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
- DELTA-Code: How RL Unlocks and Transfers New Programming Algorithms in LLMsPoster
- DES-LOC: Desynced Low Communication Adaptive Optimizers for Foundation ModelsPoster
- DESIGNER: Design-Logic-Guided Multidisciplinary Data Synthesis for LLM ReasoningPoster
- DETR-ViP: Detection Transformer with Robust Discriminative Visual PromptsPoster
- DGNet: Learning Spatiotemporal PDEs with Discrete Green NetworksPoster
- DHG-Bench: A Comprehensive Benchmark for Deep Hypergraph LearningPoster
- DIFFSPARSE: ACCELERATING DIFFUSION TRANSFORMERS WITH LEARNED TOKEN SPARSITYPoster
- DISCO: Diversifying Sample Condensation for Accelerating Model EvaluationPoster
- DIVA-GRPO: Enhancing Multimodal Reasoning through Difficulty-Adaptive Variant AdvantagePoster
- DIVERSE: Disagreement-Inducing Vector Evolution for Rashomon Set ExplorationPoster
- DM4CT: Benchmarking Diffusion Models for Computed Tomography ReconstructionPoster
- DMAP: A Distribution Map for TextPoster
- DND: Boosting Large Language Models with Dynamic Nested DepthPoster
- DNT: a Deeply Normalized Transformer that can be trained by Momentum SGDPoster
- DOPPLER: Dual-Policy Learning for Device Assignment in Asynchronous Dataflow GraphsPoster
- DP-Fusion: Token-Level Differentially Private Inference for Large Language ModelsPoster
- DPQuant: Efficient and Private Model Training via Dynamic Quantization SchedulingPoster
- DPad: Efficient Diffusion Language Models with Suffix DropoutPoster
- DR-GGAD: Dual Residual Centering for Mitigating Anomaly Non‑Discriminativity in Generalist Graph Anomaly DetectionPoster
- DR-SAC: Distributionally Robust Soft Actor-Critic for Reinforcement Learning under UncertaintyPoster
- DR-Submodular Maximization with Stochastic Biased Gradients: Classical and Quantum Gradient AlgorithmsPoster
- DRAGON: Guard LLM Unlearning in Context via Negative Detection and ReasoningPoster
- DRBench: A Realistic Benchmark for Enterprise Deep ResearchPoster
- DRIFT-Net: A Spectral-Coupled Neural Operator for PDEs LearningPoster
- DRIFT: Decompose, Retrieve, Illustrate, then Formalize TheoremsPoster
- DRIFT: Divergent Response in Filtered Transformations for Robust Adversarial DefensePoster
- DRIFT: Learning from Abundant User Dissatisfaction in Real-World Preference LearningPoster
- DRPO: Efficient Reasoning via Decoupled Reward Policy OptimizationPoster
- DSA: Efficient Inference For Video Generation Models via Distributed Sparse AttentionPoster
- DSSA: Dense-Sparse Switchable Attention for Seamless Short-to-Long AdaptationPoster
- DTO-KD: Dynamic Trade-off Optimization for Effective Knowledge DistillationOral
- DTP: Delta-Guided Two Stage Pruning for Mamba-based Multimodal Large Language ModelsPoster
- DUET: DISTILLED LLM UNLEARNING FROM AN EFFICIENTLY CONTEXTUALIZED TEACHERPoster
- DUET: Optimizing LLM Training Data Mixtures via Noisy Feedback from Unseen, Downstream Evaluation TasksPoster
- DVD-Quant: Data-free Video Diffusion Transformers QuantizationPoster
- DVLA-RL: Dual-Level Vision–Language Alignment with Reinforcement Learning Gating for Few-Shot LearningPoster
- DaVinci: Reinforcing Visual-Structural Syntax in MLLMs for Generalized Scientific Diagram ParsingPoster
- DanceTogether: Generating Interactive Multi-Person Video without Identity DriftingPoster
- Dancing in Chains: Strategic Persuasion in Academic Rebuttal via Theory of MindPoster
- Darwin Gödel Machine: Open-Ended Evolution of Self-Improving AgentsPoster
- Data Aware and Scalable Sensitivity Analysis for Decision Tree EnsemblesPoster
- Data Provenance for Image Auto-Regressive GenerationPoster
- Data Selection for LLM Alignment Using Fine-Grained PreferencesPoster
- Data-Centric Lessons To Improve Speech-Language PretrainingICLR 2026 ConditionalPoster
- Data-to-Energy Stochastic DynamicsPoster
- DataMIL: Selecting Data for Robot Imitation Learning with DatamodelsPoster
- Dataless Weight Disentanglement in Task Arithmetic via Kronecker-Factored Approximate CurvaturePoster
- Dataset Color Quantization: A Training-Oriented Framework for Dataset-Level CompressionPoster
- Dataset Distillation as Pushforward Optimal QuantizationPoster
- Dataset Distillation for Memorized Data: Soft Labels can Leak Held-Out Teacher KnowledgePoster
- DeAltHDR: Learning HDR Video Reconstruction from Degraded Alternating Exposure SequencesPoster
- DeCo-DETR: Decoupled Cognition DETR for efficient Open-Vocabulary Object DetectionPoster
- DeLeaker: Dynamic Inference-Time Reweighting For Semantic Leakage Mitigation in Text-to-Image ModelsPoster
- DeLiVR: Differential Spatiotemporal Lie Bias for Efficient Video DerainingPoster
- DeMo: Decoupled Momentum OptimizationPoster
- DeNOTS: Stable Deep Neural ODEs for Time SeriesPoster
- DePO: Demonstration-guided Policy Optimization for Molecular OptimizationPoster
- DeRaDiff: Denoising Time Realignment of Diffusion ModelsPoster
- Death of the Novel(ty): Beyond N-Gram Novelty as a Metric for Textual CreativityPoster
- Debiased and Denoised Projection Learning for Incomplete Multi-view ClusteringPoster
- Debugging Concept Bottleneck Models through Removal and RetrainingPoster
- DecAlign: Hierarchical Cross-Modal Alignment for Decoupled Multimodal Representation LearningPoster
- Decentralized Attention Fails Centralized Signals: Rethinking Transformers for Medical Time SeriesOral
- Decentralized Nonconvex Optimization under Heavy-Tailed Noise: Normalization and Optimal ConvergencePoster
- Decision Aggregation under Quantal ResponsePoster
- Decision Pre-Trained Transformer is a Scalable In-Context Reinforcement LearnerPoster
- Decision-Theoretic Approaches for Improved Learning-Augmented AlgorithmsPoster
- Declarative Audio Editing with Audio Language ModelPoster
- Decoding Dynamic Visual Experience from Calcium Imaging via Cell-Pattern-Aware SSLPoster
- Decoding Inner Speech with an End-to-End Brain-to-Text Neural InterfacePoster
- Decoding Open-Ended Information Seeking Goals from Eye Movements in ReadingPoster
- DecompGAIL: Learning Realistic Traffic Behaviors with Decomposed Multi-Agent Generative Adversarial Imitation LearningPoster
- Decomposed Attention Fusion in MLLMs for Training-free Video Reasoning SegmentationPoster
- Decomposing Extrapolative Problem Solving: Spatial Transfer and Length Scaling with Map WorldsPoster
- Decomposing Representation Space into Interpretable Subspaces with Unsupervised LearningPoster
- Decomposition of Concept-Level Rules in Visual ScenesPoster
- Deconstructing Guidance: A Semantic Hierarchy for Precise Diffusion Model EditingPoster
- Deconstructing Positional Information: From Attention Logits to Training BiasesPoster
- Decoupled DMD: CFG Augmentation as the Spear, Distribution Matching as the ShieldPoster
- Decoupled MeanFlow: Turning Flow Models into Flow Maps for Accelerated SamplingPoster
- Decoupled Q-ChunkingPoster
- Decoupling Dynamical Richness from Representation Learning: Towards Practical MeasurementPoster
- Decoupling Positional and Symbolic Attention in TransformersPoster
- Decoupling Primitive with Experts: Dynamic Feature Alignment for Compositional Zero-Shot LearningPoster
- Decoupling the Class Label and the Target Concept in Machine UnlearningPoster
- Deep FlexQP: Accelerated Nonlinear Programming via Deep UnfoldingPoster
- Deep Global-sense Hard-negative Discriminative Generation Hashing for Cross-modal RetrievalPoster
- Deep Hierarchical Learning with Nested Subspace NetworksPoster
- Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMsPoster
- Deep Latent Variable Model based Vertical Federated Learning with Flexible Alignment and Labeling ScenariosPoster
- Deep Learning for Subspace RegressionPoster
- Deep Learning with Learnable Product-Structured ActivationsPoster
- Deep SPI: Safe Policy Improvement via World ModelsPoster
- Deep Think with ConfidencePoster
- Deep-ICE: The first globally optimal algorithm for empirical risk minimization of two-layer maxout and ReLU networksPoster
- DeepAFL: Deep Analytic Federated LearningPoster
- DeepCompress: A Dual Reward Strategy for Dynamically Exploring and Compressing Reasoning ChainsPoster
- DeepEyes: Incentivizing "Thinking with Images" via Reinforcement LearningPoster
- DeepEyesV2: Toward Agentic Multimodal ModelPoster
- DeepFRC: An End-to-End Deep Learning Model for Functional Registration and ClassificationPoster
- DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing ReasoningPoster
- DeepPrim: a Physics-Driven 3D Short-term Weather Forecaster via Primitive Equation LearningPoster
- DeepRAG: Thinking to Retrieve Step by Step for Large Language ModelsPoster
- DeepResearch Bench: A Comprehensive Benchmark for Deep Research AgentsPoster
- DeepSADR: Deep Transfer Learning with Subsequence Interaction and Adaptive Readout for Cancer Drug Response PredictionPoster
- DeepScientist: Advancing Frontier-Pushing Scientific Findings ProgressivelyPoster
- DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree SearchPoster
- DeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and EvidencePoster
- DeepWeightFlow: Re-Basined Flow Matching for Generating Neural Network WeightsPoster
- Defending against Backdoor Attacks via Module SwitchingPoster
- Deforming Videos to Masks: Flow Matching for Referring Video SegmentationPoster
- Deft Scheduling of Dynamic Cloud Workflows with Varying Deadlines via Mixture-of-ExpertsPoster
- Delay Flow MatchingPoster
- Delta-XAI: A Unified Framework for Explaining Prediction Changes in Online Time Series MonitoringPoster
- Delving into Spectral Clustering with Vision-Language RepresentationsPoster
- DemoGrasp: Universal Dexterous Grasping from a Single DemonstrationPoster
- Demystifying Deep Search: A Holistic Evaluation with Hint-free Multi-Hop Questions and Factorised MetricsPoster
- Demystifying Emergent Exploration in Goal-Conditioned RLPoster
- Demystifying Robot Diffusion Policies: Action Memorization and a Simple Lookup Table AlternativePoster
- Demystifying Supervision Data Generalization in Multimodal LMsPoster
- Demystifying and Enhancing the Efficiency of Large Language Model Based Search AgentsPoster
- Denoising Neural Reranker for Recommender SystemsPoster
- Dens3R: A Foundation Model for 3D Geometry PredictionPoster
- DenseGRPO: From Sparse to Dense Reward for Flow Matching Model AlignmentPoster
- Densemarks: Learning Canonical Embeddings for Human Heads Images via Point TracksPoster
- Deploying Models to Non-participating Clients in Federated Learning without Fine-tuning: A Hypernetwork-based ApproachPoster
- Depth Anything 3: Recovering the Visual Space from Any ViewsOral
- Depth Anything with Any PriorPoster
- DepthLM: Metric Depth from Vision Language ModelsOral
- Derandomized Online-to-Non-convex Conversion for Stochastic Weakly Convex OptimizationPoster
- Designing Affine-Invariant Neural Networks for Photometric Corruption Robustness and GeneralizationPoster
- Designing Rules to Pick a Rule: Aggregation by ConsistencyPoster
- Designing Time Series Experiments in A/B Testing with Transformer Reinforcement LearningPoster
- Detect, Decide, Unlearn: A Transfer-Aware Framework for Continual LearningPoster
- Detecting Data Contamination from Reinforcement Learning Post-training for Large Language ModelsPoster
- Detecting Data Contamination in LLMs via In-Context LearningPoster
- Detecting Invariant Manifolds in ReLU-Based RNNsPoster
- Detecting Misbehaviors of Large Vision-Language Models by Evidential Uncertainty QuantificationPoster
- Detecting Temporal Misalignment Attacks in Multimodal Fusion for Autonomous DrivingPoster
- Detecting and Mitigating Memorization in Diffusion Models through Anisotropy of the Log-ProbabilityPoster
- Detection of unknown unknowns in autonomous systemsPoster
- Detective SAM: Adaptive AI-Image Forgery LocalizationPoster
- Deterministic Bounds and Random Estimates of Metric Tensors on NeuromanifoldsPoster
- DevOps-Gym: Benchmarking AI Agents in Software DevOps CyclePoster
- Developmental Federated Tuning: A Cognitive-Inspired Paradigm for Efficient LLM AdaptationPoster
- DexMove: Learning Tactile-Guided Non-Prehensile Manipulation with Dexterous HandsPoster
- DexNDM: Closing the Reality Gap for Dexterous In-Hand Rotation via Joint-Wise Neural Dynamics ModelPoster
- DiCache: Let Diffusion Model Determine Its Own CachePoster
- DiMeR: Disentangled Mesh Reconstruction Model with Normal-only Geometry TrainingPoster
- DiSRouter: Distributed Self-Routing for LLM SelectionsPoster
- DiVE-k: DIFFERENTIAL VISUAL REASONING FOR FINE-GRAINED IMAGE RECOGNITIONPoster
- DiVeQ: Differentiable Vector Quantization Using the Reparameterization TrickPoster
- DiaBlo: Diagonal Blocks Are Sufficient For FinetuningPoster
- Diagnosing Failures in Generalization from Task-Relevant Representational GeometryPoster
- Diagnosing and Improving Diffusion Models by Estimating Optimal Loss ValuePoster
- Diagnosing and Remedying Knowledge Deficiencies in LLMs via Label-free Curricular Meaningful LearningPoster
- Dichotomous Diffusion Policy OptimizationPoster
- DiffAdapt: Difficulty-Adaptive Reasoning for Token-Efficient LLM InferencePoster
- DiffInk: Glyph- and Style-Aware Latent Diffusion Transformer for Text to Online Handwriting GenerationPoster
- DiffPBR: Point-Based Rendering via Spatial-Aware Residual DiffusionPoster
- DiffSDA: Unsupervised Diffusion Sequential Disentanglement Across ModalitiesPoster
- DiffTrans: Differentiable Geometry-Materials Decomposition for Reconstructing Transparent ObjectsPoster
- DiffVax: Optimization-Free Image Immunization Against Diffusion-Based EditingPoster
- DiffWind: Physics-Informed Differentiable Modeling of Wind-Driven Object DynamicsPoster
- Difference Predictive Coding for Training Spiking Neural NetworksPoster
- Difference-Aware Retrieval Polices for Imitation LearningPoster
- Differentiable JPEG-based Input Perturbation for Knowledge Distillation Amplification via Conditional Mutual Information MaximizationPoster
- Differentiable Lifting for Topological Neural NetworksPoster
- Differentiable Model Predictive Control on the GPUOral
- Differentiable Simulation of Hard Contacts with Soft Gradients for Learning and ControlPoster
- Differential Fine-Tuning Large Language Models Towards Better Diverse Reasoning AbilitiesPoster
- Differentially Private Domain DiscoveryOral
- Differentially Private Equilibrium Finding in Polymatrix GamesPoster
- Differentially Private Two-Stage Gradient Descent for Instrumental Variable RegressionPoster
- Difficult Examples Hurt Unsupervised Contrastive Learning: A Theoretical PerspectiveOral
- Difficulty–Diversity Collaborative Filtering for Data-Efficient LLM Fine-TuningPoster
- DiffuCoder: Understanding and Improving Masked Diffusion Models for Code GenerationPoster
- DiffuDETR: Rethinking Detection Transformers with Diffusion ProcessPoster
- DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language ModelsPoster
- Diffusion & Adversarial Schrödinger Bridges via Iterative Proportional Markovian FittingPoster
- Diffusion Alignment as Variataional Expectation-MaximizationPoster
- Diffusion Blend: Inference-Time Multi-Preference Alignment for Diffusion ModelsPoster
- Diffusion Bridge Variational Inference for Deep Gaussian ProcessesPoster
- Diffusion Fine-Tuning via Reparameterized Policy Gradient of the Soft Q-FunctionPoster
- Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion ForcingPoster
- Diffusion Language Model Knows the Answer Before It DecodesOral
- Diffusion Language Models are Provably Optimal Parallel SamplersPoster
- Diffusion Models as Dataset Distillation PriorsPoster
- Diffusion Negative Preference Optimization Made SimplePoster
- Diffusion Transformers with Representation AutoencodersPoster
- Diffusion and Flow-based Copulas: Forgetting and Remembering DependenciesPoster
- Diffusion-DFL: Decision-focused Diffusion Models for Stochastic OptimizationPoster
- DiffusionBlocks: Block-wise Neural Network Training via Diffusion InterpretationPoster
- DiffusionNFT: Online Diffusion Reinforcement with Forward ProcessOral
- Dimension-Free Decision Calibration for Nonlinear Loss FunctionsPoster
- Dimension-Free Minimax Rates for Learning Pairwise Interactions in Attention-Style ModelsPoster
- DirMoE: Dirichlet-Routed Mixture of ExpertsPoster
- Direct Doubly Robust Estimation of Conditional Quantile ContrastsPoster
- Direct Preference Optimization for Primitive-Enabled Hierarchical RL: A Bilevel ApproachPoster
- Direct Reward Fine-Tuning on Poses for Single Image to 3D Human in the WildPoster
- Directed Semi-Simplicial Learning with Applications to Brain Activity DecodingPoster
- Directional Convergence, Benign Overfitting of Gradient Descent in leaky ReLU two-layer Neural NetworksPoster
- Directional Sheaf Hypergraph Networks: Unifying Learning on Directed and Undirected HypergraphsPoster
- Directional Textual Inversion for Personalized Text-to-Image GenerationPoster
- DisTaC: Conditioning Task Vectors via Distillation for Robust Model MergingPoster
- Discern Truth from Falsehood: Reducing Over-Refusal via Contrastive RefinementPoster
- Disco: Densely-overlapping Cell Instance Segmentation via Adjacency-aware Collaborative ColoringPoster
- DiscoX: Benchmarking Discourse-Level Translation in Expert DomainsPoster
- Discount Model Search for Quality Diversity Optimization in High-Dimensional Measure SpacesOral
- Discounted Online Convex Optimization: Uniform Regret Across a Continuous IntervalPoster
- Discovering Diverse Behaviors via Temporal Contrastive LearningPoster
- Discovering Hierarchical Software Engineering Agents via Bandit OptimizationPoster
- Discovering Novel LLM Experts via Task-Capability CoevolutionPoster
- Discovering alternative solutions beyond the simplicity bias in recurrent neural networksPoster
- Discovering and Steering Interpretable Concepts in Large Generative Music ModelsPoster
- Discovering heterogeneous synaptic plasticity rules via large-scale neural evolutionPoster
- Discrete Adjoint MatchingPoster
- Discrete Bayesian Sample Inference for Graph GenerationPoster
- Discrete Compositional Generation via General Soft Operators and Robust Reinforcement LearningPoster
- Discrete Diffusion Trajectory Alignment via Stepwise DecompositionPoster
- Discrete Diffusion for Bundle ConstructionPoster
- Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous DrivingPoster
- Discrete Guidance Matching: Exact Guidance for Discrete Flow MatchingPoster
- Discrete Latent Features Ablate Adversarial Attack: A Robust Prompt Tuning Framework for VLMsPoster
- Discrete Variational Autoencoding via Policy SearchPoster
- Disentangled Hierarchical VAE for 3D Human-Human Interaction GenerationPoster
- Disentangled Representation Learning for Parametric Partial Differential EquationsPoster
- Disentangled Robot Learning via Separate Forward and Inverse Dynamics PretrainingPoster
- Disentangled representation learning through unsupervised symmetry group discoveryPoster
- Disentanglement of Variations with Multimodal Generative ModelingPoster
- Disentangling Knowledge Representations for Large Language Model EditingPoster
- Disentangling Length Bias in Preference Learning via Response-Conditioned ModelingPoster
- Disentangling the Factors of Convergence between Brains and Computer Vision ModelsPoster
- DispViT: Direct Stereo Disparity Regression with a Single-Stream Vision TransformerPoster
- Displacement-Resistant Extensions of DPO with Nonconvex $f$-DivergencesPoster
- Disrupting Hierarchical Reasoning: Adversarial Protection for Geographic Privacy in Multimodal Reasoning ModelsPoster
- Dissecting Representation Misalignment in Contrastive Learning via Influence FunctionPoster
- DistDF: Time-series Forecasting Needs Joint-distribution Wasserstein AlignmentPoster
- DistMLIP: A Distributed Inference Platform for Machine Learning Interatomic PotentialsPoster
- Distill-SynthKG: Distilling Knowledge Graph Synthesis Workflow for Improved Coverage and EfficiencyPoster
- DistillKac: Few-Step Image Generation via Damped Wave EquationsPoster
- Distillation of Large Language Models via Concrete Score MatchingPoster
- Distilled Pretraining: A modern lens of Data, In-Context Learning and Test-Time ScalingPoster
- Distilling and Adapting: A Topology-Aware Framework for Zero-Shot Interaction Prediction in Multiplex Biological NetworksPoster
- Distilling the Thought, Watermarking the Answer: A Principle Semantic Guided Watermark for Reasoning Large Language ModelsPoster
- Distilling to Hybrid Attention Models via KL-Guided Layer SelectionPoster
- Distractor-free Generalizable 3D Gaussian SplattingPoster
- Distributed Algorithms for Euclidean ClusteringPoster
- Distribution-Aware Multi-Granularity Phase Coding: Towards Lower Conversion Error for Spike-Driven Large Language ModelsPoster
- Distribution-informed Online Conformal PredictionPoster
- Distributional Consistency Loss: Beyond Pointwise Data Terms in Inverse ProblemsPoster
- Distributional Equivalence in Linear Non-Gaussian Latent-Variable Cyclic Causal Models: Characterization and LearningOral
- Distributional Vision-Language Alignment by Cauchy-Schwarz DivergencePoster
- Distributional value gradients for stochastic environmentsPoster
- Distributionally Robust Classification for Multi-source Unsupervised Domain AdaptationPoster
- Distributionally Robust Cooperative Multi-agent Reinforcement Learning with Value FactorizationPoster
- Distributionally Robust Linear Regression with Block Lewis WeightsPoster
- Distributionally Robust Optimization via Generative Ambiguity ModelingPoster
- Distributions as Actions: A Unified Framework for Diverse Action SpacesPoster
- Divergence-Free Neural Networks with Application to Image DenoisingPoster
- Diverse Dictionary LearningPoster
- Diverse Text Decoding via Iterative ReweightingPoster
- Diverse Text-to-Image Generation via Contrastive Noise OptimizationPoster
- Diverse and Sparse Mixture-of-Experts for Causal Subgraph–Based Out-of-Distribution Graph LearningPoster
- Diversified Multinomial Logit Contextual BanditsPoster
- Diversity-Aware Online Prompt Assignment to Generative ModelsPoster
- Diversity-Enhanced Reasoning for Subjective QuestionsPoster
- Diversity-Incentivized Exploration for Versatile ReasoningPoster
- Divid: Disentangled Spatial-Temporal Modeling within LLMs for Temporally Grounded Video UnderstandingPoster
- Divide and Abstract: Autoformalization via Decomposition and Abstraction LearningPoster
- Divide, Harmonize, Then Conquer It: Shooting Multi-Commodity Flow Problems with Multimodal Language ModelsPoster
- Do 3D Large Language Models Really Understand 3D Spatial Relationships?Poster
- Do LLM Agents Know How to Ground, Recover, and Assess? Evaluating Epistemic Competence in Information-Seeking AgentsPoster
- Do LLMs Forget What They Should? Evaluating In-Context Forgetting in Large Language ModelsPoster
- Do Large Language Models Know What They Are Capable Of?Poster
- Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMsPoster
- Do Vision-Language Models Respect Contextual Integrity in Location Disclosure?Poster
- Do We Need All the Synthetic Data? Targeted Image Augmentation via Diffusion ModelsPoster
- Do We Really Need Permutations? Impact of Width Expansion on Linear Mode ConnectivityPoster
- DoFlow: Flow-based Generative Models for Interventional and Counterfactual Forecasting on Time SeriesPoster
- DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent SystemsPoster
- Doctor-R1: Mastering Clinical Inquiry with Experiential Agentic Reinforcement LearningPoster
- Does FLUX Already Know How to Perform Physically Plausible Image Composition?Poster
- Does Higher Interpretability Imply Better Utility? A Pairwise Analysis on Sparse AutoencodersPoster
- Does Weak-to-strong Generalization Happen under Spurious Correlations?Poster
- Does the Data Processing Inequality Reflect Practice? On the Utility of Low-Level TasksPoster
- Does “Do Differentiable Simulators Give Better Policy Gradients?” Give Better Policy Gradients?Poster
- Doloris: Dual Conditional Diffusion Implicit Bridges with Sparsity Masking Strategy for Unpaired Single-Cell Perturbation EstimationPoster
- Domain Expansion: A Latent Space Construction Framework for Multi-Task LearningPoster
- Don't Forget Its Variance! The Minimum Path Variance Principle for Accurate and Stable Score-Based ModelsPoster
- Don't Just Fine-tune the Agent, Tune the EnvironmentPoster
- Don't Settle Too Early: Self-Reflective Remasking for Diffusion Language ModelsPoster
- Don't Shift the Trigger: Robust Gradient Ascent for Backdoor UnlearningPoster
- Don't Throw Away Your Beams: Improving Consistency-based Uncertainties in LLMs via Beam SearchPoster
- Don't Throw Away Your Pretrained ModelPoster
- Don’t Pass@$k$: A Bayesian Framework for Large Language Model EvaluationPoster
- Doubly-Regressing Approach for Subgroup FairnessPoster
- Doubly-Robust LLM-as-a-Judge: Externally Valid Estimation with Imperfect PersonasPoster
- Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM UnlearningPoster
- Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning ModelsPoster
- Dr.LLM: Dynamic Layer Routing in LLMsPoster
- DrVoice: Parallel Speech-Text Voice Conversation Model via Dual-Resolution Speech RepresentationsPoster
- Draft-based Approximate Inference for LLMsPoster
- DragFlow: Unleashing DiT Priors with Region-Based Supervision for Drag EditingPoster
- Dragging with Geometry: From Pixels to Geometry-Guided Image EditingPoster
- Draw-In-Mind: Rebalancing Designer-Painter Roles in Unified Multimodal Models Benefits Image EditingPoster
- DreamCS: Geometry-Aware Text-to-3D Generation with Unpaired 3D Reward SupervisionPoster
- DreamOn: Diffusion Language Models For Code Infilling Beyond Fixed-size CanvasPoster
- DreamPhase: Offline Imagination and Uncertainty-Guided Planning for Large-Language-Model AgentsPoster
- DreamSwapV: Mask-guided Subject Swapping for Any Customized Video EditingPoster
- DriftLite: Lightweight Drift Control for Inference-Time Scaling of Diffusion ModelsPoster
- DriveAgent-R1: Advancing VLM-based Autonomous Driving with Active Perception and Hybrid ThinkingPoster
- DriveMamba: Task-Centric Scalable State Space Model for Efficient End-to-End Autonomous DrivingPoster
- DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous DrivingPoster
- DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous DrivingPoster
- Dropping Just a Handful of Preferences Can Change Top Large Language Model RankingsPoster
- DrugTrail: Explainable Drug Discovery via Structured Reasoning and Druggability‑Tailored Preference OptimizationPoster
- Drugging the Undruggable: Benchmarking and Modeling Fragment-Based ScreeningPoster
- DuPO: Enabling Reliable Self-Verification via Dual Preference OptimizationPoster
- Dual Distillation for Few-Shot Anomaly DetectionPoster
- Dual Goal RepresentationsPoster
- Dual Language Models: Balancing sample-efficiency and overfitting resiliencePoster
- Dual Optimistic Ascent (PI Control) is the Augmented Lagrangian Method in DisguisePoster
- Dual Perspectives on Non-Contrastive Self-Supervised LearningPoster
- Dual Randomized Smoothing: Beyond Global Noise VariancePoster
- Dual-Branch Representations with Dynamic Gated Fusion and Triple-Granularity Alignment for Deep Multi-View ClusteringPoster
- Dual-IPO: Dual-Iterative Preference Optimization for Text-to-Video GenerationPoster
- Dual-Kernel Adapter: Expanding Spatial Horizons for Data-Constrained Medical Image AnalysisPoster
- Dual-Objective Reinforcement Learning with Novel Hamilton-Jacobi-Bellman FormulationsPoster
- Dual-Path Condition Alignment for Diffusion TransformersPoster
- Dual-Robust Cross-Domain Offline Reinforcement Learning Against Dynamics ShiftsPoster
- Dual-Scale World Models for LLM Agents towards Hard-Exploration ProblemsPoster
- Dual-Solver: A Generalized ODE Solver for Diffusion Models with Dual PredictionPoster
- Dual-Space Smoothness for Robust and Balanced LLM UnlearningPoster
- DualMap: Enabling Both Cache Affinity and Load Balancing for Distributed LLM ServingPoster
- DualToken: Towards Unifying Visual Understanding and Generation with Dual Visual VocabulariesPoster
- Durian: Dual Reference Image-Guided Portrait Animation with Attribute TransferPoster
- Dyna-Mind: Learning to Simulate from Experience for Better AI AgentsPoster
- DynaGuard: A Dynamic Guardian Model With User-Defined PoliciesPoster
- Dynamic Chunking for End-to-End Hierarchical Sequence ModelingPoster
- Dynamic Classifier-Free Diffusion Guidance via Online FeedbackPoster
- Dynamic Early Exit in Reasoning ModelsPoster
- Dynamic Kernel Graph SparsifiersPoster
- Dynamic Multi-sample Mixup with Gradient Exploration for Open-set Graph Anomaly DetectionPoster
- Dynamic Multimodal Activation Steering for Hallucination Mitigation in Large Vision-Language ModelsPoster
- Dynamic Novel View Synthesis in High Dynamic RangePoster
- Dynamic Reflections: Probing Video Representations with Text AlignmentPoster
- Dynamic Speculative Agent PlanningPoster
- Dynamic Texture Modeling of 3D Clothed Gaussian Avatars from a Single VideoPoster
- Dynamic-dLLM: Dynamic Cache-Budget and Adaptive Parallel Decoding for Training-Free Acceleration of Diffusion LLMPoster
- DynamicInfer: Runtime-Aware Sparse Offloading for LLMs Inference on a Consumer-Grade GPUPoster
- Dynamical properties of dense associative memoryPoster
- Dynamics-Predictive Sampling for Active RL Finetuning of Large Reasoning ModelsPoster
- Dyslexify: A Mechanistic Defense Against Typographic Attacks in CLIPPoster
- EA3D: Event-Augmented 3D Diffusion for Generalizable Novel View SynthesisPoster
- EAMET: ROBUST MASSIVE MODEL EDITING VIA EMBEDDING ALIGNMENT OPTIMIZATIONPoster
- EAST: Early Action Prediction Sampling Strategy with Token MaskingPoster
- ECHO: Toward Contextual Seq2Seq Paradigms in Large EEG ModelsPoster
- EDINET-Bench: Evaluating LLMs on Complex Financial Tasks using Japanese Financial StatementsPoster
- EEPO: Exploration-Enhanced Policy Optimization via Sample-Then-ForgetPoster
- EGG-SR: Embedding Symbolic Equivalence into Symbolic Regression via Equality GraphPoster
- ELEPHANT: Measuring and understanding social sycophancy in LLMsPoster
- ELLMob: Event-Driven Human Mobility Generation with Self-Aligned LLM FrameworkPoster
- ELMUR: External Layer Memory with Update/Rewrite for Long-Horizon RLPoster
- ELViS: Efficient Visual Similarity from Local Descriptors that Generalizes Across DomainsPoster
- EMBridge: Enhancing Gesture Generalization from EMG Signals Through Cross-modal Representation LearningPoster
- EMFuse: Energy-based Model Fusion for Decision MakingPoster
- ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric InteractionPoster
- ERGO: Efficient High-Resolution Visual Understanding for Vision-Language ModelsPoster
- ERTACache: Error Rectification and Timesteps Adjustment for Efficient DiffusionPoster
- ES-dLLM: Efficient Inference for Diffusion Large Language Models by Early-SkippingPoster
- ETGS: Explicit Thermodynamics Gaussian Splatting for Dynamic Thermal ReconstructionPoster
- EUBRL: Epistemic Uncertainty Directed Bayesian Reinforcement LearningPoster
- EVEREST: A Transformer for Probabilistic Rare-Event Anomaly Detection with Evidential and Tail-Aware UncertaintyPoster
- EVLP: Learning Unified Embodied Vision-Language Planner with Reinforced Supervised Fine-TuningPoster
- EXP-Bench: Can AI Conduct AI Research Experiments?Poster
- EXPO: Stable Reinforcement Learning with Expressive PoliciesPoster
- Early Signs of Steganographic Capabilities in Frontier LLMsPoster
- Earth-Agent: Unlocking the Full Landscape of Earth Observation with AgentsPoster
- EarthSE: A Benchmark Evaluating Earth Scientific Exploration Capability for Large Language ModelsPoster
- Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?Poster
- EasyCreator: Empowering 4D Creation through Video InpaintingPoster
- EasyTune: Efficient Step-Aware Fine-Tuning for Diffusion-Based Motion GenerationPoster
- Echo: Towards Advanced Audio Comprehension via Audio-Interleaved ReasoningPoster
- EchoGen: Generating Visual Echoes in Any Scene via Feed-Forward Subject-Driven Auto-Regressive ModelPoster
- EchoMind: An Interrelated Multi-level Benchmark for Evaluating Empathetic Speech Language ModelsPoster
- EchoMotion: Unified Human Video and Motion Generation via Dual-Modality Diffusion TransformerPoster
- Echoes as Anchors: Probabilistic Costs and Attention Refocusing in LLM ReasoningPoster
- EdgeCape: Edge Weight Prediction For Category-Agnostic Pose EstimationPoster
- EdiVal-Agent: An Object-Centric Framework for Automated, Fine-Grained Evaluation of Multi-Turn EditingPoster
- Edit-Based Flow Matching for Temporal Point ProcessesPoster
- EditBench: Evaluating LLM Abilities to Perform Real-World Instructed Code EditsOral
- EditLens: Quantifying the Extent of AI Editing in TextPoster
- EditReward: A Human-Aligned Reward Model for Instruction-Guided Image EditingPoster
- EditScore: Unlocking Online RL for Image Editing via High-Fidelity Reward ModelingPoster
- EditVerse: Unifying Image and Video Editing and Generation with In-Context LearningOral
- EffiVMT: Video Motion Transfer via Efficient Spatial-Temporal Decoupled FinetuningPoster
- Efficient Adversarial Attacks on High-dimensional Offline BanditsPoster
- Efficient Agent Training for Computer UsePoster
- Efficient Approximate Posterior Sampling with Annealed Langevin Monte CarloPoster
- Efficient Audio-Visual Speech Separation with Discrete Lip Semantics and Multi-Scale Global-Local AttentionPoster
- Efficient Autoregressive Inference for Transformer Probabilistic ModelsPoster
- Efficient Best-of-Both-Worlds Algorithms for Contextual Combinatorial Semi-BanditsPoster
- Efficient Credal Prediction through DecalibrationPoster
- Efficient Degradation-agnostic Image Restoration via Channel-Wise Functional Decomposition and Manifold RegularizationPoster
- Efficient Differentiable Contact Model with Long-range InfluencePoster
- Efficient Discriminative Joint Encoders for Large Scale Vision-Language RerankingPoster
- Efficient Ensemble Conditional Independence Test Framework for Causal DiscoveryPoster
- Efficient Estimation of Kernel Surrogate Models for Task AttributionPoster
- Efficient Learning on Large Graphs using a Densifying Regularity LemmaPoster
- Efficient Message-Passing Transformer for Error Correcting CodesPoster
- Efficient Morphology–Control Co-Design via Stackelberg PPO under Non-Differentiable Leader–Follower InterfacesPoster
- Efficient Multi-objective Prompt Optimization via Pure-exploration BanditsPoster
- Efficient Multimodal Spatial Reasoning via Dynamic and Asymmetric RoutingPoster
- Efficient Offline Reinforcement Learning via Peer-Influenced ConstraintPoster
- Efficient Orthogonal Fine-Tuning with Principal Subspace AdaptationPoster
- Efficient Prediction of Large Protein Complexes via Subunit-Guided Hierarchical RefinementPoster
- Efficient Quantization of Mixture-of-Experts with Theoretical Generalization GuaranteesPoster
- Efficient Reasoning with Balanced ThinkingPoster
- Efficient Regression-based Training of Normalizing Flows for Boltzmann GeneratorsPoster
- Efficient Reinforcement Learning by Guiding World Models with Non-Curated DataPoster
- Efficient Resource-Constrained Training of Transformers via Subspace OptimizationOral
- Efficient Sliced Wasserstein Distance Computation via Adaptive Bayesian OptimizationPoster
- Efficient Spatially-Variant Convolution via Differentiable Sparse Kernel ComplexPoster
- Efficient Submodular Maximization for Sums of Concave over Modular FunctionsPoster
- Efficient Test-Time Scaling for Small Vision-Language ModelsPoster
- Efficient Testing for Correlation Clustering: Improved Algorithms and Optimal BoundsPoster
- Efficient Turing Machine Simulation with TransformersPoster
- Efficient Zero-shot Inpainting with Decoupled Diffusion GuidancePoster
- Efficient algorithms for Incremental Metric Bipartite MatchingPoster
- Efficient and Sharp Off-Policy Learning under Unobserved ConfoundingPoster
- Efficient-LVSM: Faster, Cheaper, and Better Large View Synthesis Model via Decoupled Co-Refinement AttentionPoster
- Efficient-SAM2: Accelerating SAM2 with Object-Aware Visual Encoding and Memory RetrievalPoster
- Egalitarian Gradient Descent: A Simple Approach to Accelerated GrokkingPoster
- Ego-Foresight: Self-supervised Learning of Agent-Aware Representations for Improved RLPoster
- EgoBrain: Synergizing Minds and Eyes For Human Action UnderstandingPoster
- EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric VideoPoster
- EgoHandICL: Egocentric 3D Hand Reconstruction with In-Context LearningPoster
- EgoNight: Towards Egocentric Vision Understanding at Night with a Challenging BenchmarkPoster
- EgoTwin: Dreaming Body and View in First PersonPoster
- EgoWorld: Translating Exocentric View to Egocentric View using Rich Exocentric ObservationsPoster
- Eigen-1: Scientific Reasoning through Adaptive Multi-Agent Refinement and Monitor-based RAGPoster
- EigenBench: A Comparative Behavioral Measure of Value AlignmentOral
- EigenScore: OOD Detection using Posterior Covariance in Diffusion ModelsPoster
- Einstein Fields: A Neural Perspective To Computational General RelativityPoster
- Elastic Optimal Transport: Theory, Application, and Empirical EvaluationPoster
- Eliciting Harmful Capabilities by Fine-Tuning on Safeguarded OutputsPoster
- Eliciting Numerical Predictive Distributions of LLMs Without Auto-RegressionPoster
- Eliminating Inductive Bias in Reward Models with Information-Theoretic GuidancePoster
- Eliminating VAE for Fast and High-Resolution Generative Detail RestorationPoster
- Embedding-Based Context-Aware RerankerPoster
- Embodied Agents Meet Personalization: Investigating Challenges and Solutions Through the Lens of Memory UtilizationPoster
- Embodied Navigation Foundation ModelPoster
- Embodied-R1: Reinforced Embodied Reasoning for General Robotic ManipulationPoster
- Embracing Discrete Search: A Reasonable Approach to Causal Structure LearningPoster
- Emergence of Spatial Representation in an Actor-Critic Agent with Hippocampus-Inspired Sequence GeneratorPoster
- Emergence of Superposition: Unveiling the Training Dynamics of Chain of Continuous ThoughtPoster
- Emergent Coordination in Multi-Agent Language ModelsPoster
- Emergent Dexterity Via Diverse Resets and Large-Scale Reinforcement LearningPoster
- Emergent Discrete Controller Modules for Symbolic Planning in TransformersPoster
- Emergent Hierarchical Reasoning in LLMs through Reinforcement LearningPoster
- Emergent Misalignment is Easy, Narrow Misalignment is HardPoster
- EmoPrefer: Can Large Language Models Understand Human Emotion Preferences?Poster
- EmotionHallucer: Evaluating Emotion Hallucinations in Multimodal Large Language ModelsPoster
- EmotionThinker: Prosody-Aware Reinforcement Learning for Explainable Speech Emotion ReasoningOral
- Emotions Where Art Thou: Understanding and Characterizing the Emotional Latent Space of Large Language ModelsPoster
- Empowering Efficiency and Efficacy in WebAgent via Enabling Info-Rich SeekingPoster
- Empowering LLM Tool Invocation with Tool-call Reward ModelPoster
- Empowering Multi-Robot Cooperation via Sequential World ModelsPoster
- Empowering Small VLMs to Think with Dynamic Memorization and ExplorationPoster
- Enabling Fine-Tuning of Direct Feedback Alignment via Feedback-Weight MatchingPoster
- Enabling True Global Perception in State Space Models for Visual TasksPoster
- Enabling Your Forensic Detector Know How Well It Performs on Distorted SamplesPoster
- Enabling arbitrary inference in spatio-temporal dynamic systems: A physics-inspired perspectivePoster
- End-to-End Probabilistic Framework for Learning with Hard ConstraintsPoster
- End-to-end Listen, Look, Speak and ActPoster
- Endowing GPT-4 with a Humanoid Body: Building the Bridge Between Off-the-Shelf VLMs and the Physical WorldPoster
- Energy-Based Transformers are Scalable Learners and ThinkersOral
- Energy-Efficient Random Variate Generation via Compressed Lookup TablesPoster
- Energy-Regularized Sequential Model Editing on HyperspheresPoster
- Enforcing Axioms for AI Alignment under Loss-Based RulesPoster
- Enhanced Continual Learning of Vision-Language Models with Model FusionPoster
- Enhanced Generative Model Evaluation with Clipped Density and CoveragePoster
- Enhancing Agentic Search via Data Synthesis on Hierarchical Constraint SatisfactionPoster
- Enhancing Communication Compression via Discrepancy-aware Calibration for Federated LearningPoster
- Enhancing Complex Symbolic Logical Reasoning of Large Language Models via Sparse Multi-Agent DebatePoster
- Enhancing Diffusion-Based Sampling with Molecular Collective VariablesPoster
- Enhancing Generative Auto-bidding with Offline Reward Evaluation and Policy SearchOral
- Enhancing Geometric Perception in VLMs via Translator-Guided Reinforcement LearningPoster
- Enhancing Hallucination Detection through Noise InjectionPoster
- Enhancing Image-Conditional Coverage in Segmentation: Adaptive Thresholding via Differentiable Miscoverage LossPoster
- Enhancing Instruction Following of LLMs via Activation Steering with Dynamic RejectionPoster
- Enhancing LLMs for Knowledge Base Question Answering by Chain-of-DecompositionPoster
- Enhancing Language Model Reasoning with Structured Multi-Level ModelingPoster
- Enhancing Learning with Noisy Labels via Rockafellian RelaxationPoster
- Enhancing Molecular Property Predictions by Learning from Bond Modelling and InteractionsPoster
- Enhancing Multi-Image Understanding through Delimiter Token ScalingPoster
- Enhancing Multivariate Time Series Forecasting with Global Temporal RetrievalPoster
- Enhancing Persona Following at Decoding Time via Dynamic Importance Estimation for Role-Playing AgentsPoster
- Enhancing Sparse Event Detection in Healthcare Time-Series via Adaptive Gate of Context–Detail InteractionPoster
- Enhancing Stability of Physics-Informed Neural Network Training Through Saddle-Point ReformulationPoster
- Enhancing Trustworthiness of Fine-Tuned LLMs via Regularized Subset SelectionPoster
- Enhancing Vision Transformers for Object Detection via Context-Aware Token Selection and PackingPoster
- Enhancing Visual Token Representations for Video Large Language Models via Training-free Spatial-Temporal Pooling and GriddingPoster
- Enough is as good as a feast: A Comprehensive Analysis of How Reinforcement Learning Mitigates Task Conflicts in LLMsPoster
- Ensemble Prediction of Task Affinity for Efficient Multi-Task LearningPoster
- Ensembling Pruned Attention Heads For Uncertainty-Aware Efficient TransformersPoster
- Entering the Era of Discrete Diffusion Models: A Benchmark for Schrödinger Bridges and Entropic Optimal TransportPoster
- Entropic Confinement and Mode Connectivity in Overparameterized Neural NetworksPoster
- Entropy Regularizing Activation: Boosting Continuous Control, Large Language Models, and Image Classification with Activation as Entropy ConstraintsPoster
- Entropy-Based Block Pruning for Efficient Large Language ModelsPoster
- Entropy-Guided Dynamic Tokens for Graph-LLM Alignment in Molecular UnderstandingPoster
- Entropy-Monitored Kernelized Token Distillation for Audio-Visual CompressionPoster
- Entropy-preserving reinforcement learningPoster
- EntropyLong: Effective Long-Context Training via Predictive UncertaintyPoster
- EnvSocial-Diff: A Diffusion-Based Crowd Simulation Model with Environmental Conditioning and Individual-Group InteractionPoster
- Epistemic Uncertainty Quantification To Improve Decisions From Black-Box ModelsPoster
- EquAct: An SE(3)-Equivariant Multi-Task Transformer for 3D Robotic ManipulationPoster
- Equilibrium Language ModelsPoster
- Equivariant Splitting: Self-supervised learning from incomplete dataPoster
- Erase or Hide? Suppressing Spurious Unlearning Neurons for Robust UnlearningPoster
- Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMsPoster
- Error Feedback for Muon and FriendsPoster
- Error Notebook-Guided, Training-Free Part Retrieval in 3D CAD Assemblies via Vision-Language ModelsPoster
- Error as Signal: Stiffness-Aware Diffusion Sampling via Embedded Runge-Kutta GuidancePoster
- Escaping Low-Rank Traps: Interpretable Visual Concept Learning via Implicit Vector QuantizationPoster
- Escaping Model Collapse via Synthetic Data Verification: Near-term Improvements and Long-term ConvergencePoster
- Escaping Policy Contraction: Contraction-Aware PPO (CaPPO) for Stable Language Model Fine-TuningPoster
- Escaping the Homophily Trap: A Threshold-free Graph Outlier Detection Framework via Clustering-guided Edge ReweightingPoster
- Estimating Dimensionality of Neural Representations from Finite SamplesPoster
- Estimating Semantic Alphabet Size for LLM Uncertainty QuantificationPoster
- Estimating Worst-Case Frontier Risks of Open-Weight LLMsPoster
- EvA: Evolutionary Attacks on GraphsPoster
- Evaluating Cross-Modal Reasoning Ability and Problem Charactaristics with Multimodal Item Response TheoryPoster
- Evaluating Data Influence in Meta LearningPoster
- Evaluating GFlowNet from partial episodes for stable and flexible policy-based trainingPoster
- Evaluating Intuitive Physics Understanding in Video Diffusion Models via Likelihood PreferencePoster
- Evaluating Language Models' Evaluations of GamesPoster
- Evaluating Memory in LLM Agents via Incremental Multi-Turn InteractionsPoster
- Evaluating SAE interpretability without generating explanationsPoster
- Evaluating Text Creativity across Diverse Domains: a Dataset and Large Language Model EvaluatorPoster
- Evaluating and Improving Cultural Awareness of Reward Models for LLM AlignmentPoster
- Event-T2M: Event-level Conditioning for Complex Text-to-Motion SynthesisPoster
- EventFlash: Towards Efficient MLLMs for Event-Based VisionPoster
- Every Language Model Has a Forgery-Resistant SignatureOral
- Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image ModelsPoster
- Evidence for Limited Metacognition in LLMsPoster
- EvoTest: Evolutionary Test-Time Learning for Self-Improving Agentic SystemsPoster
- Evoking User Memory: Personalizing LLM via Recollection-Familiarity Adaptive RetrievalPoster
- EvolProver: Advancing Automated theorem proving by Evolving Formalized Problems via Symmetry and DifficultyPoster
- Evolution and compression in LLMs: on the emergence of human-aligned categorizationPoster
- Evolution of Concepts in Language Model Pre-TrainingPoster
- Evolutionary Caching to Accelerate Your Off-the-Shelf Diffusion ModelPoster
- Evolving Graph Structured Programs for Circuit Generation with Large Language ModelsPoster
- ExGRPO: Learning to Reason from Prior SuccessesPoster
- ExPO-HM: Learning to Explain-then-Detect for Hateful Meme DetectionPoster
- Exchangeability of GNN Representations with Applications to Graph RetrievalOral
- Exo-Plore: Exploring Exoskeleton Control Space through Human-aligned SimulationPoster
- ExoPredicator: Learning Abstract Models of Dynamic Worlds for Robot PlanningPoster
- ExpGuard: LLM Content Moderation in Specialized DomainsPoster
- ExpVid: A Benchmark for Experiment Video Understanding & ReasoningPoster
- Expanding Reasoning Potential in Foundation Model by Learning Diverse Chains of Thought PatternsPoster
- Expanding the Capability Frontier of LLM Agents with ZPD-Guided Data SynthesisPoster
- Experience-based Knowledge Correction for Robust Planning in MinecraftPoster
- Expert Divergence Learning for MoE-based Language ModelsPoster
- Expert Heads: Robust Evidence Identification for Large Language ModelsPoster
- Expert Merging in Sparse Mixture of Experts with Nash BargainingPoster
- Expert Merging: Model Merging with Unsupervised Expert Alignment and Importance-Guided Layer ChunkingPoster
- ExpertLongBench: Benchmarking Language Models on Expert-Level Long-Form Generation Tasks with Structured ChecklistsPoster
- Expertise Can Be Helpful for Reinforcement Learning-based Macro PlacementPoster
- Explain in Your Own Words: Improving Reasoning via Token-Selective Dual Knowledge DistillationPoster
- Explainable $ K $-means Neural Networks for Multi-view ClusteringPoster
- Explainable LLM Unlearning through ReasoningPoster
- Explainable Mixture Models through Differentiable Rule LearningPoster
- Explainable Token-level Noise Filtering for LLM Fine-tuning DatasetsPoster
- Explaining Grokking and Information Bottleneck through Neural Collapse EmergencePoster
- Exploiting Low-Dimensional Manifold of Features for Few-shot Whole Slide Image ClassificationPoster
- Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious RewardPoster
- Exploratory Causal Inference in SAEnceOral
- Exploratory Diffusion Model for Unsupervised Reinforcement LearningOral
- Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy OptimizationPoster
- Explore-on-Graph: Incentivizing Autonomous Exploration of Large Language Models on Knowledge Graphs with Path-refined Reward ModelingPoster
- Exploring Cross-Modal Flows for Few-Shot LearningPoster
- Exploring Diverse Generation Paths via Inference-time Stiefel Activation SteeringPoster
- Exploring Interpretability for Visual Prompt Tuning with Cross-layer ConceptsPoster
- Exploring Knowledge Purification in Multi-Teacher Knowledge Distillation for LLMsPoster
- Exploring Mode Connectivity in Krylov Subspace for Domain GeneralizationPoster
- Exploring Real-Time Super-Resolution: Benchmarking and Fine-Tuning for Streaming ContentPoster
- Exploring Specular Reflection Inconsistency for Generalizable Face Forgery DetectionPoster
- Exploring State-Space Models for Data-Specific Neural RepresentationsPoster
- Exploring Synthesizable Chemical Space with Iterative Pathway RefinementsOral
- Exploring the Basin-Like Loss Landscape in Large Language ModelsPoster
- Exploring the Design Space of Transition MatchingPoster
- Exploring the Limits of Sub-Billion Language Model Reasoners with Open Training RecipesPoster
- Exploring the Potential of Encoder-free Architectures in 3D LMMsPoster
- Exponential-Wrapped Mechanisms: Differential Privacy on Hadamard Manifolds Made PracticalPoster
- Exposing Mixture and Annotating Confusion for Active Universal Test-Time AdaptationPoster
- Exposing Weaknesses of Large Reasoning Models through Graph Algorithm ProblemsPoster
- Exposing and Defending the Achilles' Heel of Video Mixture-of-ExpertsPoster
- Expressive and Invariant Graph Learning via Canonical Tree Cover Neural NetworksPoster
- Expressive yet Efficient Feature Expansion with Adaptive Cross-Hadamard ProductsPoster
- Expressiveness of Multi-Neuron Convex Relaxations in Neural Network CertificationPoster
- Extending Fourier Neural Operators for Modeling Parameterized and Coupled PDEsPoster
- Extending Sequence Length is Not All You Need: Effective Integration of Multimodal Signals for Gene Expression PredictionOral
- Extending the Context of Pretrained LLMs by Dropping Their Positional EmbeddingPoster
- Extreme Weather Nowcasting via Local Precipitation Pattern PredictionPoster
- E²LoRA: Efficient and Effective Low-Rank Adaptation with Entropy-Guided Adaptive SharingPoster
- FACET: A Fragment-Aware Conformer Ensemble TransformerPoster
- FACM: Flow-Anchored Consistency ModelsPoster
- FACT: Fine-grained Across-variable Convolution for Multivariate Time Series ForecastingPoster
- FACT: a first-principles alternative to the Neural Feature Ansatz for how networks learn representationsPoster
- FALCON: Few-step Accurate Likelihoods for Continuous FlowsOral
- FAME: $\underline{F}$ormal $\underline{A}$bstract $\underline{M}$inimal $\underline{E}$xplanation for neural networksPoster
- FAPO: Flawed-Aware Policy Optimization for Efficient and Reliable ReasoningPoster
- FARI: Robust One-Step Inversion for Watermarking in Diffusion ModelsPoster
- FARTrack: Fast Autoregressive Visual Tracking with High PerformancePoster
- FASA: FREQUENCY-AWARE SPARSE ATTENTIONPoster
- FASTer: Toward Powerful and Efficient Autoregressive Vision–Language–Action Models with Learnable Action Tokenizer and Block-wise DecodingPoster
- FAST‑DIPS: Adjoint‑Free Analytic Steps and Hard‑Constrained Likelihood Correction for Diffusion‑Prior Inverse ProblemsPoster
- FATE: A Formal Benchmark Series for Frontier Algebra of Multiple Difficulty LevelsPoster
- FERD: Fairness-Enhanced Data-Free Adversarial Robustness DistillationPoster
- FETAL-GAUGE: A BENCHMARK FOR ASSESSING VISION-LANGUAGE MODELS IN FETAL ULTRASOUNDPoster
- FFT-based Dynamic Subspace Selection for Low-Rank Adaptive Optimization of Large Language ModelsPoster
- FHE-Coder: Secure Agentic Code Generation for Fully Homomorphic EncryptionPoster
- FIRE: Frobenius-Isometry Reinitialization for Balancing the Stability–Plasticity TradeoffOral
- FLARE: Fully Integration of Vision-Language Representations for Deep Cross-Modal UnderstandingPoster
- FLOWER: A Flow-Matching Solver for Inverse ProblemsPoster
- FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive BenchmarkPoster
- FLoC: Facility Location-Based Efficient Visual Token Compression for Long Video UnderstandingPoster
- FLoRG: Federated Fine-tuning with Low-rank Gram Matrices and Procrustes AlignmentPoster
- FM4NPP: A Scaling Foundation Model for Nuclear and Particle PhysicsPoster
- FMIP: Joint Continuous-Integer Flow For Mixed-Integer Linear ProgrammingPoster
- FOCUS: Efficient Keyframe Selection for Long Video UnderstandingPoster
- FRABench and UFEval: Unified Fine-grained Evaluation with Task and Aspect GeneralizationOral
- FREAK: A Fine-grained Hallucination Evaluation Benchmark for Advanced MLLMsPoster
- FRIEDA: Benchmarking Multi-Step Cartographic Reasoning in Vision-Language ModelsPoster
- FROST: Filtering Reasoning Outliers with Attention for Efficient ReasoningPoster
- FS-DFM: Fast and Accurate Long Text Generation with Few-Step Diffusion Language ModelsPoster
- FS-KAN: Permutation Equivariant Kolmogorov-Arnold Networks via Function SharingPoster
- FSA: An Alternative Efficient Implementation of Native Sparse Attention KernelPoster
- FSD-CAP: Fractional Subgraph Diffusion with Class-Aware Propagation for Graph Feature ImputationPoster
- FSOD-VFM: Few-Shot Object Detection with Vision Foundation Models and Graph DiffusionPoster
- FSPO: Few-Shot Optimization of Synthetic Preferences Effectively Personalizes to Real UsersPoster
- FZOO: Fast Zeroth-Order Optimizer for Fine‑Tuning Large Language Models towards Adam‑Scale SpeedPoster
- FaLW: A Forgetting-aware Loss Reweighting for Long-tailed UnlearningPoster
- FaSTA*: Fast-Slow Toolpath Agent with Subroutine Mining for Efficient Multi-turn Image EditingPoster
- Factuality Matters: When Image Generation and Editing Meet Structured VisualsPoster
- Fair Classification by Direct Intervention on Operating CharacteristicsPoster
- Fair Conformal Classification via Learning Representation-Based GroupsPoster
- Fair Decision Utility in Human-AI Collaboration: Interpretable Confidence Adjustment for Humans with Cognitive DisparitiesPoster
- Fair Graph Machine Learning under Adversarial Missingness ProcessesPoster
- Fair Policy Aggregation from Standard Policy OptimizationPoster
- Fair in Mind, Fair in Action? A Synchronous Benchmark for Understanding and Generation in UMLLMsPoster
- Fairness via Independence: A General Regularization Framework for Machine LearningPoster
- Fairness-Aware Multi-view Evidential Learning with Adaptive PriorPoster
- FaithCoT-Bench: Benchmarking Instance-Level Faithfulness of Chain-of-Thought ReasoningPoster
- Faithful Bi-Directional Model Steering via Distribution Matching and Distributed Interchange InterventionsPoster
- Faithfulness Under the Distribution: A New Look at Attribution EvaluationPoster
- FakeXplain: AI-Generated Image Detection via Human-Aligned Grounded ReasoningPoster
- Falcon: Fast Proximal Linearization of Normalized Cuts for Unsupervised Image SegmentationPoster
- Fantastic Pretraining Optimizers and Where to Find ThemPoster
- Fantastic Tractor-Dogs and How Not to Find Them With Open-Vocabulary DetectorsPoster
- FantasyWorld: Geometry-Consistent World Modeling via Unified Video and 3D PredictionPoster
- Fast Catch-Up, Late Switching: Optimal Batch Size Scheduling via Functional Scaling LawsPoster
- Fast Convergence of Natural Gradient Descent for Over-parameterized Physics-Informed Neural NetworksPoster
- Fast Data Mixture Optimization via Gradient DescentPoster
- Fast Escape, Slow Convergence: Learning Dynamics of Phase Retrieval under Power-Law DataOral
- Fast Estimation of Wasserstein Distances via Regression on Sliced Wasserstein DistancesPoster
- Fast Frank–Wolfe Algorithms with Adaptive Bregman Step-Size for Weakly Convex FunctionsPoster
- Fast Proteome-Scale Protein Interaction Retrieval via Residue-Level FactorizationPoster
- Fast and Interpretable Protein Substructure Alignment via Optimal TransportPoster
- Fast and Stable Riemannian Metrics on SPD Manifolds via Cholesky Product GeometryPoster
- Fast training of accurate physics-informed neural networks without gradient descentOral
- Fast-dLLM v2: Efficient Block-Diffusion LLMPoster
- Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel DecodingPoster
- FastAvatar: Towards Unified and Fast 3D Avatar Reconstruction with Large Gaussian Reconstruction TransformersPoster
- FastFlow: Accelerating The Generative Flow Matching Models with Bandit InferencePoster
- FastGHA: Generalized Few-Shot 3D Gaussian Head Avatars with Real-Time AnimationPoster
- FastGRPO: Accelerating Policy Optimization via Concurrency-aware Speculative Decoding and Online Draft LearningPoster
- FastVGGT: Fast Visual Geometry TransformerPoster
- FastVMT: Eliminating Redundancy in Video Motion TransferPoster
- Fastcar: Cache Attentive Replay for Fast Auto-Regressive Video Generation on the EdgePoster
- Faster Gradient Methods for Highly-smooth Stochastic Bilevel OptimizationPoster
- Faster Parameter-Free Regret Matching AlgorithmsPoster
- Faster Vision Transformers with Adaptive PatchesPoster
- Fathom-DeepResearch: Unlocking Long Horizon Information Retrieval and Synthesis for SLMsPoster
- FeDaL: Federated Dataset Learning for General Time Series Foundation ModelsPoster
- Feature compression is the root cause of adversarial fragility in neural networksPoster
- Feature segregation by signed weights in artificial vision systems and biological modelsPoster
- FeatureBench: Benchmarking Agentic Coding for Complex Feature DevelopmentPoster
- Features Emerge as Discrete States: The First Application of SAEs to 3D RepresentationsPoster
- Fed-Duet: Dual Expert-Orchestrated Framework for Continual Federated Vision-Language LearningPoster
- FedDAG: Clustered Federated Learning via Global Data and Gradient Integration for Heterogeneous EnvironmentsPoster
- FedMC: Federated Manifold CalibrationPoster
- FedMuon: Federated Learning with Bias-corrected LMO-based OptimizationPoster
- FedOpenMatch: Towards Semi-Supervised Federated Learning in Open-Set EnvironmentsPoster
- Federated ADMM from Bayesian DualityPoster
- Federated Graph-Level Clustering Network with Dual Knowledge SeparationPoster
- Federated Learning of Quantile Inference under Local Differential PrivacyPoster
- Federated Learning with Profile Mapping under Distribution Shifts and DriftsPoster
- Feed-forward Human Performance Capture via Progressive Canonical Space UpdatesPoster
- Feedback-driven recurrent quantum neural network universalityPoster
- Fewer Battles, More Gain: An Information-Efficient Framework for Arena-based LLM EvaluationPoster
- Fewer Weights, More Problems: A Practical Attack on LLM PruningPoster
- FideDiff: Efficient Diffusion Model for High-Fidelity Image Motion DeblurringPoster
- FieryGS: In-the-Wild Fire Synthesis with Physics-Integrated Gaussian SplattingPoster
- Figma2Code: Automating Multimodal Design to Code in the WildPoster
- FilMaster: Bridging Cinematic Principles and Generative AI for Automated Film GenerationPoster
- FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and ReasoningPoster
- Financial fraud collusion among generative AI agents in social networksPoster
- Fine-Grained Activation Steering: Steering Less, Achieving MorePoster
- Fine-Grained Class-Conditional Distribution Balancing for Debiased LearningPoster
- Fine-Grained Iterative Adversarial Attacks with Limited Computation BudgetPoster
- Fine-Grained Privacy Extraction from Retrieval-Augmented Generation Systems by Exploiting Knowledge AsymmetryPoster
- Fine-R1: Make Multi-modal LLMs Excel in Fine-Grained Visual Recognition by Chain-of-Thought ReasoningPoster
- Fine-Tuning Diffusion Models via Intermediate Distribution ShapingPoster
- Fine-tuning Behavioral Cloning Policies with Preference‑Based Reinforcement LearningPoster
- Fine-tuning Done Right in Model EditingPoster
- Fine-tuning Quantized Neural Networks with Zeroth-order OptimizationPoster
- FingerTip 20K: A Benchmark for Proactive and Personalized Mobile LLM AgentsPoster
- Fingerprinting Deep Neural Networks for Ownership Protection: An Analytical ApproachPoster
- Finite-Time Analysis of Actor-Critic Methods with Deep Neural Network ApproximationPoster
- Finite-Time Convergence Analysis of ODE-based Generative Models for Stochastic InterpolantsPoster
- First is Not Really Better Than Last: Evaluating Layer Choice and Aggregation Strategies in Language Model Data Influence EstimationPoster
- Fisher-Rao Sensitivity for Out-of-Distribution Detection in Deep Neural NetworksPoster
- Fixing the Broken Compass: Diagnosing and Improving Inference-Time Reward ModelingPoster
- Flash-Mono: Feed-Forward Accelerated Gaussian Splatting Monocular SLAMPoster
- Flash-Searcher: Fast and Effective Web Agents via DAG-Based Parallel ExecutionPoster
- FlashDLM: Accelerating Diffusion Language Model Inference via Efficient KV Caching and Guided DiffusionPoster
- FlashRNN: Unlocking Parallel Training of Nonlinear RNNs for Large Language ModelsOral
- FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token MergingOral
- FlashWorld: High-quality 3D Scene Generation within SecondsOral
- Flatness Guided Test-Time Adaptation for Vision-Language ModelsPoster
- Flatter Tokens are More Valuable for Speculative Draft Model TrainingPoster
- Flattery, Fluff, and Fog: Diagnosing and Mitigating Idiosyncratic Biases in Preference ModelsPoster
- FlexHiNM-GP: Flexible Hierarchical Pruning via Region Allocation and Channel PermutationPoster
- FlexLoRA: Entropy-Guided Flexible Low-Rank AdaptationPoster
- FlexProtein: Joint Sequence and Structure Pretraining for Protein ModelingPoster
- FlexiCodec: A Dynamic Neural Audio Codec for Low Frame RatesPoster
- Flipping the Dialogue: Training and Evaluating User Language ModelsPoster
- Flock: A Knowledge Graph Foundation Model via Learning on Random WalksPoster
- Flow Actor-Critic for Offline Reinforcement LearningPoster
- Flow Along the $K$-Amplitude for Generative ModelingPoster
- Flow Autoencoders are Effective Protein TokenizersPoster
- Flow Caching for Autoregressive Video GenerationPoster
- Flow Expansion via Verifier-Constrained Noised State Space ExplorationPoster
- Flow Map Learning via GamesPoster
- Flow Matching Policy GradientsPoster
- Flow Matching with Injected Noise for Offline-to-Online Reinforcement LearningPoster
- Flow Matching with Semidiscrete CouplingsPoster
- Flow Straight and Fast in Hilbert Space: Functional Rectified FlowPoster
- Flow of Spans: Generalizing Language Models to Dynamic Span-Vocabulary via GFlowNetsPoster
- Flow-Based Single-Step Completion for Efficient and Expressive Policy LearningPoster
- Flow-Disentangled Feature ImportancePoster
- Flow-based Conformal Prediction for Multi-dimensional Time SeriesPoster
- Flow2GAN: Hybrid Flow Matching and GAN with Multi-Resolution Network for One-/Two-step High-Fidelity Audio GenerationPoster
- FlowAD: Ego-Scene Interactive Modeling for Autonomous DrivingPoster
- FlowAlign: Trajectory-Regularized, Inversion-Free Flow-based Image EditingPoster
- FlowBind: Efficient Any-to-Any Generation with Bidirectional FlowsPoster
- FlowCast: Advancing Precipitation Nowcasting with Conditional Flow MatchingPoster
- FlowCast: Trajectory Forecasting for Scalable Zero-Cost Speculative Flow MatchingPoster
- FlowGen: Synthesizing Diverse Flowcharts to Enhance and Benchmark MLLM ReasoningPoster
- FlowNIB: An Information Bottleneck Analysis of Bidirectional vs. Unidirectional Language ModelsPoster
- FlowRL: Matching Reward Distributions for LLM ReasoningPoster
- FlowSearcher: Synthesizing Memory-Guided Agentic Workflows for Web Information SeekingPoster
- FlowSymm: Physics–Aware, Symmetry–Preserving Graph Attention for Network Flow CompletionPoster
- Flowing Through States: Neural ODE Regularization for Reinforcement LearningPoster
- Fluent Alignment with Disfluent Judges: Post-training for lower-resource languagesPoster
- Fly-CL: A Fly-Inspired Framework for Enhancing Efficient Decorrelation and Reduced Training Time in Pre-trained Model-based Continual Representation LearningPoster
- FlyPrompt: Brain-Inspired Random-Expanded Routing with Temporal-Ensemble Experts for General Continual LearningPoster
- FoNE: Precise Single-Token Number Embeddings via Fourier FeaturesPoster
- Follow-Your-Preference: Towards Preference-Aligned Image InpaintingPoster
- Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region ControlPoster
- Following the Navigation: Enhancing Small Language Models Contextual Reasoning with LLM GuidancePoster
- Fore-Mamba3D: Mamba-based Foreground-Enhanced Encoding for 3D Object DetectionPoster
- Foresight Diffusion: Improving Sampling Consistency in Predictive Diffusion ModelsPoster
- Forest-Based Graph Learning for Semi-Supervised Node ClassificationPoster
- ForestPersons: A Large-Scale Dataset for Under-Canopy Missing Person DetectionPoster
- Forge: Compiling a Unified Abstraction into Scalable Kernels for Linear AttentionPoster
- Forget Forgetting: Continual Learning in a World of Abundant MemoryPoster
- Forget Many, Forget Right: Scalable and Precise Concept Unlearning in Diffusion ModelsPoster
- Formal Mechanistic Interpretability: Automated Circuit Discovery with Provable GuaranteesPoster
- FormalML: A Benchmark for Evaluating Formal Subgoal Completion in Machine Learning TheoryPoster
- Formalising Human-in-the-Loop: Computational Reductions, Failure Modes, and Legal-Moral ResponsibilityPoster
- Forward-Learned Discrete Diffusion: Learning how to noise to denoise fasterPoster
- Fostering Video Reasoning via Next-Event PredictionPoster
- Foundation Models for Causal Inference via Prior-Data Fitted NetworksPoster
- Foundation Visual Encoders Are Secretly Few-Shot Anomaly DetectorsPoster
- Foundational Automatic Evaluators: Scaling Multi-Task Generative Evaluator Training for Reasoning-Centric DomainsPoster
- Fractional-Order Spiking Neural NetworkPoster
- Fracture-GS: Dynamic Fracture Simulation with Physics-Integrated Gaussian SplattingPoster
- FragFM: Hierarchical Framework for Efficient Molecule Generation via Fragment-Level Discrete Flow MatchingPoster
- Frame Guidance: Training-Free Guidance for Frame-Level Control in Video Diffusion ModelPoster
- FrameThinker: Learning to Think with Long Videos via Multi-Turn Frame SpotlightingPoster
- Frayed RoPE and Long Inputs: A Geometric PerspectivePoster
- Free Energy MixerPoster
- Free Lunch for Stabilizing Rectified Flow InversionPoster
- Free Point-wise Anomaly Detection via Fold-bifurcationPoster
- FreeAdapt: Unleashing Diffusion Priors for Ultra-High-Definition Image RestorationPoster
- FreeKV: Boosting KV Cache Retrieval for Efficient LLM InferencePoster
- FreeViS: Training-free Video Stylization with Inconsistent ReferencesPoster
- FreqKV: Key-Value Compression in Frequency Domain for Context Window ExtensionPoster
- Frequency-Balanced Retinal Representation Learning with Mutual Information RegularizationPoster
- Frequency-Domain Better than Time-Domain for Causal Structure Recovery in Dynamical Systems on NetworksPoster
- Frequency-aware Dynamic Gaussian SplattingPoster
- Fresh in memory: Training-order recency is linearly encoded in language model activationsPoster
- From Abstract to Contextual: What LLMs Still Cannot Do in MathematicsPoster
- From Assistant to Independent Developer — Are GPTs Ready for Software Development?Poster
- From Assumptions to Actions: Turning LLM Reasoning into Uncertainty-Aware Planning for Embodied AgentsPoster
- From Broad Exploration to Stable Synthesis: Entropy-Guided Optimization for Autoregressive Image GenerationPoster
- From Cheap Geometry to Expensive Physics: Elevating Neural Operators via Latent Shape PretrainingPoster
- From Collapse to Control: Understanding and Extending Context Length in Emerging Hybrid Models via Universal Position InterpolationPoster
- From Concepts to Components: Concept-Agnostic Attention Module Discovery in TransformersPoster
- From Conversation to Query Execution: Benchmarking User and Tool Interactions for EHR Database AgentsPoster
- From Curiosity to Caution: Mitigating Reward Hacking for Best-of-$N$ with PessimismPoster
- From EduVisBench to EduVisAgent: A Benchmark and Multi-Agent Framework for Reasoning-Driven Pedagogical VisualizationPoster
- From Embedding to Control: Representations for Stochastic Multi-Object SystemsPoster
- From Evaluation to Defense: Advancing Safety in Video Large Language ModelsPoster
- From Fields to Random TreesPoster
- From Five Dimensions to Many: Large Language Models as Precise and Interpretable Psychological ProfilersPoster
- From Gradient Volume to Shapley Fairness: Towards Fair Multi-Task LearningPoster
- From Language to Locomotion: Retargeting-free Humanoid Control via Motion Latent GuidancePoster
- From Large to Small: Transferring CUDA Optimization Expertise via Reasoning GraphPoster
- From Markov to Laplace: How Mamba In-Context Learns Markov ChainsOral
- From Medical Records to Diagnostic Dialogues: A Clinical-Grounded Approach and Dataset for Psychiatric ComorbidityPoster
- From Narrow to Panoramic Vision: Attention-Guided Cold-Start Reshapes Multimodal ReasoningPoster
- From Natural Alignment to Conditional Controllability in Multimodal DialoguePoster
- From Neural Networks to Logical Theories: The Correspondence between Fibring Modal Logics and Fibring Neural NetworksPoster
- From Observations to Events: Event-Aware World Models for Reinforcement LearningPoster
- From Parameters to Behaviors: Unsupervised Compression of the Policy SpacePoster
- From Pixels to Semantics: Unified Facial Action Representation Learning for Micro-Expression AnalysisPoster
- From Pixels to Words -- Towards Native Vision-Language Primitives at ScalePoster
- From Prediction to Perfection: Introducing Refinement to Autoregressive Image GenerationPoster
- From Predictors to Samplers via the Training TrajectoryPoster
- From Reproduction to Replication: Evaluating Research Agents with Progressive Code MaskingPoster
- From Samples to Scenarios: A New Paradigm for Probabilistic ForecastingPoster
- From Seeing to Doing: Bridging Reasoning and Decision for Robotic ManipulationPoster
- From Seeing to Experiencing: Scaling Navigation Foundation Models with Reinforcement LearningPoster
- From Sequential to Parallel: Reformulating Dynamic Programming as GPU Kernels for Large-Scale Stochastic Combinatorial OptimizationPoster
- From Single to Multi-Granularity: Toward Long-Term Memory Association and Selection of Conversational AgentsPoster
- From Sorting Algorithms to Scalable Kernels: Bayesian Optimization in High-Dimensional Permutation SpacesPoster
- From Sparse to Dense: Spatio-Temporal Fusion for Multi-View 3D Human Pose Estimation with DenseWarperPoster
- From Spatial to Actions: Grounding Vision-Language-Action Model in Spatial Foundation PriorsPoster
- From Static Benchmarks to Dynamic Protocol: Agent-Centric Text Anomaly Detection for Evaluating LLM ReasoningPoster
- From Text to Talk: Audio-Language Model Needs Non-Autoregressive Joint TrainingPoster
- From Ticks to Flows: Dynamics of Neural Reinforcement Learning in Continuous EnvironmentsPoster
- From Tokens to Nodes: Semantic-Guided Motion Control for Dynamic 3D Gaussian SplattingPoster
- From Tokens to Thoughts: How LLMs and Humans Trade Compression for MeaningPoster
- From Utterance to Vividity: Training Expressive Subtitle Translation LLM via Adaptive Local Preference OptimizationPoster
- From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended GenerationPoster
- From Vicious to Virtuous Cycles: Synergistic Representation Learning for Unsupervised Video Object-Centric LearningPoster
- From What to Why: A Multi-Agent System for Evidence-based Chemical Reaction Condition ReasoningPoster
- From ``Sure" to ``Sorry": Detecting Jailbreak in Large Vision Language Model via JailNeuronsPoster
- From atom to space: A region-based readout function for spatial properties of materialsPoster
- From f(x) and g(x) to f(g(x)): LLMs Learn New Skills in RL by Composing Old OnesPoster
- From movement to cognitive maps: recurrent neural networks reveal how locomotor development shapes hippocampal spatial codingOral
- Front-Loading Reasoning: The Synergy between Pretraining and Post-Training DataPoster
- FrontierCO: Real-World and Large-Scale Evaluation of Machine Learning Solvers for Combinatorial OptimizationPoster
- Frozen Policy Iteration: Computationally Efficient RL under Linear $Q^{\pi}$ Realizability for Deterministic DynamicsPoster
- Frozen Priors, Fluid Forecasts: Prequential Uncertainty for Low-Data Deployment with Pretrained Generative ModelsPoster
- FrugalRAG: Less is More in RL Finetuning for Multi-hop Question AnsweringPoster
- Frustratingly Simple Retrieval Improves Challenging, Reasoning-Intensive BenchmarksPoster
- Full-Graph vs. Mini-Batch Training: Comprehensive Analysis from a Batch Size and Fan-Out Size PerspectivePoster
- FullPart: Generating each 3D Part at Full ResolutionPoster
- Function Induction and Task Generalization: An Interpretability Study with Off-by-One AdditionPoster
- Functional MRI Time Series Generation via Wavelet-Based Image Transform and Spectral Flow Matching for Brain Disorder IdentificationPoster
- Fused-Planes: Why Train a Thousand Tri-Planes When You Can Share?Poster
- Fusing Pixels and Genes: Spatially-Aware Learning in Computational PathologyPoster
- FutureFill: Fast Generation from Convolutional Sequence ModelsPoster
- FutureMind: Equipping Small Language Models with Strategic Thinking-Pattern Priors via Adaptive Knowledge DistillationPoster
- FutureX: An Advanced Live Benchmark for LLM Agents in Future PredictionPoster
- G-Merging: Graph Models Merging for Parameter-Efficient Multi-Task Knowledge ConsolidationPoster
- G-reasoner: Foundation Models for Unified Reasoning over Graph-structured KnowledgePoster
- G4Splat: Geometry-Guided Gaussian Splatting with Generative PriorPoster
- GAGA: Gaussianity-Aware Gaussian Approximation for Efficient 3D Molecular GenerationPoster
- GALAX: Graph-Augmented Language Model for Explainable Reinforcement-Guided Subgraph Reasoning in Precision MedicinePoster
- GAPrune: Gradient-Alignment Pruning for Domain-Aware EmbeddingsPoster
- GAR: Generative Adversarial Reinforcement Learning for Formal Theorem ProvingPoster
- GARLIC: Graph Attention-based Relational Learning of Multivariate Time Series in Intensive CarePoster
- GAS: Enhancing Reward-Cost Balance of Generative Model-assisted Offline Safe RLPoster
- GAS: Improving Discretization of Diffusion ODEs via Generalized Adversarial SolverPoster
- GAVEL: Towards Rule-Based Safety through Activation MonitoringPoster
- GCGNet: Graph-Consistent Generative Network for Time Series Forecasting with Exogenous VariablesPoster
- GDGB: A Benchmark for Generative Dynamic Text-Attributed Graph LearningPoster
- GDPval: Evaluating AI Model Performance on Real-World Economically Valuable TasksPoster
- GDR-learners: Orthogonal Learning of Generative Models for Potential OutcomesPoster
- GEM: A Gym for Generalist LLMsPoster
- GEPA: Reflective Prompt Evolution Can Outperform Reinforcement LearningOral
- GEPO: Group Expectation Policy Optimization for Stable Heterogeneous Reinforcement LearningPoster
- GGBall: Graph Generative Model on Poincaré BallPoster
- GHOST: Hallucination-Inducing Image Generation for Multimodal LLMsPoster
- GIQ: Benchmarking 3D Geometric Reasoning of Vision Foundation Models with Simulated and Real PolyhedraPoster
- GIR-Bench: Versatile Benchmark for Generating Images with ReasoningPoster
- GIT-BO: High-Dimensional Bayesian Optimization with Tabular Foundation ModelsPoster
- GLASS Flows: Efficient Inference for Reward Alignment of Flow and Diffusion ModelsOral
- GNN Explanations that do not Explain and How to find ThemPoster
- GNN-as-Judge: Unleashing the Power of LLMs for Graph Few-shot Semi-supervised Learning with GNN FeedbackPoster
- GOLDILOCS: GENERAL OBJECT-LEVEL DETECTION AND LABELING OF CHANGES IN SCENESPoster
- GOOD: Geometry-guided Out-of-Distribution Modeling for Open-set Test-time Adaptation in Point Cloud Semantic SegmentationPoster
- GOT-Edit: Geometry-Aware Generic Object Tracking via Online Model EditingPoster
- GPG: A Simple and Strong Reinforcement Learning Baseline for Model ReasoningPoster
- GPS: Directed Acyclic Graph guided Proactive Information Seeking in Large Language ModelsPoster
- GPT4Scene: Understand 3D Scenes from Videos with Vision-Language ModelsPoster
- GPTailor: Large Language Model Pruning Through Layer Cutting and StitchingPoster
- GRACE: A Language Model Framework for Explainable Inverse Reinforcement LearningPoster
- GRACE: Generative Representation Learning via Contrastive Policy OptimizationPoster
- GRADIEND: Feature Learning within Neural Networks Exemplified through BiasesPoster
- GRAM-DTI: Adaptive Multimodal Representation Learning for Drug–Target Interaction PredictionPoster
- GRL-SNAM: Geometric Reinforcement Learning with Differential Hamiltonians for Navigation and Mapping in Unknown EnvironmentsPoster
- GRO-RAG: Gradient-aware Re-rank Optimization for Multi-source Retrieval-Augmented GenerationPoster
- GT-Space: Enhancing Heterogeneous Collaborative Perception with Ground Truth Feature SpacePoster
- GTA1: GUI Test-time Scaling AgentPoster
- GTM: A General Time-series Model for Enhanced Representation Learning of Time-Series dataPoster
- GTR-Bench: Evaluating Geo-Temporal Reasoning in Vision-Language ModelsPoster
- GTool: Graph Enhanced Tool Planning with Large Language ModelPoster
- GUI-Shift: Enhancing VLM-Based GUI Agents through Self-supervised Reinforcement LearningPoster
- GUIDE: Gated Uncertainty-Informed Disentangled Experts for Long-tailed RecognitionPoster
- Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous EnvironmentsOral
- GaitSnippet: Gait Recognition Beyond Unordered Sets and Ordered SequencesPoster
- GarmentGPT: Compositional Garment Pattern Generation via Discrete Latent TokenizationPoster
- Gauge Flow Matching: Efficient Constrained Generative Modeling over General Convex Set and BeyondPoster
- Gauge-invariant representation holonomyPoster
- Gaussian certified unlearning in high dimensions: A hypothesis testing approachOral
- GaussianFusion: Unified 3D Gaussian Representation for Multi-Modal Fusion PerceptionPoster
- Gelato: Graph Edit Distance via Autoregressive Neural Combinatorial OptimizationPoster
- Gen-DFL: Decision-Focused Generative Learning for Robust Decision MakingPoster
- GenCP: Towards Generative Modeling Paradigm of Coupled physicsPoster
- GenCape: Structure-Inductive Generative Modeling for Category-Agnostic Pose EstimationPoster
- GenCompositor: Generative Video Compositing with Diffusion TransformerPoster
- GenCtrl -- A Formal Controllability Toolkit for Generative ModelsPoster
- GenDR: Lighten Generative Detail RestorationPoster
- GenSR: Symbolic regression based on equation generative spacePoster
- General Exploratory Bonus for Optimistic Exploration in RLHFPoster
- General search techniques without common knowledge for imperfect-information games, and application to superhuman Fog of War chessPoster
- Generalised Flow Maps for Few-Step Generative Modelling on Riemannian ManifoldsPoster
- Generalizable Coarse-to-Fine Robot Manipulation via Language-Aligned 3D KeypointsPoster
- Generalizable End-to-End Tool-Use RL with Synthetic CodeGymPoster
- Generalizable Heuristic Generation Through LLMs with Meta-OptimizationPoster
- Generalization Below the Edge of Stability: The Role of Data GeometryPoster
- Generalization of Diffusion Models Arises with a Balanced Representation SpacePoster
- Generalization of RLVR Using Causal Reasoning as a TestbedPoster
- Generalized Parallel Scaling with Interdependent GenerationsPoster
- Generalized Spherical Neural Operators: Green’s Function FormulationPoster
- Generalizing Linear Autoencoder Recommenders with Decoupled Expected Quadratic LossPoster
- Generate Any Scene: Scene Graph Driven Data Synthesis for Visual Generation TrainingPoster
- Generating Directed Graphs with Dual Attention and Asymmetric EncodingPoster
- Generating metamers of human scene understandingOral
- Generation then Reconstruction: Accelerating Masked Autoregressive Models via Two-Stage SamplingPoster
- Generative Adversarial Post-Training Mitigates Reward Hacking in Live Human-AI Music InteractionPoster
- Generative Adversarial Reasoner: Enhancing LLM Reasoning with Adversarial Reinforcement LearningPoster
- Generative Bayesian Optimization: Generative Models as Acquisition FunctionsPoster
- Generative Blocks World: Moving Things Around in PicturesPoster
- Generative Diffusion Prior Distillation for Long-Context Knowledge TransferPoster
- Generative Human Geometry DistributionOral
- Generative Modeling from Black-Box Corruptions via Self-Consistent Stochastic InterpolantsPoster
- Generative Universal Verifier as Multimodal Meta-ReasonerOral
- Generative Value Conflicts Reveal LLM PrioritiesPoster
- Generative View StitchingPoster
- Genie Envisioner: A Unified World Foundation Platform for Robotic ManipulationPoster
- Genomic Foundationless Models: Pretraining Does Not Promise PerformancePoster
- GeoBench: Rethinking Multimodal Geometric Problem-Solving via Hierarchical EvaluationPoster
- GeoDiv: Framework for Measuring Geographical Diversity in Text-to-Image ModelsPoster
- GeoFAR: Geography-Informed Frequency-Aware Super-Resolution for Climate DataPoster
- GeoGramBench: Benchmarking the Geometric Program Reasoning in Modern LLMsPoster
- GeoPurify: A Data-Efficient Geometric Distillation Framework for Open-Vocabulary 3D SegmentationPoster
- GeomMotif: A Benchmark for Arbitrary Geometric Preservation in Protein GenerationPoster
- Geometric Autoencoder Priors for Bayesian Inversion: Learn First Observe LaterPoster
- Geometric Constraints for Small Language Models to Understand and Expand Scientific TaxonomiesPoster
- Geometric Graph Neural Diffusion for Stable Molecular DynamicsPoster
- Geometric Image Editing via Effects-Sensitive In-Context Inpainting with Diffusion TransformersPoster
- Geometric-Mean Policy OptimizationPoster
- Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World ModelingPoster
- Geometry of Uncertainty: Learning Metric Spaces for Multimodal State Estimation in RLPoster
- Geometry-aware 4D Video Generation for Robot ManipulationPoster
- Geometry-aware Policy ImitationPoster
- Get RICH or Die Scaling: Profitably Trading Inference Compute for RobustnessPoster
- Getting Your LLMs Ready for Reinforcement Learning with Lightweight SFTPoster
- Ghost in the Cloud: Your Geo-Distributed Large Language Models Training is Easily ManipulatedPoster
- GhostEI-Bench: Do Mobile Agent Resilience to Environmental Injection in Dynamic On-Device Environments?Poster
- Gistify: Codebase-Level Understanding via Runtime ExecutionPoster
- Glance and Focus Reinforcement for Pan-cancer ScreeningPoster
- Glance for Context: Learning When to Leverage LLMs for Node-Aware GNN-LLM FusionPoster
- Global Resolution: Optimal Multi-Draft Speculative Sampling via Convex OptimizationOral
- Global and Local Topology-Aware Graph Generation via Dual Conditioning DiffusionPoster
- Global-Recent Semantic Reasoning on Dynamic Text-Attributed Graphs with Large Language ModelsPoster
- Globally aware optimization with resurgencePoster
- GlobeDiff: State Diffusion Process for Partial Observability in Multi-Agent SystemPoster
- GlowQ: Group-Shared LOw-Rank Approximation for Quantized LLMsPoster
- GmNet: Revisiting Gating Mechanisms From A Frequency ViewPoster
- GneissWeb: Preparing High Quality Data for LLMs at ScalePoster
- Go Beyond Earth: Understanding Human Actions and Scenes in Microgravity EnvironmentsPoster
- Go-Browse: Training Web Agents with Structured ExplorationPoster
- GoR: A Unified and Extensible Generative Framework for Ordinal RegressionPoster
- GoT-R1: Unleashing Reasoning Capability of Autoregressive Visual Generation with Reinforcement LearningPoster
- Goal Reaching with Eikonal-Constrained Hierarchical Quasimetric Reinforcement LearningPoster
- Goal-Aware Identification and Rectification of Misinformation in Multi-Agent SystemsPoster
- GoalRank: Group-Relative Optimization for a Large Ranking ModelPoster
- Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-CorrectionPoster
- Gogo: Group-wise granularity-ordered codec for stable and efficient speech generationPoster
- GoldenStart: Q-Guided Priors and Entropy Control for Distilling Flow PoliciesPoster
ICLR accepted papers in other years
Looking for submission deadlines instead? See the conference deadline calendar.