
Polynomial-Delay MAG Listing with Novel Locally Complete Orientation RulesOral
Polynomial-Time Approximability of Constrained Reinforcement LearningPoster
Position: A Theory of Deep Learning Must Include Compositional SparsityPoster
Position: AI Agents Need Authenticated DelegationOral
Position: AI Competitions Provide the Gold Standard for Empirical Rigor in GenAI EvaluationOral
Position: AI Evaluation Should Learn from How We Test HumansPoster
Position: AI Safety Must Embrace an Antifragile PerspectivePoster
Position: AI Safety should prioritize the Future of WorkOral
Position: AI Scaling: From Up to Down and OutPoster
Position: AI's growing due process problemPoster
Position: Algebra Unveils Deep Learning - An Invitation to Neuroalgebraic GeometrySpotlight
Position: All Current Generative Fidelity and Diversity Metrics are FlawedPoster
Position: An Empirically Grounded Identifiability Theory Will Accelerate Self Supervised Learning ResearchPoster
Position: Beyond Assistance – Reimagining LLMs as Ethical and Adaptive Co-Creators in Mental Health CarePoster
Position: Build Agent Advocates, Not Platform AgentsPoster
Position: Causal Machine Learning Requires Rigorous Synthetic Experiments for Broader AdoptionPoster
Position: Certified Robustness Does Not (Yet) Imply Model SecurityOral
Position: Challenges and Future Directions of Data-Centric AI AlignmentPoster
Position: Constants are Critical in Regret Bounds for Reinforcement LearningPoster
Position: Contextual Integrity is Inadequately Applied to Language ModelsPoster
Position: Current Model Licensing Practices are Dragging Us into a Quagmire of Legal NoncomplianceOral
Position: Democratic AI is Possible. The Democracy Levels Framework Shows How It Might Work.Poster
Position: Don't Use the CLT in LLM Evals With Fewer Than a Few Hundred DatapointsSpotlight
Position: Enough of Scaling LLMs! Lets Focus on DownscalingPoster
Position: Evaluating Generative AI Systems Is a Social Science Measurement ChallengePoster
Position: Explainable AI Cannot Advance Without Better User StudiesPoster
Position: Formal Mathematical Reasoning—A New Frontier in AISpotlight
Position: Future Research and Challenges Remain Towards AI for Software EngineeringPoster
Position: General Intelligence Requires Reward-based PretrainingSpotlight
Position: Generative AI Regulation Can Learn from Social Media RegulationOral
Position: Graph Matching Systems Deserve Better BenchmarksPoster
Position: Human Baselines in Model Evaluations Need Rigor and Transparency (With Recommendations & Reporting Checklist)Spotlight
Position: Humanity Faces Existential Risk from Gradual DisempowermentPoster
Position: In-House Evaluation Is Not Enough. Towards Robust Third-Party Evaluation and Flaw Disclosure for General-Purpose AISpotlight
Position: It Is Time We Test Neural Computation In VitroPoster
Position: Iterative Online-Offline Joint Optimization is Needed to Manage Complex LLM Copyright RisksPoster
Position: LLMs Need a Bayesian Meta-Reasoning Framework for More Robust and Generalizable ReasoningPoster
Position: Lifetime tuning is incompatible with continual reinforcement learningPoster
Position: Machine Learning Models Have a Supply Chain ProblemPoster
Position: Not All Explanations for Deep Learning Phenomena Are Equally ValuableOral
Position: Political Neutrality in AI Is Impossible — But Here Is How to Approximate ItOral
Position: Principles of Animal Cognition to Improve LLM EvaluationsOral
Position: Probabilistic Modelling is Sufficient for Causal InferenceOral
Position: Rethinking Explainable Machine Learning as Applied StatisticsPoster
Position: Rethinking LLM Bias Probing Using Lessons from the Social SciencesSpotlight
Position: Retrieval-augmented systems can be dangerous medical communicatorsPoster
Position: Societal Impacts Research Requires Benchmarks for Creative Composition TasksPoster
Position: Solve Layerwise Linear Models First to Understand Neural Dynamical Phenomena (Neural Collapse, Emergence, Lazy/Rich Regime, and Grokking)Poster
Position: Spectral GNNs Rely Less on Graph Fourier Basis than ConceivedPoster
Position: Stop treating `AGI' as the north-star goal of AI researchPoster
Position: Strong Consumer Protection is an Inalienable Defense for AI Safety in the United StatesPoster
Position: Supervised Classifiers Answer the Wrong Questions for OOD DetectionPoster
Position: The AI Conference Peer Review Crisis Demands Author Feedback and Reviewer RewardsOral
Position: The Artificial Intelligence and Machine Learning Community Should Adopt a More Transparent and Regulated Peer Review ProcessPoster
Position: The Categorization of Race in ML is a Flawed PremiseSpotlight
Position: The Future of Bayesian Prediction Is Prior-FittedPoster
Position: The Most Expensive Part of an LLM *should* be its Training DataPoster
Position: The Right to AIPoster
Position: Theory of Mind Benchmarks are Broken for Large Language ModelsPoster
Position: Truly Self-Improving Agents Require Intrinsic Metacognitive LearningPoster
Position: Trustworthy AI Agents Require the Integration of Large Language Models and Formal MethodsPoster
Position: Uncertainty Quantification Needs Reassessment for Large Language Model AgentsPoster
Position: We Can’t Understand AI Using our Existing VocabularySpotlight
Position: We Need An Algorithmic Understanding of Generative AISpotlight
Position: We Need Responsible, Application-Driven (RAD) AI ResearchPoster
Position: When Incentives Backfire, Data Stops Being HumanPoster
Position: You Can't Manufacture a NeRFPoster
Positional Attention: Expressivity and Learnability of Algorithmic ComputationPoster
Positional Encoding meets Persistent Homology on GraphsPoster
Positive-unlabeled AUC Maximization under Covariate ShiftPoster
Potemkin Understanding in Large Language ModelsPoster
Power Mean Estimation in Stochastic Continuous Monte-Carlo Tree SearchPoster
Pre-Training Graph Contrastive Masked Autoencoders are Strong Distillers for EEGPoster
Pre-training Auto-regressive Robotic Models with 4D RepresentationsPoster
Preconditioned Riemannian Gradient Descent Algorithm for Low-Multilinear-Rank Tensor CompletionPoster
Predicting High-precision Depth on Low-Precision Devices Using 2D Hilbert CurvesPoster
Predicting mutational effects on protein binding from folding energyPoster
Predicting the Susceptibility of Examples to Catastrophic ForgettingPoster
Prediction models that learn to avoid missing valuesSpotlight
Prediction via Shapley Value RegressionPoster
Prediction-Aware Learning in Multi-Agent SystemsPoster
Prediction-Powered E-ValuesPoster
Predictive Performance of Deep Quantum Data Re-uploading ModelsPoster
Preference Adaptive and Sequential Text-to-Image GenerationPoster
Preference Controllable Reinforcement Learning with Advanced Multi-Objective OptimizationPoster
Preference Learning for AI Alignment: a Causal PerspectivePoster
Preference Optimization for Combinatorial Optimization ProblemsPoster
Preference learning made easy: Everything should be understood through win ratePoster
Preference-CFR: Beyond Nash Equilibrium for Better Game StrategiesPoster
Preserving AUC Fairness in Learning with Noisy Protected GroupsPoster
Prices, Bids, Values: One ML-Powered Combinatorial Auction to Rule Them AllOral
Primal-Dual Neural Algorithmic ReasoningSpotlight
Primitive Vision: Improving Diagram Understanding in MLLMsPoster
Primphormer: Efficient Graph Transformers with Primal RepresentationsPoster
Principal-Agent Bandit Games with Self-Interested and Exploratory Learning AgentsPoster
Principled Algorithms for Optimizing Generalized Metrics in Binary ClassificationPoster
Prior Knowledge Guided Neural Architecture GenerationPoster
Privacy Amplification Through Synthetic Data: Insights from Linear RegressionPoster
Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series ForecastingSpotlight
Privacy Attacks on Image AutoRegressive ModelsPoster
Privacy-Preserving Federated Convex Optimization: Balancing Partial-Participation and Efficiency via Noise CancellationPoster
Privacy-Shielded Image Compression: Defending Against Exploitation from Vision-Language Pretrained ModelsPoster
Private Federated Learning using Preference-Optimized Synthetic DataPoster
Private Lossless Multiple ReleasePoster
Private Model Personalization RevisitedPoster
ProDiff: Prototype-Guided Diffusion for Minimal Information Trajectory ImputationPoster
ProSec: Fortifying Code LLMs with Proactive Security AlignmentPoster
Probabilistic Factorial Experimental Design for Combinatorial InterventionsSpotlight
Probabilistic Group Mask Guided Discrete Optimization for Incremental LearningPoster
Probabilistic Interactive 3D Segmentation with Hierarchical Neural ProcessesPoster
Probably Approximately Global Robustness CertificationPoster
Procurement Auctions via Approximately Optimal Submodular OptimizationSpotlight
Product of Experts with LLMs: Boosting Performance on ARC Is a Matter of PerspectivePoster
Progressive Tempering Sampler with DiffusionPoster
Progressively Label Enhancement for Large Language Model AlignmentPoster
Projection Optimization: A General Framework for Multi-Objective and Multi-Group RLHFPoster
Projection Pursuit Density Ratio EstimationPoster
Promoting Ensemble Diversity with Interactive Bayesian Distributional Robustness for Fine-tuning Foundation ModelsPoster
Prompt-based Depth Pruning of Large Language ModelsPoster
Prompt-to-Leaderboard: Prompt-Adaptive LLM EvaluationsPoster
ProofAug: Efficient Neural Theorem Proving via Fine-grained Proof Structure AnalysisPoster
Propagate and Inject: Revisiting Propagation-Based Feature Imputation for Graphs with Partially Observed FeaturesPoster
Propagation of Chaos for Mean-Field Langevin Dynamics and its Application to Model EnsemblePoster
Protein Structure Tokenization: Benchmarking and New RecipePoster
Proto Successor Measure: Representing the Behavior Space of an RL AgentPoster
Protriever: End-to-End Differentiable Protein Homology Search for Fitness PredictionPoster
Provable Benefit of Random Permutations over Uniform Sampling in Stochastic Coordinate DescentPoster
Provable Benefits of Unsupervised Pre-training and Transfer Learning via Single-Index ModelsSpotlight
Provable Efficiency of Guidance in Diffusion Models for General Data DistributionPoster
Provable In-Context Vector Arithmetic via Retrieving Task ConceptsPoster
Provable Length Generalization in Sequence Prediction via Spectral FilteringPoster
Provable Maximum Entropy Manifold Exploration via Diffusion ModelsPoster
Provable Policy Gradient for Robust Average-Reward MDPs Beyond RectangularityPoster
Provable Zero-Shot Generalization in Offline Reinforcement LearningPoster
Provable and Practical Online Learning Rate Adaptation with Hypergradient DescentPoster
Provably Cost-Sensitive Adversarial Defense via Randomized SmoothingPoster
Provably Efficient Algorithm for Best Scoring Rule Identification in Online Principal-Agent Information AcquisitionPoster
Provably Efficient RL for Linear MDPs under Instantaneous Safety Constraints in Non-Convex Feature SpacesPoster
Provably Improving Generalization of Few-shot models with Synthetic DataPoster
Provably Near-Optimal Federated Ensemble Distillation with Negligible OverheadPoster
Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without ForgettingPoster
Prune 'n Predict: Optimizing LLM Decision-making with Conformal PredictionPoster
Pruning for GNNs: Lower Complexity with Comparable ExpressivenessPoster
PyTDC: A multimodal machine learning training, evaluation, and inference platform for biomedical foundation modelsPoster
Q-Supervised Contrastive Representation: A State Decoupling Framework for Safe Offline Reinforcement LearningPoster
Q-VDiT: Towards Accurate Quantization and Distillation of Video-Generation Diffusion TransformersPoster
QEM-Bench: Benchmarking Learning-based Quantum Error Mitigation and QEMFormer as a Multi-ranged Context Learning BaselinePoster
QPRL : Learning Optimal Policies with Quasi-Potential Functions for Asymmetric TraversalPoster
QUTE: Quantifying Uncertainty in TinyML models with Early-exit-assisted ensembles for model-monitoringPoster
QoS-Efficient Serving of Multiple Mixture-of-Expert LLMs Using Partial Runtime ReconfigurationPoster
QuEST: Stable Training of LLMs with 1-Bit Weights and ActivationsPoster
QuEst: Enhancing Estimates of Quantile-Based Distributional Measures Using Model PredictionsPoster
QuRe: Query-Relevant Retrieval through Hard Negative Sampling in Composed Image RetrievalPoster
Quadratic Upper Bound for Boosting RobustnessPoster
Quadruple Attention in Many-body Systems for Accurate Molecular Property PredictionsPoster
Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space ModelsPoster
QuanONet: Quantum Neural Operator with Application to Differential EquationPoster
QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV CachePoster
Quantifying Memory Utilization with Effective State-SizePoster
Quantifying Prediction Consistency Under Fine-tuning Multiplicity in Tabular LLMsPoster
Quantifying Treatment Effects: Estimating Risk Ratios via Observational StudiesPoster
Quantum Algorithms for Finite-horizon Markov Decision ProcessesPoster
Quantum Optimization via Gradient-Based Hamiltonian DescentPoster
Quantum Speedup for Hypergraph SparsificationPoster
Quantum Speedups in Regret Analysis of Infinite Horizon Average-Reward Markov Decision ProcessesPoster
R*: Efficient Reward Design via Reward Structure Evolution and Parameter Alignment Optimization with Large Language ModelsPoster
R2-T2: Re-Routing in Test-Time for Multimodal Mixture-of-ExpertsPoster
R3DM: Enabling Role Discovery and Diversity Through Dynamics Models in Multi-agent Reinforcement LearningPoster
RAGGED: Towards Informed Design of Scalable and Stable RAG SystemsPoster
RAPID: Long-Context Inference with Retrieval-Augmented Speculative DecodingSpotlight
RATE: Causal Explainability of Reward Models with Imperfect CounterfactualsPoster
RBench: Graduate-level Multi-disciplinary Benchmarks for LLM & MLLM Complex Reasoning EvaluationPoster
RE-IMAGINE: Symbolic Benchmark Synthesis for Reasoning EvaluationPoster
REG: Rectified Gradient Guidance for Conditional Diffusion ModelsPoster
REINFORCE Adversarial Attacks on Large Language Models: An Adaptive, Distributional, and Semantic ObjectivePoster
RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion TransformersPoster
RISE: Radius of Influence based Subgraph Extraction for 3D Molecular Graph ExplanationPoster
RLTHF: Targeted Human Feedback for LLM AlignmentPoster
ROME is Forged in Adversity: Robust Distilled Datasets via Information BottleneckPoster
ROS: A GNN-based Relax-Optimize-and-Sample Framework for Max-$k$-Cut ProblemsPoster
RULEBREAKERS: Challenging LLMs at the Crossroads between Formal Logic and Human-like ReasoningPoster
RWKVQuant: Quantizing the RWKV Family with Proxy Guided Hybrid of Scalar and Vector QuantizationPoster
RZ-NAS: Enhancing LLM-guided Neural Architecture Search via Reflective Zero-Cost StrategyPoster
Radio: Rate–Distortion Optimization for Large Language Model CompressionPoster
Random Feature Representation BoostingPoster
Random Policy Evaluation Uncovers Policies of Generative Flow NetworksPoster
Random Registers for Cross-Domain Few-Shot LearningPoster
Randomized Dimensionality Reduction for Euclidean Maximization and Diversity MeasuresPoster
Rank-One Modified Value IterationPoster
Ranked Entropy Minimization for Continual Test-Time AdaptationPoster
Ranked from Within: Ranking Large Multimodal Models Without LabelsPoster
Ranking with Multiple Oracles: From Weak to Strong Stochastic TransitivityPoster
Rapid Overfitting of Multi-Pass SGD in Stochastic Convex OptimizationSpotlight
Raptor: Scalable Train-Free Embeddings for 3D Medical Volumes Leveraging Pretrained 2D Foundation ModelsSpotlight
Re-ranking Reasoning Context with Tree Search Makes Large Vision-Language Models StrongerSpotlight
ReFrame: Layer Caching for Accelerated Inference in Real-Time RenderingPoster
RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network LayersPoster
Reaction Graph: Towards Reaction-Level Modeling for Chemical Reactions with 3D StructuresPoster
Reasoning Through Execution: Unifying Process and Outcome Rewards for Code GenerationPoster
Recommendations with Sparse Comparison Data: Provably Fast Convergence for Nonconvex Matrix FactorizationPoster
Reconstructing Cell Lineage Trees from Phenotypic Features with Metric LearningPoster
Reducing Confounding Bias without Data Splitting for Causal Inference via Optimal TransportPoster
Reducing Variance of Stochastic Optimization for Approximating Nash Equilibria in Normal-Form GamesSpotlight
Redundancy Undermines the Trustworthiness of Self-Interpretable GNNsPoster
ReferSplat: Referring Segmentation in 3D Gaussian SplattingOral
Refined generalization analysis of the Deep Ritz Method and Physics-Informed Neural NetworksPoster
Refining Adaptive Zeroth-Order Optimization at EasePoster
Reflect-then-Plan: Offline Model-Based Planning through a Doubly Bayesian LensPoster
Reflection-Bench: Evaluating Epistemic Agency in Large Language ModelsPoster
Regress, Don't Guess: A Regression-like Loss on Number Tokens for Language ModelsPoster
Regression for the Mean: Auto-Evaluation and Inference with Few Labels through Post-hoc RegressionPoster
Regret-Free Reinforcement Learning for Temporal Logic SpecificationsPoster
Reidentify: Context-Aware Identity Generation for Contextual Multi-Agent Reinforcement LearningPoster
ReinboT: Amplifying Robot Visual-Language Manipulation with Reinforcement LearningPoster
Reinforce LLM Reasoning through Multi-Agent ReflectionPoster
Reinforced Learning Explicit Circuit Representations for Quantum State Characterization from Local MeasurementsPoster
Reinforcement Learning Control of a Physical Robot Device for Assisted Human Walking without a SimulatorPoster
Reinforcement Learning with Adaptive Reward Modeling for Expensive-to-Evaluate SystemsPoster
Reinforcement Learning with Random Time HorizonsPoster
Reinforcement Learning with Segment FeedbackPoster
Rejecting Hallucinated State Targets during PlanningPoster
Relational Conformal Prediction for Correlated Time SeriesPoster
Relational Invariant Learning for Robust Solvation Free Energy PredictionSpotlight
Relative Error Fair Clustering in the Weak-Strong Oracle ModelPoster
Reliable Algorithm Selection for Machine Learning-Guided DesignPoster
Representation Preserving Multiclass Agnostic to Realizable ReductionPoster
Representation Shattering in Transformers: A Synthetic Study with Knowledge EditingPoster
Representation Surgery in Model Merging with Probabilistic ModelingPoster
Representations Shape Weak-to-Strong Generalization: Theoretical Insights and Empirical PredictionsPoster
Representative Language GenerationPoster
Representative Ranking for Deliberation in the Public SpherePoster
ResKoopNet: Learning Koopman Representations for Complex Dynamics with Spectral ResidualsPoster
Residual Matrix Transformers: Scaling the Size of the Residual StreamPoster
Residual TPP: A Unified Lightweight Approach for Event Stream Data AnalysisPoster
Resolving Lexical Bias in Model EditingPoster
RestoreGrad: Signal Restoration Using Conditional Denoising Diffusion Models with Jointly Learned PriorPoster
Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning ApproachPoster
Rethink GraphODE Generalization within Coupled Dynamical SystemSpotlight
Rethink the Role of Deep Learning towards Large-scale Quantum SystemsPoster
Rethinking Causal Ranking: A Balanced Perspective on Uplift Model EvaluationPoster
Rethinking Confidence Scores and Thresholds in Pseudolabeling-based SSLPoster
Rethinking Latent Redundancy in Behavior Cloning: An Information Bottleneck Approach for Robot ManipulationPoster
Rethinking Point Cloud Data Augmentation: Topologically Consistent DeformationPoster
Rethinking Score Distilling Sampling for 3D Editing and GenerationPoster
Rethinking Time Encoding via Learnable Transformation FunctionsPoster
Rethinking the Bias of Foundation Model under Long-tailed DistributionPoster
Rethinking the Stability-Plasticity Trade-off in Continual Learning from an Architectural PerspectivePoster
Rethinking the Temperature for Federated Heterogeneous DistillationPoster
Retraining-free Merging of Sparse MoE via Hierarchical ClusteringPoster
Retrieval Augmented Zero-Shot Enzyme Generation for Specified SubstratePoster
Retrieval-Augmented Language Model for Knowledge-aware Protein EncodingPoster
Retrieval-Augmented Perception: High-resolution Image Perception Meets Visual RAGOral
Return Capping: Sample Efficient CVaR Policy Gradient OptimisationPoster
Return of the Latent Space COWBOYS: Re-thinking the use of VAEs for Bayesian Optimisation of Structured SpacesSpotlight
Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite AttacksPoster
ReverB-SNN: Reversing Bit of the Weight and Activation for Spiking Neural NetworksPoster
Revisiting Chain-of-Thought in Code Generation: Do Language Models Need to Learn Reasoning before Coding?Poster
Revisiting Continuity of Image Tokens for Cross-domain Few-shot LearningSpotlight
Revisiting Convergence: Shuffling Complexity Beyond Lipschitz SmoothnessPoster
Revisiting Cooperative Off-Policy Multi-Agent Reinforcement LearningPoster
Revisiting Differentially Private Algorithms for Decentralized Online LearningPoster
Revisiting Diffusion Models: From Generative Pre-training to One-Step GenerationPoster
Revisiting Neural Networks for Few-Shot Learning: A Zero-Cost NAS PerspectivePoster
Revisiting Noise Resilience Strategies in Gesture Recognition: Short-Term Enhancement in sEMG AnalysisPoster
Revisiting Unbiased Implicit Variational InferencePoster
Revisiting the Predictability of Performative, Social EventsPoster
Reward Translation via Reward Machine in Semi-Alignable MDPsPoster
Reward-Guided Iterative Refinement in Diffusion Models at Test-Time with Applications to Protein and DNA DesignPoster
Reward-Guided Prompt Evolving in Reinforcement Learning for LLMsPoster
Reward-free World Models for Online Imitation LearningPoster
Rhomboid Tiling for Geometric Graph Deep LearningPoster
Riemann Tensor Neural Networks: Learning Conservative Systems with Physics-Constrained NetworksPoster
Riemannian Diffusion Adaptation for Distributed Optimization on ManifoldsPoster
Right Now, Wrong Then: Non-Stationary Direct Preference Optimization under Preference DriftPoster
Right Time to Learn: Promoting Generalization via Bio-inspired Spacing Effect in Knowledge DistillationPoster
Risk-Sensitive Theory of Mind: Coordinating with Agents of Unknown Bias using Cumulative Prospect TheoryPoster
RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language ModelsPoster
Robot-Gated Interactive Imitation Learning with Adaptive Intervention MechanismPoster
Robust Automatic Modulation Classification with Fuzzy RegularizationSpotlight
Robust Consensus Anchor Learning for Efficient Multi-view Subspace ClusteringPoster
Robust ML Auditing using Prior KnowledgeSpotlight
Robust Multi-Agent Reinforcement Learning with Stochastic AdversaryPoster
Robust Multimodal Large Language Models Against Modality ConflictPoster
Robust Noise Attenuation via Adaptive Pooling of Transformer OutputsSpotlight
Robust Offline Reinforcement Learning with Linearly Structured $f$-Divergence RegularizationPoster
Robust Reward Alignment via Hypothesis Space Batch CuttingPoster
Robust Secure Swap: Responsible Face Swap With Persons of Interest Redaction and Provenance TraceabilityPoster
Robust Sparsification via SensitivityPoster
Robust Spatio-Temporal Centralized Interaction for OOD LearningPoster
RobustLight: Improving Robustness via Diffusion Reinforcement Learning for Traffic Signal ControlPoster
RobustZero: Enhancing MuZero Reinforcement Learning Robustness to State PerturbationsPoster
RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache CompressionPoster
Roll the dice & look before you leap: Going beyond the creative limits of next-token predictionOral
RollingQ: Reviving the Cooperation Dynamics in Multimodal TransformerPoster
RuleAdapter: Dynamic Rules for training Safety Reward Models in RLHFPoster
Runtime Analysis of Evolutionary NAS for Multiclass ClassificationPoster
Rényi Neural ProcessesOral
S2-Track: A Simple yet Strong Approach for End-to-End 3D Multi-Object TrackingPoster
S4S: Solving for a Fast Diffusion Model SolverPoster
SADA: Stability-guided Adaptive Diffusion AccelerationPoster
SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model InterpretabilityPoster
SAFE: Finding Sparse and Flat Minima to Improve PruningSpotlight
SAFER: A Calibrated Risk-Aware Multimodal Recommendation Model for Dynamic Treatment RegimesPoster
SAH-Drive: A Scenario-Aware Hybrid Planner for Closed-Loop Vehicle Trajectory GenerationPoster
SAN: Hypothesizing Long-Term Synaptic Development and Neural Engram Mechanism in Scalable Model's Parameter-Efficient Fine-TuningPoster
SAND: One-Shot Feature Selection with Additive Noise DistortionPoster
SBGD: Improving Graph Diffusion Generative Model via Stochastic Block DiffusionPoster
SCENIR: Visual Semantic Clarity through Unsupervised Scene Graph RetrievalPoster
SCENT: Robust Spatiotemporal Learning for Continuous Scientific Data via Scalable Conditioned Neural FieldsPoster
SCISSOR: Mitigating Semantic Bias through Cluster-Aware Siamese Networks for Robust ClassificationPoster
SDE Matching: Scalable and Simulation-Free Training of Latent Stochastic Differential EquationsPoster
SDMG: Smoothing Your Diffusion Models for Powerful Graph Representation LearningPoster
SDP-CROWN: Efficient Bound Propagation for Neural Network Verification with Tightness of Semidefinite ProgrammingSpotlight
SE(3)-Equivariant Diffusion Policy in Spherical Fourier SpacePoster
SEAD: Unsupervised Ensemble of Streaming Anomaly DetectorsPoster
SECOND: Mitigating Perceptual Hallucination in Vision-Language Models via Selective and Contrastive DecodingPoster
SEFE: Superficial and Essential Forgetting Eliminator for Multimodal Continual Instruction TuningPoster
SEMU: Singular Value Decomposition for Efficient Machine UnlearningPoster
SERENA: A Unified Stochastic Recursive Variance Reduced Gradient Framework for Riemannian Non-Convex OptimizationPoster
SGD Jittering: A Training Strategy for Robust and Accurate Model-Based ArchitecturesPoster
SHARP-Distill: A 68× Faster Recommender System with Hypergraph Neural Networks and Language ModelsPoster
SHE: Streaming-media Hashing RetrievalPoster
SHIELD: Multi-task Multi-distribution Vehicle Routing Solver with Sparsity and HierarchyPoster
SIMPLEMIX: Frustratingly Simple Mixing of Off- and On-policy Data in Language Model Preference LearningPoster
SING: Spatial Context in Large Language Model for Next-Gen WearablesPoster
SKOLR: Structured Koopman Operator Linear RNN for Time-Series ForecastingPoster
SLiM: One-shot Quantization and Sparsity with Low-rank Approximation for LLM Weight CompressionPoster
SMART-PC: Skeletal Model Adaptation for Robust Test-Time Training in Point CloudsPoster
SNS-Bench: Defining, Building, and Assessing Capabilities of Large Language Models in Social Networking ServicesPoster
SOLD: Slot Object-Centric Latent Dynamics Models for Relational Manipulation Learning from PixelsPoster
SPACE: Your Genomic Profile Predictor is a Powerful DNA Foundation ModelPoster
SPD: Sync-Point Drop for Efficient Tensor Parallelism of Large Language ModelsPoster
SPEX: Scaling Feature Interaction Explanations for LLMsPoster
SPMC: Self-Purifying Federated Backdoor Defense via Margin ContributionPoster
SPRI: Aligning Large Language Models with Context-Situated PrinciplesPoster
SSHR: More Secure Generative Steganography with High-Quality Revealed Secret ImagesPoster
STAMP Your Content: Proving Dataset Membership via Watermarked RephrasingsPoster
STAR: Learning Diverse Robot Skill Abstractions through Rotation-Augmented Vector QuantizationSpotlight
STD-FD: Spatio-Temporal Distribution Fitting Deviation for AIGC Forgery IdentificationPoster
STP: Self-play LLM Theorem Provers with Iterative Conjecturing and ProvingPoster
SToFM: a Multi-scale Foundation Model for Spatial TranscriptomicsPoster
SWAN: SGD with Normalization and Whitening Enables Stateless LLM TrainingPoster
Sable: a Performant, Efficient and Scalable Sequence Model for MARLPoster
Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse DatasetsPoster
Safe-EF: Error Feedback for Non-smooth Constrained OptimizationPoster
SafeAuto: Knowledge-Enhanced Safe Autonomous Driving with Multimodal Foundation ModelsPoster
SafeMap: Robust HD Map Construction from Incomplete ObservationsPoster
Safely Learning Optimal Auctions: A Testable Learning Framework for Mechanism DesignPoster
Safety Alignment Can Be Not Superficial With Explicit Safety SignalsPoster
Safety Certificate against Latent Variables with Partially Unidentifiable DynamicsPoster
Safety Reasoning with GuidelinesPoster
Safety-Polarized and Prioritized Reinforcement LearningPoster
SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI BehaviorPoster
SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 QuantizationPoster
Sample Complexity of Branch-length Estimation by Maximum LikelihoodPoster
Sample Complexity of Correlation Detection in the Gaussian Wigner ModelPoster
Sample Complexity of Distributionally Robust Off-Dynamics Reinforcement Learning with Online InteractionPoster
Sample Efficient Demonstration Selection for In-Context LearningPoster
Sample-Optimal Agnostic Boosting with Unlabeled DataPoster
Sample-specific Noise Injection for Diffusion-based Adversarial PurificationPoster
Sampling Binary Data by Denoising through Score FunctionsPoster
Sampling from Binary Quadratic Distributions via Stochastic LocalizationPoster
Sanity Checking Causal Representation Learning on a Simple Real-World SystemOral
Sassha: Sharpness-aware Adaptive Second-order Optimization with Stable Hessian ApproximationPoster
Scaffold with Stochastic Gradients: New Analysis with Linear Speed-UpPoster
Scalable Approximation Algorithms for $p$-Wasserstein Distance and Its VariantsPoster
Scalable Attribute-Missing Graph Clustering via Neighborhood DifferentiationPoster
Scalable First-order Method for Certifying Optimal k-Sparse GLMsPoster
Scalable Gaussian Processes with Latent Kronecker StructurePoster
Scalable Generation of Spatial Transcriptomics from Histology Images via Whole-Slide Flow MatchingSpotlight
Scalable Meta-Learning via Mixed-Mode DifferentiationPoster
Scalable Model Merging with Progressive Layer-wise DistillationPoster
Scalable Non-Equivariant 3D Molecule Generation via Rotational AlignmentPoster
Scalable Private Partition Selection via Adaptive WeightingPoster
Scalable Sobolev IPM for Probability Measures on a GraphPoster
Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural NetworksOral
Scaling Inference-Efficient Language ModelsPoster
Scaling Large Motion Models with Million-Level Human MotionsPoster
Scaling Laws for Upcycling Mixture-of-Experts Language ModelsPoster
Scaling Probabilistic Circuits via Monarch MatricesPoster
Scaling Sparse Feature Circuits For Studying In-Context LearningPoster
Scaling Trends in Language Model RobustnessSpotlight
Scaling Video-Language Models to 10K Frames via Hierarchical Differential DistillationPoster
Schwarz–Schur Involution: Lightspeed Differentiable Sparse Linear SolversPoster
Score Matching with Missing DataOral
Score-Based Diffusion Policy Compatible with Reinforcement Learning via Optimal TransportPoster
Score-based Pullback Riemannian Geometry: Extracting the Data Manifold Geometry using Anisotropic FlowsPoster
Score-of-Mixture Training: One-Step Generative Model Training Made Simple via Score Estimation of Mixture DistributionsSpotlight
SecEmb: Sparsity-Aware Secure Federated Learning of On-Device Recommender System with Large EmbeddingPoster
Secant Line Search for Frank-Wolfe AlgorithmsPoster
Securing Equal Share: A Principled Approach for Learning Multiplayer Symmetric GamesPoster
SeedLoRA: A Fusion Approach to Efficient LLM Fine-TuningPoster
Segment Anyword: Mask Prompt Inversion for Open-Set Grounded SegmentationPoster
Selective Preference AggregationPoster
Self-Bootstrapping for Versatile Test-Time AdaptationPoster
Self-Consuming Generative Models with Adversarially Curated DataPoster
Self-Disentanglement and Re-Composition for Cross-Domain Few-Shot SegmentationPoster
Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGIPoster
Self-Organizing Visual Prototypes for Non-Parametric Representation LearningPoster
Self-Play $Q$-Learners Can Provably Collude in the Iterated Prisoner's DilemmaPoster
Self-Supervised Learning of Intertwined Content and Positional Features for Object DetectionPoster
Self-Supervised Transformers as Iterative Solution Improvers for Constraint SatisfactionPoster
Self-cross Feature based Spiking Neural Networks for Efficient Few-shot LearningPoster
Self-supervised Adversarial Purification for Graph Neural NetworksPoster
Self-supervised Masked Graph Autoencoder via Structure-aware CurriculumSpotlight
SelfCite: Self-Supervised Alignment for Context Attribution in Large Language ModelsPoster
Semantic Shift Estimation via Dual-Projection and Classifier Reconstruction for Exemplar-Free Class-Incremental LearningPoster
Semantics-aware Test-time Adaptation for 3D Human Pose EstimationPoster
Semi-Supervised Blind Quality Assessment with Confidence-quantifiable Pseudo-label Learning for Authentic ImagesPoster
Separating Knowledge and Perception with Procedural DataPoster
Set Valued Predictions For Robust Domain GeneralizationPoster
Settling the Maximin Share Fairness for Scheduling among Groups of MachinesPoster
Sharp Generalization for Nonparametric Regression by Over-Parameterized Neural Networks: A Distribution-Free Analysis in Spherical CovariateSpotlight
Sharp Optimality of Simple, Plug-in Estimation of the Fisher Information of a Smoothed DensityPoster
ShieldAgent: Shielding Agents via Verifiable Safety Policy ReasoningPoster
Shielded Diffusion: Generating Novel and Diverse Images using Sparse RepellencyPoster
Shifting Time: Time-series Forecasting with Khatri-Rao Neural OperatorsPoster
Should Decision-Makers Reveal Classifiers in Online Strategic Classification?Poster
Sidechain conditioning and modeling for full-atom protein sequence design with FAMPNNPoster
Signed Laplacians for Constrained Graph ClusteringSpotlight
Simple Path Structural Encoding for Graph TransformersPoster
Simple Randomized Rounding for Max-Min Eigenvalue AugmentationPoster
Simple and Critical Iterative Denoising: A Recasting of Discrete Diffusion in Graph GenerationPoster
Simplicity Bias and Optimization Threshold in Two-Layer ReLU NetworksPoster
Simplifying DINO via Coding Rate RegularizationPoster
Simultaneous Multi-Robot Motion Planning with Projected Diffusion ModelsPoster
Since Faithfulness Fails: The Performance Limits of Neural Causal DiscoveryPoster
Sketch to Adapt: Fine-Tunable Sketches for Efficient LLM AdaptationPoster
SketchDNN: Joint Continuous-Discrete Diffusion for CAD Sketch GenerationPoster
Skip the Equations: Learning Behavior of Personalized Dynamical Systems Directly From DataPoster
SkipGPT: Each Token is One of a KindPoster
Skrr: Skip and Re-use Text Encoder Layers for Memory Efficient Text-to-Image GenerationPoster
Sleeping Reinforcement LearningPoster
SlimLLM: Accurate Structured Pruning for Large Language ModelsPoster
Slimming the Fat-Tail: Morphing-Flow for Adaptive Time Series ModelingPoster
Smooth Interpolation for Improved Discrete Graph Generative ModelsPoster
Smoothed Preference Optimization via ReNoise Inversion for Aligning Diffusion Models with Varied Human PreferencesPoster
Socialized Coevolution: Advancing a Better World through Cross-Task CollaborationPoster
Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding ExplorationSpotlight
Softmax is not Enough (for Sharp Size Generalisation)Poster
Solving Linear-Gaussian Bayesian Inverse Problems with Decoupled Diffusion Sequential Monte CarloPoster
Solving Probabilistic Verification Problems of Neural Networks using Branch and BoundPoster
Solving Satisfiability Modulo Counting Exactly with Probabilistic CircuitsPoster
Solving Zero-Sum Convex Markov GamesPoster
Sorbet: A Neuromorphic Hardware-Compatible Transformer-Based Spiking Language ModelPoster
Sort Before You Prune: Improved Worst-Case Guarantees of the DiskANN Family of GraphsPoster
Sortformer: A Novel Approach for Permutation-Resolved Speaker Supervision in Speech-to-Text SystemsPoster
Sounding that Object: Interactive Object-Aware Image to Audio GenerationPoster
Soup-of-Experts: Pretraining Specialist Models via Parameters AveragingPoster
SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model InferencePoster
Sparse Autoencoders, Again?Poster
Sparse Causal Discovery with Generative Intervention for Unsupervised Graph Domain AdaptationPoster
Sparse Training from Random Initialization: Aligning Lottery Ticket Masks using Weight SymmetryPoster
Sparse-pivot: Dynamic correlation clustering for node insertionsSpotlight
SparseLoRA: Accelerating LLM Fine-Tuning with Contextual SparsityPoster
SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model InferencePoster
Sparsing Law: Towards Large Language Models with Greater Activation SparsityPoster
SpeCache: Speculative Key-Value Caching for Efficient Generation of LLMsPoster
Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple InteractionsPoster
Spectral-Aware Reservoir Computing for Fast and Accurate Time Series ClassificationPoster
Speculative Prefill: Turbocharging TTFT with Lightweight and Training-Free Token Importance EstimationPoster
Spherical-Nested Diffusion Model for Panoramic Image OutpaintingPoster
SpikF: Spiking Fourier Network for Efficient Long-term PredictionPoster
SpikeVideoFormer: An Efficient Spike-Driven Video Transformer with Hamming Attention and $\mathcal{O}(T)$ ComplexityPoster
Splitting & Integrating: Out-of-Distribution Detection via Adversarial Gradient AttributionPoster
Splitting with Importance-aware Updating for Heterogeneous Federated Learning with Large Language ModelsPoster
Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-ParameterizationPoster
Square$\chi$PO: Differentially Private and Robust $\chi^2$-Preference Optimization in Offline Direct AlignmentPoster
Stability and Generalization Analysis of Decentralized SGD: Sharper Bounds Beyond Lipschitzness and SmoothnessPoster
Stability and Generalization Capability of Subgraph Reasoning Models for Inductive Knowledge Graph CompletionPoster
Stabilizing Sample Similarity in Representation via Mitigating Random ConsistencyPoster
Stable Fair Graph Representation Learning with Lipschitz ConstraintPoster
Stable Offline Value Function Learning with Bisimulation-based RepresentationsPoster
Stacey: Promoting Stochastic Steepest Descent via Accelerated $\ell_p$-Smooth Nonconvex OptimizationPoster
Staged and Physics-Grounded Learning Framework with Hyperintensity Prior for Pre-Contrast MRI SynthesisPoster
Statistical Collusion by Collectives on Learning PlatformsOral
Statistical Hypothesis Testing for Auditing Robustness in Language ModelsPoster
Statistical Query Hardness of Multiclass Linear Classification with Random Classification NoiseOral
Stay Hungry, Keep Learning: Sustainable Plasticity for Deep Reinforcement LearningPoster
Stay-Positive: A Case for Ignoring Real Image Features in Fake Image DetectionPoster
Stealix: Model Stealing via Prompt EvolutionPoster
StealthInk: A Multi-bit and Stealthy Watermark for Large Language ModelsPoster
Steer LLM Latents for Hallucination DetectionPoster
Steerable Transformers for Volumetric DataPoster
Steering Protein Language ModelsPoster
Stochastic Encodings for Active Feature AcquisitionPoster
Stochastic Forward–Backward Deconvolution: Training Diffusion Models with Finite Noisy DatasetsPoster
Stochastic Layer-Wise Shuffle for Improving Vision Mamba TrainingPoster
Stochastic Poisson Surface Reconstruction with One Solve using Geometric Gaussian ProcessesPoster
Stochastic Smoothed Primal-Dual Algorithms for Nonconvex Optimization with Linear Inequality ConstraintsSpotlight
Strategic A/B testing via Maximum Probability-driven Two-armed BanditPoster
Strategic Planning: A Top-Down Approach to Option GenerationPoster
Strategy Coopetition Explains the Emergence and Transience of In-Context LearningOral
Stray Intrusive Outliers-Based Feature Selection on Intra-Class Asymmetric Instance Distribution or Multiple High-Density ClustersPoster
Stream-level Flow Matching with Gaussian ProcessesPoster
Streamline Without Sacrifice - Squeeze out Computation Redundancy in LMMPoster
Strengthen Out-of-Distribution Detection Capability with Progressive Self-Knowledge DistillationPoster
Strong and Weak Identifiability of Optimization-based Causal Discovery in Non-linear Additive Noise ModelsPoster
Stronger Neyman Regret Guarantees for Adaptive Experimental DesignSpotlight
Structure Is All You Need: Structural Representation Learning on Hyper-Relational Knowledge GraphsPoster
Structure-Guided Large Language Models for Text-to-SQL GenerationPoster
Structure-informed Risk Minimization for Robust Ensemble LearningPoster
Subgoal-Guided Policy Heuristic Search with Learned SubgoalsPoster
Subgroups Matter for Robust Bias MitigationPoster
Suitability Filter: A Statistical Framework for Classifier Evaluation in Real-World Deployment SettingsOral
Sum-of-Parts: Self-Attributing Neural Networks with End-to-End Learning of Feature GroupsPoster
Super Deep Contrastive Information Bottleneck for Multi-modal ClusteringPoster
Supercharging Graph Transformers with Advective DiffusionPoster
Supervised Contrastive Learning from Weakly-Labeled Audio Segments for Musical Version MatchingPoster
Surrogate Prompt Learning: Towards Efficient and Diverse Prompt Learning for Vision-Language ModelsPoster
Survival Analysis via Density EstimationPoster
Symmetry-Aware GFlowNetsPoster
Symmetry-Driven Discovery of Dynamical Variables in Molecular SimulationsPoster
Symmetry-Robust 3D Orientation EstimationPoster
SynEVO: A neuro-inspired spatiotemporal evolutional framework for cross-domain adaptationSpotlight
Synonymous Variational Inference for Perceptual Image CompressionPoster
Synthesizing Images on Perceptual Boundaries of ANNs for Uncovering and Manipulating Human Perceptual VariabilityPoster
Synthesizing Privacy-Preserving Text Data via Finetuning *without* Finetuning Billion-Scale LLMsPoster
Synthesizing Software Engineering Data in a Test-Driven MannerPoster
Synthetic Text Generation for Training Large Language Models via Gradient MatchingPoster
System-Aware Unlearning Algorithms: Use Lesser, Forget FasterPoster
T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference ScalingPoster
TANGO: Clustering with Typicality-Aware Nonlocal Mode-Seeking and Graph-Cut OptimizationPoster
TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference OptimizationPoster
TIMING: Temporality-Aware Integrated Gradients for Time Series ExplanationSpotlight
TINED: GNNs-to-MLPs by Teacher Injection and Dirichlet Energy DistillationPoster
TLLC: Transfer Learning-based Label Completion for CrowdsourcingSpotlight

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.