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
- Robustness of Probabilistic Models to Low-Quality Data: A Multi-Perspective AnalysisPoster
- Rodrigues Network for Learning Robot ActionsOral
- Rolling Forcing: Autoregressive Long Video Diffusion in Real TimePoster
- Rote Learning Considered Useful: Generalizing over Memorized Data in LLMsPoster
- RouterArena: An Open Platform for Comprehensive Comparison of LLM RoutersPoster
- Routing Channel-Patch Dependencies in Time Series Forecasting with Graph Spectral DecompositionPoster
- Routing Manifold Alignment Improves Generalization of Mixture-of-Experts LLMsPoster
- Routing Matters in MoE: Scaling Diffusion Transformers with Explicit Routing GuidancePoster
- Routing, Cascades, and User Choice for LLMsPoster
- Rubrics as Rewards: Reinforcement Learning Beyond Verifiable DomainsPoster
- RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic SamplingPoster
- Rényi Sharpness: A Novel Sharpness that Strongly Correlates with GeneralizationPoster
- S$^2$-Guidance: Stochastic Self-Guidance for Training-Free Enhancement of Diffusion ModelsPoster
- S2GO: Streaming Sparse Gaussian OccupancyPoster
- S2R-HDR: A Large-Scale Rendered Dataset for HDR FusionPoster
- S3OD: Towards Generalizable Salient Object Detection with Synthetic DataPoster
- SABRE-FL: Selective and Accurate Backdoor Rejection for Federated Prompt LearningPoster
- SAC Flow: Sample-Efficient Reinforcement Learning of Flow-Based Policies via Velocity-Reparameterized Sequential ModelingPoster
- SAE as a Crystal Ball: Interpretable Features Predict Cross-domain Transferability of LLMs without TrainingPoster
- SAES-SVD: Self-Adaptive Suppression of Accumulated and Local Errors for SVD-based LLM CompressionPoster
- SAFA-SNN: Sparsity-Aware On-Device Few-Shot Class-Incremental Learning with Fast-Adaptive Structure of Spiking Neural NetworkPoster
- SAFER: Risk-Constrained Sample-then-Filter in Large Language ModelsPoster
- SAFETY-GUIDED FLOW (SGF): A UNIFIED FRAMEWORK FOR NEGATIVE GUIDANCE IN SAFE GENERATIONOral
- SAGA: Structural Aggregation Guided Alignment with Dynamic View and Neighborhood Order Selection for Multiview Graph Domain AdaptationPoster
- SAGE: Spatial-visual Adaptive Graph Exploration for Efficient Visual Place RecognitionPoster
- SAIL: Self-Amplified Iterative Learning for Diffusion Model Alignment with Minimal Human FeedbackPoster
- SAIR: Enabling Deep Learning for Protein-Ligand Interactions with a Synthetic Structural DatasetPoster
- SAM 3: Segment Anything with ConceptsPoster
- SAM-Veteran: An MLLM-Based Human-like SAM Agent for Reasoning SegmentationPoster
- SANA-Video: Efficient Video Generation with Block Linear Diffusion TransformerOral
- SAQ: Stabilizer-Aware Quantum Error Correction DecoderPoster
- SARM: Stage-Aware Reward Modeling for Long Horizon Robot ManipulationPoster
- SASFT: Sparse Autoencoder-guided Supervised Finetuning to Mitigate Unexpected Code-Switching in LLMsPoster
- SAVE: A Generalizable Framework for Multi-Condition Single-Cell Generation with Gene Block AttentionPoster
- SC-Arena: A Natural Language Benchmark for Single-Cell Reasoning with Knowledge-Augmented EvaluationPoster
- SCAD: Super-Class-Aware Debiasing for Long-Tailed Semi-Supervised LearningPoster
- SCI-Verifier: Scientific Verifier with ThinkingPoster
- SCOPED: Score–Curvature Out-of-distribution Proximity Evaluator for DiffusionPoster
- SCRAPL: Scattering Transform with Random Paths for Machine LearningPoster
- SCRIBES: Web-Scale Script-Based Semi-Structured Data Extraction with Reinforcement LearningPoster
- SCUBA: Salesforce Computer Use BenchmarkPoster
- SCoT: Teaching 3D-LLMs to Think Spatially with Million-scale CoT AnnotationsPoster
- SDErasure: Concept-Specific Trajectory Shifting for Concept Erasure via Adaptive Diffusion ClassifierPoster
- SE-Diff: Simulator and Experience Enhanced Diffusion Model for Comprehensive ECG GenerationPoster
- SEED-SET: Scalable Evolving Experimental Design for System-level Ethical TestingPoster
- SEED: Towards More Accurate Semantic Evaluation for Visual Brain DecodingPoster
- SELF-HARMONY: LEARNING TO HARMONIZE SELF-SUPERVISION AND SELF-PLAY IN TEST-TIME REINFORCEMENT LEARNINGPoster
- SEMA: Simple yet Effective Learning for Multi-Turn Jailbreak AttacksPoster
- SERE: Similarity-based Expert Re-routing for Efficient Batch Decoding in MoE ModelsPoster
- SERQ: Saliency-Aware Low-Rank Error Reconstruction for LLM QuantizationPoster
- SERUM: Simple, Efficient, Robust, and Unifying Marking for Diffusion-based Image GenerationPoster
- SESaMo: Symmetry-Enforcing Stochastic Modulation for Normalizing FlowsPoster
- SFBD-OMNI: Bridge models for lossy measurement restoration with limited clean samplesPoster
- SFT Doesn’t Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMsPoster
- SGD with Adaptive Preconditioning: Unified Analysis and Momentum AccelerationPoster
- SGD-Based Knowledge Distillation with Bayesian Teachers: Theory and GuidelinesPoster
- SHAPO: Sharpness-Aware Policy Optimization for Safe ExplorationPoster
- SHE-LoRA: Selective Homomorphic Encryption for Federated Tuning with Heterogeneous LoRAPoster
- SHIELD: Suppressing Hallucinations In LVLM Encoders via Bias and Vulnerability DefensePoster
- SIGMA-GEN: STRUCTURE AND IDENTITY GUIDED MULTI-SUBJECT ASSEMBLY FOR IMAGE GENERATIONPoster
- SIGMark: Scalable In-Generation Watermark with Blind Extraction for Video DiffusionPoster
- SIM-CoT: Supervised Implicit Chain-of-ThoughtPoster
- SIPDO: Closed-Loop Prompt Optimization via Synthetic Data FeedbackPoster
- SK2Decompile: LLM-based Two-Phase Binary Decompilation from Skeleton to SkinPoster
- SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear AttentionPoster
- SLM-MUX: Orchestrating Small Language Models for ReasoningPoster
- SMAN-Bench: A Cross-System Benchmark for Mobile Agents under Single- and Multi-path, Ambiguous, and Noisy TasksPoster
- SMOTE and Mirrors: Exposing Privacy Leakage from Synthetic Minority OversamplingPoster
- SMixer: Rethinking Efficient-Training and Event-Driven SNNsPoster
- SNAP-UQ: Self-supervised Next-Activation Prediction for Single-Pass Uncertainty in TinyMLPoster
- SNAPHARD CONTRAST LEARNINGPoster
- SNaX: sparse narrow accelerated mixture of expertsPoster
- SONA: Learning Conditional, Unconditional, and Matching-Aware DiscriminatorPoster
- SONATA: Synergistic Coreset Informed Adaptive Temporal Tensor FactorizationPoster
- SONIC: Spectral Oriented Neural Invariant ConvolutionsPoster
- SOSBENCH: Benchmarking Safety Alignment on Scientific KnowledgePoster
- SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model AccelerationPoster
- SPACeR: Self-Play Anchoring with Centralized Reference ModelsPoster
- SPARTA: Scalable and Principled Benchmark of Tree-Structured Multi-hop QA over Text and TablesPoster
- SPECS: Decoupling Multimodal Learning via Self-distilled Preference-based Cold StartPoster
- SPEED: Scalable, Precise, and Efficient Concept Erasure for Diffusion ModelsPoster
- SPELL: Self-Play Reinforcement Learning for Evolving Long-Context Language ModelsPoster
- SPG: Sandwiched Policy Gradient for Masked Diffusion Language ModelsPoster
- SPICE: Submodular Penalized Information–Conflict Selection for Efficient Large Language Model TrainingPoster
- SPIKE-RL: Video-LLMs meet Bayesian SurprisePoster
- SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement LearningPoster
- SPR$^2$Q: Static Priority-based Rectifier Routing Quantization for Image Super-ResolutionPoster
- SPREAD: Sampling-based Pareto front Refinement via Efficient Adaptive DiffusionPoster
- SPRIG: Improving Large Language Model Performance by System Prompt OptimizationPoster
- SPRINT: Sparse-Dense Residual Fusion for Efficient Diffusion TransformersPoster
- SPWOOD: Sparse Partial Weakly-Supervised Oriented Object DetectionPoster
- SR-Scientist: Scientific Equation Discovery With Agentic AIPoster
- SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for ReasoningPoster
- SRT: Super-Resolution for Time Series via Disentangled Rectified FlowPoster
- SSD-GS: Scattering and Shadow Decomposition for Relightable 3D Gaussian SplattingPoster
- SSDi8: Accurate and Efficient 8-bit Quantization for State Space DualityPoster
- SSG: Scaled Spatial Guidance for Multi-Scale Visual Autoregressive GenerationPoster
- SSVPO: Effective Step-Level Credit Assignment for RL Training of Language ModelsPoster
- ST-HHOL: Spatio-Temporal Hierarchical Hypergraph Online Learning for Crime PredictionPoster
- ST-SimDiff: Balancing Spatiotemporal Similarity and Difference for Efficient Video Understanding with MLLMsPoster
- ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web AgentsPoster
- STAIRS-Former: Spatio-Temporal Attention with Interleaved Recursive Structure TransFormer for Offline Mulit-task Multi-agent Reinforcement LearningPoster
- STAR-Bench: Probing Deep Spatio-Temporal Reasoning as Audio 4D IntelligencePoster
- STAR: Similarity-guided Teacher-Assisted Refinement for Super-Tiny Function Calling ModelsPoster
- STAR: Strategy-driven Automatic Jailbreak Red-teaming For Large Language ModelPoster
- STARK: Strategic Team of Agents for Refining KernelsPoster
- STAT: Skill-Targeted Adaptive TrainingPoster
- STDDN: A Physics-Guided Deep Learning Framework for Crowd SimulationPoster
- STEDiff: Revealing the Spatial and Temporal Redundancy of Backdoor Attacks in Text-to-Image Diffusion ModelsPoster
- STEM: SCALING TRANSFORMERS WITH EMBEDDING MODULESPoster
- STITCH: Simultaneous Thinking and Talking with Chunked Reasoning for Spoken Language ModelsPoster
- STORK: Faster Diffusion and Flow Matching Sampling by Resolving both Stiffness and Structure-DependencePoster
- STORM: Synergistic Cross-Scale Spatio-Temporal Modeling for Weather ForecastingPoster
- STVG-R1: Incentivizing Instance-Level Reasoning and Grounding in Videos via Reinforcement LearningPoster
- STaMP: Sequence Transformation and Mixed Precision for Low-Precision Activation QuantizationPoster
- STream3R: Scalable Sequential 3D Reconstruction with Causal TransformerPoster
- SURGE: Surprise-Guided Token Reduction for Efficient Video Understanding with VLMsPoster
- SUSD: Structured Unsupervised Skill Discovery through State FactorizationPoster
- SVD Provably Denoises Nearest Neighbor DataPoster
- SWE-RM: Execution-free Feedback for Software Engineering AgentsPoster
- SWERank: Software Issue Localization with Code RankingPoster
- SWINGARENA: Adversarial Programming Arena for Long-context GitHub Issue SolvingOral
- SYNC: Measuring and Advancing Synthesizability in Structure-Based Drug DesignPoster
- Saddle-To-Saddle Dynamics in Deep ReLU Networks: Low-Rank Bias in the First Saddle EscapePoster
- Saddle-to-Saddle Dynamics Explains A Simplicity Bias Across Neural Network ArchitecturesPoster
- Safe Continuous-time Multi-Agent Reinforcement Learning via Epigraph FormPoster
- Safe Exploration via Policy PriorsPoster
- SafeDPO: A Simple Approach to Direct Preference Optimization with Enhanced SafetyOral
- SafeDialBench: A Fine-Grained Safety Evaluation Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak AttacksPoster
- SafeFlowMatcher: Safe and Fast Planning using Flow Matching with Control Barrier FunctionsPoster
- SafeMPO: Constrained Reinforcement Learning with Probabilistic Incremental ImprovementPoster
- SafeMoE: Safe Fine-Tuning for MoE LLMs by Aligning Harmful Input RoutingPoster
- Safeguarding Multimodal Knowledge Copyright in the RAG-as-a-Service EnvironmentPoster
- Safety Instincts: LLMs Learn to Trust Their Internal Compass for Self-DefensePoster
- Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine UnlearningPoster
- Safety Subspaces are Not Linearly Distinct: A Fine-Tuning Case StudyPoster
- Safety at One Shot: Patching Fine-Tuned LLMs with A Single InstancePoster
- Salient Object Ranking via Cyclical Perception-Viewing Interaction ModelingPoster
- Same Content, Different Representations: A Controlled Study for Table QAPoster
- Sample Complexity and Representation Ability of Test-time Scaling ParadigmsPoster
- Sample Efficient Offline RL via T-Symmetry Enforced Latent State-StitchingPoster
- Sample Lottery: Unsupervised Discovery of Critical Instances for LLM ReasoningPoster
- Sample More to Think Less: Group Filtered Policy Optimization for Concise ReasoningPoster
- Sample Reward Soups: Query-efficient Multi-Reward Guidance for Text-to-Image Diffusion ModelsPoster
- Sample Smart, Not Hard: Correctness-First Decoding for Better Reasoning in LLMsPoster
- Sample-Efficient Distributionally Robust Multi-Agent Reinforcement Learning via Online InteractionPoster
- Sample-efficient and Scalable Exploration in Continuous-Time RLPoster
- Sample-efficient evidence estimation of score based priors for model selectionPoster
- Samples Are Not Equal: A Sample Selection Approach for Deep ClusteringPoster
- Sampling Complexity of TD and PPO in RKHSPoster
- Sampling-aware Adversarial Attacks Against Large Language ModelsPoster
- Sapiens2Poster
- Sat3DGen: Comprehensive Street-Level 3D Scene Generation from Single Satellite ImagePoster
- SatDreamer360: Multiview-Consistent Generation of Ground-Level Scenes from Satellite ImageryPoster
- Scaf-GRPO: Scaffolded Group Relative Policy Optimization for Enhancing LLM ReasoningPoster
- Scalable Chain of Thoughts via Elastic ReasoningPoster
- Scalable Energy-Based Models via Adversarial Training: Unifying Discrimination and GenerationPoster
- Scalable Exploration for High-Dimensional Continuous Control via Value-Guided FlowPoster
- Scalable In-Context Q-LearningPoster
- Scalable Multilingual Multimodal Machine Translation with Speech-Text FusionPoster
- Scalable Offline Model-Based RL with Action ChunksPoster
- Scalable Oversight via Partitioned Human SupervisionPoster
- Scalable Random Wavelet Features: Efficient Non-Stationary Kernel Approximation with Convergence GuaranteesPoster
- Scalable Second-order Riemannian Optimization for $K$-means ClusteringPoster
- Scalable Spatio-Temporal SE(3) Diffusion for Long-Horizon Protein DynamicsPoster
- Scalable Training for Vector-Quantized Networks with 100% Codebook UtilizationPoster
- Scalable and Adaptive Trust-Region Learning via Projection Convex HullPoster
- Scale-wise Distillation of Diffusion ModelsPoster
- ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform DataOral
- ScaleCap: Scalable Image Captioning via Dual-Modality DebiasingPoster
- ScaleLong: A Multi-Timescale Benchmark for Long Video UnderstandingPoster
- Scaling Agent Learning via Experience SynthesisPoster
- Scaling Agents via Continual Pre-trainingPoster
- Scaling Atomistic Protein Binder Design with Generative Pretraining and Test-Time ComputeOral
- Scaling Attention via Feature SparsityPoster
- Scaling Bayesian Experimental Design to High-Dimensions with Information-Guided DiffusionPoster
- Scaling Behavior of Discrete Diffusion Language ModelsPoster
- Scaling Direct Feedback Learning with Theoretical GuaranteesPoster
- Scaling Generalist Data-Analytic AgentsPoster
- Scaling Goal-conditioned Reinforcement Learning with Multistep Quasimetric DistancesPoster
- Scaling Group Inference for Diverse and High-Quality GenerationPoster
- Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV DatabasePoster
- Scaling Laws Meet Model Architecture: Toward Inference-Efficient LLMsPoster
- Scaling Laws Revisited: Modeling the Role of Data Quality in Language Model PretrainingPoster
- Scaling Laws and Spectra of Shallow Neural Networks in the Feature Learning RegimeOral
- Scaling Laws and Symmetry, Evidence from Neural Force FieldsPoster
- Scaling Laws for Diffusion TransformersPoster
- Scaling Laws of SignSGD in Linear Regression: When Does It Outperform SGD?Poster
- Scaling Linear Attention with Sparse State ExpansionPoster
- Scaling Multi-Task Bayesian Optimization with Large Language ModelsPoster
- Scaling Reasoning Hop Exposes Weaknesses: Demystifying and Improving Hop Generalization in Large Language ModelsPoster
- Scaling Sequence-to-Sequence Generative Neural RenderingPoster
- Scaling Speech Tokenizers with Diffusion AutoencodersPoster
- Scaling Synthetic Task Generation for Agents via ExplorationPoster
- Scaling Up, Speeding Up: A Benchmark of Speculative Decoding for Efficient LLM Test-Time ScalingPoster
- Scaling up Memory for Robotic Control via Experience RetrievalPoster
- Scaling with Collapse: Efficient and Predictable Training of LLM FamiliesPoster
- ScalingCache: Extreme Acceleration of DiTs through Difference Scaling and Dynamic Interval CachingPoster
- SceneCOT: Eliciting Chain-of-Thought Reasoning in 3D ScenesPoster
- SceneTransporter: Optimal Transport-Guided Compositional Latent Diffusion for Single-Image Structured 3D Scene GenerationPoster
- Scenethesis: A Language and Vision Agentic Framework for 3D Scene GenerationPoster
- Scheduling Your LLM Reinforcement Learning with Reasoning TreesPoster
- Sci2Pol: Evaluating and Fine-tuning LLMs on Scientific-to-Policy Brief GenerationPoster
- SciNav: A Principled Agent Framework for Scientific Coding TasksPoster
- SciTS: Scientific Time Series Understanding and Generation with LLMsPoster
- ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific WorkflowsPoster
- Score Distillation Beyond Acceleration: Generative Modeling from Corrupted DataPoster
- Score-Based Density Estimation from Pairwise ComparisonsPoster
- Score-based Greedy Search for Structure Identification of Partially Observed Linear Causal ModelsPoster
- Sculpting Subspaces: Constrained Full Fine-Tuning in LLMs for Continual LearningPoster
- Sculptor: Empowering LLMs with Cognitive Agency via Active Context ManagementPoster
- SeRI: Gradient-Free Sensitive Region Identification in Decision-Based Black-Box AttacksPoster
- SealQA: Raising the Bar for Reasoning in Search-Augmented Language ModelsPoster
- Search Arena: Analyzing Search-Augmented LLMsPoster
- Search Self-Play: Pushing the Frontier of Agent Capability without SupervisionPoster
- Searching for Privacy Risks in LLM Agents via SimulationPoster
- SecP-Tuning: Efficient Privacy-Preserving Prompt Tuning for Large Language Models via MPCPoster
- Secret-Protected Evolution for Differentially Private Synthetic Text GenerationPoster
- Secure Inference for Diffusion Models via Unconditional ScoresPoster
- Secure Outlier-Aware Large Language Model InferencePoster
- SeeDNorm: Self-Rescaled Dynamic NormalizationPoster
- SeedPrints: Fingerprints Can Even Tell Which Seed Your Large Language Model Was Trained FromPoster
- SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-TrainingPoster
- Seeing Across Views: Benchmarking Spatial Reasoning of Vision-Language Models in Robotic ScenesPoster
- Seeing Through Deception: Uncovering Misleading Creator Intent in Multimodal News with Vision-Language ModelsPoster
- Seeing Through Words: Controlling Visual Retrieval Quality with LanguagePoster
- Seeing Through the Brain: New Insights from Decoding Visual Stimuli with fMRIOral
- Seeing What’s Not There: Negation Understanding Needs More Than TrainingPoster
- Seeing What’s Wrong: A Trajectory-Guided Approach to Caption Error DetectionPoster
- Seeing but Not Believing: Probing the Disconnect Between Visual Attention and Answer Correctness in VLMsPoster
- Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term MemoryPoster
- Seek-CAD: A Self-refined Generative Modeling for 3D Parametric CAD Using Local Inference via DeepSeekPoster
- Seesaw: Accelerating Training by Balancing Batch Size and Learning Rate SchedulingPoster
- Segment Any Events with LanguagePoster
- Segment-Level Attribution for Selective Learning of Long Reasoning TracesPoster
- Selection, Reflection and Self-Refinement: Revisit Reasoning Tasks via a Causal LensPoster
- Selective Data Removal for Distributional Machine UnlearningPoster
- Selective Expert Guidance for Effective and Diverse Exploration in Reinforcement Learning of LLMsPoster
- Selective Rotary Position EmbeddingPoster
- Self-Aligned Reward: Towards Effective and Efficient ReasonersPoster
- Self-Augmented Visual Contrastive DecodingPoster
- Self-Consistency Improves the Trustworthiness of Self-Interpretable GNNsPoster
- Self-Destructive Language ModelsPoster
- Self-Evolving Vision-Language Models for Image Quality Assessment via Voting and RankingPoster
- Self-Forcing++: Towards Minute-Scale High-Quality Video GenerationPoster
- Self-Guided Low Light Object Detection FrameworkPoster
- Self-Improving Loops for Visual Robotic PlanningPoster
- Self-Improving Skill Learning for Robust Skill-based Meta-Reinforcement LearningPoster
- Self-Improving Vision-Language-Action Models with Data Generation via Residual RLPoster
- Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning TrainingPoster
- Self-Predictive Representations for Combinatorial Generalization in Behavioral CloningPoster
- Self-Refining Vision Language Model for Robotic Failure Detection and ReasoningPoster
- Self-Rewarding Vision-Language Model via Reasoning Decomposition and Multi-Reward Policy OptimizationPoster
- Self-Speculative Decoding Accelerates Lossless Inference in Any-Order and Any-Subset Autoregressive ModelsPoster
- Self-Speculative Masked DiffusionsPoster
- Self-Supervised Evolution Operator Learning for High-Dimensional Dynamical SystemsPoster
- Self-Supervised Learning from Structural InvariancePoster
- SelfReflect: Can LLMs Communicate Their Internal Answer Distribution?Poster
- SelvaBox: A high‑resolution dataset for tropical tree crown detectionPoster
- Sem-MoE: Semantic-aware Model-Data Collaborative Scheduling for Efficient MoE InferencePoster
- SemHiTok: A Unified Image Tokenizer via Semantic-Guided Hierarchical Codebook for Multimodal Understanding and GenerationPoster
- Semantic Regexes: Auto-Interpreting LLM Features with a Structured LanguagePoster
- Semantic Uncertainty Quantification of Hallucinations in LLMs: A Quantum Tensor Network Based MethodPoster
- Semantic Visual Anomaly Detection and Reasoning in AI-Generated ImagesPoster
- Semantic Voting: A Self-Evaluation-Free Approach for Efficient LLM Self-Improvement on Unverifiable Open-ended TasksPoster
- Semantic-Aware Diffusion LLM Inference With Adaptive Block SizePoster
- Semantic-Enhanced Time-Series Forecasting via Large Language ModelsPoster
- Semantic-aware Wasserstein Policy Regularization for Large Language Model AlignmentPoster
- Semi-Parametric Contextual Pricing with General SmoothnessPoster
- Semi-Supervised Preference Optimization with Limited FeedbackOral
- SenseFlow: Scaling Distribution Matching for Flow-based Text-to-Image DistillationPoster
- Separable Neural Networks: Approximation Theory, NTK Regime, and Preconditioned Gradient DescentPoster
- Seq vs Seq: An Open Suite of Paired Encoders and DecodersPoster
- Sequences of Logits Reveal the Low Rank Structure of Language ModelsOral
- Sequential Information Bottleneck Fusion: Towards Robust and Generalizable Multi-Modal Brain Tumor SegmentationPoster
- Sequential Parallel Duality in Prefix Scannable ModelsPoster
- SesaHand: Enhancing 3D Hand Reconstruction via Controllable Generation with Semantic and Structural AlignmentPoster
- Set Representation Auxiliary Learning with Adversarial Encoding Perturbation and OptimizationPoster
- Setting up for failure: automatic discovery of the neural mechanisms of cognitive errorsPoster
- ShapeGen4D: Towards High Quality 4D Shape Generation from VideosPoster
- Sharing State Between Prompts and ProgramsPoster
- Sharp Monocular View Synthesis in Less Than a SecondPoster
- Sharp asymptotic theory for Q-learning with \texttt{LD2Z} learning rate and its generalizationPoster
- Sharpness-Aware Machine UnlearningPoster
- Sharpness-Aware Minimization in Logit Space Efficiently Enhances Direct Preference OptimizationPoster
- Sheaves Reloaded: A Direction AwakeningPoster
- ShieldedCode: Learning Robust Representations for Virtual Machine Protected CodePoster
- Shift-Tolerant Allocation via Black-Litterman Using Conditional Diffusion EstimatesPoster
- Shift-and-Sum Quantization for Visual Autoregressive ModelsPoster
- ShinkaEvolve: Towards Open-Ended and Sample-Efficient Program EvolutionPoster
- Shoot First, Ask Questions Later? Building Rational Agents that Explore and Act Like PeopleOral
- Shop-R1: Rewarding LLMs to Simulate Human Behavior in Online Shopping via Reinforcement LearningPoster
- Short Window Attention Enables Long-Term MemorizationPoster
- Shortcut Diffusion Training with Cumulative Consistency Loss: An Optimal Control ViewPoster
- Should We Still Pretrain Encoders with Masked Language Modeling?Poster
- Shrinking Proteins with DiffusionPoster
- Shuffle-R1: Efficient RL framework for Multimodal Large Language Models via Data-centric Dynamic ShufflePoster
- Shuffling the Data, Extrapolating the Step: Sharper Bias In Constant Step-Size SGDPoster
- Si-GT: Fast Interconnect Signal Integrity Analysis for Integrated Circuit Design via Graph TransformersPoster
- SiMO: Single-Modality-Operable Multimodal Collaborative PerceptionPoster
- SiNGER: A Clearer Voice Distills Vision Transformers FurtherPoster
- SigLIP-HD by Fine-to-Coarse SupervisionPoster
- SigmaDock: Untwisting Molecular Docking with Fragment-Based SE(3) DiffusionPoster
- Sign-SGD via Parameter-Free OptimizationPoster
- Signal Structure-Aware Gaussian Splatting for Large-Scale Scene ReconstructionPoster
- Signal in the Noise: Polysemantic Interference Transfers and Predicts Cross-Model InfluencePoster
- Silent Leaks: Implicit Knowledge Extraction Attack on RAG SystemsPoster
- Sim2Real VLA: Zero-Shot Generalization of Synthesized Skills to Realistic ManipulationPoster
- SimBench: Benchmarking the Ability of Large Language Models to Simulate Human BehaviorsPoster
- SimULi: Real-Time LiDAR and Camera Simulation with Unscented TransformsPoster
- SimpleFold: Folding Proteins is Simpler than You ThinkPoster
- SimpleGVR: A Simple Baseline for Latent-Cascaded Generative Video Super-ResolutionPoster
- SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated ReasoningPoster
- SimpleToM: Exposing the Gap between Explicit ToM Inference and Implicit ToM Application in LLMsPoster
- SimpleVLA-RL: Scaling VLA Training via Reinforcement LearningPoster
- Simplicial Embeddings Improve Sample Efficiency in Actor–Critic AgentsPoster
- SimuHome: A Temporal- and Environment-Aware Benchmark for Smart Home LLM AgentsOral
- Simulation to Rules: A Dual-VLM Framework for Formal Visual PlanningPoster
- Single Index Bandits: Generalized Linear Contextual Bandits with Unknown Reward FunctionsPoster
- Single-Loop Byzantine-Resilient Federated Bilevel OptimizationPoster
- Single-stream Policy OptimizationPoster
- Singleton-Optimized Conformal PredictionPoster
- SinkTrack: Attention Sink based Context Anchoring for Large Language ModelsPoster
- SketchEvo: Leveraging Drawing Dynamics for Enhanced Image SynthesisPoster
- SketchThinker-R1: Towards Efficient Sketch-Style Reasoning in Large Multimodal ModelsPoster
- SketchingReality: From Freehand Scene Sketches to Photorealistic ImagesPoster
- Skill Learning via Policy Diversity Yields Identifiable Representations for Reinforcement LearningPoster
- SkillFactory: Self-Distillation for Learning Cognitive BehaviorsPoster
- Skirting Additive Error Lower Bounds for Private Turnstile StreamsPoster
- SkyEvents: A Large-Scale Event-enhanced UAV Dataset for Robust 3D Scene ReconstructionPoster
- Slicing Wasserstein over Wasserstein via Functional Optimal TransportPoster
- SliderQuant: Accurate Post-Training Quantization for LLMsPoster
- SlotGCG: Exploiting the Positional Vulnerability in LLMs for Jailbreak AttacksPoster
- Slow-Fast Policy Optimization: Reposition-Before-Update for LLM ReasoningPoster
- Small Drafts, Big Verdict: Information-Intensive Visual Reasoning via SpeculationPoster
- SmartChunk Retrieval: Query-Aware Chunk Compression with Planning for Efficient Document RAGPoster
- Smarter Not Harder: Generative Process Evaluation with Intrinsic-Signal Driving and Ability‑Adaptive Reward ShapingPoster
- SmellNet: A Large-scale Dataset for Real-world Smell RecognitionPoster
- Smooth Calibration Error: Uniform Convergence and Functional Gradient AnalysisPoster
- Smooth Reading: Bridging the Gap of Recurrent LLM to Self-Attention LLM on Long-Context UnderstandingPoster
- SoFlow: Solution Flow Models for One-Step Generative ModelingPoster
- SoLoPO: Unlocking Long-Context Capabilities in LLMs via Short-to-Long Preference OptimizationPoster
- Sobolev Gradient Ascent for Optimal Transport: Barycenter Optimization and Convergence AnalysisPoster
- Social Agents: Collective Intelligence Improves LLM PredictionsPoster
- SocialHarmBench: Revealing LLM Vulnerabilities to Socially Harmful RequestsPoster
- SocialJax: An Evaluation Suite for Multi-agent Reinforcement Learning in Sequential Social DilemmasPoster
- Soft Equivariance Regularization for Invariant Self-Supervised LearningPoster
- Soft Quality-Diversity OptimizationPoster
- Soft Tokens, Hard TruthsPoster
- Soft-Di[M]O: Improved one-step Image Discrete ModelPoster
- Soft-Masked Diffusion Language ModelsPoster
- SoftCFG: Uncertainty-guided Stable Guidance for Visual Autoregressive ModelPoster
- Softmax Transformers are Turing-CompleteOral
- Softmax is not Enough (for Adaptive Conformal Classification)Poster
- Solving Football by Exploiting Equilibrium Structure of 2p0s Differential Games with One-Sided InformationPoster
- Solving General-Utility Markov Decision Processes in the Single-Trial Regime with Online PlanningPoster
- Solving Parameter-Robust Avoid Problems with Unknown Feasibility using Reinforcement LearningPoster
- Solving the 2-norm k-hyperplane clustering problem via multi-norm formulationsPoster
- Solving the Granularity Mismatch: Hierarchical Preference Learning for Long-Horizon LLM AgentsPoster
- Some Neural Networks Inherently Preserve Subspace Clustering StructurePoster
- SongEcho: Towards Cover Song Generation via Instance-Adaptive Element-wise Linear ModulationPoster
- SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking RewardPoster
- Source-Guided Flow MatchingPoster
- SpaCE-10: A Comprehensive Benchmark for Multimodal Large Language Models in Compositional Spatial IntelligencePoster
- SpaCE-Eval: A Benchmark for Real-World Multi-Modal ReasoningPoster
- SpaceControl: Introducing Test-Time Spatial Control to 3D Generative ModelingPoster
- SpareTrain: Fault-Tolerant LLM Training via Low-Cost Dual Modular RedundancyPoster
- Sparkle: A Robust and Versatile Representation for Point Cloud-based Human Motion CapturePoster
- Sparling: End-to-End Spatial Concept Learning via Extremely Sparse ActivationsPoster
- Sparse Attention Adaptation for Long ReasoningPoster
- Sparse Autoencoders Trained on the Same Data Learn Different FeaturesPoster
- Sparse CLIP: Co-Optimizing Interpretability and Performance in Contrastive LearningPoster
- Sparse Imagination for Efficient Visual World Model PlanningPoster
- Sparse but Critical: A Token-Level Analysis of Distributional Shifts in RLVR Fine-Tuning of LLMsPoster
- SparseD: Sparse Attention for Diffusion Language ModelsPoster
- SparseEval: Efficient Evaluation of Large Language Models by Sparse OptimizationPoster
- Sparsity Forcing: Reinforcing Token Sparsity of MLLMsPoster
- Sparsity-promoting Fine-tuning for Equivariant Materials Foundation ModelPoster
- SpatiaLab: Can Vision–Language Models Perform Spatial Reasoning in the Wild?Poster
- Spatial CAPTCHA: Generatively Benchmarking Spatial Reasoning for Human-Machine DifferentiationPoster
- Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action ModelPoster
- Spatial Reasoning with Vision-Language Models in Ego-Centric Multi-View ScenesPoster
- Spatial Structure and Selective Text Jointly Facilitate Image ClusteringPoster
- Spatial-DISE: A Unified Benchmark for Evaluating Spatial Reasoning in Vision-Language ModelsICLR 2026 ConditionalPoster
- SpatialHand: Generative Object Manipulation from 3D PrespectivePoster
- SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language ModelsPoster
- SpatialViz-Bench: A Cognitively-Grounded Benchmark for Diagnosing Spatial Visualization in MLLMsPoster
- Spatially Guided Training for Vision-Language-Action ModelPoster
- Spatially Informed Autoencoders for Interpretable Visual Representation LearningPoster
- SpeakerVid-5M: A Large-Scale High-Quality Dataset for Audio-Visual Dyadic Interactive Human GenerationICLR 2026 ConditionalPoster
- SpecBranch: Speculative Decoding via Hybrid Drafting and Rollback-Aware Branch ParallelismPoster
- Special Unitary Parameterized Estimators of RotationPoster
- Specialization after Generalization: Towards Understanding Test-Time Training in Foundation ModelsPoster
- SpectraLLM: Uncovering the Ability of LLMs for Molecule Structure Elucidation from Multi-SpectraPoster
- Spectral Attention Steering for Prompt HighlightingPoster
- Spectral Bellman Method: Unifying Representation and Exploration in RLPoster
- Spectral-guided Physical Dynamics DistillationPoster
- SpectralGCD: Spectral Concept Selection and Cross-modal Representation Learning for Generalized Category DiscoveryPoster
- Spectrum Tuning: Post-Training for Distributional Coverage and In-Context SteerabilityPoster
- Speculative Actions: A Lossless Framework for Faster AI AgentsOral
- Speculative Speculative DecodingPoster
- Speech World Model: Causal State–Action Planning with Explicit Reasoning for SpeechPoster
- Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and SentencesPoster
- SpeechJudge: Towards Human-Level Judgment for Speech NaturalnessPoster
- SpeechOp: Inference-Time Task Composition for Generative Speech ProcessingPoster
- Spherical Watermark: Encryption-Free, Lossless Watermarking for Diffusion ModelsOral
- Spike-based Digital Brain: a novel fundamental model for brain activity analysisPoster
- SpikeGen: Decoupled “Rods and Cones” Visual Representation Processing with Latent Generative FrameworkPoster
- SpikePingpong: Spike Vision-based Fast-Slow Pingpong Robot SystemPoster
- SpikeStereoNet: A Brain-Inspired Framework for Stereo Depth Estimation from Spike StreamsPoster
- Spiking Discrepancy Transformer for Point Cloud AnalysisPoster
- Spilled Energy in Large Language ModelsPoster
- Spilling the Beans: Teaching LLMs to Self-Report Their Hidden ObjectivesPoster
- SpinBench: Perspective and Rotation as a Lens on Spatial Reasoning in VLMsPoster
- SpineBench: A Clinically Salient, Level-Aware Benchmark Powered by the SpineMed-450k CorpusICLR 2026 ConditionalPoster
- Spinning Straw into Gold: Relabeling LLM Agent Trajectories in Hindsight for Successful DemonstrationsPoster
- Splat Feature SolverPoster
- Splat Regression ModelsPoster
- Splat and Distill: Augmenting Teachers with Feed-Forward 3D Reconstruction For 3D-Aware DistillationPoster
- Splat the Net: Radiance Fields with Splattable Neural PrimitivesPoster
- SplitLoRA: Balancing Stability and Plasticity in Continual Learning Through Gradient Space SplittingPoster
- SportR: A Benchmark for Multimodal Large Language Model Reasoning in SportsPoster
- SpotIt: Evaluating Text-to-SQL Evaluation with Formal VerificationPoster
- Spotlight on Token Perception for Multimodal Reinforcement LearningPoster
- Spurious Correlation-Aware Embedding Regularization for Worst-Group RobustnessPoster
- Squeeze the Soaked Sponge: Efficient Off-policy RFT for Large Language ModelPoster
- StPR: Spatiotemporal Preservation and Routing for Exemplar-Free Video Class-Incremental LearningPoster
- Stability Under Scrutiny: Benchmarking Representation Paradigms for Online HD MappingPoster
- Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive ClippingPoster
- Stabilizing Policy Gradients for Sample-Efficient Reinforcement Learning in LLM ReasoningPoster
- Stable Video Infinity: Infinite-Length Video Generation with Error RecyclingOral
- Stable and Scalable Deep Predictive Coding Networks with Meta Prediction ErrorsPoster
- Stable coresets: Unleashing the power of uniform samplingPoster
- Stable-LoRA: Stabilizing Feature Learning of Low-Rank AdaptionPoster
- StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMsPoster
- Stacked from One: Multi-Scale Self-Injection for Context Window ExtensionPoster
- Stackelberg Coupling of Online Representation Learning and Reinforcement LearningPoster
- Stackelberg Learning from Human Feedback: Preference Optimization as a Sequential GamePoster
- Stage-wise Dynamics of Classifier-Free Guidance in Diffusion ModelsPoster
- Statistical Advantage of Softmax Attention: Insights from Single-Location RegressionPoster
- Statistical Guarantees for Offline Domain RandomizationPoster
- Statistical Guarantees in the Search for Less Discriminatory AlgorithmsPoster
- Steerable Adversarial Scenario Generation through Test-Time Preference AlignmentPoster
- Steering Autoregressive Music Generation with Recursive Feature MachinesPoster
- Steering Diffusion Models Towards Credible Content RecommendationPoster
- Steering Embedding Models with Geometric Rotation: Mapping Semantic Relationships Across Languages and ModelsPoster
- Steering Evaluation-Aware Language Models To Act Like They Are DeployedPoster
- Steering Language Models with Weight ArithmeticPoster
- Steering MoE LLMs via Expert (De)ActivationPoster
- Steering and Rectifying Latent representation manifolds in Frozen Multi-modal LLMs for Video Anomaly DetectionPoster
- Steering the Herd: A Framework for LLM-based Control of Social LearningOral
- SteinsGate: Adding Causality to Diffusions for Long Video Generation via Path IntegralPoster
- Step-Aware Residual-Guided Diffusion for EEG Spatial Super-ResolutionPoster
- StepORLM: A Self-Evolving Framework With Generative Process Supervision For Operations Research Language ModelsPoster
- StochasTok: Improving Fine-Grained Subword Understanding in LLMsPoster
- Stochastic Neural Networks for Causal Inference with Missing ConfoundersPoster
- Stochastic Optimal Control for Continuous-Time fMRI Representation LearningPoster
- Stochastic Self-Organization in Multi-Agent SystemsPoster
- Stop Guessing: Choosing the Optimization-Consistent Uncertainty Measurement for Evidential Deep LearningPoster
- Stop Tracking Me! Proactive Defense Against Attribute Inference Attack in LLMsPoster
- Stop Unnecessary Reflection: Training LRMs for Efficient Reasoning with Adaptive Reflection and Length Coordinated PenaltyPoster
- Stop Wasting Your Tokens: Towards Efficient Runtime Multi-Agent SystemsPoster
- Stopping Computation for Converged Tokens in Masked Diffusion-LM DecodingPoster
- Story-Iter: A Training-free Iterative Paradigm for Long Story VisualizationPoster
- StoryAlign: Evaluating and Training Reward Models for Story GenerationPoster
- Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLMsPoster
- Strategic Obfuscation of Deceptive Reasoning in Language ModelsPoster
- Strategic Planning and Rationalizing on Trees Make LLMs Better DebatersPoster
- Strategic Scaling of Test-Time Compute: A Bandit Learning ApproachPoster
- StreamSplat: Towards Online Dynamic 3D Reconstruction from Uncalibrated Video StreamsPoster
- Streaming Autoregressive Video Generation via Diagonal DistillationPoster
- Streaming Drag-Oriented Interactive Video Manipulation: Drag Anything, Anytime!Poster
- Streaming Visual Geometry TransformerPoster
- StreamingThinker: Large Language Models Can Think While ReadingPoster
- StreamingVLM: Real-Time Understanding for Infinite Video StreamsPoster
- Stretching Beyond the Obvious: A Gradient-Free Framework to Unveil the Hidden Landscape of Visual InvariancePoster
- Strict Subgoal Execution: Reliable Long-Horizon Planning in Hierarchical Reinforcement LearningPoster
- Strictly Constrained Generative Modeling via Split Augmented Langevin SamplingPoster
- String Seed of Thought: Prompting LLMs for Distribution-Faithful and Diverse GenerationPoster
- Stroke3D: Lifting 2D strokes into rigged 3D model via latent diffusion modelsPoster
- Strong Correlations Induce Cause Only Predictions in Transformer TrainingPoster
- Stronger-MAS: Multi-Agent Reinforcement Learning for Collaborative LLMsPoster
- Strongly Convex Sets in Riemannian ManifoldsPoster
- Structural Inference: Interpreting Small Language Models with SusceptibilitiesPoster
- Structural Prognostic Event Modeling for Multimodal Cancer Survival AnalysisPoster
- Structurally Human, Semantically Biased: Detecting LLM-Generated References with Embeddings and GNNsPoster
- Structure Learning from Time-Series Data with Lag-Agnostic Structural PriorPoster
- Structure-Aware Graph Hypernetworks for Neural Program SynthesisPoster
- Structured Flow Autoencoders: Learning Structured Probabilistic Representations with Flow MatchingOral
- Structured Reasoning for LLMs: A Unified Framework for Efficiency and ExplainabilityPoster
- Study of Training Dynamics for Memory-Constrained Fine-TuningPoster
- StyliTruth : Unlocking Stylized yet Truthful LLM Generation via Disentangled SteeringPoster
- Stylos: Multi-View 3D Stylization with Single-Forward Gaussian SplattingPoster
- SubDyve: Subgraph-Driven Dynamic Propagation for Virtual Screening Enhancement Controlling False PositivePoster
- Sublinear Spectral Clustering Oracle with Little MemoryPoster
- Sublinear Time Quantum Algorithm for Attention ApproximationPoster
- Submodular Function Minimization with Dueling OraclePoster
- Subquadratic Algorithms and Hardness for Attention with Any TemperaturePoster
- Subspace Kernel Learning on Tensor SequencesPoster
- SumRA: Parameter Efficient Fine-tuning with Singular Value Decomposition and Summed Orthogonal BasisPoster
- Summaries as Centroids for Interpretable and Scalable Text ClusteringPoster
- SupCLAP: Controlling Optimization Trajectory Drift in Audio-Text Contrastive Learning with Support Vector RegularizationPoster
- SuperF: Neural Implicit Fields for Multi-Image Super-ResolutionPoster
- Superficial Safety Alignment HypothesisPoster
- Supervised Fine-Tuning or Contrastive Learning? Towards Better Multimodal LLM RerankingPoster
- Supervised Reinforcement Learning: From Expert Trajectories to Step-wise ReasoningPoster
- Supporting High-Stakes Decision Making Through Interactive Preference Elicitation in the Latent SpacePoster
- Supporting Multimodal Intermediate Fusion with Informatic Constraint and Distribution CoherencePoster
- SurfSplat: Conquering Feedforward 2D Gaussian Splatting with Surface Continuity PriorsPoster
- SurvHTE-Bench: A Benchmark for Heterogeneous Treatment Effect Estimation in Survival AnalysisPoster
- Swap-guided Preference Learning for Personalized Reinforcement Learning from Human FeedbackPoster
- SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMsPoster
- SwiftTS: A Swift Selection Framework for Time Series Pre-trained Models via Multi-task Meta-LearningPoster
- Symmetric Space Learning for Combinatorial GeneralizationPoster
- Symmetry-Aware Bayesian Optimization via Max KernelsPoster
- SynCoGen: Synthesizable 3D Molecule Generation via Joint Reaction and Coordinate ModelingPoster
- SyncTrack: Rhythmic Stability and Synchronization in Multi-Track Music GenerationPoster
- Synchronizing Probabilities in Model-Driven Lossless CompressionPoster
- Syncphony: Synchronized Audio-to-Video Generation with Diffusion TransformersPoster
- Synergizing Understanding and Generation with Interleaved Analyzing-Drafting ThinkingPoster
- SynthWorlds: Controlled Parallel Worlds for Disentangling Reasoning and Knowledge in Language ModelsPoster
- Synthesising Counterfactual Explanations via Label-Conditional Gaussian Mixture Variational AutoencodersPoster
- Synthesizing High-Quality Visual Question Answering from Medical Documents with Generator-Verifier LMMsPoster
- Synthesizing Multimodal Verifiable Game Data to Boost VLMs' General ReasoningPoster
- Synthetic Bootstrapped PretrainingPoster
- Synthetic History: Evaluating Visual Representations of the Past in Diffusion ModelsPoster
- SysMoBench: Evaluating AI on Formally Specifying Complex Real-World SystemsPoster
- Sysformer: Safeguarding Frozen Large Language Models with Adaptive System PromptsPoster
- Systematic Biosafety Evaluation of DNA Language Models under Jailbreak AttacksPoster
- T-TAMER: Provably Taming Trade-offs in ML ServingPoster
- T1: One-to-One Channel-Head Binding for Multivariate Time-Series ImputationPoster
- T1: Tool-integrated Verification for Test-time Compute Scaling in Small Language ModelsPoster
- TABLET: A Large-Scale Dataset for Robust Visual Table UnderstandingPoster
- TAMMs: Change Understanding and Forecasting in Satellite Image Time Series with Temporal-Aware Multimodal ModelsPoster
- TAO-Attack: Toward Advanced Optimization-Based Jailbreak Attacks for Large Language ModelsPoster
- TAPTRv3: Spatial and Temporal Context Foster Robust Tracking of Any Point in Long VideoPoster
- TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language ModelingPoster
- TAVAE: A VAE with Adaptable Priors Explains Contextual Modulation in the Visual CortexPoster
- TCD-Arena: Assessing Robustness of Time Series Causal Discovery Methods Against Assumption ViolationsPoster
- TD-JEPA: Latent-predictive Representations for Zero-Shot Reinforcement LearningOral
- TD-MoE: Tensor Decomposition for MoE ModelsPoster
- TEDM: Time Series Forecasting with Elucidated Diffusion ModelsPoster
- TEMPFLOW-GRPO: WHEN TIMING MATTERS FOR GRPO IN FLOW MODELSPoster
- TEN-DM: Topology-Enhanced Diffusion Model for Spatio-Temporal Event PredictionPoster
- TESSAR: Geometry-Aware Active Regression via Dynamic Voronoi TessellationPoster
- TEST-TIME SCALING IN DIFFUSION LLMS VIA HIDDEN SEMI-AUTOREGRESSIVE EXPERTSPoster
- TGM: A Modular and Efficient Library for Machine Learning on Temporal GraphsPoster
- THE END OF MANUAL DECODING: TOWARDS TRULY END-TO-END LANGUAGE MODELSPoster
- THE PATH OF LEAST RESISTANCE: GUIDING LLM REASONING TRAJECTORIES WITH PREFIX CONSENSUSPoster
- THE SELF-RE-WATERMARKING TRAP: FROM EXPLOIT TO RESILIENCEPoster
- THEMIS: Towards Holistic Evaluation of MLLMs for Scientific Paper Fraud ForensicsPoster
- THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical ReasoningPoster
- TIGaussian: Disentangle Gaussians for Spatial-Awared Text-Image-3D AlignmentPoster
- TIMESLIVER : SYMBOLIC-LINEAR DECOMPOSITION FOR EXPLAINABLE TIME SERIES CLASSIFICATIONPoster
- TINKER: Diffusion's Gift to 3D--Multi-View Consistent Editing From Sparse Inputs without Per-Scene OptimizationPoster
- TINY BUT MIGHTY: A SOFTWARE-HARDWARE CO- DESIGN APPROACH FOR EFFICIENT MULTIMODAL IN- FERENCE ON BATTERY-POWERED SMALL DEVICESPoster
- TIPO: Text to Image with Text Pre-sampling for Prompt OptimizationPoster
- TIPS: Turn-level Information-Potential Reward Shaping for Search-Augmented LLMsPoster
- TNT: Improving Chunkwise Training for Test-Time MemorizationPoster
- TOUCH: Text-guided Controllable Generation of Free-Form Hand-Object InteractionsPoster
- TP-Spikformer: Token Pruned Spiking TransformerPoster
- TPDiff: Temporal Pyramid Video Diffusion ModelPoster
- TPRU: Advancing Temporal and Procedural Understanding in Large Multimodal ModelsPoster
- TRAC: Tensor-Train based Across-layer Compression for Parameter-Efficient Fine-TuningPoster
- TRACE: Your Diffusion Model is Secretly an Instance Edge DetectorOral
- TRACED: Transition-aware Regret Approximation with Co-learnability for Environment DesignPoster
- TRACEDET: HALLUCINATION DETECTION FROM THE DECODING TRACE OF DIFFUSION LARGE LANGUAGE MODELSPoster
- TRAJECT-Bench:A Trajectory-Aware Benchmark for Evaluating Agentic Tool UsePoster
- TRIBE: TRImodal Brain Encoder for whole-brain fMRI response predictionPoster
- TRIDENT: Cross-Domain Trajectory Spatio-Temporal Representation via Distance-Preserving Triplet LearningPoster
- TRIM: Hybrid Inference via Targeted Stepwise Routing in Multi-Step Reasoning TasksPoster
- TROLL: Trust Regions Improve Reinforcement Learning for Large Language ModelsOral
- TS$^2$: Training with Sparsemax+, Testing with Softmax for Accurate and Diverse LLM Fine-TuningPoster
- TS-Attn: Temporal-wise Separable Attention for Multi-Event Video GenerationPoster
- TS-DDAE: A novel Temporal-Spectral Denoising Diffusion AutoEncoder for Wireless Signal Recognition Model Pre-trainingPoster
- TSLM: Tree-Structured Language Modeling for Divergent ThinkingPoster
- TSM-Bench: Detecting LLM-Generated Text in Real-World Wikipedia Editing PracticesPoster
- TSPulse: Tiny Pre-Trained Models with Disentangled Representations for Rapid Time-Series AnalysisPoster
- TTOM: Test-Time Optimization and Memorization for Compositional Video GenerationPoster
- TTS Can Speak in Any Style with Any VoicePoster
- TTSDS2: Resources and Benchmark for Evaluating Human-Quality Text to Speech SystemsOral
- TTT3R: 3D Reconstruction as Test-Time TrainingPoster
- TUMIX: Multi-Agent Test-Time Scaling with Tool-Use MixturePoster
- TVTSyn: Content-Synchronous Time-Varying Timbre for Streaming Voice Conversion and AnonymizationPoster
- TaCo: A Benchmark for Lossless and Lossy Codecs of Heterogeneous Tactile DataPoster
- TaTToo: Tool-Grounded Thinking PRM for Test-Time Scaling in Tabular ReasoningPoster
- Tab-MIA: A Benchmark Dataset for Membership Inference Attacks on Tabular Data in LLMsPoster
- TabStruct: Measuring Structural Fidelity of Tabular DataOral
- TableDART: Dynamic Adaptive Multi-Modal Routing for Table UnderstandingPoster
- TableMaster: A Recipe to Advance Table Understanding with Language ModelsPoster
- Tackling Heavy-Tailed Q-Value Bias in Offline-to-Online Reinforcement Learning with Laplace-Robust ModelingPoster
- Tackling Time-Series Forecasting Generalization via Mitigating Concept DriftPoster
- Tackling the XAI Disagreement Problem with Adaptive Feature GroupingPoster
- Tactic: Adaptive Sparse Attention with Clustering and Distribution Fitting for Long-Context LLMsPoster
- Take Note: Your Molecular Dataset Is Probably AlignedPoster
- Talk, Evaluate, Diagnose: User-aware Agent Evaluation with Automated Error AnalysisPoster
- Talking Points: Describing and Localizing PixelsPoster
- Taming Curvature: Architecture Warm-up for Stable Transformer TrainingPoster
- Taming Hierarchical Image Coding Optimization: A Spectral Regularization PerspectivePoster
- Taming Imperfect Process Verifiers: A Sampling Perspective on BacktrackingPoster
- Taming Momentum: Rethinking Optimizer States Through Low-Rank ApproximationOral
- Taming Polysemanticity in LLMs: Theory-Grounded Feature Recovery via Sparse AutoencodersPoster
- Taming Score-Based Denoisers in ADMM: A Convergent Plug-and-Play FrameworkPoster
- Taming the Fragility of KV Cache Eviction in LLM InferencePoster
- TangleScore: Tangle-Guided Purge and Imprint for Unstructured Knowledge EditingPoster
- TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference OptimizationPoster
- Target-Aware Video Diffusion ModelsPoster
- Task Tokens: A Flexible Approach to Adapting Behavior Foundation ModelsPoster
- Task Vectors, Learned Not Extracted: Performance Gains and Mechanistic InsightsPoster
- Task-Adaptive Parameter-Efficient Fine-Tuning for Weather Foundation ModelsPoster
- Task-Agnostic Amortized Multi-Objective OptimizationPoster
- Task-Aware Data Selection via Proxy-Label Enhanced Distribution Matching for LLM FinetuningPoster
- Task-Related Token Compression in Multimodal Large Language Models from an Explainability PerspectivePoster
- Task-free Adaptive Meta Black-box OptimizationOral
- TaskCraft: Automated Generation of Agentic TasksPoster
- Teach to Reason Safely: Policy-Guided Safety Tuning for MLRMsPoster
- Teach2Eval: An Interaction-Driven LLMs Evaluation Method via Teaching EffectivenessPoster
- Teaching Metric Distance to Discrete Autoregressive Language ModelsPoster
- Teaching VLMs to Admit Uncertainty in OCR from Lossy Visual InputsPoster
- Tell me Habibi, is it Real or Fake?Poster
- Temperature as a Meta-Policy: Adaptive Temperature in LLM Reinforcement LearningPoster
- Temporal Concept Dynamics in Diffusion Models via Prompt-Conditioned InterventionsPoster
- Temporal Generalization: A Reality CheckPoster
- Temporal Geometry of Deep Networks: Hyperbolic Representations of Training Dynamics for Intrinsic ExplainabilityPoster
- Temporal Graph Thumbnail: Robust Representation Learning with Global Evolutionary SkeletonPoster
- Temporal Slowness in Central Vision Drives Semantic Object LearningPoster
- Temporal Sparse Autoencoders: Leveraging the Sequential Nature of Language for InterpretabilityOral
- Temporal superposition and feature geometry of RNNs under memory demandsOral
- Temporally Detailed Hypergraph Neural ODE for Disease Progression ModelingPoster
- Tensor learning with orthogonal, Lorentz, and symplectic symmetriesPoster
- Tequila: Deadzone-free Ternary Quantization for Large Language ModelsPoster
- Terminal Velocity MatchingPoster
- Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line InterfacesPoster
- TerraFM: A Scalable Foundation Model for Unified Multisensor Earth ObservationPoster
- Test-Time Accuracy-Cost Control in Neural Simulators via Recurrent-DepthPoster
- Test-Time Adaptation for LLM Agents via Environment InteractionPoster
- Test-Time Adaptation without Source Data for Out-of-Domain Bioactivity PredictionPoster
- Test-Time Alignment for Large Language Models via Textual Model Predictive ControlPoster
- Test-Time Efficient Pretrained Model Portfolios for Time Series ForecastingPoster
- Test-Time Iterative Error Correction for Efficient Diffusion ModelsPoster
- Test-Time Matching: Unlocking Compositional Reasoning in Multimodal ModelsPoster
- Test-Time Mixture of World Models for Embodied Agents in Dynamic EnvironmentsPoster
- Test-Time Optimization of 3D Point Cloud LLM via Manifold-Aware In-Context Guidance and RefinementPoster
- Test-Time Poisoned Sample Detection by Exploiting Shallow Malicious Matching in Backdoored CLIPPoster
- Test-Time Scaling with Reflective Generative ModelPoster
- Test-Time Training Done RightPoster
- Test-time Domain Generalization for Image Super-resolutionPoster
- Test-time Verification via Optimal Transport: Coverage, ROC, & Sub-optimalityPoster
- Testing Most Influential SetsPoster
- TetraGT: Tetrahedral Geometry-Driven Explicit Token Interactions with Graph Transformer for Molecular Representation LearningPoster
- Text summarization via global structure awarenessPoster
- Text-Aware Image Restoration with Diffusion ModelsPoster
- Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video GeneratorOral
- Text2Arch: A Dataset for Generating Scientific Architecture Diagrams from Natural Language DescriptionsPoster
- Text2Grad: Reinforcement Learning from Natural Language FeedbackPoster
- Text2Interact: High-Fidelity and Diverse Text-to-Two-Person Interaction GenerationPoster
- Textual Bayes: Quantifying Uncertainty in LLM-Based SystemsPoster
- Textual Equilibrium Propagation for Deep Compound AI SystemsPoster
- Texture Vector-Quantization and Reconstruction Aware Prediction for Generative Super-ResolutionPoster
- The Achilles’ Heel of LLMs: How Altering a Handful of Neurons Can Cripple Language AbilitiesPoster
- The Alignment Auditor: A Bayesian Framework for Verifying and Refining LLM ObjectivesPoster
- The Alignment Waltz: Jointly Training Agents to Collaborate for SafetyPoster
- The Art of Scaling Reinforcement Learning Compute for LLMsOral
- The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable RewardPoster
- The CoT Encyclopedia: Analyzing, Predicting, and Controlling how a Reasoning Model will ThinkPoster
- The Counting Power of TransformersPoster
- The Coverage Principle: How Pre-Training Enables Post-TrainingOral
- The Curious Case of In-Training Compression of State Space ModelsPoster
- The Deleuzian Representation HypothesisPoster
- The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMsPoster
- The Diffusion Duality, Chapter II: $\Psi$-Samplers and Efficient CurriculumPoster
- The Effect of Attention Head Count on Transformer ApproximationPoster
- The Expressive Limits of Diagonal SSMs for State-TrackingPoster
- The False Promise of Zero-Shot Super-Resolution in Machine-Learned OperatorsPoster
- The First Impression Problem: Internal Bias Triggers Overthinking in Reasoning ModelsPoster
- The Forecast After the Forecast: A Post-Processing Shift in Time SeriesPoster
- The Gaussian-Head OFL Family: One-Shot Federated Learning from Client Global StatisticsPoster
- The Geometry and Topology of Circuits: the Manifolds of Modular AdditionPoster
- The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane AlgorithmPoster
- The Geometry of Reasoning: Flowing Logics in Representation SpacePoster
- The Hot Mess of AI: How Does Misalignment Scale With Model Intelligence and Task Complexity?Poster
- The Human Brain as a Dynamic Mixture of Expert Models in Video UnderstandingPoster
- The Ideation-Execution Gap: Execution Outcomes of LLM-Generated versus Human Research IdeasPoster
- The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMsPoster
- The Imitation Game: Turing Machine Imitator is Length Generalizable ReasonerPoster
- The Intricate Dance of Prompt Complexity, Quality, Diversity and Consistency in T2I ModelsPoster
- The Lattice Geometry of Neural Network Quantization: A Short Equivalence Proof of GPTQ and Babai's AlgorithmPoster
- The Lattice Representation Hypothesis and Concept Algebra in LLMsPoster
- The Less You Depend, The More You Learn: Synthesizing Novel Views from Sparse, Unposed Images without Any 3D KnowledgePoster
- The Lie of the Average: How Class Incremental Learning Evaluation Deceives You?Poster
- The Limits of Inference Scaling Through ResamplingPoster
- The Logical Expressiveness of Topological Neural NetworksPoster
- The Markovian ThinkerPoster
- The Matthew Effect of AI Programming Assistants: A Hidden Bias in Software EvolutionPoster
- The Mind's Transformer: Computational Neuroanatomy of LLM-Brain AlignmentPoster
- The Natural Geometry of Code: Hyperbolic Representation Learning for Program ReasoningPoster
- The Open Proof Corpus: A Large-Scale Study of LLM-Generated Mathematical ProofsPoster
- The Overthinking Predicament: When Reasoning Hurts RankingPoster
- The Pensieve Paradigm: Stateful Language Models with Learned Memory ManagementPoster
- The Polar Express: Optimal Matrix Sign Methods and their Application to the Muon AlgorithmOral
- The Potential of Second-Order Optimization for LLMs: A Study with Full Gauss-NewtonPoster
- The Power of Small Initialization in Noisy Low-Tubal-Rank Tensor RecoveryPoster
- The Price of Amortized inference in Sparse AutoencodersPoster
- The Price of Robustness: Stable Classifiers Need OverparameterizationPoster
- The Quest for Efficient Reasoning: A Data-Centric Benchmark to CoT DistillationPoster
- The Quest for Generalizable Motion Generation: Data, Model, and EvaluationPoster
- The Rank and Gradient Lost in Non-stationarity: Sample Weight Decay for Mitigating Plasticity Loss in Reinforcement LearningPoster
- The Sample Complexity of Online Reinforcement Learning: A Multi-model PerspectivePoster
- The Seismic Wavefield Common Task FrameworkPoster
- The Serial Scaling HypothesisPoster
- The Shape of Adversarial Influence: Characterizing LLM Latent Spaces with Persistent HomologyOral
- The Softmax Bottleneck Does Not Limit the Probabilities of the Most Likely TokensPoster
- The Spacetime of Diffusion Models: An Information Geometry PerspectiveOral
- The State of Reinforcement Finetuning for Transformer-based Generative AgentsPoster
- The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task ExecutionPoster
- The Tutor-Pupil Augmentation: Enhancing Learning and Interpretability via Input CorrectionsPoster
- The Unseen Bias: How Norm Discrepancy in Pre-Norm MLLMs Leads to Visual Information LossPoster
- The Unseen Frontier: Pushing the Limits of LLM Sparsity with Surrogate-Free ADMMPoster
- The Value of Information in Human-AI Decision-makingPoster
- Theoretical Analysis of Contrastive Learning under Imbalanced Data: From Training Dynamics to a Pruning SolutionPoster
- Theoretical Guarantees for Causal Discovery on Large Random GraphsPoster
- Theoretical Modeling of Large Language Model Self-Improvement Training Dynamics Through Solver-Verifier GapPoster
- Theory of Scaling Laws for In-Context Regression: Depth, Width, Context and TimePoster
- Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?Poster
- Theory-Grounded Evaluation of Human-Like Fallacy Patterns in LLM ReasoningPoster
- There Was Never a Bottleneck in Concept Bottleneck ModelsPoster
- There and Back Again: On the relation between Noise and Image Inversions in Diffusion ModelsPoster
- Thicker and Quicker: The Jumbo Token for Fast Plain Vision TransformersPoster
- ThinKV: Thought-Adaptive KV Cache Compression for Efficient Reasoning ModelsOral
- Think Then Embed: Generative Context Improves Multimodal EmbeddingPoster
- Think in Parallel, Answer as One: Logit Averaging for Open-Ended ReasoningPoster
- Think-While-Generating: On-the-Fly Reasoning for Personalized Long-Form GenerationPoster
- ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought ReasoningPoster
- ThinkOmni: Lifting Textual Reasoning to Omni-modal Scenarios via Guidance DecodingPoster
- Thinking as Society: Multi-Social-Agent Self-Distillation for Multimodal Misinformation DetectionPoster
- Thinking on the Fly: Test-Time Reasoning Enhancement via Latent Thought Policy OptimizationPoster
- Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and GenerationPoster
- Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient ReasonersPoster
- Thompson Sampling via Fine-Tuning of LLMsPoster
- Thought Branches: Interpreting LLM Reasoning Requires ResamplingPoster
- Threading Keyframe with Narratives: MLLMs as Strong Long Video ComprehendersPoster
- Three Forward, One Backward: Memory-Efficient Full-Rank Fine-Tuning of Large Models via Extra Forward PassesPoster
- Through the Lens of Contrast: Self-Improving Visual Reasoning in VLMsOral
- Thyme: Think Beyond ImagesPoster
- TiTok: Transfer Token-level Knowledge via Contrastive Excess to Transplant LoRAPoster
- TianQuan-S2S: A Subseasonal-to-Seasonal Global Weather Model via Incorporate Climatology StatePoster
- Tight Bounds for Schrodinger Potential Estimation in Unpaired Data TranslationPoster
- Tighter Performance Theory of FedExProxPoster
- TikZilla: Scaling Text-to-TikZ with High-Quality Data and Reinforcement LearningPoster
- TileLang: Bridge Programmability and Performance in Modern Neural KernelsOral
- Time Is All It Takes: Spike-Retiming Attacks on Event-Driven Spiking Neural NetworksPoster
- Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language ModelsPoster
- Time Optimal Execution of Action Chunk Policies Beyond Demonstration SpeedPoster
- Time-Gated Multi-Scale Flow Matching for Time-Series ImputationPoster
- Time-To-Inconsistency: A Survival Analysis of Large Language Model Robustness to Adversarial AttacksPoster
- Time-to-Move: Training-Free Motion-Controlled Video Generation via Dual-Clock DenoisingPoster
- TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language ModelsPoster
- TimeRecipe: A Time-Series Forecasting Recipe via Benchmarking Module Level EffectivenessPoster
- TimeSearch-R: Adaptive Temporal Search for Long-Form Video Understanding via Self-Verification Reinforcement LearningPoster
- TimeSeg: An Information-Theoretic Segment-Wise Explainer for Time-Series PredictionsPoster
- TimeSeriesExamAgent: Creating TimeSeries Reasoning Benchmarks at ScalePoster
- Tina: Tiny Reasoning Models via LoRAPoster
- To Augment or Not to Augment? Diagnosing Distributional Symmetry BreakingPoster
- To Compress or Not? Pushing the Frontier of Lossless GenAI Model Weights Compression with Exponent ConcentrationPoster
- To Infinity and Beyond: Tool-Use Unlocks Length Generalization in State Space ModelsOral
- To Sink or Not to Sink: Visual Information Pathways in Large Vision-Language ModelsPoster
- To View Transform or Not to View Transform: NeRF-based Pre-training PerspectivePoster
- ToProVAR: Efficient Visual Autoregressive Modeling via Tri-Dimensional Entropy-Aware Semantic Analysis and Sparsity OptimizationPoster
- TokMem: Tokenized Procedural Memory for Large Language ModelsPoster
- TokUR: Token-Level Uncertainty Estimation for Large Language Model ReasoningPoster
- Token Distillation: Attention-Aware Input Embeddings for New TokensPoster
- Token Hidden Reward: Steering Exploration-Exploitation in Group Relative Deep Reinforcement LearningPoster
- Token-Based Audio Inpainting via Discrete DiffusionPoster
- Token-Efficient Long-Term Interest Sketching and Internalized Reasoning for LLM-based RecommendationPoster
- Token-Guard: Towards Token-Level Hallucination Control via Self-Checking DecodingPoster
- Token-Importance Guided Direct Preference OptimizationOral
- Token-level Data Selection for Safe LLM Fine-tuningPoster
- TokenSeek: Memory Efficient Fine Tuning via Instance-Aware Token DitchingPoster
- Tokenisation over Bounded Alphabets is HardPoster
- Tokenizing Single-Channel EEG with Time-Frequency Motif LearningPoster
- ToolACE-MT: Non-Autoregressive Generation for Agentic Multi-Turn InteractionPoster
- ToolTree: Efficient LLM Tool Planning via Dual-Feedback Monte Carlo Tree Search and Bidirectional PruningPoster
- ToolWeaver: Weaving Collaborative Semantics for Scalable Tool Use in Large Language ModelsPoster
- Tools are under-documented: Simple Document Expansion Boosts Tool RetrievalPoster
- ToonComposer: Streamlining Cartoon Production with Generative Post-KeyframingPoster
- TopoFormer: Topology Meets Attention for Graph LearningPoster
- Topological Anomaly Quantification for Semi-supervised Graph Anomaly DetectionPoster
- Topological Causal EffectsPoster
- Topological Flow MatchingPoster
- Topology Matters in RTL Circuit Representation LearningPoster
- Topology and geometry of the learning space of ReLU networks: connectivity and singularitiesPoster
- Topology of Reasoning: Retrieved Cell Complex-Augmented Generation for Textual Graph Question AnsweringPoster
- Topology-Preserved Auto-regressive Mesh Generation in the Manner of Weaving SilkPoster
- Toward Complex-Valued Neural Networks for Waveform GenerationPoster
- Toward Conservative Planning from Preferences in Offline Reinforcement LearningPoster
- Toward Effective Tool-Integrated Reasoning via Self-Evolved Preference LearningPoster
- Toward Efficient Exploration by Large Language Model AgentsPoster
- Toward Enhancing Representation Learning in Federated Multi-Task SettingsPoster
- Toward Faithful Retrieval-Augmented Generation with Sparse AutoencodersPoster
- Toward Practical Equilibrium Propagation: Brain-inspired Recurrent Neural Network with Feedback Regulation and Residual ConnectionsPoster
- Toward Principled Flexible Scaling for Self-Gated Neural ActivationPoster
- Toward Safer Diffusion Language Models: Discovery and Mitigation of Priming VulnerabilityPoster
- Toward Universal and Transferable Jailbreak Attacks on Vision-Language ModelsPoster
- Towards All-Atom Foundation Models for Biomolecular Binding Affinity PredictionPoster
- Towards Anomaly-Aware Pre-Training and Fine-Tuning for Graph Anomaly DetectionPoster
- Towards Better Branching Policies: Leveraging the Sequential Nature of Branch-and-Bound TreePoster
- Towards Better Optimization For Listwise Preference in Diffusion ModelsPoster
- Towards Bridging the Gap between Large-Scale Pretraining and Efficient Finetuning for Humanoid ControlPoster
- Towards Cognitively-Faithful Decision-Making Models to Improve AI AlignmentPoster
- Towards Dynamic Interleaving OptimizersPoster
- Towards Efficient Constraint Handling in Neural Solvers for Routing ProblemsPoster
- Towards Efficient Optimizer Design for LLM via Structured Fisher Approximation with a Low-Rank ExtensionPoster
- Towards Faithful Reasoning in Remote Sensing: A Perceptually-Grounded GeoSpatial Chain-of-Thought for Vision-Language ModelsPoster
- Towards Generalizable PDE Dynamics Forecasting via Physics-Guided Invariant LearningPoster
- Towards Greater Leverage: Scaling Laws for Efficient Mixture-of-Experts Language ModelsPoster
- Towards High Data Efficiency in Reinforcement Learning with Verifiable RewardPoster
- Towards Improved Sentence Representations using Token GraphsPoster
- Towards Improvisational TAMP: Learning Low-Level Shortcuts in Abstract Planning GraphsPoster
- Towards Interpretable Visual Decoding with Attention to Brain RepresentationsPoster
- Towards Knowledge‑and‑Data‑Driven Organic Reaction Prediction: RAG‑Enhanced and Reasoning‑Powered Hybrid System with LLMsPoster
- Towards Learned Optimization Free LunchPoster
- Towards Lossless Memory-efficient Training of Spiking Neural Networks via Gradient Checkpointing and Spike CompressionPoster
- Towards Multimodal Data-Driven Scientific Discovery Powered by LLM AgentsPoster
- Towards Multimodal Time Series Anomaly Detection with Semantic Alignment and Condensed InteractionPoster
- Towards One-step Causal Video Generation via Adversarial Self-DistillationPoster
- Towards Persistent Noise-Tolerant Active Learning of Regular Languages with Class QueryPoster
- Towards Personalized Deep Research: Benchmarks and EvaluationsICLR 2026 ConditionalPoster
- Towards Physically Executable 3D Gaussian for Embodied NavigationPoster
- Towards Privacy-Guaranteed Label Unlearning in Vertical Federated Learning: Few-Shot Forgetting Without DisclosurePoster
- Towards Quantifying Long-Range Interactions in Graph Machine Learning: a Large Graph Dataset and a MeasurementPoster
- Towards Quantization-Aware Training for Ultra-Low-Bit Reasoning LLMsPoster
- Towards Real-World Routing with Neural Combinatorial OptimizationPoster
- Towards Reliable Benchmarking: A Contamination Free, Controllable Evaluation Framework for Multi-step LLM Function CallingPoster
- Towards Reliable Detection of Empty Space: Conditional Marked Point Processes for Object DetectionPoster
- Towards Robust Real-World Multivariate Time Series Forecasting: A Unified Framework for Dependency, Asynchrony, and MissingnessPoster
- Towards Safe Reasoning in Large Reasoning Models via Corrective InterventionPoster
- Towards Safe and Optimal Online Bidding: A Modular Look-ahead Lyapunov FrameworkPoster
- Towards Sampling Data Structures for Tensor Products in Turnstile StreamsPoster
- Towards Self-Evolving Agent Benchmarks : Validatable Agent Trajectory via Test-Time ExplorationPoster
- Towards Self-Robust LLMs: Intrinsic Prompt Noise Resistance via CoIPOPoster
- Towards Sequence Modeling Alignment between Tokenizer and Autoregressive ModelPoster
- Towards Spatial Supersensing in VideoPoster
- Towards Strategic Persuasion with Language ModelsPoster
- Towards Sustainable Investment Policies Informed by Opponent ShapingPoster
- Towards Text-Mask Consistency in Medical Image SegmentationPoster
- Towards True Speech-to-Speech Models Without Text GuidancePoster
- Towards Understanding Subliminal Learning: When and How Hidden Biases TransferPoster
- Towards Understanding The Calibration Benefits of Sharpness-Aware MinimizationPoster
- Towards Understanding Valuable Preference Data for Large Language Model AlignmentPoster
- Towards Understanding the Nature of Attention with Low-Rank Sparse DecompositionPoster
- Towards Understanding the Shape of Representations in Protein Language ModelsPoster
- Towards a Certificate of Trust: Task-Aware OOD Detection for Scientific AIPoster
- Towards a Foundation Model for Crowdsourced Label AggregationPoster
- Towards a Sharp Analysis of Learning Offline $f$-Divergence-Regularized Contextual BanditsPoster
- Towards a Theoretical Understanding of In-context Learning: Stability and Non-I.I.D GeneralisationPoster
- Towards a Universally Transferable Acceleration Method for Density Functional TheoryPoster
- TraPO: A Semi-Supervised Reinforcement Learning Framework for Boosting LLM ReasoningPoster
- Trace Anything: Representing Any Video in 4D via Trajectory FieldsPoster
- Traceable Black-Box Watermarks For Federated LearningPoster
- Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and MethodPoster
- Tracing and Reversing Edits in LLMsPoster
- Tracing the Traces: Latent Temporal Signals for Efficient and Accurate ReasoningPoster
- Tractability via Low Dimensionality: The Parameterized Complexity of Training Quantized Neural NetworksPoster
- Trade in Minutes! Rationality-Driven Agentic System for Quantitative Financial TradingPoster
- Train Once, Answer All: Many Pretraining Experiments for the Cost of OnePoster
- Train on Validation (ToV): Fast data selection with applications to fine-tuningPoster
- Train-before-Test Harmonizes Language Model RankingsOral
- TrainRef: Curating Data with Label Distribution and Minimal Reference for Accurate Prediction and Reliable ConfidencePoster
- Trained on Tokens, Calibrated on Concepts: The Emergence of Semantic Calibration in LLMsPoster
- Training Deep Normalization-Free Spiking Neural Networks with Lateral InhibitionPoster
- Training Dynamics Impact Post-Training Quantization RobustnessPoster
- Training Large Language Models To Reason In Parallel With Global Forking TokensPoster
- Training Large Reasoning Models Efficiently via Progressive Thought EncodingPoster
- Training-Free Determination of Network Width via Neural Tangent KernelPoster
- Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact MatchPoster
- Training-Free Reward-Guided Image Editing via Trajectory Optimal ControlPoster
- Training-Free Text-Guided Color Editing with Multi-Modal Diffusion TransformerPoster
- Training-free Counterfactual Explanation for Temporal Graph Model InferencePoster
- TrajFlow: Nation-wide Pseudo GPS Trajectory Generation with Flow Matching ModelsPoster
- TrajTok: What makes for a good trajectory tokenizer in behavior generation?Poster
- Trajectory Generation with Conservative Value Guidance for Offline Reinforcement LearningPoster
- Trajectory-aware Shifted State Space Models for Online Video Super-ResolutionPoster
- Transducing Language ModelsPoster
- Transductive Visual Programming: Evolving Tool Libraries from Experience for Spatial ReasoningPoster
- Transfer Learning in Infinite Width Feature Learning NetworksPoster
- Transferable and Stealthy Adversarial Attacks on Large Vision-Language ModelsPoster
- Transformers Don’t Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and Implications for Mechanistic InterpretabilityPoster
- Transformers Learn Latent Mixture Models In-Context via Mirror DescentPoster
- Transformers Trained via Gradient Descent Can Provably Learn a Class of Teacher ModelsPoster
- Transformers are Inherently SuccinctPoster
- Transformers as Measure-Theoretic Associative Memory: A Statistical Perspective and Minimax OptimalityPoster
- Transformers as Unsupervised Learning Algorithms: A study on Gaussian MixturesPoster
- Transformers with Endogenous In-Context Learning: Bias Characterization and MitigationPoster
- Transitive RL: Value Learning via Divide and ConquerPoster
- Translate Policy to Language: Flow Matching Generated Rewards for LLM ExplanationsPoster
- Translating Flow to Policy via Hindsight Online ImitationPoster
- Translation Heads: Unveiling Attention's Role in LLM Multilingual TranslationPoster
- Trapped by simplicity: When Transformers fail to learn from noisy featuresPoster
- Tree Search for LLM Agent Reinforcement LearningPoster
- Tree-based Dialogue Reinforced Policy Optimization for Red-Teaming AttacksPoster
- Tree-sliced Sobolev IPMPoster
- TreeGRPO: Tree-Advantage GRPO for Online RL Post-Training of Diffusion ModelsPoster
- TreeGrad-Ranker: Feature Ranking via $O(L)$-Time Gradients for Decision TreesPoster
- TriC-Motion: Tri-Domain Causal Modeling Grounded Text-to-Motion GenerationPoster
- TriQDef: Disrupting Semantic and Gradient Alignment to Prevent Adversarial Patch Transferability in Quantized Neural NetworksPoster
- Triangle Multiplication is All You Need for Biomolecular Structure RepresentationsPoster
- Tricks or Traps? A Deep Dive into RL for LLM ReasoningPoster
- TrimR: Verifier-based Training-Free Thinking Trimming for Efficient Test-Time ScalingPoster
- Trinity: An Evolved LLM CoordinatorPoster
- Triple-BERT: Do We Really Need MARL for Order Dispatch on Ride-Sharing Platforms?Oral
- TripleSumm: Adaptive Triple-Modality Fusion for Video SummarizationPoster
- TrojanTO: Action-Level Backdoor Attacks Against Trajectory Optimization ModelsPoster
- True Self-Supervised Novel View Synthesis is TransferableOral
- Trust The TypicalPoster
- Trust but Verify: Adaptive Conditioning for Reference-Based Diffusion Super-Resolution via Implicit Reference Correlation ModelingPoster
- Trust-Region Adaptive Policy OptimizationPoster
- TrustGen: A Platform of Dynamic Benchmarking on the Trustworthiness of Generative Foundation ModelsPoster
- TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate ThemPoster
- Truthful or Fabricated? Using Causal Attribution to Mitigate Reward Hacking in ExplanationsPoster
- Truthfulness Despite Weak Supervision: Evaluating and Training LLMs Using Peer PredictionPoster
- Tucker-FNO: Tensor Tucker-Fourier Neural Operator and its Universal Approximation TheoryPoster
- Tug-of-War No More: Harmonizing Accuracy and Robustness in Vision-Language Models via Stability-Aware Task Vector MergingPoster
- TumorChain: Interleaved Multimodal Chain-of-Thought Reasoning for Traceable Clinical Tumor AnalysisPoster
- Tuning the burn-in phase in training recurrent neural networks improves their performancePoster
- Turbo-DDCM: Fast and Flexible Zero-Shot Diffusion-Based Image CompressionPoster
- TurboBoA: Faster and Exact Attention-aware Quantization without BackpropagationPoster
- TurboQuant: Online Vector Quantization with Near-optimal Distortion RatePoster
- Turning Internal Gap into Self-Improvement: Promoting the Generation-Understanding Unification in MLLMsPoster
- TusoAI: Agentic Optimization for Scientific MethodsPoster
- Tversky Neural Networks: Psychologically Plausible Deep Learning with Differentiable Tversky SimilarityPoster
- TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial FlowsPoster
- TwinVLA: Data-Efficient Bimanual Manipulation with Twin Single-Arm Vision-Language-Action ModelsPoster
- Two (narrow) heads are better than (an arbitrarily wide) onePoster
- Two failure modes of deep transformers and how to avoid them: a unified theory of signal propagation at initialisationPoster
- Two-Layer Convolutional Autoencoders Trained on Normal Data Provably Detect Unseen AnomaliesPoster
- Two-Way Is Better Than One: Bidirectional Alignment with Cycle Consistency for Exemplar-Free Class-Incremental LearningPoster
- Type-Compliant Adaptation CascadesPoster
- TyphoonMLA: A Mixed Naive-Absorb MLA Kernel For Shared PrefixPoster
- U-MARVEL: Unveiling Key Factors for Universal Multimodal Retrieval via Embedding Learning with MLLMsPoster
- U2-BENCH: Benchmarking Large Vision-Language Models on Ultrasound UnderstandingPoster
- UALM: Unified Audio Language Model for Understanding, Generation and ReasoningOral
- UFO-4D: Unposed Feedforward 4D reconstruction from Two ImagesPoster
- UI-Ins: Enhancing GUI Grounding with Multi-Perspective Instruction as ReasoningPoster
- UIS-Digger: Towards Comprehensive Research Agent Systems for Real-world Unindexed Information SeekingPoster
- ULD-Net: Enabling Ultra-Low-Degree Fully Polynomial Networks for Homomorphically Encrypted InferencePoster
- ULTRA-360: Unconstrained Dataset for Large-scale Temporal 3D Reconstruction across Altitudes and Omnidirectional ViewsPoster
- UME-R1: Exploring Reasoning-Driven Generative Multimodal EmbeddingsPoster
- UNDERSTANDING TRANSFORMERS FOR TIME SEIRES FORECASTING: A CASE STUDY ON MOIRAIPoster
- UNITE: Universal kNowledge Integration from Task-specific ExpertsPoster
- UNIVERSAL AND EFFICIENT LOADING BALANCING FOR RL TRAINING OF LARGE MULTIMODAL MODELSPoster
- UP2You: Fast Reconstruction of Yourself from Unconstrained Photo CollectionsPoster
- USTBench: Benchmarking and Dissecting Spatiotemporal Reasoning Capabilities of LLMs as Urban AgentsPoster
- Ultra-Fast Language Generation via Discrete Diffusion Divergence InstructPoster
- UltraGauss: Ultrafast Gaussian Reconstruction of 3D Ultrasound VolumesPoster
- UltraLLaDA: Scaling the Context Length to 128K for Diffusion Large Language ModelsPoster
- UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior Long-Context LearningPoster
- UltraViCo: Breaking Extrapolation Limits in Video Diffusion TransformersPoster
- UnLoc: Leveraging Depth Uncertainties for Floorplan LocalizationPoster
- Unbalanced Soft-Matching Distance For Neural Representational Comparison With Partial Unit CorrespondencePoster
- Unbiased Gradient Estimation for Event Binning via Functional BackpropagationPoster
- Uncertainty Estimation via Hyperspherical Confidence MappingPoster
- Uncertainty Matters in Dynamic Gaussian Splatting for Monocular 4D ReconstructionPoster
- Uncertainty as Feature Gaps: Epistemic Uncertainty Quantification of LLMs in Contextual Question-AnsweringPoster
- Uncertainty-Aware 3D Reconstruction for Dynamic Underwater ScenesPoster
- Uncertainty-Aware Diagnostics for Physics-Informed Machine LearningPoster
- Uncertainty-Aware Gaussian Map for Vision-Language NavigationPoster
- Uncertainty-driven Embedding ConvolutionPoster
- Uncover Underlying Correspondence for Robust Multi-view ClusteringOral
- Uncovering Conceptual Blindspots in Generative Image Models Using Sparse AutoencodersPoster
- Uncovering Robot Vulnerabilities through Semantic Potential FieldsPoster
- Uncovering Semantic Selectivity of Latent Groups in Higher Visual Cortex with Mutual Information-Guided DiffusionPoster
- Understanding Dataset Distillation via Spectral FilteringPoster
- Understanding In-Context Learning on Structured Manifolds: Bridging Attention to Kernel MethodsPoster
- Understanding Language Prior of LVLMs by Contrasting Chain-of-EmbeddingPoster
- Understanding Routing Mechanism in Mixture-of-Experts Language ModelsPoster
- Understanding Sensitivity of Differential Attention through the Lens of Adversarial RobustnessPoster
- Understanding Task Vectors in In-Context Learning: Emergence, Functionality, and LimitationsPoster
- Understanding Transformers for Time Series: Rank Structure, Flow-of-ranks, and CompressibilityPoster
- Understanding VLMs Spatial Mental Modeling Capability from Limited ViewsPoster
- Understanding and Improving Continuous LLM Adversarial Training via In-context Learning TheoryPoster
- Understanding and Improving Hyperbolic Deep Reinforcement LearningPoster
- Understanding and Improving Length Generalization in Hierarchical Sparse Attention ModelsPoster
- Understanding and Relaxing the Limitations of Transformers for Linear AlgebraPoster
- Understanding and improving Shampoo and SOAP via Kullback-Leibler MinimizationPoster
- Understanding the Dynamics of Forgetting and Generalization in Continual Learning via the Neural Tangent KernelPoster
- Understanding the Emergence of Seemingly Useless Features in Next-Token PredictorsPoster
- Understanding the Implicit Biases of Design Choices for Time Series Foundation ModelsPoster
- Understanding the Learning Phases in Self-Supervised Learning via Critical PeriodsPoster
- Understanding the Mechanisms of Fast Hyperparameter TransferPoster
- Understanding the Mixture-of-Experts with Nadaraya-Watson KernelPoster
- Understanding the Robustness of Distributed Self-Supervised Learning Frameworks Against Non-IID DataPoster
- Understanding the Role of Training Data in Test-Time ScalingPoster
- Understanding vs. Generation: Navigating Optimization Dilemma in Multimodal ModelsPoster
- Unfolding Spatial Cognition: Evaluating Multimodal Models on Visual SimulationsPoster
- Uni-CoT: Towards Unified Chain-of-Thought Reasoning Across Text and VisionPoster
- Uni-DPO: A Unified Paradigm for Dynamic Preference Optimization of LLMsPoster
- Uni-NTFM: A Unified Foundation Model for EEG Signal Representation LearningPoster
- Uni-X: Mitigating Modality Conflict with a Two-End-Separated Architecture for Unified Multimodal ModelsPoster
- UniCA: Unified Covariate Adaptation for Time Series Foundation ModelPoster
- UniCalli: A Unified Diffusion Framework for Column-Level Generation and Recognition of Chinese CalligraphyPoster
ICLR accepted papers in other years
Looking for submission deadlines instead? See the conference deadline calendar.