ICLR 2026 Accepted Papers
The full list of 5,356 papers accepted at ICLR 2026 (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: 5,118Oral: 223ICLR 2026 ConditionalPoster: 14ICLR 2026 ConditionalOral: 1
- Good allocations from bad estimatesPoster
- GradPCA: Leveraging NTK Alignment for Reliable Out-of-Distribution DetectionPoster
- GradPruner: Gradient-guided Layer Pruning Enabling Efficient Fine-Tuning and Inference for LLMsPoster
- GradShield: Alignment Preserving FinetuningPoster
- Gradient Descent Dynamics of Rank-One Matrix DenoisingPoster
- Gradient Descent with Large Step Sizes: Chaos and Fractal Convergence RegionPoster
- Gradient Intrinsic Dimensionality Alignment：Narrowing The Gap Between Low-Rank Adaptation and Full Fine-TuningPoster
- Gradient-Aligned Calibration for Post-Training Quantization of Diffusion ModelsPoster
- Gradient-Based Diversity Optimization with Differentiable Top-$k$ ObjectivePoster
- Gradient-Based Program Synthesis with Neurally Interpreted LanguagesPoster
- Gradient-Direction-Aware Density Control for 3D Gaussian SplattingPoster
- Gradient-Normalized Smoothness for Optimization with Approximate HessiansPoster
- Gradient-Sign Masking for Task Vector Transport Across Pre-Trained ModelsPoster
- GranViT: A Fine-Grained Vision Model With Autoregressive Perception For MLLMsPoster
- Graph Diffusion Transformers are In-Context Molecular DesignersPoster
- Graph Mixing Additive NetworksPoster
- Graph Random Features for Scalable Gaussian ProcessesPoster
- Graph Representational Learning: When Does More Expressivity Hurt Generalization?Poster
- Graph Signal Processing Meets Mamba2: Adaptive Filter Bank via Delta ModulationPoster
- Graph Tokenization for Bridging Graphs and TransformersPoster
- Graph homophily booster: Reimagining the role of discrete features in heterophilic graph learningPoster
- Graph-Theoretic Intrinsic Reward: Guiding RL with Effective ResistancePoster
- Graph-based Nearest Neighbors with Dynamic Updates via Random WalksPoster
- Graph-of-Agents: A Graph-based Framework for Multi-Agent LLM CollaborationPoster
- GraphOmni: A Comprehensive and Extensible Benchmark Framework for Large Language Models on Graph-theoretic TasksPoster
- GraphPlanner: Graph-Based Agentic Routing for LLMsPoster
- GraphShield: Graph-Theoretic Modeling of Network-Level Dynamics for Robust Jailbreak DetectionPoster
- GraphUniverse: Enabling Systematic Evaluation of Inductive GeneralizationPoster
- Graphon Cross-Validation: Assessing Models on Network DataPoster
- Grasp Any Region: Prompting MLLM to Understand the Dense WorldPoster
- Greater than the Sum of Its Parts: Building Substructure into Protein Encoding ModelsPoster
- Grokking in LLM Pretraining? Monitor Memorization-to-Generalization without TestPoster
- Ground Slow, Move Fast: A Dual-System Foundation Model for Generalizable Vision-Language NavigationPoster
- Grounding Computer Use Agents on Human DemonstrationsPoster
- Grounding Generative Planners in Verifiable Logic: A Hybrid Architecture for Trustworthy Embodied AIPoster
- Grounding and Enhancing Informativeness and Utility in Dataset DistillationPoster
- Grounding or Guessing? Visual Signals for Detecting Hallucinations in Sign Language TranslationPoster
- Grounding-IQA: Grounding Multimodal Language Model for Image Quality AssessmentPoster
- Group Critical-token Policy Optimization for Autoregressive Image GenerationPoster
- Group Representational Position EncodingPoster
- Group Verification-based Policy Optimization for Interactive Coding AgentsPoster
- Group-Normalized Implicit Value Optimization for Language ModelsPoster
- Group-Relative REINFORCE Is Secretly an Off-Policy Algorithm: Demystifying Some Myths About GRPO and Its FriendsPoster
- Grouping Nodes with known Value Differences: A lossless UCT-based Abstraction AlgorithmPoster
- Guaranteed Simply Connected Mesh Reconstruction from an Unorganized Point CloudPoster
- GuardAlign: Robust Safety Alignment in Multimodal Large Language ModelsPoster
- Guidance Matters: Rethinking the Evaluation Pitfall for Text-to-Image GenerationPoster
- Guidance Watermarking for Diffusion ModelsPoster
- Guided Flow Policy: Learning from High-Value Actions in Offline Reinforcement LearningPoster
- Guided Policy Optimization under Partial ObservabilityPoster
- Guided Query Refinement: Multimodal Hybrid Retrieval with Test-Time OptimizationPoster
- Guided Speculative Inference for Efficient Test-Time Alignment of LLMsPoster
- GuidedBench: Measuring and Mitigating the Evaluation Discrepancies of In-the-wild LLM Jailbreak MethodsPoster
- GuidedSampling: Steering LLMs Towards Diverse Candidate Solutions at Inference-TimePoster
- Guiding Mixture-of-Experts with Temporal Multimodal InteractionsPoster
- GuirlVG: Incentivize GUI Visual Grounding via Empirical Exploration on Reinforcement LearningPoster
- Gumbel Distillation for Parallel Text GenerationPoster
- H$^3$DP: Triply‑Hierarchical Diffusion Policy for Visuomotor LearningPoster
- H$^3$GNNs: Harmonizing Heterophily and Homophily in GNNs via Self-Supervised Node EncodingPoster
- H2OFlow: Grounding Human-Object Affordances with 3D Generative Models and Dense Diffused FlowsPoster
- HAMLET: Hyperadaptive Agent-based Modeling for Live Embodied TheatricsPoster
- HAMLET: Switch Your Vision-Language-Action Model into a History-Aware PolicyPoster
- HARDTESTGEN: A High-Quality RL Verifier Generation Pipeline for LLM Algorithimic CodingPoster
- HARP: Hallucination Detection via Reasoning Subspace ProjectionPoster
- HATSolver: Learning Gröbner Bases with Hierarchical Attention TransformersOral
- HBO: Hierarchical Balancing Optimization for Fine-Tuning Large Language ModelsPoster
- HDR-NSFF: High Dynamic Range Neural Scene Flow FieldsPoster
- HEAPr: Hessian-based Efficient Atomic Expert Pruning in Output SpacePoster
- HEEGNet: Hyperbolic Embeddings for EEGPoster
- HEIST: A Graph Foundation Model for Spatial Transcriptomics and Proteomics DataPoster
- HFSTI-Net: Hierarchical Frequency-spatial-temporal Interactions for Video Polyp SegmentationPoster
- HGNet: Scalable Foundation Model for Automated Knowledge Graph Generation from Scientific LiteraturePoster
- HLD: Approximate Hierarchical Linguistic Distribution Modeling for LLM-Generated Text DetectionPoster
- HOG-Diff: Higher-Order Guided Diffusion for Graph GenerationPoster
- HOTA: Hamiltonian framework for Optimal Transport AdvectionPoster
- HSG-12M: A Large-Scale Benchmark of Spatial Multigraphs from the Energy Spectra of Non-Hermitian CrystalsPoster
- HSIC Bottleneck for Cross-Generator and Domain-Incremental Synthetic Image DetectionPoster
- HSSBench: Benchmarking Humanities and Social Sciences Ability for Multimodal Large Language ModelsPoster
- HUME: Measuring the Human-Model Performance Gap in Text Embedding TasksPoster
- HUMOF: Human Motion Forecasting in Interactive Social ScenesPoster
- HWC-Loco: A Hierarchical Whole-Body Control Approach to Robust Humanoid LocomotionPoster
- HYPER: A Foundation Model for Inductive Link Prediction with Knowledge HypergraphsPoster
- HackWorld: Evaluating Computer-Use Agents on Exploiting Web Application VulnerabilitiesPoster
- Half-order Fine-Tuning for Diffusion Model: A Recursive Likelihood Ratio OptimizerOral
- HalluGuard: Demystifying Data-Driven and Reasoning-Driven Hallucinations in LLMsPoster
- Hallucination Begins Where Saliency DropsOral
- Hallucination Reduction with CASAL: Contrastive Activation Steering for Amortized LearningPoster
- Hallucination-aware Intermediate Representation Editing in Large Vision-Lanugage ModelsPoster
- HardcoreLogic: Challenging Large Reasoning Models with Long-tail Logic Puzzle GamesPoster
- Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question ReformulationPoster
- Harmonized Cone for Feasible and Non-conflict Directions in Training Physics-Informed Neural NetworksPoster
- Harnessing Hyperbolic Geometry for Harmful Prompt Detection and SanitizationPoster
- Harnessing Temporal Databases for Systematic Evaluation of Factual Time-Sensitive Question-Answering in LLMsPoster
- Harpoon: Generalised Manifold Guidance for Conditional Tabular DiffusionPoster
- Healthcare Insurance Fraud Detection via Continual Fiedler Vector Graph ModelPoster
- Hedonic Neurons: A Mechanistic Mapping of Latent Coalitions in Transformer MLPsPoster
- Helix: Evolutionary Reinforcement Learning for Open-Ended Scientific Problem SolvingPoster
- Helmsman: Autonomous Synthesis of Federated Learning Systems via Collaborative LLM AgentsPoster
- Hessian-Enhanced Token Attribution (HETA): Interpreting Autoregressive LLMsPoster
- Heterogeneous Agent Q-weighted Policy OptimizationPoster
- Heterogeneous Federated Fine-Tuning with Parallel One-Rank AdaptationPoster
- Heterogeneous Front-Door Effects: Debiased Estimation with Quasi-Oracle GuaranteesPoster
- HeurekaBench: A Benchmarking Framework for AI Co-scientistPoster
- HeuriGym: An Agentic Benchmark for LLM-Crafted Heuristics in Combinatorial OptimizationPoster
- Hey, That's My Model! Introducing Chain & Hash, An LLM Fingerprinting TechniquePoster
- HiCache: A Plug-in Scaled-Hermite Upgrade for Taylor-Style Cache-then-Forecast Diffusion AccelerationPoster
- HiDivDrop: Vision Token Reduction in MLLMs via Late Injection and Differentiable Top-KPoster
- HiFo-Prompt: Prompting with Hindsight and Foresight for LLM-based Automatic Heuristic DesignPoster
- HiGS: History-Guided Sampling for Plug-and-Play Enhancement of Diffusion ModelsPoster
- HiMAE: Hierarchical Masked Autoencoders Discover Resolution-Specific Structure in Wearable Time SeriesPoster
- HiPO: Self-Hint Policy Optimization for RLVRPoster
- HiPRAG: Hierarchical Process Rewards for Efficient Agentic Retrieval Augmented GenerationPoster
- HiTeA: Hierarchical Temporal Alignment for Training-Free Long-Video Temporal GroundingPoster
- HiVid: LLM-Guided Video Saliency For Content-Aware VOD And Live StreamingPoster
- Hidden Breakthroughs in Language Model TrainingPoster
- Hidden Patterns in Chain-of-Thought ReasoningPoster
- HiddenEcho: Mitigating Noise Amplification in Differentially Private LLMs with Hidden-State CorrectionPoster
- HierLoc: Hyperbolic Entity Embeddings for Hierarchical Visual GeolocationPoster
- Hierarchical Concept-based Interpretable ModelsPoster
- Hierarchical Encoding Tree with Modality Mixup for Cross-modal HashingPoster
- Hierarchical Entity-centric Reinforcement Learning with Factored Subgoal DiffusionPoster
- Hierarchical Multi-Scale Molecular Conformer Generation with Structural AwarenessPoster
- Hierarchical Multi-Stage Recovery Framework for Kronecker Compressed SensingPoster
- Hierarchical Prototype Learning for Semantic SegmentationPoster
- Hierarchical Semantic-Acoustic Modeling via Semi-Discrete Residual Representations for Expressive End-to-End Speech SynthesisPoster
- Hierarchical Value-Decomposed Offline Reinforcement Learning for Whole-Body ControlPoster
- Hierarchy Decoding: A Training-free Parallel Decoding Strategy for Diffusion Large Language ModelsPoster
- Hierarchy-of-Groups Policy Optimization for Long-Horizon Agentic TasksPoster
- High Accuracy, Less Talk (HALT): Reliable LLMs through Capability-Aligned FinetuningPoster
- High Probability Bounds for Non-Convex Stochastic Optimization with MomentumPoster
- High-Dimensional Analysis of Single-Layer Attention for Sparse-Token ClassificationPoster
- High-Probability Bounds for the Last Iterate of Clipped SGDPoster
- High-dimensional Analysis of Synthetic Data SelectionOral
- High-dimensional Mean-Field Games by Particle-based Flow MatchingPoster
- High-dimensional limit theorems for SGD: Momentum and Adaptive Step-sizesPoster
- Highly Efficient and Effective LLMs with Multi-Boolean ArchitecturesPoster
- Hilbert-Guided Sparse Local AttentionPoster
- Hilbert: Recursively Building Formal Proofs with Informal ReasoningPoster
- Hinge Regression Tree: A Newton Method for Oblique Regression Tree SplittingPoster
- HippoTune: A Hippocampal Associative Loop–Inspired Fine-Tuning Method for Continual LearningPoster
- Hippoformer: Integrating Hippocampus-inspired Spatial Memory with TransformersPoster
- HistoPrism: Unlocking Functional Pathway Analysis from Pan-Cancer Histology via Gene Expression PredictionPoster
- Histopathology-Genomics Multi-modal Structural Representation Learning for Data-Efficient Precision OncologyPoster
- Holdout-Loss-Based Data Selection for LLM Finetuning via In-Context LearningPoster
- Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent EvaluationPoster
- HoloPart: Generative 3D Part Amodal SegmentationPoster
- Homeostatic Adaptation of Optimal Population Codes under Metabolic StressPoster
- Horizon Imagination: Efficient On-Policy Rollout in Diffusion World ModelsPoster
- Horseshoe Splatting: Handling Structural Sparsity for Uncertainty-Aware Gaussian-Splatting Radiance Field RenderingPoster
- Hot Fuzz: Temperature-Tunable Composition of Diffusion models with Fuzzy LogicPoster
- Hot PATE: Private Aggregation of Distributions for Diverse TasksPoster
- Hourglass Persistence for Graphs, Simplices, and CellsPoster
- Householder-Diagonalized Linear Attention (HDLA): Utilizing Enhanced Decay Mechanism for Efficient Sequence ModelingPoster
- How Base Frequency Shapes RoPE: An Analytical Study of Frequency-Band FormationPoster
- How Catastrophic is Your LLM? Certifying Risk in ConversationPoster
- How Dark Patterns Manipulate Web AgentsPoster
- How Do Medical MLLMs Fail? A Study on Visual Grounding in Medical ImagesPoster
- How Do Transformers Learn to Associate Tokens: Gradient Leading Terms Bring Mechanistic InterpretabilityOral
- How Far Are LLMs from Professional Poker Players? Revisiting Game-Theoretic Reasoning with Agentic Tool UsePoster
- How Far Can Unsupervised RLVR Scale LLM Training?Poster
- How Learning Rate Decay Wastes Your Best Data in Curriculum-Based LLM PretrainingOral
- How Many Code and Test Cases Are Enough? Evaluating Test Cases Generation from a Binary-Matrix PerspectivePoster
- How Muon’s Spectral Design Benefits Generalization: A Study on Imbalanced DataPoster
- How NOT to benchmark your SITE metric: Beyond Static Leaderboards and Towards Realistic Evaluation.Poster
- How Reliable is Language Model Micro-Benchmarking?Oral
- How Stable is the Next Token? A Geometric View of LLM Prediction StabilityPoster
- How Text Quality Interventions Reshape Neural Scaling Laws for LLMs: Empirical StudyPoster
- How Transformers Learn Causal Structures In-Context: Explainable Mechanism Meets Theoretical GuaranteePoster
- How Well Does GPT-4o Understand Vision? Evaluating Multimodal Foundation Models on Standard Computer Vision TasksPoster
- How does the optimizer implicitly bias the model merging loss landscape?Poster
- How hard is learning to cut? Trade-offs and sample complexityPoster
- How reinforcement learning after next-token prediction facilitates learningPoster
- How to Lose Inherent Counterfactuality in Reinforcement LearningPoster
- How to Square Tensor Networks and Circuits Without Squaring ThemPoster
- How to train data-efficient LLMsPoster
- Hubble: a Model Suite to Advance the Study of LLM MemorizationOral
- Human Behavior Atlas: Benchmarking Unified Psychological And Social Behavior UnderstandingPoster
- Human Uncertainty-Aware Data Selection and Automatic Labeling in Visual Question AnsweringPoster
- Human or Machine? A Preliminary Turing Test for Speech-to-Speech InteractionPoster
- Human-AI Curation Synergy: Scaling Preference Data Curation via Human-Guided AI FeedbackPoster
- Human-LLM Collaborative Feature Engineering for Tabular DataPoster
- Human-MME: A Holistic Evaluation Benchmark for Human-Centric Multimodal Large Language ModelsPoster
- Human-Object Interaction via Automatically Designed VLM-Guided Motion PolicyPoster
- Human3R: Everyone Everywhere All at OncePoster
- HumanPCR: Probing MLLM Capabilities in Diverse Human-Centric ScenesPoster
- Humanline: Online Alignment as Perceptual LossPoster
- Huxley-G\"odel Machine: Human-Level Coding Agent Development by an Approximation of the Optimal Self-Improving MachineOral
- Hybrid Deep Searcher: Scalable Parallel and Sequential Search ReasoningPoster
- Hybrid Reinforcement: when reward is sparse, better to be densePoster
- Hybrid Training for Vision-Language-Action ModelsPoster
- Hyden: A Hybrid Dual-Path Encoder for Monocular Geometry of High-resolution ImagesPoster
- Hyper-SET: Designing Transformers via Hyperspherical Energy MinimizationPoster
- Hyperbolic Aware Minimization: Implicit Bias for SparsityPoster
- Hyperparameter Trajectory Inference with Conditional Lagrangian Optimal TransportOral
- Hyperspherical Latents Improve Continuous-Token Autoregressive GenerationPoster
- Hystar: Hypernetwork-driven Style-adaptive Retrieval via Dynamic SVD ModulationPoster
- I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data?Poster
- I-DRUID: Layout to image generation via instance-disentangled representation and unpaired dataPoster
- I2Mole: Interaction-aware Invariant Molecular Learning For Generalizable Property PredictionPoster
- IA2: Alignment with ICL Activations improves Supervised Fine-TuningPoster
- IC-Custom: Diverse Image Customization via In-Context LearningPoster
- ICDiffAD: Implicit Conditioning Diffusion Model for Time Series Anomaly DetectionPoster
- ICPO: Provable and Practical In-Context Policy Optimization for Test-Time ScalingPoster
- ICYM2I: The illusion of multimodal informativeness under missingnessPoster
- ICaRus: Identical Cache Reuse for Efficient Multi-Model InferencePoster
- IDEAL: Data Equilibrium Adaptation for Multi-Capability Language Model AlignmentPoster
- IDER: IDEMPOTENT EXPERIENCE REPLAY FOR RELIABLE CONTINUAL LEARNINGPoster
- IF-VidCap: Can Video Caption Models Follow Instructions?Poster
- IGC-Net for conditional average potential outcome estimation over timePoster
- IGGT: Instance-Grounded Geometry Transformer for Semantic 3D ReconstructionPoster
- IGU-LoRA: Adaptive Rank Allocation via Integrated Gradients and Uncertainty-Aware ScoringPoster
- IMSE: Intrinsic Mixture of Spectral Experts Fine-tuning for Test-Time AdaptationPoster
- INO-SGD: Addressing Utility Imbalance under Individualized Differential PrivacyPoster
- INSTANT: Compressing Gradients and Activations for Resource-Efficient TrainingPoster
- INTIMA: A Benchmark for Human-AI Companionship BehaviorPoster
- IR-Agent: Expert-Inspired LLM Agents for Structure Elucidation from Infrared SpectraPoster
- IV-Bench: A Benchmark for Image-Grounded Video Perception and Reasoning in Multimodal LLMsPoster
- IVC-Prune: Revealing the Implicit Visual Coordinates in LVLMs for Vision Token PruningPoster
- IVEBench: Modern Benchmark Suite for Instruction-Guided Video Editing AssessmentPoster
- IWR-Bench: Can LVLMs reconstruct interactive webpage from a user interaction video?Poster
- Ice Cream Doesn’t Cause Drowning: Benchmarking LLMs Against Statistical Pitfalls in Causal InferencePoster
- IceCache: Memory-Efficient KV-cache Management for Long-Sequence LLMsPoster
- Identifiability Challenges in Sparse Linear Ordinary Differential EquationsPoster
- Identifiability and recoverability in self-supervised modelsPoster
- Identifying Robust Neural Pathways: Few-Shot Adversarial Mask Tuning for Vision-Language ModelsPoster
- Identifying and Evaluating Inactive Heads in Pretrained LLMsPoster
- Identity-Free Deferral For Unseen ExpertsPoster
- Image Can Bring Your Memory Back: A Novel Multi-Modal Guided Attack against Image Generation Model UnlearningPoster
- Image Quality Assessment for Embodied AIPoster
- Image is All You Need: Towards Efficient and Effective Large Language Model-Based Recommender SystemsPoster
- ImageDoctor: Diagnosing Text-to-Image Generation via Grounded Image ReasoningPoster
- ImageRAG: Dynamic Image Retrieval for Reference-Guided Image GenerationPoster
- ImagenWorld: Stress-Testing Image Generation Models with Explainable Human Evaluation on Open-ended Real-World TasksPoster
- Imagine How To Change: Explicit Procedure Modeling for Change CaptioningPoster
- Imitating the Truth: Attention-aware Truth-Guided Enhancement for Hallucination Mitigation in Large Vision-Language ModelsPoster
- Imitation Learning as Return Distribution MatchingPoster
- Implicit 4D Gaussian Splatting for Fast Motion with Large Inter-Frame DisplacementsPoster
- Implicit Bias and Loss of Plasticity in Matrix Completion: Depth Promotes Low-RanknessPoster
- Implicit Bias of Per-sample Adam on Separable Data: Departure from the Full-batch RegimePoster
- Implicit Inversion turns CLIP into a DecoderPoster
- Implicit Models: Expressive Power Scales with Test-Time ComputePoster
- Implicit Regularisation in Diffusion Models: An Algorithm-Dependent Generalisation AnalysisPoster
- Implicit Sensing for Fourier Sparse Boolean FunctionsPoster
- Implicit bias produces neural scaling laws in learning curves, from perceptrons to deep networksPoster
- Importance Sampling for Multi-Negative Multimodal Direct Preference OptimizationPoster
- ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test CasesPoster
- Improved $\ell_{p}$ Regression via Iteratively Reweighted Least SquaresPoster
- Improved Adversarial Diffusion Compression for Real-World Video Super-ResolutionPoster
- Improved Object-Centric Diffusion Learning with Registers and Contrastive AlignmentPoster
- Improved high-dimensional estimation with Langevin dynamics and stochastic weight averagingPoster
- Improving 2D Diffusion Models for 3D Medical Imaging with Inter‑Slice Consistent StochasticityPoster
- Improving Attributed Long-form Question Answering with Intent AwarenessPoster
- Improving Autoregressive Video Modeling with History UnderstandingPoster
- Improving Black-Box Generative Attacks via Generator Semantic ConsistencyPoster
- Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and VariationsPoster
- Improving Classifier-Free Guidance in Masked Diffusion: Low-Dim Theoretical Insights with High-Dim ImpactPoster
- Improving Code Localization with Repository MemoryPoster
- Improving Diffusion Models for Class-imbalanced Training Data via Capacity ManipulationOral
- Improving Discrete Diffusion Unmasking Policies Beyond Explicit Reference PoliciesPoster
- Improving Extreme Wind Prediction with Frequency-Informed LearningPoster
- Improving Feasibility via Fast Autoencoder-Based ProjectionsPoster
- Improving Human-AI Coordination through Online Adversarial Training and Generative ModelsPoster
- Improving LLM-based Global Optimization with Search Space PartitioningPoster
- Improving Long-Range Interactions in Graph Neural Simulators via Hamiltonian DynamicsPoster
- Improving Online-to-Nonconvex Conversion for Smooth Optimization via Double OptimismPoster
- Improving Reasoning for Diffusion Language Models via Group Diffusion Policy OptimizationPoster
- Improving Semantic Proximity in English-Centric Information Retrieval through Cross-Lingual AlignmentPoster
- Improving Set Function Approximation with Quasi-Arithmetic Neural NetworksPoster
- Improving Text-guided CAD Prototyping via Modality-Specific TokenizationPoster
- Improving and Accelerating Offline RL in Large Discrete Action Spaces with Structured Policy InitializationPoster
- In Agents We Trust, but Who Do Agents Trust? Latent Preferences Steer LLM GenerationsPoster
- In Context Semi-Supervised LearningPoster
- In Good GRACES: Principled Teacher Selection for Knowledge DistillationPoster
- In-Context AlgebraPoster
- In-Context Algorithm Emulation in Fixed-Weight TransformersPoster
- In-Context Compositional Q-Learning for Offline Reinforcement LearningPoster
- In-Context Learning for Pure ExplorationPoster
- In-Context Learning of Temporal Point Processes with Foundation Inference ModelsPoster
- In-Context Watermarks for Large Language ModelsPoster
- In-Place Test-Time TrainingOral
- In-The-Flow Agentic System Optimization for Effective Planning and Tool UseOral
- InSight-o3: Empowering Multimodal Foundation Models with Generalized Visual SearchPoster
- IncVGGT: Incremental VGGT for Memory-Bounded Long-Range 3D ReconstructionPoster
- Incentive-Aligned LLM SummariesPoster
- Incentives in Federated Learning with Heterogeneous AgentsPoster
- Incentivizing Agentic Reasoning in LLM Judges via Tool-Integrated Reinforcement LearningPoster
- Incentivizing Consistent, Effective and Scalable Reasoning Capability in Audio LLMs via Reasoning Process RewardsPoster
- Incentivizing LLM Reasoning via Reinforcement Learning with Functional Monte Carlo Tree SearchPoster
- InclusiveVidPose: Bridging the Pose Estimation Gap for Individuals with Limb Deficiencies in Video-Based MotionPoster
- Incomplete Data, Complete Dynamics: A Diffusion ApproachPoster
- Incomplete Multi-View Multi-Label Classification via Shared Codebook and Fused-Teacher Self-DistillationPoster
- Inconsistency Biases in Dynamic Data PruningPoster
- Incorporating Expert Priors into Bayesian Optimization via Dynamic Mean DecayPoster
- Independence Test for Linear Non-Gaussian Data and Applications in Causal DiscoveryPoster
- IndicVisionBench: Benchmarking Cultural and Multilingual Understanding in VLMsPoster
- Inducing Dyslexia in Vision Language ModelsPoster
- Inductive Reasoning for Temporal Knowledge Graphs with Emerging EntitiesPoster
- InfBaGel: Human-Object-Scene Interaction Generation with Dynamic Perception and Iterative RefinementPoster
- InfGen: Scenario Generation as Next Token Group PredictionPoster
- Inference-Time Dynamic Modality Selection for Incomplete Multimodal ClassificationPoster
- Inference-Time Personalized Safety Control via Paired Difference-in-Means InterventionPoster
- Inference-Time Scaling of Discrete Diffusion Models via Importance Weighting and Optimal Proposal DesignPoster
- Inference-time scaling of diffusion models through classical searchPoster
- Inferring brain plasticity rule under long-term stimulation with structured recurrent dynamicsPoster
- Inferring the Invisible: Neuro-Symbolic Rule Discovery for Missing Value ImputationPoster
- Infinite Horizon Markov EconomiesPoster
- Influence Dynamics and Stagewise Data AttributionPoster
- Influence without Confounding: Causal Discovery from Temporal Data with Long-term Carry-over EffectsPoster
- Influence-Preserving Proxies for Gradient-Based Data Selection in LLM FineTuningPoster
- InfoBridge: Mutual Information estimation via Bridge MatchingPoster
- InfoDet: A Dataset for Infographic Element DetectionPoster
- InfoMosaic-Bench: Evaluating Multi-Source Information Seeking in Tool-Augmented AgentsPoster
- InfoNCE Induces Gaussian DistributionOral
- InfoScan: Information-Efficient Visual Scanning via Resource-Adaptive WalksPoster
- InfoTok: Adaptive Discrete Video Tokenizer via Information-Theoretic CompressionOral
- Information Estimation with Discrete DiffusionPoster
- Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn LLM AgentsPoster
- Information Shapes Koopman RepresentationOral
- Information-based Value Iteration Networks for Decision Making Under UncertaintyPoster
- InftyThink: Breaking the Length Limits of Long-Context Reasoning in Large Language ModelsPoster
- Inheriting Generalizable Knowledge from LLMs to Diverse Vertical TasksPoster
- Initialization Schemes for Kolmogorov–Arnold Networks: An Empirical StudyPoster
- Inlier-Centric Post-Training Quantization for Object Detection ModelsPoster
- InnoGym: Benchmarking the Innovation Potential of AI AgentsPoster
- InnovatorBench: Evaluating Agents’ Ability to Conduct Innovative AI ResearchPoster
- Inoculation Prompting: Eliciting traits from LLMs during training can reduce trait expression at test-timePoster
- Inpainting-Guided Policy Optimization for Diffusion Large Language ModelsPoster
- InputDSA: Demixing, then comparing recurrent and externally driven dynamicsPoster
- Instance-Dependent Fixed-Budget Pure Exploration in Reinforcement LearningPoster
- Instance-wise Adaptive Scheduling via Derivative-Free Meta-LearningPoster
- Instilling an Active Mind in Avatars via Cognitive SimulationOral
- Intention-Conditioned Flow Occupancy ModelsPoster
- Inter-Agent Relative Representations for Multi-Agent Option DiscoveryPoster
- InterActHuman: Multi-Concept Human Animation with Layout-Aligned Audio ConditionsPoster
- Interact-RAG: Reason and Interact with the Corpus, Beyond Black-Box RetrievalPoster
- Interaction Field Matching: Overcoming Limitations of Electrostatic ModelsPoster
- Interaction-aware Representation Modeling With Co-Occurrence Consistency for Egocentric Hand-Object ParsingPoster
- Interactive Agents to Overcome Underspecificity in Software EngineeringPoster
- Interactive Learning of Single-Index Models via Stochastic Gradient DescentPoster
- Interference-Isolated Elastic Weight Consolidation and Knowledge Calibration for Incremental Object DetectionPoster
- Interleave-VLA: Enhancing Robot Manipulation with Image-Text Interleaved InstructionsPoster
- Interleaving Reasoning for Better Text-to-Image GenerationPoster
- InternSVG: Towards Unified SVG Tasks with Multimodal Large Language ModelsPoster
- InternSpatial: A Comprehensive Dataset for Spatial Reasoning in Vision-Language ModelsPoster
- Internal Evaluation of Density-Based Clusterings with NoisePoster
- Internal Planning in Language Models: Characterizing Horizon and Branch AwarenessPoster
- Interp3D: Correspondence-aware Interpolation for Generative Textured 3D MorphingPoster
- Interpolation-Based Conditioning of Flow Matching Models for Bioisosteric Ligand DesignPoster
- Interpretable 3D Neural Object Volumes for Robust Conceptual ReasoningPoster
- Into the Rabbit Hull: From Task-Relevant Concepts in DINO to Minkowski GeometryPoster
- Intrinsic Entropy of Context Length Scaling in LLMsOral
- Intrinsic Explanation of Random Subspace Method for Enhanced Security ApplicationsPoster
- Intrinsic Lorentz Neural NetworkPoster
- Intrinsic training dynamics of deep neural networksPoster
- Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?Poster
- Inverse Reinforcement Learning with Dynamic Reward Scaling for LLM AlignmentPoster
- Inverse Virtual Try-On: Generating Multi-Category Product-Style Images from Clothed IndividualsPoster
- Invert4TVG: A Temporal Video Grounding Framework with Inversion Tasks Preserving Action Understanding AbilityPoster
- Investigating Redundancy in Multimodal Large Language Models with Multiple Vision EncodersPoster
- Invisible Safety Threat: Malicious Finetuning for LLM via SteganographyOral
- Is Finer Better? The Limits of Microscaling Formats in Large Language ModelsPoster
- Is Graph Unlearning Ready for Practice? A Benchmark on Efficiency, Utility, and ForgettingPoster
- Is In-Context Learning Learning?Poster
- Is On-Policy Data always the Best Choice for Direct Preference Optimization-Based LM Alignment?Poster
- Is Pure Exploitation Sufficient in Exogenous MDPs with Linear Function Approximation?Poster
- Is This Just Fantasy? Language Model Representations Reflect Human Judgments of Event PlausibilityPoster
- Is Your Paper Being Reviewed by an LLM? Benchmarking AI Text Detection in Peer ReviewPoster
- Is it Thinking or Cheating? Detecting Implicit Reward Hacking by Measuring Reasoning EffortOral
- Is the Reversal Curse a Binding Problem? Uncovering Limitations of Transformers from a Basic Generalization FailurePoster
- It's All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online OptimizationPoster
- It's All Just Vectorization: einx, a Universal Notation for Tensor OperationsOral
- IterResearch: Rethinking Long-Horizon Agents via Markovian State ReconstructionPoster
- Iterative Distillation for Reward-Guided Fine-Tuning of Diffusion Models in Biomolecular DesignPoster
- Iterative Training of Physics-Informed Neural Networks with Fourier-enhanced FeaturesPoster
- J1: Incentivizing Thinking in LLM-as-a-Judge via Reinforcement LearningPoster
- JALMBench: Benchmarking Jailbreak Vulnerabilities in Audio Language ModelsPoster
- JAPAN: Joint Adaptive Prediction Areas with Normalising FlowPoster
- JULI: Jailbreak Large Language Models by Self-IntrospectionPoster
- Jackpot: Align Actor-Policy Distribution for scalable and stable RL for LLMPoster
- Jacobian Aligned Random ForestsPoster
- JailNewsBench: Multi-Lingual and Regional Benchmark for Fake News Generation under Jailbreak AttacksPoster
- Jailbreak Transferability Emerges from Shared RepresentationsPoster
- JailbreakLoRA: Your Downloaded LoRA from Sharing Platforms might be UnsafePoster
- Jailbreaking on Text-to-Video Models via Scene Splitting StrategyPoster
- Jailbreaking the Matrix: Nullspace Steering for Controlled Model SubversionPoster
- JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code IntelligencePoster
- JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language NavigationPoster
- JavisDiT++: Unified Modeling and Optimization for Joint Audio-Video GenerationPoster
- JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior SynchronizationPoster
- Jet Expansions: Restructuring LLM Computation for Model InspectionPoster
- Johnson-Lindenstrauss Lemma Guided Network for Efficient 3D Medical SegmentationPoster
- Joint Adaptation of Uni-modal Foundation Models for Multi-modal Alzheimer's Disease DiagnosisPoster
- Joint Distillation for Fast Likelihood Evaluation and Sampling in Flow-based ModelsPoster
- Joint Distribution–Informed Shapley Values for Sparse Counterfactual ExplanationsPoster
- Joint Optimization for 4D Human-Scene Reconstruction in the WildPoster
- Joint Selection for Large-Scale Pre-Training Data via Policy Gradient-based Mask LearningPoster
- Joint Shadow Generation and Relighting via Light-Geometry Interaction MapsPoster
- JointAVBench: A Benchmark for Joint Audio-Visual Reasoning EvaluationPoster
- JointDiff: Bridging Continuous and Discrete in Multi-Agent Trajectory GenerationPoster
- Journey to the Centre of Cluster: Harnessing Interior Nodes for A/B Testing under Network InterferencePoster
- Judo: A Juxtaposed Domain-oriented Multimodal Reasoner for Industrial Anomaly QAPoster
- Just Do It!? Computer-Use Agents Exhibit Blind Goal-DirectednessPoster
- K-Prism: A Knowledge-Guided and Prompt Integrated Universal Medical Image Segmentation ModelPoster
- K-Sort Eval: Efficient Preference Evaluation for Visual Generation via Corrected VLM-as-a-JudgePoster
- KANO: Kolmogorov-Arnold Neural OperatorPoster
- KBVQ-MoE: KLT-guided SVD with Bias-Corrected Vector Quantization for MoE Large Language ModelsPoster
- KDP: Simplifying Representation Dynamics in Kernel SpacePoster
- KGOT: Unified Knowledge Graph and Optimal Transport Pseudo-Labeling for Molecule-Protein Interaction PredictionPoster
- KL-Regularized Reinforcement Learning is Designed to Mode CollapsePoster
- KLAS: Using Similarity to Stitch Neural Networks for an Improved Accuracy-Efficiency TradeoffPoster
- KRAMABENCH: A Benchmark for AI Systems on Data-to-Insight Pipelines over Data LakesPoster
- KV-Cache Transform Coding for Compact Storage in LLM InferencePoster
- KVComm: Enabling Efficient LLM Communication through Selective KV SharingPoster
- KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding ModelPoster
- KaVa: Latent Reasoning via Compressed KV-Cache DistillationPoster
- Kaleidoscope: In-language Exams for Massively Multilingual Vision EvaluationPoster
- Keep the Best, Forget the Rest: Reliable Alignment with Order-Aware Preference OptimizationPoster
- KeepLoRA: Continual Learning with Residual Gradient AdaptationPoster
- KernelFusion: Zero-Shot Blind Super-Resolution via Patch DiffusionPoster
- Kevin: Multi-Turn RL for Generating CUDA KernelsPoster
- Kimi-Dev: Agentless Training as Skill Prior for SWE-agentsPoster
- KinemaDiff: Towards Diffusion for Coherent and Physically Plausible Human Motion PredictionPoster
- Know When to Abstain: Optimal Selective Classification with Likelihood RatiosPoster
- KnowGuard: Knowledge-Driven Abstention for Multi-Round Clinical ReasoningPoster
- KnowProxy: Adapting Large Language Models by Knowledge-guided ProxyPoster
- Knowing When to Quit: Probabilistic Early Exits for Speech Separation NetworksPoster
- Knowledge Distillation as Decontamination? Revisiting the “Data Laundering” ConcernPoster
- Knowledge Distillation for Large Language Models through Residual LearningPoster
- Knowledge Editing with Subspace-Aware Key-Value MappingsPoster
- Knowledge Exchange with Confidence: Cost-Effective LLM Integration for Reliable and Efficient Visual Question AnsweringPoster
- Knowledge Externalization: Reversible Unlearning and Modular Retrieval in Multimodal Large Language ModelsPoster
- Knowledge Fusion of Large Language Models via Modular SkillPacksPoster
- Knowledge Reasoning Language Model: Unifying Knowledge and Language for Inductive Knowledge Graph ReasoningPoster
- KnowledgeSmith: Uncovering Knowledge Updating in LLMs with Model Editing and UnlearningPoster
- Knowledgeable Language Models as Black-Box Optimizers for Personalized MedicinePoster
- Koopman-Assisted Trajectory Synthesis: A Data Augmentation Framework for Offline Imitation LearningPoster
- K²-Agent: Co-Evolving Know-What and Know-How for Hierarchical Mobile Device ControlPoster
- LABEL-FREE MITIGATION OF SPURIOUS CORRELATIONS IN VLMS USING SPARSE AUTOENCODERSPoster
- LAMDA: A Longitudinal Android Malware Benchmark for Concept Drift AnalysisPoster
- LANE: Label-Aware Noise Elimination for Fine-Grained Text ClassificationPoster
- LCA: Local Classifier Alignment for Continual LearningPoster
- LD-EnSF: Synergizing Latent Dynamics with Ensemble Score Filters for Fast Data Assimilation with Sparse ObservationsPoster
- LD-MoLE: Learnable Dynamic Routing for Mixture of LoRA ExpertsPoster
- LDT: Layer-Decomposition Training Makes Networks More GeneralizablePoster
- LEAP: Local ECT-Based Learnable Positional Encodings for GraphsPoster
- LEGACY: A Lightweight Dynamic Gradient Compression Strategy for Distributed Deep LearningPoster
- LEGATO: Large-scale End-to-end Generalizable Approach to Typeset OMRPoster
- LENS: Multi-level Evaluation of Multimodal Reasoning with Large Language ModelsICLR 2026 ConditionalPoster
- LEXam: Benchmarking Legal Reasoning on 340 Law ExamsPoster
- LFQA-E: Carefully Benchmarking Long-form QA EvaluationPoster
- LH-DECEPTION: Simulating and Understanding LLM Deceptive Behaviors in Long-Horizon InteractionsPoster
- LINGOLY-TOO: Disentangling Reasoning from Knowledge with Templatised Orthographic ObfuscationPoster
- LINK: Learning Instance-level Knowledge from Vision-Language Models for Human-Object Interaction DetectionPoster
- LLEMA: Accelerating Materials Design via LLM-Guided Evolutionary SearchPoster
- LLM DNA: Tracing Model Evolution via Functional RepresentationsOral
- LLM Fingerprinting via Semantically Conditioned WatermarksOral
- LLM Pretraining with Continuous ConceptsPoster
- LLM Unlearning with LLM BeliefsPoster
- LLM as an Algorithmist: Enhancing Anomaly Detectors via Programmatic SynthesisPoster
- LLM-Guided Evolutionary Program Synthesis for Quasi-Monte Carlo DesignPoster
- LLM-JEPA: Large Language Models Meet Joint Embedding Predictive ArchitecturesPoster
- LLM-as-a-Prophet: Understanding Predictive Intelligence with Prophet ArenaPoster
- LLM2Fx-Tools: Tool Calling for Music Post-ProductionPoster
- LLMS ON TRIAL: Evaluating Judicial Fairness For Large Language ModelsPoster
- LLMs Can Hide Text in Other Text of the Same LengthPoster
- LLMs Get Lost In Multi-Turn ConversationOral
- LLMs Must Think Thrice to Solve Executable CounterfactualsPoster
- LLMs Process Lists With General Filter HeadsPoster
- LLMs Struggle to Balance Reasoning and World Knowledge in Causal Narrative UnderstandingPoster
- LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making AbilitiesPoster
- LLMs are Single-threaded Reasoners: Demystifying the Working Mechanism of Soft ThinkingPoster
- LLMs as Rules Oracles: Exploring Real-World Multimodal Reasoning in Tabletop Strategy Game EnvironmentsPoster
- LLaVA-4D: Embedding SpatioTemporal Prompt into LMMs for 4D Scene UnderstandingPoster
- LLaVA-FA: Learning Fourier Approximation for Compressing Large Multimodal ModelsPoster
- LLaVAction: evaluating and training multi-modal large language models for action understandingPoster
- LMask: Learn to Solve Constrained Routing Problems with Lazy MaskingPoster
- LORE: Jointly Learning The Intrinsic Dimensionality and Relative Similarity Structure from Ordinal DataPoster
- LRIM: a Physics-Based Benchmark for Provably Evaluating Long-Range Capabilities in Graph LearningPoster
- LS-Merge: Merging Language Models in Latent SpacePoster
- LSA: Layer-wise Sparsity Allocation for Large Language Model Pruning Based on Minimal Linear Reconstruction ErrorPoster
- LUMINA: Detecting Hallucinations in RAG System with Context–Knowledge SignalsPoster
- LVTINO: LAtent Video consisTency INverse sOlver for High Definition Video RestorationPoster
- La-Proteina: Atomistic Protein Generation via Partially Latent Flow MatchingPoster
- LaDiR: Latent Diffusion Enhances LLMs for Text ReasoningPoster
- LaSeR: Reinforcement Learning with Last-Token Self-RewardingPoster
- LaTo: Landmark-tokenized Diffusion Transformer for Fine-grained Human Face EditingPoster
- LaVCa: LLM-assisted Visual Cortex CaptioningPoster
- Label Smoothing Improves Machine UnlearningPoster
- LadderSym: A Multimodal Interleaved Transformer for Music Practice Error DetectionPoster
- Landing with the Score: Riemannian Optimization through DenoisingPoster
- Landscape of Thoughts: Visualizing the Reasoning Process of Large Language ModelsPoster
- Language Agents for Hypothesis-driven Clinical Decision Making with Reinforcement LearningPoster
- Language Confusion Gate: Language-Aware Decoding Through Model Self-DistillationPoster
- Language Identification in the Limit with Computational TracePoster
- Language Models Use Lookbacks to Track BeliefsPoster
- Language Models are Injective and Hence InvertiblePoster
- Language and Experience: A Computational Model of Social Learning in Complex TasksPoster
- Language in the Flow of Time: Time-Series-Paired Texts Weaved into a Unified Temporal NarrativePoster
- Language-Instructed Vision Embeddings for Controllable and Generalizable PerceptionPoster
- Language-guided Open-world Video Anomaly Detection under Weak SupervisionICLR 2026 ConditionalPoster
- Laplacian Kernelized BanditPoster
- Laplacian Multi-scale Flow Matching for Generative ModelingPoster
- LaplacianFormer:Rethinking Linear Attention with Laplacian KernelPoster
- Large Depth Completion Model from Sparse ObservationsPoster
- Large Scale Diffusion Distillation via Score-Regularized Continuous-Time ConsistencyPoster
- Larger Datasets Can Be Repeated More: A Theoretical Analysis of Multi-Epoch Scaling in Linear RegressionPoster
- Late-to-Early Training: LET LLMs Learn Earlier, So Faster and BetterPoster
- Latent Adaptation of Foundation Policies for Sim-to-Real TransferPoster
- Latent Concept Disentanglement in Transformer-based Language ModelsPoster
- Latent Denoising Makes Good TokenizersPoster
- Latent Diffusion Model without Variational AutoencoderPoster
- Latent Fourier TransformOral
- Latent Geometry-Driven Network Automata for Complex Network DismantlingPoster
- Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics ModelingOral
- Latent Planning Emerges with ScalePoster
- Latent Speech-Text TransformerOral
- Latent Stochastic InterpolantsPoster
- Latent Thinking Optimization: Your Latent Reasoning Language Model Secretly Encodes Reward Signals in its Latent ThoughtsPoster
- Latent Veracity Inference for Identifying Errors in Stepwise ReasoningPoster
- Latent Visual ReasoningPoster
- Latent Wasserstein Adversarial Imitation LearningPoster
- Latent Wavelet Diffusion For Ultra High-Resolution Image SynthesisPoster
- Latent-Guided Reasoning: Empowering Small LLMs with Large-Model ThinkingPoster
- Latent-to-Data Cascaded Diffusion Models for Unconditional Time Series GenerationPoster
- LatentQA: Teaching LLMs to Decode Activations Into Natural LanguagePoster
- Lavida-O: Elastic Large Masked Diffusion Models for Unified Multimodal Understanding and GenerationPoster
- LayerSync: Self-aligning Intermediate LayersPoster
- Layerwise Federated Learning for Heterogeneous Quantum Clients using QuorusPoster
- LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit CorrespondencePoster
- LeRobot: An Open-Source Library for End-to-End Robot LearningPoster
- LeSTD: LLM Compression via Learning-based Sparse Tensor DecompositionPoster
- Lean Finder: Semantic Search for Mathlib That Understands User IntentsPoster
- LeanForPhysics: Comprehensive Reasoning Framework for University-level Physics in Lean4ICLR 2026 ConditionalPoster
- LearNAT: Learning NL2SQL with AST-guided Task Decomposition for Large Language ModelsPoster
- Learn More with Less: Uncertainty Consistency Guided Query Selection for RLVRPoster
- Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement LearningPoster
- Learn to Guide Your Diffusion ModelPoster
- Learn to Reason Efficiently with Adaptive Length-based Reward ShapingPoster
- Learn-to-Distance: Distance Learning for Detecting LLM-Generated TextPoster
- LearnIR: Learnable Posterior Sampling for Real-World Image RestorationPoster
- LearnPruner: Rethinking Attention-based Token Pruning in Vision Language ModelsPoster
- Learnability and Privacy Vulnerability are Entangled in a Few Critical WeightsPoster
- Learnable Fractional Superlets with a Spectro-Temporal Emotion Encoder for Speech Emotion RecognitionPoster
- Learnable Sparsity for Vision Generative ModelsPoster
- Learned Meta-Tokens for Language ModelingPoster
- Learning AND–OR Templates for Compositional Representation in Art and DesignPoster
- Learning Adaptive Distribution Alignment with Neural Characteristic Function for Graph Domain AdaptationPoster
- Learning Admissible Heuristics for A*: Theory and PracticePoster
- Learning Boltzmann Generators via Constrained Mass TransportPoster
- Learning Brain Representation with Hierarchical Visual EmbeddingsPoster
- Learning Collective Variables from BioEmu with Time-Lagged GenerationPoster
- Learning Concept Bottleneck Models from Mechanistic ExplanationsPoster
- Learning Correlated Reward Models: Statistical Barriers and OpportunitiesPoster
- Learning Data-Efficient and Generalizable Neural Operators via Fundamental Physics KnowledgePoster
- Learning Distributions over Permutations and Rankings with Factorized RepresentationsPoster
- Learning Domain-Aware Task Prompt Representations for Multi-Domain All-in-One Image RestorationPoster
- Learning Dynamic Causal Graphs Under Parametric Uncertainty via Polynomial Chaos ExpansionsPoster
- Learning Dynamics Feature Representation via Policy Attention for Dynamic Path Planning in Urban Road NetworksPoster
- Learning Dynamics of Logits Debiasing for Long-Tailed Semi-Supervised LearningPoster
- Learning Efficient and Interpretable Multi-Agent CommunicationPoster
- Learning Escorted Protocols For Multistate Free-Energy EstimationPoster
- Learning Explicit Single-Cell Dynamics Using ODE RepresentationsPoster
- Learning Exposure Mapping Functions for Inferring Heterogeneous Peer EffectsPoster
- Learning Facts at Scale with Active ReadingPoster
- Learning Flexible Forward Trajectories for Masked Molecular DiffusionPoster
- Learning From Dictionary: Enhancing Robustness of Machine-Generated Text Detection in Zero-Shot Language via Adversarial TrainingPoster
- Learning From the Past with Cascading Eligibility TracesPoster
- Learning Global Hypothesis Space for Enhancing Synergistic Reasoning ChainPoster
- Learning Heterogeneous Degradation Representation for Real-World Super-ResolutionPoster
- Learning Hierarchical and Geometry-Aware Graph Representations for Text-to-CADPoster
- Learning Human Habits with Rule-Guided Active InferencePoster
- Learning Koopman Representations with Controllability GuaranteesPoster
- Learning Massively Multitask World Models for Continuous ControlPoster
- Learning Mixtures of Linear Dynamical Systems (MoLDS) via Hybrid Tensor–EM MethodPoster
- Learning Molecular Chirality via Chiral Determinant KernelsPoster
- Learning More with Less: A Dynamic Dual-Level Down-Sampling Framework for Efficient Policy OptimizationPoster
- Learning Nonlinear Causal Reductions to Explain Reinforcement Learning PoliciesPoster
- Learning Ordinal Probabilistic Reward from PreferencesPoster
- Learning Part-Aware Dense 3D Feature Field For Generalizable Articulated Object ManipulationPoster
- Learning Patient-Specific Disease Dynamics With Latent Flow Matching For Longitudinal Imaging GenerationPoster
- Learning Physics-Grounded 4D Dynamics with Neural Gaussian Force FieldsPoster
- Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph PriorsPoster
- Learning Pseudorandom Numbers with Transformers: Permuted Congruential Generators, Curricula, and InterpretabilityPoster
- Learning Recursive Multi-Scale Representations for Irregular Multivariate Time Series ForecastingPoster
- Learning Retrieval Models with Sparse AutoencodersPoster
- Learning Robust Intervention Representations with Delta EmbeddingsPoster
- Learning Self-Critiquing Mechanisms for Region-Guided Chest X-Ray Report GenerationPoster
- Learning Semi-Structured Sparsity for LLMs via Shared and Context-Aware HypernetworkPoster
- Learning Shrinks the Hard Tail: Training‑Dependent Inference Scaling in a Solvable Linear ModelPoster
- Learning Structure-Semantic Evolution Trajectories for Graph Domain AdaptationPoster
- Learning Survival Distributions with Individually Calibrated Asymmetric Laplace DistributionPoster
- Learning To Draft: Adaptive Speculative Decoding with Reinforcement LearningPoster
- Learning Unified Representation of 3D Gaussian SplattingPoster
- Learning Video Generation for Robotic Manipulation with Collaborative Trajectory ControlPoster
- Learning What Matters Now: Dynamic Preference Inference under Contextual ShiftsPoster
- Learning What Reinforcement Learning Can't: Interleaved Online Fine-Tuning for Hardest QuestionsPoster
- Learning a Game by Paying the AgentsPoster
- Learning a distance measure from the information-estimation geometry of dataPoster
- Learning an Image Editing Model without Image Editing PairsPoster
- Learning for Highly Faithful ExplainabilityPoster
- Learning from Algorithm Feedback: One-Shot SAT Solver Guidance with GNNsPoster
- Learning from Historical Activations in Graph Neural NetworksPoster
- Learning from Label Proportions via Proportional Value ClassificationPoster
- Learning from Noisy Preferences: A Semi-Supervised Learning Approach to Direct Preference OptimizationPoster
- Learning from Synthetic Data Improves Multi-hop ReasoningPoster
- Learning from the Electronic Structure of Molecules across the Periodic TablePoster
- Learning in Prophet Inequalities with Noisy ObservationsPoster
- Learning is Forgetting; LLM Training As Lossy CompressionPoster
- Learning linear state-space models with sparse system matricesPoster
- Learning multimodal dictionary decompositions with group-sparse autoencodersPoster
- Learning of Population Dynamics: Inverse Optimization Meets JKO SchemePoster
- Learning on a Razor’s Edge: Identifiability and Singularity of Polynomial Neural NetworksPoster
- Learning residue level protein dynamics with multiscale GaussiansPoster
- Learning the Inverse Temperature of Ising Models under Hard Constraints using One SamplePoster
- Learning to Adapt: In-Context Learning Beyond StationarityPoster
- Learning to Answer from Correct DemonstrationsPoster
- Learning to Be Uncertain: Pre-training World Models with Horizon-Calibrated UncertaintyPoster
- Learning to Generate Stylized Handwritten Text via a Unified Representation of Style, Content, and NoisePoster
- Learning to Generate Unit Test via Adversarial Reinforcement LearningPoster
- Learning to Grasp Anything By Playing with Random ToysPoster
- Learning to Interpret Weight Differences in Language ModelsPoster
- Learning to Lie: Adversarial Attacks on Human-AI Teams and LLMsPoster
- Learning to Orchestrate Agents in Natural Language with the ConductorPoster
- Learning to Parallel: Accelerating Diffusion Large Language Models via Adaptive Parallel DecodingPoster
- Learning to Play Multi-Follower Bayesian Stackelberg GamesPoster
- Learning to Reason Efficiently with Discounted Reinforcement LearningPoster
- Learning to Reason as Action Abstractions with Scalable Mid-Training RLPoster
- Learning to Reason for Hallucination Span DetectionPoster
- Learning to Reason in Structured In-context Environments with Reinforcement LearningPoster
- Learning to Reason over Continuous Tokens with Reinforcement LearningPoster
- Learning to Reason via Mixture-of-Thought for Logical ReasoningPoster
- Learning to Reason without External RewardsPoster
- Learning to Recall with Transformers Beyond Orthogonal EmbeddingsPoster
- Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-trainingOral
- Learning to Segment for Vehicle Routing ProblemsOral
- Learning to Solve Orienteering Problem with Time Windows and Variable ProfitsPoster
- Learning to Summarize by Learning to Quiz: Adversarial Agentic Collaboration for Long Document SummarizationPoster
- Learning to Weight Parameters for Training Data AttributionPoster
- Learning to summarize user information for personalized reinforcement learning from human feedbackPoster
- Learning under Quantization for High-Dimensional Linear RegressionPoster
- Learning with Dual-level Noisy Correspondence for Multi-modal Entity AlignmentOral
- Learning-Augmented Moment Estimation on Time-Decay ModelsPoster
- Learning-Time Encoding Shapes Unlearning in LLMsPoster
- Less Gaussians, Texture More: 4K Feed-Forward Textured SplattingPoster
- Less Is More: Clustered Cross-Covariance Control for Offline RLPoster
- Let Features Decide Their Own Solvers: Hybrid Feature Caching for Diffusion TransformersOral
- Let LLMs Speak Embedding Languages: Generative Text Embeddings via Iterative Contrastive RefinementPoster
- Let OOD Feature Exploring Vast Predefined ClassifiersPoster
- Let's (not) just put things in Context: Test-time Training for Long-context LLMsPoster
- Let's Explore Step by Step: Generating Provable Formal Statements with Deductive ExplorationPoster
- Let's Split Up: Zero-Shot Classifier Edits for Fine-Grained Video UnderstandingPoster
- Let's Think in Two Steps: Mitigating Agreement Bias in MLLMs with Self-Grounded VerificationPoster
- Leveraging Data to Say No: Memory Augmented Plug-and-Play Selective PredictionPoster
- Leveraging Discrete Function Decomposability for Scientific DesignPoster
- Leveraging Explanation to Improve Generalization of Meta Reinforcement LearningPoster
- Leveraging Pretrained Knowledge at Inference Time: LoRA-Gated Contrastive Decoding for Multilingual Factual Language Generation in Adapted LLMsPoster
- LiFR-Seg: Anytime High-Frame-Rate Segmentation via Event-Guided PropagationPoster
- LiTo: Surface Light Field TokenizationPoster
- Libra: Effective yet Efficient Load Balancing for Large-scale MoE InferencePoster
- Lifelong Embodied Navigation LearningPoster
- Lifelong Learning with Behavior Consolidation for Vehicle RoutingPoster
- Light Differentiable Logic Gate NetworksPoster
- Light of Normals: Unified Feature Representation for Universal Photometric StereoPoster
- Light-X: Generative 4D Video Rendering with Camera and Illumination ControlPoster
- LightCtrl: Training-free Controllable Video RelightingPoster
- LightMem: Lightweight and Efficient Memory-Augmented GenerationPoster
- LightRetriever: A LLM-based Text Retrieval Architecture with Extremely Faster Query InferencePoster
- Lightweight Spatio-Temporal Modeling via Temporally Shifted Distillation for Real-Time Accident AnticipationPoster
- Lightweight Transformer for EEG Classification via Balanced Signed Graph Algorithm UnrollingPoster
- Linear Mechanisms for Spatiotemporal Reasoning in Vision Language ModelsPoster
- LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale CorporaPoster
- LinearSR: Unlocking Linear Attention for Stable and Efficient Image Super-ResolutionPoster
- LingoLoop Attack: Trapping MLLMs via Linguistic Context and State Entrapment into Endless LoopsPoster
- LinguaMap: Which Layers of LLMs Speak Your Language and How to Tune Them?Poster
- Linking Process to Outcome: Conditional Reward Modeling for LLM ReasoningPoster
- LipNeXt: Scaling up Lipschitz-based Certified Robustness to Billion-parameter ModelsPoster
- Lipschitz Bandits with Stochastic Delayed FeedbackPoster
- LiteGuard: Efficient Task-Agnostic Model Fingerprinting with Enhanced GeneralizationPoster
- LiveClin: A Live Clinical Benchmark without LeakagePoster
- LiveMoments: Reselected Key Photo Restoration in Live Photos via Reference-guided DiffusionPoster
- LiveResearchBench: Benchmarking Single- and Multi-Agent Systems for Citation-Grounded Deep ResearchPoster
- LiveWeb-IE: A Benchmark For Online Web Information ExtractionPoster
- LoC-Decomp: LLM Autoformalization via Logical Concept Decomposition and Iterative Feedback CorrectionPoster
- LoFT: Low-Rank Adaptation That Behaves Like Full Fine-TuningPoster
- LoRA meets Riemannion: Muon Optimizer for Parametrization-independent Low-Rank AdaptersPoster
- LoRA-Mixer: Coordinate Modular LoRA Experts Through Serial Attention RoutingPoster
- LoRA-S: An Efficient Low Rank Adaptation scheme via Sylvester equationPoster
- LoRAGen: Structure-Aware Weight Space Learning for LoRA GenerationPoster
- Loc$^{2}$: Interpretable Cross-View Localization via Depth-Lifted Local Feature MatchingPoster
- Local Entropy Search over Descent Sequences for Bayesian OptimizationPoster
- Local Geometry Attention for Time Series Forecasting under Realistic CorruptionsPoster
- Local Linear Attention: An Optimal Interpolation of Linear and Softmax Attention For Test-Time RegressionPoster
- Local Reinforcement Learning with Action-Conditioned Root Mean Squared Q-FunctionsPoster
- Local Success Does Not Compose: Benchmarking Large Language Models for Compositional Formal VerificationPoster
- Locality-Attending Vision TransformerPoster
- Locality-aware Parallel Decoding for Efficient Autoregressive Image GenerationOral
- Localized Concept Erasure in Text-to-Image Diffusion Models via High-Level Representation MisdirectionPoster
- Localizing Task Recognition and Task Learning in In-Context Learning via Attention Head AnalysisPoster
- Locally Subspace-Informed Neural Operators for Efficient Multiscale PDE SolvingPoster
- Log Probability Tracking of LLM APIsPoster
- Log-Augmented Generation: Scaling Test-Time Reasoning with Reusable ComputationPoster
- Log-Linear AttentionPoster
- LogART: Pushing the Limit of Efficient Logarithmic Post-Training QuantizationPoster
- LogiConBench: Benchmarking Logical Consistencies of LLMsPoster
- LogiStory: A Logic-Aware Framework for Multi-Image Story VisualizationPoster
- LogicReward: Incentivizing LLM Reasoning via Step-Wise Logical SupervisionPoster
- LogicXGNN: Grounded Logical Rules for Explaining Graph Neural NetworksPoster
- Logit‑KL Flow Matching: Non‑Autoregressive Text Generation via Sampling‑Hybrid InferencePoster
- Long Chain-of-Thought Reasoning Across LanguagesPoster
- Long-Context Attention Benchmark: From Kernel Efficiency to Distributed Context ParallelismPoster
- Long-Context Generalization with Sparse AttentionPoster
- Long-Document QA with Chain-of-Structured-Thought and Fine-Tuned SLMsPoster
- Long-Text-to-Image Generation via Compositional Prompt DecompositionPoster
- Long-range Modeling and Processing of Multimodal Event SequencesPoster
- Long-tailed Test-Time Adaptation for Vision-Language ModelsPoster
- LongHorizonUI: A Unified Framework for Robust long-horizon Task Automation of GUI AgentPoster
- LongLive: Real-time Interactive Long Video GenerationPoster
- LongRLVR: Long-Context Reinforcement Learning Requires Verifiable Context RewardsPoster
- LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement LearningOral
- Look Back to Reason Forward: Revisitable Memory for Long-Context LLM AgentsPoster
- Look Carefully: Adaptive Visual Reinforcements in Multimodal Large Language Models for Hallucination MitigationPoster
- Look-ahead Reasoning with a Learned Model in Imperfect Information GamesPoster
- Lookahead Tree-Based Rollouts for Enhanced Trajectory-Level Exploration in Reinforcement Learning with Verifiable RewardsPoster
- LookaheadKV: Fast and Accurate KV Cache Eviction by Glimpsing into the Future without GenerationPoster
- Lookup multivariate Kolmogorov-Arnold NetworksPoster
- LoongRL: Reinforcement Learning for Advanced Reasoning over Long ContextsOral
- LoopFormer: Elastic-Depth Looped Transformers for Latent Reasoning via Shortcut ModulationPoster
- Loopholing Discrete Diffusion: Deterministic Bypass of the Sampling WallPoster
- Lossless Vocabulary Reduction for Auto-Regressive Language ModelsPoster
- Lossy Common Information in a Learnable Gray-Wyner NetworkPoster
- Lost in Tokenization: Context as the Key to Unlocking Biomolecular Understanding in Scientific LLMsPoster
- Lost in the Non-convex Loss Landscape: How to Fine-tune the Large Time Series Model?Poster
- LouisKV: Efficient KV Cache Retrieval for Long Input-Output SequencesPoster
- Low Rank Transformer for Multivariate Time Series Anomaly Detection and LocalizationPoster
- Low rank adaptation of chemical foundation models generate effective odorant representationsPoster
- Low-Latency Neural LiDAR Compression with 2D Context ModelsPoster
- Low-Pass Filtering Improves Behavioral Alignment of Vision ModelsPoster
- Low-Rank Few-Shot Node Classification by Node-Level Graph DiffusionPoster
- Low-pass Personalized Subgraph Federated RecommendationPoster
- LucidFlux: Caption-Free Universal Image Restoration via a Large-Scale Diffusion TransformerPoster
- LumiTex: Towards High-Fidelity PBR Texture Generation with Illumination ContextPoster
- Lumos-1: On Autoregressive Video Generation with Discrete Diffusion from a Unified Model PerspectivePoster
- LumosX: Relate Any Identities with Their Attributes for Personalized Video GenerationPoster
- LycheeDecode: Accelerating Long-Context LLM Inference via Hybrid-Head Sparse DecodingPoster
- Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-DistillationPoster
- M$^2$-Miner: Multi-Agent Enhanced MCTS for Mobile GUI Agent Data MiningPoster
- M$^3$E: Continual Vision-and-Language Navigation via Mixture of Macro and Micro ExpertsPoster
- M3CoTBench: Benchmark Chain-of-Thought of MLLMs in Medical Image UnderstandingPoster
- M4PQA: A Comprehensive QA Dataset for AI Research with Instance-Level EvaluationPoster
- MAC-AMP: A Closed-Loop Multi-Agent Collaboration System for Multi-Objective Antimicrobial Peptide DesignPoster
- MAGE: Multi-scale Autoregressive Generation for Offline Reinforcement LearningPoster
- MAGO: Beyond Fixed Hyperparameters with Multi-Objective Pareto Optimization for Hybrid LLM ReasoningPoster
- MAGREF: Masked Guidance for Any-Reference Video Generation with Subject DisentanglementPoster
- MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision TokenizerPoster
- MAPSS: Manifold-based Assessment of Perceptual Source SeparationPoster
- MARC: Memory-Augmented RL Token Compression for Efficient Video UnderstandingPoster
- MARS - A Foundational Map Auto-RegressorPoster
- MARS-Sep: Multimodal-Aligned Reinforced Sound SeparationPoster
- MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMsPoster
- MARTI: A Framework for Multi-Agent LLM Systems Reinforced Training and InferencePoster
- MAS$^2$: Self-Generative, Self-Configuring, Self-Rectifying Multi-Agent SystemsPoster
- MASAM: Multimodal Adaptive Sharpness-Aware Minimization for Heterogeneous Data FusionPoster
- MASS: MoErging through Adaptive Subspace SelectionPoster
- MATA: A Trainable Hierarchical Automaton System for Multi-Agent Visual ReasoningPoster
- MATH-Beyond: A Benchmark for RL to Expand Beyond the Base ModelPoster
- MATHMO: Automated Mathematical Modeling Through Adaptive SearchPoster
- MATRIX: Mask Track Alignment for Interaction-aware Video GenerationPoster
- MAVEN: A Mesh-Aware Volumetric Encoding Network for Simulating 3D Flexible DeformationPoster
- MC-Search: Evaluating and Enhancing Multimodal Agentic Search with Structured Long Reasoning ChainsOral
- MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific TalksPoster
- MCP Security Bench (MSB): Benchmarking Attacks Against Model Context Protocol in LLM AgentsPoster
- MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP ServersPoster
- MCP-SafetyBench: A Benchmark for Safety Evaluation of Large Language Models with Real-World MCP ServersPoster
- MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP UsePoster
- MCbiF: Measuring Topological Autocorrelation in Multiscale Clusterings via 2-Parameter Persistent HomologyPoster
- MEGS^{2}: Memory-Efficient Gaussian Splatting via Spherical Gaussians and Unified PruningPoster
- MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon AgentsPoster
- MENLO: From Preferences to Proficiency – Evaluating and Modeling Native-like Quality Across 47 LanguagesPoster
- MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-HeadPoster
- MIAM: Modality Imbalance-Aware Masking for Multimodal Ecological ApplicationsPoster
- MICLIP: Learning to Interpret Representation in Vision ModelsPoster
- MIDAS: Multi-Image Dispersion and Semantic Reconstruction for Jailbreaking MLLMsPoster
- MILCO: Learned Sparse Retrieval Across Languages via a Multilingual ConnectorPoster
- MILPnet: A Multi-Scale Architecture with Geometric Feature Sequence Representations for Advancing MILP ProblemsPoster
- MILR: Improving Multimodal Image Generation via Test-Time Latent ReasoningPoster
- MIMIC-Bench: Exploring the User-Like Thinking and Mimicking Capabilities of Multimodal Large Language ModelsICLR 2026 ConditionalPoster
- MIMIC: Mask-Injected Manipulation Video Generation with Interaction ControlPoster
- MIRA: Memory-Integrated Reinforcement Learning Agent with Limited LLM GuidancePoster
- MIRACLE: Model-free Imitation and Reinforcement Learning for Adaptive Cut-SelectionPoster
- MLE-Smith: Scaling MLE Tasks with Automated Multi-agent PipelinePoster
- MLP Memory: A Retriever-Pretrained Memory for Large Language ModelsPoster
- MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy OptimizationPoster
- MMDuet2: Enhancing Proactive Interaction of Video MLLMs with Multi-Turn Reinforcement LearningPoster
- MME-Emotion: A Holistic Evaluation Benchmark for Emotional Intelligence in Multimodal Large Language ModelsPoster
- MME-Unify: A Comprehensive Benchmark for Unified Multimodal Understanding and Generation ModelsPoster
- MMPD: Diverse Time Series Forecasting via Multi-Mode Patch Diffusion LossPoster
- MMR-Life: Piecing Together Real-life Scenes for Multimodal Multi-image ReasoningPoster
- MMR-V: What's Left Unsaid? A Benchmark for Multimodal Deep Reasoning in VideosPoster
- MMReD: a Cross-Modal Benchmark for Dense Context ReasoningPoster
- MMSI-Bench: A Benchmark for Multi-Image Spatial IntelligencePoster
- MMSU: A Massive Multi-task Spoken Language Understanding and Reasoning BenchmarkPoster
- MMSearch-Plus: Benchmarking Provenance-Aware Search for Multimodal Browsing AgentsPoster
- MMTok: Multimodal Coverage Maximization for Efficient Inference of VLMsPoster
- MMedAgent-RL: Optimizing Multi-Agent Collaboration for Multimodal Medical ReasoningPoster
- MOAI: Module-Optimizing Architecture for Non-Interactive Secure Transformer InferencePoster
- MOBODY: Model-Based Off-Dynamics Offline Reinforcement LearningPoster
- MOLM: Mixture of LoRA MarkersPoster
- MOSAIC: Multi-Subject Personalized Generation via Correspondence-Aware Alignment and DisentanglementPoster
- MOSS: Efficient and Accurate FP8 LLM Training with Microscaling and Automatic ScalingPoster
- MRAD: Zero-Shot Anomaly Detection with Memory-Driven RetrievalPoster
- MRMR: A Realistic and Expert-Level Multidisciplinary Benchmark for Reasoning-Intensive Multimodal RetrievalPoster
- MSCR: Exploring the Vulnerability of LLMs’ Mathematical Reasoning Abilities Using Multi-Source Candidate ReplacementPoster
- MT-DAO: Multi-Timescale Distributed Adaptive Optimizers with Local UpdatesPoster
- MTVCraft: Tokenizing 4D Motion for Arbitrary Character AnimationPoster
- MULTIMODALITY AS SUPERVISION: SELF-SUPERVISED SPECIALIZATION TO THE TEST ENVIRONMENT VIA MULTIMODALITYPoster
- MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample SelectionPoster
- MVAR: Visual Autoregressive Modeling with Scale and Spatial Markovian ConditioningPoster
- MVCustom: Multi-View Customized Diffusion via Geometric Latent Rendering and CompletionPoster
- MVR: Multi-view Video Reward Shaping for Reinforcement LearningPoster
- MaRS: Memory-Adaptive Routing for Reliable Capacity Expansion and Knowledge RetentionPoster
- Machine Unlearning under Retain–Forget EntanglementPoster
- Making Slow Thinking Faster: Compressing LLM Chain-of-Thought via Step EntropyPoster
- Making, Not Taking, the Best of NPoster
- Mamba-3: Improved Sequence Modeling using State Space PrinciplesOral
- MambaSL: Exploring Single-Layer Mamba for Time Series ClassificationPoster
- MambaVoiceCloning: Efficient and Expressive Text-to-Speech via State-Space Modeling and Diffusion ControlPoster
- ManagerBench: Evaluating the Safety-Pragmatism Trade-off in Autonomous LLMsPoster
- Mango-GS: Enhancing Spatio-Temporal Consistency in Dynamic Scenes Reconstruction using Multi-Frame Node-Guided 4D Gaussian SplattingPoster
- ManipEvalAgent: Promptable and Efficient Evaluation Framework for Robotic Manipulation PoliciesPoster
- Manipulation as in Simulation: Enabling Accurate Geometry Perception in RobotsPoster
- Many Eyes, One Mind: Temporal Multi-Perspective and Progressive Distillation for Spiking Neural NetworksPoster
- Many-for-Many: Unify the Training of Multiple Video and Image Generation and Manipulation TasksPoster
- Map as a Prompt: Learning Multi-Modal Spatial-Signal Foundation Models for Cross-scenario Wireless LocalizationPoster
- Map the Flow: Revealing Hidden Pathways of Information in VideoLLMsPoster
- Mapping Overlaps in Benchmarks through Perplexity in the WildPoster
- Mapping Post-Training Forgetting in Language Models at ScalePoster
- MarS-FM: Generative Modeling of Molecular Dynamics via Markov State ModelsPoster
- Market Games for Generative Models: Equilibria, Welfare, and Strategic EntryPoster
- Markovian Transformers for Informative Language ModelingPoster
- MaskCO: Masked Generation Drives Effective Representation Learning and Exploiting for Combinatorial OptimizationPoster
- MaskInversion: Localized Embeddings via Optimization of Explainability MapsPoster
- MaskPro: Linear-Space Probabilistic Learning for Strict (N:M)-Sparsity on LLMsPoster
- Masked Generative Policy for Robotic ControlPoster
- Masked Skill Token Training for Hierarchical Off-Dynamics TransferPoster
- Massive Activations are the Key to Local Detail Synthesis in Diffusion TransformersPoster
- Massive Editing for Large Language Models Based on Dynamic Weight GenerationPoster
- Massive Memorization with Hundreds of Trillions of Parameters for Sequential Transducer Generative RecommendersPoster
- Master Skill Learning with Policy-Grounded Synergy of LLM-based Reward Shaping and ExploringPoster
- Mastering Sparse CUDA Generation through Pretrained Models and Deep Reinforcement LearningOral
- MatRIS: Toward Reliable and Efficient Pretrained Machine Learning Interaction PotentialsPoster
- Matched Data, Better Models: Target Aligned Data Filtering with Sparse FeaturesPoster
- Matching multiple experts: on the exploitability of multi-agent imitation learningPoster
- Matching without Group Barrier for Heterogeneous Treatment Effect EstimationPoster
- Math Blind: Failures in Diagram Understanding Undermine Reasoning in MLLMsPoster
- MathFimer: Enhancing Mathematical Reasoning by Expanding Reasoning Steps through Fill-in-the-Middle TaskPoster
- MathNet: A Global Multimodal Benchmark for Mathematical Reasoning and RetrievalPoster
- Mathesis: Towards Formal Theorem Proving from Natural LanguagesPoster
- Matting Anything 2: Towards Video Matting for AnythingPoster
- Maximizing Asynchronicity in Event-based Neural NetworksPoster
- Maximizing Incremental Information Entropy for Contrastive LearningPoster
- MeSH: Memory-as-State-Highways for Recursive TransformersPoster
- Mean Estimation from Coarse Data: Characterizations and Efficient AlgorithmsPoster
- Mean Flow Policy with Instantaneous Velocity Constraint for One-step Action GenerationOral
- Mean-Field Neural Differential Equations: A Game-Theoretic Approach to Sequence PredictionPoster
- MeanCache: From Instantaneous to Average Velocity for Accelerating Flow Matching InferencePoster
- Measure Twice, Cut Once: A Semantic-Oriented Approach to Video Temporal Localization with Video LLMsPoster
- Measurement Score-Based Diffusion ModelPoster
- Measuring Audio's Impact on Correctness: Audio-Contribution-Aware Post-Training of Large Audio Language ModelsPoster
- Measuring Bias Amplification in Multi-Agent Systems with Large Language ModelsPoster
- Measuring LLM Novelty As The Frontier Of Original And High-Quality OutputPoster
- Measuring Physical-World Privacy Awareness of Large Language Models: An Evaluation BenchmarkPoster
- Measuring Uncertainty CalibrationPoster
- Measuring and Mitigating Rapport Bias of Large Language Models under Multi-Agent Social InteractionsPoster
- Measuring the Intrinsic Dimension of Earth RepresentationsPoster
- Mechanism of Task-oriented Information Removal in In-context LearningPoster
- Mechanistic Detection and Mitigation of Hallucination in Large Reasoning ModelsPoster
- Mechanistic Independence: A Principle for Identifiable Disentangled RepresentationsPoster
- MedAgent-Pro: Towards Evidence-based Multi-modal Medical Diagnosis via Reasoning Agentic WorkflowPoster
- MedAgentGym: A Scalable Agentic Training Environment for Code-Centric Reasoning in Biomedical Data ScienceOral
- MedAraBench: Large-scale Arabic Medical Question Answering Dataset and BenchmarkPoster
- MedGMAE: Gaussian Masked Autoencoders for Medical Volumetric Representation LearningPoster
- MedLesionVQA: A Multimodal Benchmark Emulating Clinical Visual Diagnosis for Body Surface HealthPoster
- MedVR: Annotation-Free Medical Visual Reasoning via Agentic Reinforcement LearningPoster
- Medical Interpretability and Knowledge Maps of Large Language ModelsPoster
- Medical thinking with multiple imagesPoster
- MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory AgentOral
- MemGen: Weaving Generative Latent Memory for Self-Evolving AgentsPoster
- Memba: Membrane-driven Parameter-Efficient Fine-Tuning for MambaPoster
- Membership Inference Attacks Against Fine-tuned Diffusion Language ModelsPoster
- Membership Privacy Risks of Sharpness Aware MinimizationPoster
- Memento: Toward an All-Day Proactive Assistant for Ultra-Long Streaming VideoPoster
- Memorization Through the Lens of Sample GradientsPoster
- Memorizing Long-tail Data Can Help Generalization Through CompositionPoster
- Memory, Benchmark & Robots: A Benchmark for Solving Complex Tasks with Reinforcement LearningPoster
- Memory-Free Continual Learning with Null Space Adaptation for Zero-Shot Vision-Language ModelsPoster
- Memory-Statistics Tradeoff in Continual Learning with Structural RegularizationPoster
- Memory-T1: Reinforcement Learning for Temporal Reasoning in Multi-session AgentsPoster
- MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic ManipulationPoster
- MergOPT: A Merge-Aware Optimizer for Robust Model MergingPoster
- Merge before Forget: A Single LoRA Continual Learning via Continual MergingPoster
- MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal UnderstandingPoster
- MergePRAG: Orthogonal Merging of Passage-experts for Multi-hop Parametric RAGPoster
- MergeTune: Continued Fine-Tuning of Vision-Language ModelsPoster
- MesaNet: Sequence Modeling by Locally Optimal Test-Time TrainingPoster
- Mesh Splatting for End-to-end Multiview Surface ReconstructionPoster
- Meta-Adaptive Prompt Distillation for Few-Shot Visual Question AnsweringPoster
- Meta-Learning Theory-Informed Inductive Biases using Deep Kernel Gaussian ProcessesPoster
- Meta-RL Induces Exploration in Language AgentsPoster
- Meta-Router: Bridging Gold-standard and Preference-based Evaluations in LLM RoutingPoster
- Meta-UCF: Unified Task-Conditioned LoRA Generation for Continual Learning in Large Language ModelsPoster
- MetaCaptioner: Towards Generalist Visual Captioning with Open-source SuitesPoster
- MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late InteractionOral
- MetaSpatial: Reinforcing 3D Spatial Reasoning in VLMs for the MetaversePoster
- MetaVLA: Unified Meta Co-Training for Efficient Embodied AdaptationPoster
- Metis: Training LLMs with FP4 QuantizationPoster
- Metric $k$-clustering using only Weak Comparison OraclesPoster
- MiSS: Revisiting the Trade-off in LoRA with an Efficient Shard-Sharing StructurePoster
- Micro-Macro Coupled Koopman Modeling on Graph for Traffic Flow PredictionPoster
- Micro-Macro Retrieval: Reducing Long-Form Hallucination in Large Language ModelsPoster
- MicroMix: Efficient Mixed-Precision Quantization with Microscaling Formats for Large Language ModelsPoster
- MicroVerse: A Preliminary Exploration Toward a Micro-World SimulationPoster
- Midway Network: Learning Representations for Recognition and Motion from Latent DynamicsPoster
- MindMix: A Multimodal Foundation Model for Auditory Perception Decoding via Deep Neural-Acoustic AlignmentPoster
- MindPilot: Closed-loop Visual Stimulation Optimization for Brain Modulation with EEG-guided DiffusionPoster
- Mini-cluster Guided Long-tailed Deep ClusteringPoster
- Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual SearchPoster
- Minimax Optimal Adversarial Reinforcement LearningPoster
- Minimax Sample Complexity of Graph Neural Networks: Lower Bounds and Structural EffectsPoster
- Minimax-Optimal Aggregation for Density Ratio EstimationPoster
- Minor First, Major Last: A Depth-Induced Implicit Bias of Sharpness-Aware MinimizationPoster
- Mirage or Method? How Model–Task Alignment Induces Divergent RL ConclusionsPoster
- Mirror Flow Matching with Heavy-Tailed Priors for Generative Modeling on Convex DomainsPoster
- Misaligned Roles, Misplaced Images: Structural Input Perturbations Expose Multimodal Alignment Blind SpotsPoster
- Missingness Bias Calibration in Feature Attribution ExplanationsPoster
- Mitigating Hallucination in Vision-Language Model with Depth and Spatial-aware Key-Value RefinementPoster
- Mitigating Mismatch within Reference-based Preference OptimizationPoster
- Mitigating Noise Shift in Denoising Generative Models with Noise Awareness GuidancePoster
- Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable SparsityPoster
- Mitigating Privacy Risk via Forget Set-Free UnlearningPoster
- Mitigating Safety Fallback in Editing-based Backdoor Injection on LLMsPoster
- Mitigating Semantic Collapse in Generative Personalization with Test-Time Embedding AdjustmentPoster
- Mitigating Spurious Correlation via Distributionally Robust Learning with Hierarchical Ambiguity SetsPoster
- Mitigating the Curse of Detail: Scaling Arguments for Feature Learning and Sample ComplexityPoster
- Mitigating the Safety Alignment Tax with Null-Space Constrained Policy OptimizationPoster
- Mix-Ecom: Towards Mixed-Type E-Commerce Dialogues with Complex Domain RulesPoster
- MixLinear: Extreme Low Resource Multivariate Time Series Forecasting with $0.1K$ ParametersPoster
- Mixed-Curvature Tree-Sliced Wasserstein DistancePoster
- Mixing Importance with Diversity: Joint Optimization for KV Cache Compression in Large Vision-Language ModelsPoster
- Mixing Mechanisms: How Language Models Retrieve Bound Entities In-ContextPoster
- Mixture of Cognitive Reasoners: Modular Reasoning with Brain-Like SpecializationPoster
- Mixture of Contexts for Long Video GenerationPoster
- Mixture of Mini Experts: Overcoming the Linear Layer Bottleneck in Multiple Instance LearningPoster
- Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal ResourceOral
- Mixture-of-Visual-Thoughts: Exploring Context-Adaptive Reasoning Mode Selection for General Visual ReasoningPoster
- Mixture-of-World Models: Scaling Multi-Task Reinforcement Learning with Modular Latent DynamicsPoster
- MnemoDyn: Learning Resting State Dynamics from $40$K FMRI sequencesPoster
- MoAlign: Motion-Centric Representation Alignment for Video Diffusion ModelsPoster
- MoBE: Mixture-of-Basis-Experts for Compressing MoE-based LLMsPoster
- MoCa: Modeling Object Consistency for 3D Camera Control in Video GenerationPoster
- MoDr: Mixture-of-Depth-Recurrent Transformers for Test-Time ReasoningPoster
- MoE-GS: Mixture of Experts for Dynamic Gaussian SplattingPoster
- MoEEdit: Efficient and Routing-Stable Knowledge Editing for Mixture-of-Experts LLMsPoster
- MoGA: Mixture-of-Groups Attention for End-to-End Long Video GenerationPoster
- MoGen: Detailed Neuronal Morphology Generation via Point Cloud Flow MatchingPoster
- MoL: Adaptive Mixture-of-Length Reasoning for Efficient Question Answering with ContextPoster
- MoM: Linear Sequence Modeling with Mixture-of-MemoriesPoster
- MoMa: A Simple Modular Learning Framework for Material Property PredictionPoster
- MoMaGen: Generating Demonstrations under Soft and Hard Constraints for Multi-Step Bimanual Mobile ManipulationPoster
- MoNE: Replacing Redundant Experts with Lightweight Novices for Structured Pruning of MoEPoster
- MoRA: Missing Modality Low-Rank Adaptation for Visual RecognitionPoster
- MoRA: Mobility as the Backbone for Geospatial Representation Learning at ScalePoster
- MoReBench: Evaluating Procedural and Pluralistic Moral Reasoning in Language Models, More than OutcomesPoster
- MoSA: Mosaic Shared Adaptation of Large Language ModelsPoster
- MoSA: Motion-Coherent Human Video Generation via Structure-Appearance DecouplingPoster
- MobiEdit: Resource-efficient Knowledge Editing for Personalized On-device LLMsPoster
- Mobile-GS: Real-time Gaussian Splatting for Mobile DevicesPoster
- MobileIPL: Enhancing Mobile Agents Thinking Process via Iterative Preference LearningPoster
- MobileKGQA: On-Device KGQA System on Dynamic Mobile EnvironmentsPoster
- MobileRL: Online Agentic Reinforcement Learning for Mobile GUI AgentsPoster
- Mod-Adapter: Tuning-Free and Versatile Multi-concept Personalization via Modulation AdapterPoster
- Modal Aphasia: Can Unified Multimodal Models Describe Images From Memory?Poster
- Modality Alignment across Trees on Heterogeneous Hyperbolic ManifoldsPoster
- Modality-free Graph In-context AlignmentOral
- Mode-conditioning unlocks superior test-time compute scalingPoster
- Model Already Knows the Best Noise: Bayesian Active Noise Selection via Attention in Video Diffusion ModelPoster
- Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMsPoster
- Model Predictive Adversarial Imitation Learning for Planning from ObservationPoster
- Model-Guided Microstimulation Steers Primate Visual BehaviorPoster
- Model-based Offline RL via Robust Value-Aware Model Learning with Implicitly Differentiable Adaptive WeightingPoster
- Modeling Interference for Treatment Effect Estimation in Network Dynamic EnvironmentPoster
- Modeling Others' Minds as CodePoster
- Modeling the Density of Pixel-level Self-supervised Embeddings for Unsupervised Pathology Segmentation in Medical CTPoster
- MolEditRL: Structure-Preserving Molecular Editing via Discrete Diffusion and Reinforcement LearningPoster
- MolLangBench: A Comprehensive Benchmark for Language-Prompted Molecular Structure Recognition, Editing, and GenerationPoster
- MolecularIQ: Characterizing Chemical Reasoning Capabilities Through Symbolic Verification on Molecular GraphsPoster
- MomaGraph: State-Aware Unified Scene Graphs with Vision-Language Models for Embodied Task PlanningOral
- Monitoring Decomposition Attacks with Lightweight Sequential MonitorsPoster
- Mono4DGS-HDR: High Dynamic Range 4D Gaussian Splatting from Alternating-exposure Monocular VideosPoster
- Monocular Normal Estimation via Shading Sequence EstimationOral
- Monotone Near-Zero-Sum Games: A Generalization of Convex-Concave MinimaxPoster
ICLR accepted papers in other years
Looking for submission deadlines instead? See the conference deadline calendar.