ICLR 2025 Accepted Papers

The full list of 3,704 papers accepted at ICLR 2025 (International Conference on Learning Representations). 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: 3,111Spotlight: 380Oral: 213

Metric-Driven Attributions for Vision TransformersPoster
Mind the GAP: Glimpse-based Active Perception improves generalization and sample efficiency of visual reasoningPoster
MindSimulator: Exploring Brain Concept Localization via Synthetic fMRIPoster
Mini-batch Coresets for Memory-efficient Language Model Training on Data MixturesPoster
Minimal Impact ControlNet: Advancing Multi-ControlNet IntegrationPoster
Minimal Variance Model Aggregation: A principled, non-intrusive, and versatile integration of black box modelsPoster
Minimalistic Predictions for Online Class Constraint SchedulingPoster
Minimax Optimal Reinforcement Learning with Quasi-OptimismPoster
Minimax Optimal Two-Stage Algorithm For Moment Estimation Under Covariate ShiftPoster
Mitigate the Gap: Improving Cross-Modal Alignment in CLIPPoster
Mitigating Information Loss in Tree-Based Reinforcement Learning via Direct OptimizationSpotlight
Mitigating Object Hallucination in MLLMs via Data-augmented Phrase-level AlignmentPoster
Mitigating Parameter Interference in Model Merging via Sharpness-Aware Fine-TuningPoster
Mitigating Reward Over-Optimization in RLHF via Behavior-Supported RegularizationPoster
Mitigating Spurious Correlations in Zero-Shot Multimodal ModelsPoster
MixMax: Distributional Robustness in Function Space via Optimal Data MixturesPoster
Mixture Compressor for Mixture-of-Experts LLMs Gains MorePoster
MoDGS: Dynamic Gaussian Splatting from Casually-captured Monocular Videos with Depth PriorsPoster
Modality-Specialized Synergizers for Interleaved Vision-Language GeneralistsPoster
Model Risk-sensitive Offline Reinforcement LearningPoster
Model-Agnostic Knowledge Guided Correction for Improved Neural Surrogate RolloutPoster
Model-Free Offline Reinforcement Learning with Enhanced RobustnessPoster
Model-based Offline Reinforcement Learning with Lower Expectile Q-LearningPoster
Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation LearningPoster
Modeling Unseen Environments with Language-guided Composable Causal Components in Reinforcement LearningPoster
Moner: Motion Correction in Undersampled Radial MRI with Unsupervised Neural RepresentationSpotlight
Monet: Mixture of Monosemantic Experts for TransformersPoster
Monte Carlo Planning with Large Language Model for Text-Based Game AgentsPoster
More Experts Than Galaxies: Conditionally-Overlapping Experts with Biologically-Inspired Fixed RoutingPoster
Motion Control of High-Dimensional Musculoskeletal Systems with Hierarchical Model-Based PlanningPoster
MotionDreamer: One-to-Many Motion Synthesis with Localized Generative Masked TransformerPoster
MuHBoost: Multi-Label Boosting For Practical Longitudinal Human Behavior ModelingPoster
Multi-Draft Speculative Sampling: Canonical Decomposition and Theoretical LimitsSpotlight
Multi-Label Node Classification with Label Influence PropagationPoster
Multi-Label Test-Time Adaptation with Bound Entropy MinimizationPoster
Multi-Modal and Multi-Attribute Generation of Single Cells with CFGenPoster
Multi-Resolution Decomposable Diffusion Model for Non-Stationary Time Series Anomaly DetectionPoster
Multi-Reward as Condition for Instruction-based Image EditingPoster
Multi-Task Corrupted Prediction for Learning Robust Audio-Visual Speech RepresentationPoster
Multi-Task Dense Predictions via Unleashing the Power of DiffusionPoster
Multi-level Certified Defense Against Poisoning Attacks in Offline Reinforcement LearningPoster
Multi-modal brain encoding models for multi-modal stimuliPoster
Multi-objective antibody design with constrained preference optimizationPoster
Multimodal Lego: Model Merging and Fine-Tuning Across Topologies and Modalities in BiomedicinePoster
Multimodal Quantitative Language for Generative RecommendationPoster
Multimodal Unsupervised Domain Generalization by Retrieving Across the Modality GapPoster
Multiplicative Logit Adjustment Approximates Neural-Collapse-Aware Decision Boundary AdjustmentPoster
Multiview Equivariance Improves 3D Correspondence Understanding with Minimal Feature FinetuningPoster
MuseGNN: Forming Scalable, Convergent GNN Layers that Minimize a Sampling-Based EnergyPoster
Mutual Effort for Efficiency: A Similarity-based Token Pruning for Vision Transformers in Self-Supervised LearningPoster
N-ForGOT: Towards Not-forgetting and Generalization of Open Temporal Graph LearningPoster
NExUME: Adaptive Training and Inference for DNNs under Intermittent Power EnvironmentsPoster
NL-Eye: Abductive NLI For ImagesPoster
NRGBoost: Energy-Based Generative Boosted TreesPoster
Narrowing Information Bottleneck Theory for Multimodal Image-Text Representations InterpretabilityPoster
Navigation-Guided Sparse Scene Representation for End-to-End Autonomous DrivingPoster
NeSyC: A Neuro-symbolic Continual Learner For Complex Embodied Tasks In Open DomainsPoster
Near, far: Patch-ordering enhances vision foundation models' scene understandingPoster
Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph FormPoster
Near-optimal Active Regression of Single-Index ModelsPoster
NetFormer: An interpretable model for recovering dynamical connectivity in neuronal population dynamicsSpotlight
NeurFlow: Interpreting Neural Networks through Neuron Groups and Functional InteractionsPoster
Neural Causal Graph for Interpretable and Intervenable ClassificationPoster
Neural Exploratory Landscape Analysis for Meta-Black-Box-OptimizationPoster
Neural Fluid Simulation on Geometric SurfacesPoster
Neural Functions for Learning Periodic SignalPoster
Neural Multi-Objective Combinatorial Optimization via Graph-Image Multimodal FusionPoster
Neural ODE Transformers: Analyzing Internal Dynamics and Adaptive Fine-tuningPoster
Neural Stochastic Differential Equations for Uncertainty-Aware Offline RLPoster
Neural Wave Equation for Irregularly Sampled Sequence DataPoster
Neural networks on Symmetric Spaces of Noncompact TypePoster
NeuralPlane: Structured 3D Reconstruction in Planar Primitives with Neural FieldsOral
Neuralized Markov Random Field for Interaction-Aware Stochastic Human Trajectory PredictionPoster
Neuron Platonic Intrinsic Representation From Dynamics Using Contrastive LearningPoster
Neuron-based Multifractal Analysis of Neuron Interaction Dynamics in Large ModelsPoster
New Algorithms for the Learning-Augmented k-means ProblemPoster
Newton Meets Marchenko-Pastur: Massively Parallel Second-Order Optimization with Hessian Sketching and DebiasingPoster
NextBestPath: Efficient 3D Mapping of Unseen EnvironmentsPoster
No Equations Needed: Learning System Dynamics Without Relying on Closed-Form ODEsPoster
No Free Lunch: Fundamental Limits of Learning Non-Hallucinating Generative ModelsPoster
No Location Left Behind: Measuring and Improving the Fairness of Implicit Representations for Earth DataPoster
Node Identifiers: Compact, Discrete Representations for Efficient Graph LearningPoster
Node Similarities under Random Projections: Limits and Pathological CasesPoster
Noise Separation guided Candidate Label Reconstruction for Noisy Partial Label LearningPoster
Noise-conditioned Energy-based Annealed Rewards (NEAR): A Generative Framework for Imitation Learning from ObservationPoster
Noisy Test-Time Adaptation in Vision-Language ModelsPoster
Nonlinear Sequence Embedding by Monotone Variational InequalitySpotlight
Nonlinear multiregion neural dynamics with parametric impulse response communication channelsSpotlight
Not All Language Model Features Are One-Dimensionally LinearPoster
Not-So-Optimal Transport Flows for 3D Point Cloud GenerationPoster
Nova: Generative Language Models for Assembly Code with Hierarchical Attention and Contrastive LearningPoster
Null Counterfactual Factor Interactions for Goal-Conditioned Reinforcement LearningPoster
NutriBench: A Dataset for Evaluating Large Language Models in Nutrition Estimation from Meal DescriptionsPoster
OCCAM: Towards Cost-Efficient and Accuracy-Aware Classification InferencePoster
OCEAN: Offline Chain-of-thought Evaluation and Alignment in Large Language ModelsPoster
ODE-based Smoothing Neural Network for Reinforcement Learning TasksSpotlight
OMG: Opacity Matters in Material Modeling with Gaussian SplattingPoster
ONLINE EPSILON NET & PIERCING SET FOR GEOMETRIC CONCEPTSPoster
ORSO: Accelerating Reward Design via Online Reward Selection and Policy OptimizationPoster
OSDA Agent: Leveraging Large Language Models for De Novo Design of Organic Structure Directing AgentsSpotlight
OVTR: End-to-End Open-Vocabulary Multiple Object Tracking with TransformerPoster
Object-Centric Pretraining via Target Encoder BootstrappingPoster
ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation GroundingPoster
Occlusion-aware Non-Rigid Point Cloud Registration via Unsupervised Neural Deformation CorrentropyPoster
Offline RL in Regular Decision Processes: Sample Efficiency via Language MetricsPoster
Offline RL with Smooth OOD Generalization in Convex Hull and its NeighborhoodPoster
OmniSep: Unified Omni-Modality Sound Separation with Query-MixupPoster
On Bits and Bandits: Quantifying the Regret-Information Trade-offPoster
On Conformal Isometry of Grid Cells: Learning Distance-Preserving Position EmbeddingOral
On Discriminative Probabilistic Modeling for Self-Supervised Representation LearningPoster
On Disentangled Training for Nonlinear Transform in Learned Image CompressionSpotlight
On Generalization Across Environments In Multi-Objective Reinforcement LearningPoster
On Large Language Model Continual UnlearningPoster
On Linear Representations and Pretraining Data Frequency in Language ModelsPoster
On Minimizing Adversarial Counterfactual Error in Adversarial Reinforcement LearningPoster
On Quantizing Neural Representation for Variable-Rate Video CodingSpotlight
On Rollouts in Model-Based Reinforcement LearningPoster
On Speeding Up Language Model EvaluationPoster
On Stochastic Contextual Bandits with Knapsacks in Small Budget RegimePoster
On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data PoisoningPoster
On the Adversarial Vulnerability of Label-Free Test-Time AdaptationPoster
On the Almost Sure Convergence of the Stochastic Three Points AlgorithmPoster
On the Benefits of Attribute-Driven Graph Domain AdaptationPoster
On the Importance of Language-driven Representation Learning for Heterogeneous Federated LearningPoster
On the Learn-to-Optimize Capabilities of Transformers in In-Context Sparse RecoveryPoster
On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared RepresentationsPoster
On the Optimization Landscape of Low Rank Adaptation Methods for Large Language ModelsPoster
On the Performance Analysis of Momentum Method: A Frequency Domain PerspectivePoster
On the Price of Differential Privacy for Hierarchical ClusteringPoster
On-the-fly Preference Alignment via Principle-Guided DecodingPoster
One Hundred Neural Networks and Brains Watching Videos: Lessons from AlignmentPoster
One Model Transfer to All: On Robust Jailbreak Prompts Generation against LLMsPoster
One-for-All Few-Shot Anomaly Detection via Instance-Induced Prompt LearningPoster
Online Clustering with Nearly Optimal ConsistencyPoster
Online Reward-Weighted Fine-Tuning of Flow Matching with Wasserstein RegularizationPoster
Online-to-Offline RL for Agent AlignmentPoster
Open-CK: A Large Multi-Physics Fields Coupling benchmarks in Combustion KineticsPoster
Optimal Brain ApoptosisPoster
Optimal Flow Transport and its Entropic Regularization: a GPU-friendly Matrix Iterative Algorithm for Flow Balance SatisfactionPoster
Optimal Learning of Kernel Logistic Regression for Complex Classification ScenariosPoster
Optimal Non-Asymptotic Rates of Value Iteration for Average-Reward Markov Decision ProcessesPoster
Optimality of Matrix Mechanism on $\ell_p^p$-metricPoster
Optimizing $(L_0, L_1)$-Smooth Functions by Gradient MethodsPoster
Optimizing 4D Gaussians for Dynamic Scene Video from Single Landscape ImagesPoster
Optimizing Neural Network Representations of Boolean NetworksPoster
Optimizing importance weighting in the presence of sub-population shiftsPoster
OptionZero: Planning with Learned OptionsOral
Oracle efficient truncated statisticsPoster
Order-aware Interactive SegmentationPoster
Overcoming Slow Decision Frequencies in Continuous Control: Model-Based Sequence Reinforcement Learning for Model-Free ControlPoster
OvercookedV2: Rethinking Overcooked for Zero-Shot CoordinationPoster
PABBO: Preferential Amortized Black-Box OptimizationSpotlight
PEARL: Parallel Speculative Decoding with Adaptive Draft LengthPoster
PEARL: Towards Permutation-Resilient LLMsPoster
PETRA: Parallel End-to-end Training with Reversible ArchitecturesSpotlight
PFDiff: Training-Free Acceleration of Diffusion Models Combining Past and Future ScoresPoster
PFGuard: A Generative Framework with Privacy and Fairness SafeguardsPoster
PICASO: Permutation-Invariant Context Composition with State Space ModelsPoster
PIED: Physics-Informed Experimental Design for Inverse ProblemsPoster
PIG: Physics-Informed Gaussians as Adaptive Parametric Mesh RepresentationsPoster
PIN: Prolate Spheroidal Wave Function-based Implicit Neural RepresentationsPoster
PINP: Physics-Informed Neural Predictor with latent estimation of fluid flowsPoster
PIORF: Physics-Informed Ollivier-Ricci Flow for Long–Range Interactions in Mesh Graph Neural NetworksPoster
PN-GAIL: Leveraging Non-optimal Information from Imperfect DemonstrationsPoster
POTEC: Off-Policy Contextual Bandits for Large Action Spaces via Policy DecompositionSpotlight
PPT: Patch Order Do Matters In Time Series Pretext TaskPoster
PRDP: Progressively Refined Differentiable PhysicsPoster
PRISM: Privacy-Preserving Improved Stochastic Masking for Federated Generative ModelsPoster
PT-T2I/V: An Efficient Proxy-Tokenized Diffusion Transformer for Text-to-Image/Video-TaskPoster
PWM: Policy Learning with Multi-Task World ModelsPoster
PaCA: Partial Connection Adaptation for Efficient Fine-TuningPoster
PaLD: Detection of Text Partially Written by Large Language ModelsPoster
PaRa: Personalizing Text-to-Image Diffusion via Parameter Rank ReductionSpotlight
Painting with Words: Elevating Detailed Image Captioning with Benchmark and Alignment LearningPoster
Pairwise Elimination with Instance-Dependent Guarantees for Bandits with Cost SubsidyPoster
Palu: KV-Cache Compression with Low-Rank ProjectionPoster
ParFam -- (Neural Guided) Symbolic Regression via Continuous Global OptimizationPoster
Param$\Delta$ for Direct Mixing: Post-Train Large Language Model At Zero CostPoster
Parameter and Memory Efficient Pretraining via Low-rank Riemannian OptimizationPoster
Pareto Prompt OptimizationPoster
Partial Gromov-Wasserstein MetricPoster
Pedestrian Motion Reconstruction: A Large-scale Benchmark via Mixed Reality Rendering with Multiple Perspectives and ModalitiesPoster
Periodic Materials Generation using Text-Guided Joint Diffusion ModelPoster
Permute-and-Flip: An optimally stable and watermarkable decoder for LLMsPoster
Perplexity Trap: PLM-Based Retrievers Overrate Low Perplexity DocumentsPoster
Personalized Representation from Personalized GenerationPoster
PerturboLLaVA: Reducing Multimodal Hallucinations with Perturbative Visual TrainingSpotlight
PharmacoMatch: Efficient 3D Pharmacophore Screening via Neural Subgraph MatchingPoster
PhysPDE: Rethinking PDE Discovery and a Physical Hypothesis Selection BenchmarkPoster
Physics-aligned field reconstruction with diffusion bridgeSpotlight
Physics-informed Temporal Difference Metric Learning for Robot Motion PlanningPoster
Physiome-ODE: A Benchmark for Irregularly Sampled Multivariate Time-Series Forecasting Based on Biological ODEsPoster
Point Cluster: A Compact Message Unit for Communication-Efficient Collaborative PerceptionPoster
Point-based Instance Completion with Scene ConstraintsPoster
Poisson-Dirac Neural Networks for Modeling Coupled Dynamical Systems across DomainsPoster
Policy Design in Long-run Welfare DynamicsPoster
Policy Optimization under Imperfect Human Interactions with Agent-Gated Shared AutonomyPoster
PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training RunsPoster
PolyhedronNet: Representation Learning for Polyhedra with Surface-attributed GraphPoster
Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM EvaluationPoster
PooDLe🐩: Pooled and dense self-supervised learning from naturalistic videosPoster
Port-Hamiltonian Architectural Bias for Long-Range Propagation in Deep Graph NetworksPoster
Positive-Unlabeled Diffusion Models for Preventing Sensitive Data GenerationPoster
PostEdit: Posterior Sampling for Efficient Zero-Shot Image EditingPoster
Precise Localization of Memories: A Fine-grained Neuron-level Knowledge Editing Technique for LLMsPoster
Precise Parameter Localization for Textual Generation in Diffusion ModelsPoster
Predicate Hierarchies Improve Few-Shot State ClassificationPoster
Predicting the Energy Landscape of Stochastic Dynamical System via Physics-informed Self-supervised LearningPoster
Prediction Risk and Estimation Risk of the Ridgeless Least Squares Estimator under General Assumptions on Regression ErrorsPoster
Preference Elicitation for Offline Reinforcement LearningPoster
Preserving Diversity in Supervised Fine-Tuning of Large Language ModelsPoster
Privacy-Aware Lifelong LearningPoster
Private Mechanism Design via Quantile EstimationPoster
Privately Counting Partially Ordered DataPoster
ProAdvPrompter: A Two-Stage Journey to Effective Adversarial Prompting for LLMsPoster
Probabilistic Geometric Principal Component Analysis with application to neural dataSpotlight
Probabilistic Learning to Defer: Handling Missing Expert Annotations and Controlling Workload DistributionOral
Probabilistic Neural Pruning via Sparsity Evolutionary Fokker-Planck-Kolmogorov EquationSpotlight
Procedural Synthesis of Synthesizable MoleculesPoster
Progressive Parameter Efficient Transfer Learning for Semantic SegmentationPoster
Progressive Token Length Scaling in Transformer Encoders for Efficient Universal SegmentationPoster
Projection Head is Secretly an Information BottleneckPoster
Prompt as Knowledge Bank: Boost Vision-language model via Structural Representation for zero-shot medical detectionPoster
Prompting Fairness: Integrating Causality to Debias Large Language ModelsPoster
ProtComposer: Compositional Protein Structure Generation with 3D EllipsoidsOral
ProtPainter: Draw or Drag Protein via Topology-guided DiffusionPoster
ProtoSnap: Prototype Alignment For Cuneiform SignsPoster
Prototype antithesis for biological few-shot class-incremental learningPoster
Provable Convergence Bounds for Hybrid Dynamical Sampling and OptimizationPoster
Provable Robust Overfitting Mitigation in Wasserstein Distributionally Robust OptimizationPoster
Provably Reliable Conformal Prediction Sets in the Presence of Data PoisoningSpotlight
Provably Safeguarding a Classifier from OOD and Adversarial SamplesPoster
Proving Olympiad Inequalities by Synergizing LLMs and Symbolic ReasoningPoster
Proximal Mapping Loss: Understanding Loss Functions in Crowd Counting & LocalizationPoster
Proxy Denoising for Source-Free Domain AdaptationOral
PseDet: Revisiting the Power of Pseudo Label in Incremental Object DetectionPoster
PvNeXt: Rethinking Network Design and Temporal Motion for Point Cloud Video RecognitionPoster
Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting MitigationPoster
QA-Calibration of Language Model Confidence ScoresPoster
QERA: an Analytical Framework for Quantization Error ReconstructionPoster
QMP: Q-switch Mixture of Policies for Multi-Task Behavior SharingPoster
QP-SNN: Quantized and Pruned Spiking Neural NetworksPoster
QPM: Discrete Optimization for Globally Interpretable Image ClassificationPoster
QuaDiM: A Conditional Diffusion Model For Quantum State Property EstimationPoster
Quality Measures for Dynamic Graph Generative ModelsSpotlight
Quality over Quantity in Attention Layers: When Adding More Heads HurtsPoster
Quantitative Approximation for Neural Operators in Nonlinear Parabolic EquationsPoster
Quantized Spike-driven TransformerPoster
Query-based Knowledge Transfer for Heterogeneous Learning EnvironmentsPoster
R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM InferencePoster
R2Det: Exploring Relaxed Rotation Equivariance in 2D Object DetectionPoster
RA-TTA: Retrieval-Augmented Test-Time Adaptation for Vision-Language ModelsPoster
RAG-SR: Retrieval-Augmented Generation for Neural Symbolic RegressionSpotlight
RAPID: Retrieval Augmented Training of Differentially Private Diffusion ModelsPoster
RB-Modulation: Training-Free Stylization using Reference-Based ModulationOral
REBIND: Enhancing Ground-state Molecular Conformation Prediction via Force-Based Graph RewiringPoster
RECAST: Reparameterized, Compact weight Adaptation for Sequential TasksPoster
RESfM: Robust Deep Equivariant Structure from MotionPoster
RESuM: A Rare Event Surrogate Model for Physics Detector DesignSpotlight
RMP-SAM: Towards Real-Time Multi-Purpose Segment AnythingOral
RRM: Robust Reward Model Training Mitigates Reward HackingPoster
RTDiff: Reverse Trajectory Synthesis via Diffusion for Offline Reinforcement LearningPoster
RTop-K: Ultra-Fast Row-Wise Top-K Selection for Neural Network Acceleration on GPUsPoster
Radar: Fast Long-Context Decoding for Any TransformerPoster
RandLoRA: Full rank parameter-efficient fine-tuning of large modelsPoster
Random Is All You Need: Random Noise Injection on Feature Statistics for Generalizable Deep Image DenoisingPoster
Range, not Independence, Drives Modularity in Biologically Inspired RepresentationsPoster
RankSHAP: Shapley Value Based Feature Attributions for Learning to RankPoster
Ranking-aware adapter for text-driven image ordering with CLIPPoster
Rapid Selection and Ordering of In-Context Demonstrations via Prompt Embedding ClusteringPoster
Rare event modeling with self-regularized normalizing flows: what can we learn from a single failure?Poster
Rational Decision-Making Agent with Learning Internal Utility JudgmentPoster
Rationalizing and Augmenting Dynamic Graph Neural NetworksPoster
Re-Aligning Language to Visual Objects with an Agentic WorkflowPoster
Re-Evaluating the Impact of Unseen-Class Unlabeled Data on Semi-Supervised Learning ModelPoster
ReCogLab: a framework testing relational reasoning & cognitive hypotheses on LLMsPoster
ReGen: Generative Robot Simulation via Inverse DesignPoster
ReMatching Dynamic Reconstruction FlowPoster
ReNovo: Retrieval-Based \emph{De Novo} Mass Spectrometry Peptide SequencingPoster
Ready-to-React: Online Reaction Policy for Two-Character Interaction GenerationPoster
Reasoning Elicitation in Language Models via Counterfactual FeedbackOral
Reassessing How to Compare and Improve the Calibration of Machine Learning ModelsPoster
Recognize Any Surgical Object: Unleashing the Power of Weakly-Supervised DataSpotlight
Reconsidering Faithfulness in Regular, Self-Explainable and Domain Invariant GNNsPoster
Reconstruction-Guided Policy: Enhancing Decision-Making through Agent-Wise State ConsistencyPoster
Recovering Manifold Structure Using Ollivier Ricci CurvatureSpotlight
Redefining the task of Bioactivity PredictionPoster
Refining CLIP's Spatial Awareness: A Visual-Centric PerspectivePoster
Reframing Structure-Based Drug Design Model Evaluation via Metrics Correlated to Practical NeedsPoster
Regret Bounds for Episodic Risk-Sensitive Linear Quadratic RegulatorPoster
Regret-Optimal List Replicable Bandit Learning: Matching Upper and Lower BoundsPoster
Regularizing Energy among Training Samples for Out-of-Distribution GeneralizationPoster
Regulatory DNA Sequence Design with Reinforcement LearningPoster
Reinforcement Learning for Control of Non-Markovian Cellular Population DynamicsSpotlight
Relation-Aware Diffusion for Heterogeneous Graphs with Partially Observed FeaturesPoster
Relax and Merge: A Simple Yet Effective Framework for Solving Fair $k$-Means and $k$-sparse Wasserstein Barycenter ProblemsPoster
Release the Powers of Prompt Tuning: Cross-Modality Prompt TransferPoster
Reliable and Diverse Evaluation of LLM Medical Knowledge MasteryPoster
Remove Symmetries to Control Model Expressivity and Improve OptimizationPoster
Representational Similarity via Interpretable Visual ConceptsPoster
Representative Guidance: Diffusion Model Sampling with CoherenceSpotlight
Repulsive Latent Score Distillation for Solving Inverse ProblemsPoster
Residual Deep Gaussian Processes on ManifoldsOral
Residual Kernel Policy Network: Enhancing Stability and Robustness in RKHS-Based Reinforcement LearningPoster
Resolution Attack: Exploiting Image Compression to Deceive Deep Neural NetworksPoster
Restyling Unsupervised Concept Based Interpretable Networks with Generative ModelsPoster
Rethinking Audio-Visual Adversarial Vulnerability from Temporal and Modality PerspectivesPoster
Rethinking Classifier Re-Training in Long-Tailed Recognition: Label Over-Smooth Can BalancePoster
Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a PosteriorPoster
Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous WordsPoster
Rethinking Fair Representation Learning for Performance-Sensitive TasksPoster
Rethinking Graph Neural Networks From A Geometric Perspective Of Node FeaturesPoster
Rethinking Invariance Regularization in Adversarial Training to Improve Robustness-Accuracy Trade-offPoster
Rethinking Multiple-Instance Learning From Feature Space to Probability SpacePoster
Rethinking Neural Multi-Objective Combinatorial Optimization via Neat Weight EmbeddingPoster
Rethinking Self-Distillation: Label Averaging and Enhanced Soft Label Refinement with Partial LabelsPoster
Rethinking Shapley Value for Negative Interactions in Non-convex GamesPoster
Rethinking Spiking Neural Networks from an Ensemble Learning PerspectivePoster
Rethinking and Improving Autoformalization: Towards a Faithful Metric and a Dependency Retrieval-based ApproachSpotlight
Rethinking the generalization of drug target affinity prediction algorithms via similarity aware evaluationOral
Retri3D: 3D Neural Graphics Representation RetrievalSpotlight
RetroInText: A Multimodal Large Language Model Enhanced Framework for Retrosynthetic Planning via In-Context Representation LearningPoster
Reveal Object in Lensless Photography via Region Gaze and AmplificationPoster
Revealing the 3D Cosmic Web through Gravitationally Constrained Neural FieldsPoster
Revisit Micro-batch Clipping: Adaptive Data Pruning via Gradient ManipulationPoster
Revisit the Open Nature of Open Vocabulary Semantic SegmentationPoster
Revisiting Convolution Architecture in the Realm of DNA Foundation ModelsPoster
Revisiting Large-Scale Non-convex Distributionally Robust OptimizationPoster
Revisiting Mode Connectivity in Neural Networks with Bezier SurfacePoster
Revisiting Nearest Neighbor for Tabular Data: A Deep Tabular Baseline Two Decades LaterPoster
Revisiting Source-Free Domain Adaptation: a New Perspective via Uncertainty ControlPoster
Revolutionizing EMCCD Denoising through a Novel Physics-Based Learning Framework for Noise ModelingPoster
Reward Dimension Reduction for Scalable Multi-Objective Reinforcement LearningPoster
Risk-Sensitive Diffusion: Robustly Optimizing Diffusion Models with Noisy SamplesPoster
Risk-Sensitive Variational Actor-Critic: A Model-Based ApproachPoster
Robust Conformal Prediction with a Single Binary CertificatePoster
Robust Representation Consistency Model via Contrastive DenoisingPoster
Robust Root Cause Diagnosis using In-Distribution InterventionsPoster
Robust Simulation-Based Inference under Missing Data via Neural ProcessesPoster
Robust System Identification: Finite-sample Guarantees and Connection to RegularizationPoster
Robust Transfer of Safety-Constrained Reinforcement Learning AgentsPoster
Robust Weight Initialization for Tanh Neural Networks with Fixed Point AnalysisPoster
Robust-PIFu: Robust Pixel-aligned Implicit Function for 3D Human Digitalization from a Single ImagePoster
Robustness Inspired Graph Backdoor DefenseOral
RocketEval: Efficient automated LLM evaluation via grading checklistPoster
Rodimus*: Breaking the Accuracy-Efficiency Trade-Off with Efficient AttentionsPoster
Root Cause Analysis of Anomalies in Multivariate Time Series through Granger Causal DiscoveryOral
Rotated Runtime Smooth: Training-Free Activation Smoother for accurate INT4 inferencePoster
Routing Experts: Learning to Route Dynamic Experts in Existing Multi-modal Large Language ModelsPoster
S4M: S4 for multivariate time series forecasting with Missing valuesPoster
SAGEPhos: Sage Bio-Coupled and Augmented Fusion for Phosphorylation Site DetectionPoster
SAMRefiner: Taming Segment Anything Model for Universal Mask RefinementPoster
SBSC: Step-by-Step Coding for Improving Mathematical Olympiad PerformancePoster
SC-OmniGS: Self-Calibrating Omnidirectional Gaussian SplattingPoster
SCOPE: A Self-supervised Framework for Improving Faithfulness in Conditional Text GenerationPoster
SEMDICE: Off-policy State Entropy Maximization via Stationary Distribution Correction EstimationPoster
SEPARATE: A Simple Low-rank Projection for Gradient Compression in Modern Large-scale Model Training ProcessPoster
SFESS: Score Function Estimators for $k$-Subset SamplingPoster
SFS: Smarter Code Space Search improves LLM Inference ScalingPoster
SIM: Surface-based fMRI Analysis for Inter-Subject Multimodal Decoding from Movie-Watching ExperimentsPoster
SIMPL: Scalable and hassle-free optimisation of neural representations from behaviourPoster
SINGER: Stochastic Network Graph Evolving Operator for High Dimensional PDEsPoster
SLMRec: Distilling Large Language Models into Small for Sequential RecommendationPoster
SMT: Fine-Tuning Large Language Models with Sparse MatricesPoster
SOAP: Improving and Stabilizing Shampoo using Adam for Language ModelingPoster
SOO-Bench: Benchmarks for Evaluating the Stability of Offline Black-Box OptimizationPoster
SOREL: A Stochastic Algorithm for Spectral Risks MinimizationPoster
SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM TrainingPoster
SRSA: Skill Retrieval and Adaptation for Robotic Assembly TasksSpotlight
SSLAM: Enhancing Self-Supervised Models with Audio Mixtures for Polyphonic SoundscapesPoster
SSOLE: Rethinking Orthogonal Low-rank Embedding for Self-Supervised LearningPoster
ST-GCond: Self-supervised and Transferable Graph Dataset CondensationPoster
STAR: Stability-Inducing Weight Perturbation for Continual LearningPoster
SV-RAG: LoRA-Contextualizing Adaptation of MLLMs for Long Document UnderstandingPoster
SVG: 3D Stereoscopic Video Generation via Denoising Frame MatrixPoster
SWEb: A Large Web Dataset for the Scandinavian LanguagesPoster
SaMer: A Scenario-aware Multi-dimensional Evaluator for Large Language ModelsPoster
SaRA: High-Efficient Diffusion Model Fine-tuning with Progressive Sparse Low-Rank AdaptationPoster
Safety Representations for Safer Policy LearningPoster
Safety-Prioritizing Curricula for Constrained Reinforcement LearningPoster
Salvage: Shapley-distribution Approximation Learning Via Attribution Guided Exploration for Explainable Image ClassificationPoster
Satisficing Regret Minimization in BanditsPoster
Scalable Influence and Fact Tracing for Large Language Model PretrainingPoster
Scalable Universal T-Cell Receptor Embeddings from Adaptive Immune RepertoiresPoster
Scale-Aware Contrastive Reverse Distillation for Unsupervised Medical Anomaly DetectionPoster
Scale-Free Graph-Language ModelsPoster
Scale-aware Recognition in Satellite Images under Resource ConstraintsPoster
Scaling Instruction-tuned LLMs to Million-token Contexts via Hierarchical Synthetic Data GenerationPoster
Scaling LLM Test-Time Compute Optimally Can be More Effective than Scaling Parameters for ReasoningOral
Scaling Laws for Adversarial Attacks on Language Model Activations and TokensPoster
Scaling Long Context Training Data by Long-Distance ReferralsPoster
Scaling Stick-Breaking Attention: An Efficient Implementation and In-depth StudyPoster
Scaling up the Banded Matrix Factorization Mechanism for Large Scale Differentially Private MLSpotlight
Schur's Positive-Definite Network: Deep Learning in the SPD cone with structurePoster
Score-based free-form architectures for high-dimensional Fokker-Planck equationsPoster
SeCom: On Memory Construction and Retrieval for Personalized Conversational AgentsPoster
SeRA: Self-Reviewing and Alignment of LLMs using Implicit Reward MarginsPoster
SecureGS: Boosting the Security and Fidelity of 3D Gaussian Splatting SteganographyPoster
See It from My Perspective: How Language Affects Cultural Bias in Image UnderstandingPoster
SeedLM: Compressing LLM Weights into Seeds of Pseudo-Random GeneratorsPoster
SegLLM: Multi-round Reasoning Segmentation with Large Language ModelsPoster
SelKD: Selective Knowledge Distillation via Optimal Transport PerspectivePoster
Select before Act: Spatially Decoupled Action Repetition for Continuous ControlPoster
SelectFormer in Data Markets: Privacy-Preserving and Efficient Data Selection for Transformers with Multi-Party ComputationPoster
Selective Induction Heads: How Transformers Select Causal Structures in ContextPoster
Selective Label Enhancement Learning for Test-Time AdaptationPoster
Selective Task Group Updates for Multi-Task OptimizationPoster
Selective Unlearning via Representation Erasure Using Domain Adversarial TrainingPoster
Self-Attention-Based Contextual Modulation Improves Neural System IdentificationPoster
Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language ModelsPoster
Self-Normalized Resets for Plasticity in Continual LearningPoster
Self-Supervised Diffusion Models for Electron-Aware Molecular Representation LearningPoster
Self-Updatable Large Language Models by Integrating Context into Model ParametersPoster
Self-supervised Monocular Depth Estimation Robust to Reflective Surface Leveraged by Triplet MiningPoster
Self-supervised contrastive learning performs non-linear system identificationPoster
Semantic Aware Representation Learning for Lifelong LearningPoster
Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMsPoster
Semantic Temporal Abstraction via Vision-Language Model Guidance for Efficient Reinforcement LearningPoster
Semantix: An Energy-guided Sampler for Semantic Style TransferPoster
Semi-Parametric Retrieval via Binary Bag-of-Tokens IndexPoster
Semi-Supervised CLIP Adaptation by Enforcing Semantic and Trapezoidal ConsistencyPoster
Semi-Supervised Vision-Centric 3D Occupancy World Model for Autonomous DrivingPoster
Semialgebraic Neural Networks: From roots to representationsPoster
Sensitivity Verification for Additive Decision Tree EnsemblesPoster
Sensitivity-Constrained Fourier Neural Operators for Forward and Inverse Problems in Parametric Differential EquationsPoster
Separation Power of Equivariant Neural NetworksPoster
Sequential Stochastic Combinatorial Optimization Using Hierarchal Reinforcement LearningPoster
ShEPhERD: Diffusing shape, electrostatics, and pharmacophores for bioisosteric drug designOral
Shape as Line Segments: Accurate and Flexible Implicit Surface RepresentationPoster
Shapley-Guided Utility Learning for Effective Graph Inference Data ValuationPoster
Shared-AE: Automatic Identification of Shared Subspaces in High-dimensional Neural and Behavioral ActivityPoster
Sharper Guarantees for Learning Neural Network Classifiers with Gradient MethodsPoster
Sharpness-Aware Black-Box OptimizationPoster
Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late In TrainingSpotlight
Sharpness-Aware Minimization: General Analysis and Improved RatesPoster
Shedding Light on Time Series Classification using Interpretability Gated NetworksPoster
Shifting the Paradigm: A Diffeomorphism Between Time Series Data Manifolds for Achieving Shift-Invariancy in Deep LearningPoster
Should VLMs be Pre-trained with Image Data?Poster
SiMHand: Mining Similar Hands for Large-Scale 3D Hand Pose Pre-trainingPoster
SigDiffusions: Score-Based Diffusion Models for Time Series via Log-Signature EmbeddingsPoster
SimXRD-4M: Big Simulated X-ray Diffraction Data and Crystal Symmetry Classification BenchmarkPoster
Simple yet Effective Incomplete Multi-view Clustering: Similarity-level Imputation and Intra-view Hybrid-group Prototype ConstructionSpotlight
Simple, Good, Fast: Self-Supervised World Models Free of BaggagePoster
SimulPL: Aligning Human Preferences in Simultaneous Machine TranslationPoster
Simulating Training Dynamics to Reconstruct Training Data from Deep Neural NetworksPoster
Single Teacher, Multiple Perspectives: Teacher Knowledge Augmentation for Enhanced Knowledge DistillationPoster
Sketch2Diagram: Generating Vector Diagrams from Hand-Drawn SketchesPoster
Sketching for Convex and Nonconvex Regularized Least Squares with Sharp GuaranteesPoster
SleepSMC: Ubiquitous Sleep Staging via Supervised Multimodal CoordinationPoster
Slot-Guided Adaptation of Pre-trained Diffusion Models for Object-Centric Learning and Compositional GenerationPoster
Small Models are LLM Knowledge Triggers for Medical Tabular PredictionPoster
Small-to-Large Generalization: Training Data Influences Models Consistently Across ScalePoster
SoftCVI: Contrastive variational inference with self-generated soft labelsSpotlight
SoftMatcha: A Soft and Fast Pattern Matcher for Billion-Scale Corpus SearchesPoster
Solving Differential Equations with Constrained LearningPoster
SoundCTM: Unifying Score-based and Consistency Models for Full-band Text-to-Sound GenerationPoster
Sparse components distinguish visual pathways & their alignment to neural networksSpotlight
SparsyFed: Sparse Adaptive Federated LearningPoster
Spectral Compressive Imaging via Unmixing-driven Subspace Diffusion RefinementSpotlight
Spectro-Riemannian Graph Neural NetworksPoster
SplineGS: Learning Smooth Trajectories in Gaussian Splatting for Dynamic Scene ReconstructionPoster
Stabilizing Reinforcement Learning in Differentiable Multiphysics SimulationSpotlight
Stable Hadamard Memory: Revitalizing Memory-Augmented Agents for Reinforcement LearningPoster
Start Smart: Leveraging Gradients For Enhancing Mask-based XAI MethodsPoster
State Space Model Meets Transformer: A New Paradigm for 3D Object DetectionPoster
State Space Models are Provably Comparable to Transformers in Dynamic Token SelectionPoster
Statistical Tractability of Off-policy Evaluation of History-dependent Policies in POMDPsPoster
Stealthy Shield Defense: A Conditional Mutual Information-Based Approach against Black-Box Model Inversion AttacksPoster
Steering Protein Family Design through Profile Bayesian FlowOral
Stem-OB: Generalizable Visual Imitation Learning with Stem-Like Convergent Observation through Diffusion InversionSpotlight
Stiefel Flow Matching for Moment-Constrained Structure ElucidationPoster
StochSync: Stochastic Diffusion Synchronization for Image Generation in Arbitrary SpacesPoster
Stochastic Bandits Robust to Adversarial AttacksPoster
Stochastic variance-reduced Gaussian variational inference on the Bures-Wasserstein manifoldPoster
Storybooth: Training-Free Multi-Subject Consistency for Improved Visual StorytellingPoster
Strategist: Self-improvement of LLM Decision Making via Bi-Level Tree SearchPoster
Streaming Algorithms For $\ell_p$ Flows and $\ell_p$ RegressionSpotlight
Strength Estimation and Human-Like Strength Adjustment in GamesPoster
StringLLM: Understanding the String Processing Capability of Large Language ModelsPoster
Strong Preferences Affect the Robustness of Preference Models and Value AlignmentPoster
Structuring Benchmark into Knowledge Graphs to Assist Large Language Models in Retrieving and Designing ModelsPoster
Studying the Interplay Between the Actor and Critic Representations in Reinforcement LearningPoster
Style Outweighs Substance: Failure Modes of LLM Judges in Alignment BenchmarkingPoster
Subtask-Aware Visual Reward Learning from Segmented DemonstrationsPoster
Supervised and Semi-Supervised Diffusion Maps with Label-Driven DiffusionPoster
Support is All You Need for Certified VAE TrainingPoster
Surprising Effectiveness of pretraining Ternary Language Model at ScaleSpotlight
Swift Hydra: Self-Reinforcing Generative Framework for Anomaly Detection with Multiple Mamba ModelsPoster
Swing-by Dynamics in Concept Learning and Compositional GeneralizationPoster
SymDiff: Equivariant Diffusion via Stochastic SymmetrisationPoster
SymmetricDiffusers: Learning Discrete Diffusion on Finite Symmetric GroupsOral
Synergy Between Sufficient Changes and Sparse Mixing Procedure for Disentangled Representation LearningPoster
Synthesizing Realistic fMRI: A Physiological Dynamics-Driven Hierarchical Diffusion Model for Efficient fMRI AcquisitionPoster
SysBench: Can LLMs Follow System Message?Poster
Systems with Switching Causal Relations: A Meta-Causal PerspectiveSpotlight
T2V2: A Unified Non-Autoregressive Model for Speech Recognition and Synthesis via Multitask LearningPoster
TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language ModelsSpotlight
TAU-106K: A New Dataset for Comprehensive Understanding of Traffic AccidentPoster
TC-MoE: Augmenting Mixture of Experts with Ternary Expert ChoicePoster
TD-Paint: Faster Diffusion Inpainting Through Time-Aware Pixel ConditioningPoster
TDDBench: A Benchmark for Training data detectionPoster
TFG-Flow: Training-free Guidance in Multimodal Generative FlowPoster
THE ROBUSTNESS OF DIFFERENTIABLE CAUSAL DISCOVERY IN MISSPECIFIED SCENARIOSPoster
TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech SeparationPoster
TIGeR: Unifying Text-to-Image Generation and Retrieval with Large Multimodal ModelsPoster
TRENDy: Temporal Regression of Effective Nonlinear DynamicsPoster
TS-LIF: A Temporal Segment Spiking Neuron Network for Time Series ForecastingPoster
TSC-Net: Prediction of Pedestrian Trajectories by Trajectory-Scene-Cell ClassificationPoster
TTVD: Towards a Geometric Framework for Test-Time Adaptation Based on Voronoi DiagramPoster
TVNet: A Novel Time Series Analysis Method Based on Dynamic Convolution and 3D-VariationPoster
TabDiff: a Mixed-type Diffusion Model for Tabular Data GenerationPoster
TabWak: A Watermark for Tabular Diffusion ModelsSpotlight
Tackling Data Corruption in Offline Reinforcement Learning via Sequence ModelingPoster
Taming Transformer Without Using Learning Rate WarmupPoster
Targeted Attack Improves Protection against Unauthorized Diffusion CustomizationSpotlight
Task Descriptors Help Transformers Learn Linear Models In-ContextPoster
Teaching Human Behavior Improves Content Understanding Abilities Of VLMsPoster
Teaching LLMs How to Learn with Contextual Fine-TuningPoster
TeaserGen: Generating Teasers for Long DocumentariesPoster
Temporal Difference Learning: Why It Can Be Fast and How It Will Be FasterPoster
Temporal Flexibility in Spiking Neural Networks: Towards Generalization Across Time Steps and Deployment FriendlinessPoster
Temporal Heterogeneous Graph Generation with Privacy, Utility, and EfficiencySpotlight
Test-Time Adaptation for Combating Missing Modalities in Egocentric VideosPoster
Test-Time Ensemble via Linear Mode Connectivity: A Path to Better AdaptationPoster
Test-time Adaptation for Cross-modal Retrieval with Query ShiftSpotlight
Test-time Adaptation for Regression by Subspace AlignmentPoster
TexTailor: Customized Text-aligned Texturing via Effective ResamplingPoster
The Belief State TransformerPoster
The Breakdown of Gaussian Universality in Classification of High-dimensional Linear Factor MixturesPoster
The Case for Cleaner Biosignals: High-fidelity Neural Compressor Enables Transfer from Cleaner iEEG to Noisier EEGPoster
The Computational Complexity of Positive Non-Clashing Teaching in GraphsPoster
The Directionality of Optimization Trajectories in Neural NetworksPoster
The Effectiveness of Curvature-Based Rewiring and the Role of Hyperparameters in GNNs RevisitedPoster
The Hidden Cost of Waiting for Accurate PredictionsOral
The Journey Matters: Average Parameter Count over Pre-training Unifies Sparse and Dense Scaling LawsPoster
The Labyrinth of Links: Navigating the Associative Maze of Multi-modal LLMsPoster
The Ramanujan Library - Automated Discovery on the Hypergraph of Integer RelationsPoster
The Value of Sensory Information to a RobotPoster
The adaptive complexity of parallelized log-concave samplingPoster
The impact of allocation strategies in subset learning on the expressive power of neural networksPoster
Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional SamplersPoster
Think Thrice Before You Act: Progressive Thought Refinement in Large Language ModelsPoster
Three Mechanisms of Feature Learning in a Linear NetworkPoster
ThunderKittens: Simple, Fast, and $\textit{Adorable}$ KernelsSpotlight
Tight Lower Bounds under Asymmetric High-Order Hölder Smoothness and Uniform ConvexityOral
Tight Time Complexities in Parallel Stochastic Optimization with Arbitrary Computation DynamicsPoster
Time After Time: Deep-Q Effect Estimation for Interventions on When and What to doPoster
To Clip or not to Clip: the Dynamics of SGD with Gradient Clipping in High-DimensionsPoster
To Tackle Adversarial Transferability: A Novel Ensemble Training Method with Fourier TransformationPoster
To Trust or Not to Trust? Enhancing Large Language Models' Situated Faithfulness to External ContextsSpotlight
ToVE: Efficient Vision-Language Learning via Knowledge Transfer from Vision ExpertsPoster
ToddlerDiffusion: Interactive Structured Image Generation with Cascaded Schrödinger BridgePoster
Token-Supervised Value Models for Enhancing Mathematical Problem-Solving Capabilities of Large Language ModelsPoster
TopoGaussian: Inferring Internal Topology Structures from Visual CluesPoster
Topological Zigzag Spaghetti for Diffusion-based Generation and Prediction on GraphsPoster
Toward Efficient Multi-Agent Exploration With Trajectory Entropy MaximizationPoster
Towards Auto-Regressive Next-Token Prediction: In-context Learning Emerges from GeneralizationPoster
Towards Certification of Uncertainty Calibration under Adversarial AttacksPoster
Towards Continuous Reuse of Graph Models via Holistic Memory DiversificationPoster
Towards Domain Adaptive Neural Contextual BanditsPoster
Towards Effective Evaluations and Comparisons for LLM Unlearning MethodsPoster
Towards Empowerment Gain through Causal Structure Learning in Model-Based Reinforcement LearningPoster
Towards Explaining the Power of Constant-depth Graph Neural Networks for Structured Linear ProgrammingPoster
Towards Faster Decentralized Stochastic Optimization with Communication CompressionPoster
Towards Federated RLHF with Aggregated Client Preference for LLMsPoster
Towards Generalization Bounds of GCNs for Adversarially Robust Node ClassificationPoster
Towards Homogeneous Lexical Tone Decoding from Heterogeneous Intracranial RecordingsPoster
Towards Improving Exploration through Sibling Augmented GFlowNetsPoster
Towards Learning High-Precision Least Squares Algorithms with Sequence ModelsPoster
Towards Marginal Fairness Sliced Wasserstein BarycenterSpotlight
Towards Multiple Character Image Animation Through Enhancing Implicit DecouplingPoster
Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMsPoster
Towards Scalable Topological RegularizersPoster
Towards Self-Supervised Covariance Estimation in Deep Heteroscedastic RegressionPoster
Towards Synergistic Path-based Explanations for Knowledge Graph Completion: Exploration and EvaluationPoster
Towards Unbiased Learning in Semi-Supervised Semantic SegmentationPoster
Towards Understanding Text Hallucination of Diffusion Models via Local Generation BiasPoster
Towards Understanding Why FixMatch Generalizes Better Than Supervised LearningOral
Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix ItPoster
Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic PerspectivePoster
Towards a Complete Logical Framework for GNN ExpressivenessOral
Towards a Unified and Verified Understanding of Group-Operation NetworksSpotlight
Towards counterfactual fairness through auxiliary variablesPoster
Towards hyperparameter-free optimization with differential privacySpotlight
Tracing Representation Progression: Analyzing and Enhancing Layer-Wise SimilarityPoster
Tractable Multi-Agent Reinforcement Learning through Behavioral EconomicsOral
Train Small, Infer Large: Memory-Efficient LoRA Training for Large Language ModelsPoster
Training Free Exponential Context Extension via Cascading KV CachePoster
Training Large Language Models for Retrieval-Augmented Question Answering through Backtracking CorrectionPoster
Training One-Dimensional Graph Neural Networks is NP-HardPoster
Training Robust Ensembles Requires Rethinking Lipschitz ContinuityPoster
Training-Free Dataset Pruning for Instance SegmentationPoster
Training-Free Message Passing for Learning on HypergraphsPoster
Training-free LLM-generated Text Detection by Mining Token Probability SequencesPoster
Trajectory attention for fine-grained video motion controlPoster
Trajectory-Class-Aware Multi-Agent Reinforcement LearningPoster
Transformer Block Coupling and its Correlation with Generalization in LLMsPoster
Transformer Encoder Satisfiability: Complexity and Impact on Formal ReasoningPoster
Transformer Learns Optimal Variable Selection in Group-Sparse ClassificationPoster
Transformer Meets Twicing: Harnessing Unattended Residual InformationPoster
Transformers Learn Low Sensitivity Functions: Investigations and ImplicationsPoster
Transformers Learn to Implement Multi-step Gradient Descent with Chain of ThoughtSpotlight
Transformers Provably Learn Two-Mixture of Linear Classification via Gradient FlowPoster
Transition Path Sampling with Improved Off-Policy Training of Diffusion Path SamplersPoster
Triples as the Key: Structuring Makes Decomposition and Verification Easier in LLM-based TableQAPoster
Trivialized Momentum Facilitates Diffusion Generative Modeling on Lie GroupsPoster
Trusted Multi-View Classification via Evolutionary Multi-View FusionPoster
Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language ModelsOral
Two Sparse Matrices are Better than One: Sparsifying Neural Networks with Double Sparse FactorizationPoster
TypedThinker: Diversify Large Language Model Reasoning with Typed ThinkingPoster
U-shaped and Inverted-U Scaling behind Emergent Abilities of Large Language ModelsPoster
UIFace: Unleashing Inherent Model Capabilities to Enhance Intra-Class Diversity in Synthetic Face RecognitionPoster
UTILITY: Utilizing Explainable Reinforcement Learning to Improve Reinforcement LearningPoster
UV-Attack: Physical-World Adversarial Attacks on Person Detection via Dynamic-NeRF-based UV MappingPoster
Uncertainty Herding: One Active Learning Method for All Label BudgetsPoster
Uncertainty-Aware Decoding with Minimum Bayes RiskPoster
Uncovering Gaps in How Humans and LLMs Interpret Subjective LanguageSpotlight
Uncovering Latent Memories in Large Language ModelsPoster
Understanding Matrix Function Normalizations in Covariance Pooling through the Lens of Riemannian GeometryPoster
Understanding Virtual Nodes: Oversquashing and Node HeterogeneityPoster
Understanding Warmup-Stable-Decay Learning Rates: A River Valley Loss Landscape ViewPoster
Understanding and Enhancing Safety Mechanisms of LLMs via Safety-Specific NeuronPoster
Understanding and Enhancing the Transferability of Jailbreaking AttacksPoster
Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothingPoster
Understanding and Mitigating Hallucination in Large Vision-Language Models via Modular Attribution and InterventionPoster
Understanding the Generalization of In-Context Learning in Transformers: An Empirical StudyPoster
Understanding the Stability-based Generalization of Personalized Federated LearningPoster
Unhackable Temporal Reward for Scalable Video MLLMsPoster
Uni-Sign: Toward Unified Sign Language Understanding at ScalePoster
UniCBE: An Uniformity-driven Comparing Based Evaluation Framework with Unified Multi-Objective OptimizationSpotlight
UniCon: Unidirectional Information Flow for Effective Control of Large-Scale Diffusion ModelsPoster
UniGS: Unified Language-Image-3D Pretraining with Gaussian SplattingPoster
UniMatch: Universal Matching from Atom to Task for Few-Shot Drug DiscoverySpotlight
UniRestore3D: A Scalable Framework For General Shape RestorationPoster
UniWav: Towards Unified Pre-training for Speech Representation Learning and GenerationPoster
Union-over-Intersections: Object Detection beyond Winner-Takes-AllSpotlight
Universal generalization guarantees for Wasserstein distributionally robust modelsSpotlight
Unlearning-based Neural InterpretationsOral
Unlocking Global Optimality in Bilevel Optimization: A Pilot StudyPoster
Unposed Sparse Views Room Layout Reconstruction in the Age of Pretrain ModelPoster
Unsupervised Disentanglement of Content and Style via Variance-Invariance ConstraintsPoster
Unsupervised Multiple Kernel Learning for Graphs via Ordinality PreservationPoster
Unsupervised Zero-Shot Reinforcement Learning via Dual-Value Forward-Backward RepresentationPoster
Utilitarian Algorithm Configuration for Infinite Parameter SpacesPoster
Utility-Directed Conformal Prediction: A Decision-Aware Framework for Actionable Uncertainty QuantificationPoster
VCR: A Task for Pixel-Level Complex Reasoning in Vision Language Models via Restoring Occluded TextPoster
VICtoR: Learning Hierarchical Vision-Instruction Correlation Rewards for Long-horizon ManipulationPoster
VLMaterial: Procedural Material Generation with Large Vision-Language ModelsSpotlight
VOILA: Evaluation of MLLMs For Perceptual Understanding and Analogical ReasoningPoster
VTDexManip: A Dataset and Benchmark for Visual-tactile Pretraining and Dexterous Manipulation with Reinforcement LearningPoster
VVC-Gym: A Fixed-Wing UAV Reinforcement Learning Environment for Multi-Goal Long-Horizon ProblemsPoster
Value-aligned Behavior Cloning for Offline Reinforcement Learning via Bi-level OptimizationPoster
Variance-Reducing Couplings for Random FeaturesPoster
Variational Bayesian Pseudo-CoresetPoster
Variational Diffusion Posterior Sampling with Midpoint GuidanceOral
Variational Search DistributionsPoster
Vertical Federated Learning with Missing Features During Training and InferencePoster
ViSAGe: Video-to-Spatial Audio GenerationPoster
Video Action DifferencingPoster
Vision CNNs trained to estimate spatial latents learned similar ventral-stream-aligned representationsPoster
Vision and Language Synergy for Rehearsal Free Continual LearningPoster
Visually Consistent Hierarchical Image ClassificationPoster
Visually Guided Decoding: Gradient-Free Hard Prompt Inversion with Language ModelsPoster
W-PCA Based Gradient-Free Proxy for Efficient Search of Lightweight Language ModelsPoster
WardropNet: Traffic Flow Predictions via Equilibrium-Augmented LearningPoster
Warm Diffusion: Recipe for Blur-Noise Mixture Diffusion ModelsPoster
Wasserstein-Regularized Conformal Prediction under General Distribution ShiftPoster
Watch Less, Do More: Implicit Skill Discovery for Video-Conditioned PolicyPoster
Wavelet-based Positional Representation for Long ContextPoster
Wayward Concepts In Multimodal ModelsPoster
Weakly Supervised Video Scene Graph Generation via Natural Language SupervisionPoster
Weakly-Supervised Affordance Grounding Guided by Part-Level Semantic PriorsPoster
Weighted Multi-Prompt Learning with Description-free Large Language Model DistillationPoster
Weighted Point Set Embedding for Multimodal Contrastive Learning Toward Optimal Similarity MetricSpotlight
What's New in My Data? Novelty Exploration via Contrastive GenerationPoster
When GNNs meet symmetry in ILPs: an orbit-based feature augmentation approachPoster
When Graph Neural Networks Meet Dynamic Mode DecompositionPoster
When LLMs Play the Telephone Game: Cultural Attractors as Conceptual Tools to Evaluate LLMs in Multi-turn SettingsPoster
When Selection Meets Intervention: Additional Complexities in Causal DiscoveryOral
When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear TransformersOral
When narrower is better: the narrow width limit of Bayesian parallel branching neural networksPoster
Where Am I and What Will I See: An Auto-Regressive Model for Spatial Localization and View PredictionPoster
Which Tasks Should Be Compressed Together? A Causal Discovery Approach for Efficient Multi-Task Representation CompressionPoster
Why In-Context Learning Models are Good Few-Shot Learners?Poster
Words in Motion: Extracting Interpretable Control Vectors for Motion TransformersPoster
X-NeMo: Expressive Neural Motion Reenactment via Disentangled Latent AttentionPoster
XAIguiFormer: explainable artificial intelligence guided transformer for brain disorder identificationPoster
YOLO-RD: Introducing Relevant and Compact Explicit Knowledge to YOLO by Retriever-DictionaryPoster
You Only Prune Once: Designing Calibration-Free Model Compression With Policy LearningPoster
Youku Dense Caption: A Large-scale Chinese Video Dense Caption Dataset and BenchmarksPoster
ZIP: An Efficient Zeroth-order Prompt Tuning for Black-box Vision-Language ModelsPoster
Zero-Shot Natural Language ExplanationsPoster
Zero-cost Proxy for Adversarial Robustness EvaluationPoster
Zero-shot Imputation with Foundation Inference Models for Dynamical SystemsPoster
Zeroth-Order Fine-Tuning of LLMs with Transferable Static SparsityPoster
Zigzag Diffusion Sampling: Diffusion Models Can Self-Improve via Self-ReflectionPoster
ZooProbe: A Data Engine for Evaluating, Exploring, and Evolving Large-scale Training Data for Multimodal LLMsPoster
econSG: Efficient and Multi-view Consistent Open-Vocabulary 3D Semantic GaussiansPoster
h4rm3l: A Language for Composable Jailbreak Attack SynthesisPoster
metabench - A Sparse Benchmark of Reasoning and Knowledge in Large Language ModelsPoster
pMoE: Prompting Diverse Experts Together Wins More in Visual AdaptationPoster
qNBO: quasi-Newton Meets Bilevel OptimizationPoster
uniINF: Best-of-Both-Worlds Algorithm for Parameter-Free Heavy-Tailed MABsSpotlight
xFinder: Large Language Models as Automated Evaluators for Reliable EvaluationPoster

ICLR accepted papers in other years

ICLR 2026 (5,356)ICLR 2024 (2,260)ICLR 2023 (1,575)ICLR 2022 (1,094)ICLR 2021 (860)ICLR 2020 (687)ICLR 2019 (502)ICLR 2018 (429)ICLR 2017 (245)

Looking for submission deadlines instead? See the conference deadline calendar.