MMODELYST
Literature

Papers

Showing 701–800 of 1,326 notable papers
PaperTopicAuthorsPublishedHF ▲
Online Skill Learning for Web Agents via State-Grounded Dynamic RetrievalAgentsJiaxi Li +7Jun 3, 202610
SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated ConstructionAgentsYuting Ning +10Jun 1, 202610
Light-WAM: Efficient World Action Models with State-Fusion Action DecodingRoboticsZiang Li +7Jun 6, 202610
Why Muon Outperforms Adam: A Curvature PerspectiveSafety & alignmentShuche Wang +4Jun 3, 202610
Text-to-Image Models Need Less from Text Encoders Than You ThinkImage & video genNurit Spingarn +3Jun 2, 202610
AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware UnderstandingRoboticsQize Yu +12Jun 4, 202610
MAOAM: Unified Object and Material Selection with Vision-Language ModelsImage & video genJaden Park +7Jun 2, 202610
Large Language Models Hack Rewards, and SocietyReinforcement learningWei Liu +4Jun 2, 202610
Ultralytics YOLO26: Unified Real-Time End-to-End Vision ModelsVision & multimodalGlenn Jocher +5Jun 2, 202610
Agent Skills Should Go Beyond Text: The Case for Visual SkillsVision & multimodalBinxiao Xu +3May 31, 202610
RoboStressBench: Benchmarking VLM Robustness to Physical Visual Stress in Embodied ScenesRoboticsLeyi Wu +13May 30, 202610
Speculative Pipeline Decoding: Higher-Accruacy and Zero-Bubble Speculation via Pipeline ParallelismCodeYijiong Yu +4May 29, 202610
PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language UnderstandingVision & multimodalSelim Kuzucu +5May 28, 202610
The Flip Side of RLHF: On-Policy Feedback for Reward Model Self-Supervised ImprovementReinforcement learningXiaobo Wang +5May 29, 202610
VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action PoliciesRoboticsMingjian Gao +11May 28, 202610
REPOT: Recoverable Program-of-Thought via Checkpoint RepairData & benchmarksParsa MazaheriMay 28, 202610
Verifiable Rewards Beyond Math and Code: Lightweight Corpus-Grounded Process Supervision for Factual Question AnsweringCodeShicheng Fan +5May 28, 202610
ChildVox: A Speech, Audio, and Large Audio-Language Model Benchmark in Understanding and Characterizing Sound across ChildhoodSpeech & audioTiantian Feng +12May 28, 202610
Thinking Before Constraining: A Unified Decoding Framework for Large Language ModelsCodeNgoc Trinh Hung Nguyen +5May 28, 202610
Category-Level 3D Correspondence in Camera Space via Morphable Object PriorsRoboticsLeonhard Sommer +3May 27, 202610
Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent MemoryAgentsJingwei Sun +4May 19, 202610
WildCity: A Real-World City-Scale Testbed for Rendering, Simulation, and Spatial IntelligenceRoboticsXiangyu Han +11Jul 7, 20269
CGGS: Consistency-Augmented Geometric Gaussian Splatting for Ego-centric 3D Scene GenerationImage & video genZhenyu Sun +3Jul 4, 20269
Deform360: A Massive Multi-view Visuotactile Dataset for Deformable World ModelsRoboticsHongyu Li +13Jul 6, 20269
PraMem: Practice-derived Experiential Memory for Long-horizon Behavior PredictionCodeZhuoqun Li +13Jul 3, 20269
Teaching LLMs to Recommend and Defer in Underrepresented Epilepsy CareAgentsShreyas Rajesh +10Jun 30, 20269
WARP: Weight-Space Analysis for Recovering Training Data PortfoliosEfficiency & systemsTzu-Heng Huang +3Jul 2, 20269
AnyGroundBench: A Specialized-Domain Benchmark for Video Grounding in Vision-Language ModelsVision & multimodalRintaro Otsubo +8Jul 2, 20269
NoPA: Non-Parametric Online 3D Scene Graph GenerationEfficiency & systemsQi Xun Yeo +3Jul 1, 20269
AtomiMed: Hierarchical Atomic Fact-Checking for Universal Clinical-Aware Medical Report EvaluationSpeech & audioYuan Wang +10Jun 30, 20269
Goku: A Million-Scale Universal Dataset and Benchmark for Instruction-Based Video EditingRoboticsSen Liang +10Jun 30, 20269
AVTok: 1D Unified Tokenization for Holistic Audio-Video GenerationSpeech & audioKien T. Pham +3Jun 29, 20269
Cognitive Episodes in LLM Reasoning Traces Enable Interpretable Human Item Difficulty PredictionSafety & alignmentChenguang Wang +6Jun 26, 20269
Hallucination in World Models is Predictable and PreventableImage & video genNicklas Hansen +1Jun 25, 20269
CoffeeBench: Benchmarking Long-Horizon LLM Agents in Heterogeneous Multi-Agent EconomiesAgentsIssa Sugiura +7Jun 15, 20269
Look Light, Think Heavy: What Multimodal Chain-of-Thought Reasoning Can and Cannot DoVision & multimodalZhuoran Jin +7Jun 21, 20269
Tapered Language ModelsData & benchmarksReza Bayat +2Jun 22, 20269
Rethinking Shrinkage Bias in LLM FP4 Pretraining: Geometric Origin, Systemic Impact, and UFP4 RecipeSafety & alignmentQian Zhao +11Jun 18, 20269
Understanding the Behaviors of Environment-aware Information RetrievalCodeRuifeng Yuan +6Jun 15, 20269
ViT-Up: Faithful Feature Upsampling for Vision TransformersVision & multimodalKrispin Wandel +2Jun 12, 20269
ProCUA-SFT Technical ReportVision & multimodalJaehun Jung +13Jun 15, 20269
RefGC-SR^2: Reference-guided Generated Content Super-Resolution and RefinementImage & video genJeahun Sung +3Jun 13, 20269
Prompt-Level Distillation: A Non-Parametric Alternative to Model Fine-Tuning for Efficient ReasoningSafety & alignmentSanket Badhe +1Jun 2, 20269
The Hidden Power of Scaling Factor in LoRA OptimizationEfficiency & systemsZicheng Zhang +12Jun 11, 20269
Avatar V: Scaling Video-Reference Avatar Video GenerationImage & video genBenjamin Liang +22Jun 11, 20269
Risk Under Pressure: Compute-Aware Evaluation of Adversarial Robustness in Language ModelsSpeech & audioMalikeh Ehghaghi +3Jun 9, 20269
OPRD: On-Policy Representation DistillationCodeShenzhi Yang +9Jun 4, 20269
PlatonicNav: Unveiling Semantic Correspondence in Navigation with Platonic Topological MapsRoboticsJunlin Long +7Jun 1, 20269
Diagnosing Harmful Continuation in Answer-Correct Long-CoT Training TracesSafety & alignmentChen He +4May 28, 20269
Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime MonitoringRoboticsSeongheon Park +6May 29, 20269
From Model Scaling to System Scaling: Scaling the Harness in Agentic AIAgentsShangding GuMay 25, 20269
CoHyDE: Iterative Co-Training of LLM Rewriter & Dense Encoder for Tool RetrievalAgentsVaishali Senthil +2May 28, 20269
CONF-KV: Confidence-Aware KV Cache Eviction with Mixed-Precision Storage for Long-Horizon LLMVision & multimodalYubo Li +1May 24, 20269
Reflective Prompt Tuning through Language Model Function-CallingEfficiency & systemsFarima Fatahi Bayat +3May 20, 20269
SAM: State-Adaptive Memory for Long-Horizon Reasoning AgentAgentsYuyang Hu +7May 23, 20269
Beyond Final Answers: Auditing Trajectory-Level Hallucinations in Multi-Agent Industrial WorkflowsVision & multimodalHarshada Badave +8May 22, 20269
CoSPlay: Cooperative Self-Play at Test-Time with Self-Generated Code and Unit TestSpeech & audioZhangyi Hu +8May 22, 20269
OPSD-V: On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video GeneratorsImage & video genHongyu Liu +8Jul 9, 20268
TREK: Distill to Explore, Reinforce to RefineAgentsYuanda Xu +12Jul 6, 20268
Attending to Multimodal Generation One Token at a TimeVision & multimodalVarun Gupta +2Jul 4, 20268
Mastermind: Strategy-grounded Learning for Repository-Scale Vulnerability ReproductionAgentsMingzhe Du +6Jul 2, 20268
Are Performance-Optimization Benchmarks Reliably Measuring Coding Agents?AgentsZhi Chen +4Jul 1, 20268
Autonomous Scientific Discovery via Iterative Meta-ReflectionVision & multimodalBingchen Zhao +2Jul 1, 20268
GRPO, Dr. GRPO, and DAPO Are Three Operations on One Number: The Group-Standard-Deviation IdentityReinforcement learningYong Yi Bay +1Jun 30, 20268
SciIR: A Large-scale Training Dataset and Benchmark for Scientific Image Reasoning GenerationImage & video genZhiyuan Ma +8Jun 29, 20268
When More Sampling Hurts: The Modal Ceiling and Correlation Ceiling of Test-Time ScalingData & benchmarksYong Yi Bay +1Jun 27, 20268
Building to the Test: Coding Agents Deliver What You Check, Not What You RequestedAgentsYanuo Ma +2Jun 26, 20268
AI translation of literary texts is "fine", but readers still prefer human translationsAgentsYves Ferstler +5Jun 24, 20268
One Forward Beats Two: InnerZoom for Accurate and Efficient GUI GroundingVision & multimodalChen Liu +7Jun 29, 20268
Walking in the Implicit: Interactive World Exploration via Neural Scene RepresentationImage & video genZhiqi Li +8Jun 29, 20268
MirrorPPR: Exemplar-Based Portrait Photo RetouchingImage & video genZhihong Liu +6Jun 28, 20268
PolicyGuard: A Dialogue-Grounded Sub-Agent Verifier for Policy Adherence in LLM AgentsAgentsSeongjae Kang +2Jun 28, 20268
Ko-WideSearch: A Korean Breadth-Search Benchmark for Exhaustive Set Enumeration by Web AgentsAgentsMinbyul JeongJun 25, 20268
AgentOdyssey: Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning AgentsAgentsZheyuan Zhang +6May 29, 20268
RoPE-Aware Bit Allocation for KV-Cache QuantizationCodeFengfeng Liang +2Jun 23, 20268
Safe Few-Step Generation via Velocity EditingRoboticsYujin Choi +1Jun 22, 20268
Connect the Dots: Training LLMs for Long-Lifecycle Agents with Cross-Domain Generalization Via Reinforcement LearningAgentsYanxi Chen +6Jun 18, 20268
Freeing the Law with LOCUS: A Local Ordinance Corpus for the United StatesVision & multimodalDenis Peskoff +3Jun 17, 20268
LooseControlVideo: Directorial Video Control using Spatial BlockingImage & video genShariq Farooq Bhat +2Jun 17, 20268
CEO-Bench: Can Agents Play the Long Game?Speech & audioHaozhe Chen +2Jun 16, 20268
SciOrch: Learning to Orchestrate Expert LLMs for Solving Frontier Multimodal Scientific Reasoning TasksVision & multimodalJingru Guo +8Jun 14, 20268
ActWorld: From Explorable to Interactive World Model via Action-Aware MemoryImage & video genZhexiao Xiong +13Jun 16, 20268
ChLogic: Evaluating Robustness of Logical Reasoning in Chinese ExpressionsData & benchmarksPeixian Zhou +5Jun 16, 20268
A Gradient Perspective on RLVR Stability and Winner Advantage Policy OptimizationCodePrasanth YSS +8Jun 15, 20268
Unstable Features, Reproducible Subspaces: Understanding Seed Dependence in Sparse AutoencodersEfficiency & systemsGleb Gerasimov +5Jun 10, 20268
VISTA: View-Consistent Self-Verified Training for GUI GroundingReinforcement learningXinyu Qiu +5Jun 12, 20268
ClinHallu: A Benchmark for Diagnosing Stage-Wise Hallucinations in Medical MLLM ReasoningVision & multimodalSicheng Yang +7Jun 12, 20268
When is Your LLM Steerable?CodeChenrui Fan +4Jun 10, 20268
Breaking the Bubble: Asynchronous Pipeline Parallel Training with Bounded Weight InconsistencyEfficiency & systemsItay Elam +3Jun 5, 20268
BrainSurgery: Reproducible and Reliable Declarative Weight Manipulations for Model Editing and UpcyclingRoboticsGianluca Barmina +4Jun 8, 20268
Reasoning Arena: Trace Tournaments When Verifiable Rewards Fall ShortCodeHan Zhou +4Jun 8, 20268
Answer Presence Drives RAG Rewriting GainsCodeYuejie Li +10Jun 4, 20268
Liberating LLM Capabilities in Full-Duplex Speech ModelsSpeech & audioLuoyuan Zhang +6May 4, 20268
LLMs Can Leak Training Data But Do They Want To? A Propensity-Aware Evaluation of Memorization in LLMsData & benchmarksGianluca Barmina +2Jun 4, 20268
World-Language-Action Model for Unified World Modeling, Language Reasoning, and Action SynthesisRoboticsYi Yang +11Jun 4, 20268
WebRISE: Requirement-Induced State Evaluation for MLLM-Generated Web ArtifactsVision & multimodalYuxin Meng +11Jun 2, 20268
Economy of Minds: Emerging Multi-Agent Intelligence with Economic InteractionsAgentsZhenting Qi +15Jun 1, 20268
Value-Aware Stochastic KV Cache Eviction for Reasoning ModelsEfficiency & systemsTing-Yun Chang +5Jun 2, 20268
OmniOPD: Logit-Free On-Policy Distillation via Speculative VerificationReinforcement learningYuhang Zhou +7May 31, 20268
MERIT: Learning Disentangled Music Representations for Audio SimilaritySpeech & audioAbhinaba Roy +2May 26, 20268
← PrevPage 8 of 14Next →