MMODELYST
Literature

Papers

Showing 301–400 of 1,326 notable papers
PaperTopicAuthorsPublishedHF ▲
SkillGrad: Optimizing Agent Skills Like Gradient DescentAgentsHanyu Wang +4May 26, 202627
MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and EvaluationAgentsHuawei Lin +4May 26, 202627
LLaVA-OneVision-2: Towards Next-Generation Perceptual IntelligenceRoboticsXiang An +29May 25, 202627
EVA-Client: A Unified Data Collection, Inference, and Deployment Framework for Embodied Policies on Real RobotsRoboticsHeqing Yang +10Jul 2, 202626
Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMsReinforcement learningGabrielle Kaili-May Liu +4Jun 30, 202626
From Trainee to Trainer: LLM-Designed Training Environment for RL with Multi-Agent ReasoningAgentsChao Chen +4Jun 16, 202626
Smaller Models are Natural Explorers for Policy-Level Diversity in GRPOReinforcement learningYiming Ren +10Jun 2, 202626
World Pilot: Steering Vision-Language-Action Models with World-Action PriorsRoboticsZefu Lin +6Jun 10, 202626
Direct 3D-Aware Object Insertion via Decomposed Visual ProxiesRoboticsJingbo Gong +8Jun 4, 202626
RobotValues: Evaluating Household Robots When Human Values ConflictRoboticsJongwook Han +2Jun 2, 202626
M^3Eval: Multi-Modal Memory Evaluation through Cognitively-Grounded Video TasksVision & multimodalJie Huang +6Jun 3, 202626
AutoMedBench: Towards Medical AutoResearch with Agentic AI ModelsVision & multimodalJunqi Liu +14Jun 1, 202626
VideoMLA: Low-Rank Latent KV Cache for Minute-Scale Autoregressive Video DiffusionImage & video genHidir Yesiltepe +6May 28, 202626
VLM3: Vision Language Models Are Native 3D LearnersVision & multimodalZhipeng Cai +5May 28, 202626
Not All Disagreement Is Learnable: Token Teachability in On-Policy DistillationReinforcement learningYuanyi Wang +8May 26, 202626
UniSteer: Text-Guided Flow Matching in Activation Space for Versatile LLM SteeringEfficiency & systemsYingdong Shi +6May 28, 202626
AI Research Agents Narrow Scientific ExplorationAgentsYixuan Tang +1May 27, 202626
Parallelized Autoregressive Decoding for Omni-Modal Dense Video CaptioningSpeech & audioWenzheng Zeng +4Jul 3, 202625
InternVLA-A1.5: Unifying Understanding, Latent Foresight, and Action for Compositional GeneralizationRoboticsHaoxiang Ma +28Jul 6, 202625
Video-MME-Logical: A Controlled Diagnostic Benchmark for Video Temporal-Logical ReasoningVision & multimodalHohin Kwan +7Jun 26, 202625
Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World ModelsImage & video genKaiwen Zheng +9Jun 24, 202625
End-to-End Context Compression at ScaleAgentsAng Li +14Jun 8, 202625
Reinforcement Learning Elicits Contextual Learning of Unseen Language TranslationCodeHanxu Hu +4Jun 4, 202625
ThoughtFold: Folding Reasoning Chains via Introspective Preference LearningReinforcement learningZiyan Liu +9Jun 2, 202625
Benchmarks are Not Enough: RAMP for Runtime Assessing of Agentic Models in Production SystemsAgentsYipeng Ouyang +5May 26, 202625
Which Pretraining Paradigm Better Serves Spatial Intelligence? An Empirical Comparison of Vision-Language and Video Generation ModelsImage & video genHaozhan Shen +3May 27, 202625
SAAS: Self-Aware Reinforcement Learning for Over-Search Mitigation in Agentic SearchAgentsYunbo Tang +6May 28, 202625
Colored Noise Diffusion SamplingImage & video genHadar Davidson +2May 28, 202625
Triplet-Block Diffusion RWKVImage & video genKe Lin +4May 25, 202625
Managing Procedural Memory in LLM Agents: Control, Adaptation, and EvaluationAgentsJulia Belikova +6Jun 22, 202624
One-Step Gradient Delay is Not a Barrier for Large-Scale Asynchronous Pipeline Parallel LLM PretrainingEfficiency & systemsPhilip Zmushko +4Jun 29, 202624
BioMatrix: Towards a Comprehensive Biological Foundation Model Spanning the Modality Matrix of Sequences, Structures, and LanguageVision & multimodalQizhi Pei +11Jun 20, 202624
Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer DecodingCodeXuanming Zhang +10Jun 20, 202624
EfficientRollout: System-Aware Self-Speculative Decoding for RL RolloutsAgentsMinseo Kim +9Jun 17, 202624
N-GRPO: Embedding-Level Neighbor Mixing for Enhanced Policy OptimizationReinforcement learningXukun Zhu +3Jun 9, 202624
ARM: An AutoRegressive Large Multimodal Model with Unified Discrete RepresentationsImage & video genJunke Wang +18Jun 9, 202624
Skill-3D: Evolving Scene-Aware Skills for Agentic 3D Spatial ReasoningVision & multimodalHaoyuan Li +4Jun 5, 202624
LoomVideo: Unifying Multimodal Inputs into Video Generation and EditingImage & video genJianzong Wu +13Jun 4, 202624
Self-Distilled Policy GradientCodeYifeng Liu +3Jun 2, 202624
When Should Models Change Their Minds? Contextual Belief Management in Large Language ModelsCodeHaoming Xu +8May 28, 202624
OSP-Next: Efficient High-Quality Video Generation with Sparse Sequence Parallelism, HiF8 Quantization, and Reinforcement LearningImage & video genYunyang Ge +6May 27, 202624
QUACK: Questioning, Understanding, and Auditing Communicated Knowledge in Multimodal Social Deduction AgentsVision & multimodalYe Yuan +14May 26, 202624
AutoTrainess: Teaching Language Models to Improve Language Models AutonomouslyAgentsZhaojian Yu +5Jun 30, 202623
FLAT: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene GenerationImage & video genOrest Kupyn +5Jun 23, 202623
LingxiDiagBench: A Multi-Agent Framework for Benchmarking LLMs in Chinese Psychiatric Consultation and DiagnosisAgentsShihao Xu +10Jun 11, 202623
RedAct: Redacting Agent Capability Traces for Procedural Skill ProtectionVision & multimodalShuwen Xu +2Jun 10, 202623
Skip a Layer or Loop It? Learning Program-of-Layers in LLMsEfficiency & systemsZiyue Li +2Jun 4, 202623
On Subquadratic Architectures: From Applications to PrinciplesCodeAnamaria-Roberta Hartl +8Jun 10, 202623
InternVideo3: Agentify Foundation Models with Multimodal Contextual ReasoningVision & multimodalZiang Yan +12Jun 10, 202623
When Tools Fail: Benchmarking Dynamic Replanning and Anomaly Recovery in LLM AgentsAgentsDongsheng Zhu +7Jun 4, 202623
Benchmarking Visual State Tracking in Multimodal Video UnderstandingVision & multimodalSihyun Yu +10Jun 2, 202623
WALL-WM: Carving World Action Modeling at the Event JointsRoboticsShalfun Li +30Jun 1, 202623
Exploring Autonomous Agentic Data Engineering for Model SpecializationAgentsYujie Luo +12May 28, 202623
LoMo: Local Modality Substitution for Deeper Vision-Language FusionVision & multimodalFeng Han +4May 28, 202623
GUI-CIDER: Mid-training GUI Agents via Causal Internalization and Density-aware Exemplar ReselectionVision & multimodalZheng Wu +7May 27, 202623
Long Live The Balance: Information Bottleneck Driven Tree-based Policy OptimizationCodeHao Jiang +9May 27, 202623
Gemini Embedding 2: A Native Multimodal Embedding Model from GeminiSpeech & audioMadhuri Shanbhogue +39May 26, 202623
Multiplayer Interactive World Models with Representation AutoencodersImage & video genAnthony Hu +26Jul 6, 202622
Domain Arithmetic: One-Shot VLA Adaptation under Environmental ShiftsRoboticsTaewook Kang +3Jul 1, 202622
ASPIRE: Agentic /Skills Discovery for RoboticsRoboticsRunyu Lu +13Jun 30, 202622
VideoSearch-R1: Iterative Video Retrieval and Reasoning via Soft Query RefinementVision & multimodalSeohyun Lee +4Jul 1, 202622
OSWorld2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World TasksVision & multimodalMengqi Yuan +35Jun 28, 202622
One Model, Many Latencies: Universal Speech Enhancement for Diverse Real-Time ApplicationsSpeech & audioSzu-Wei Fu +6Jun 24, 202622
WorldCraft: From Camera Navigation to Object Manipulation in Interactive Video World ModelsRoboticsBohai Gu +11May 24, 202622
NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle SimulationRoboticsNVIDIA +33Jun 2, 202622
Bootstrap Your Generator: Unpaired Visual Editing with Flow MatchingImage & video genYoad Tewel +3Jun 2, 202622
MIRA: Mid-training Rubric Anchoring for Source-Aware Data SelectionCodeHaowen Wang +10May 28, 202622
Light-Omni: Reflex over Reasoning in Agentic Video Understanding with Long-Term MemoryVision & multimodalChang Nie +4Jul 6, 202621
Do All Visual Tokens Matter Equally? Object-Evidence Preserving Token Merging for Vision-Language RetrievalVision & multimodalSuhyeong Park +3Jul 6, 202621
TACO: Tool-Augmented Credit Optimization for Agentic Tool UseVision & multimodalMingkuan Feng +7Jun 29, 202621
Monte Carlo Energy Aggregation for Mobile 3D Gaussian SplattingVision & multimodalXiaobiao Du +5Jun 29, 202621
Critique of Agent ModelImage & video genEric Xing +2Jun 22, 202621
MCompassRAG: Topic Metadata as a Semantic Compass for Paragraph-Level RetrievalCodeAmirhossein Abaskohi +5Jun 16, 202621
FlowBender: Feedback-Aware Training for Self-Correcting Conditional FlowsImage & video genDaniel Gilo +3Jun 18, 202621
ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?RoboticsYuyang Zhang +9Jun 17, 202621
Show the Signal, Hide the Noise: Spectral Forcing for Pixel-Space DiffusionImage & video genWeichen Fan +3Jun 16, 202621
Demystifying Hidden-State Recurrence: Switchable Latent Reasoning with On-Policy Reinforcement LearningReinforcement learningJiayu Yang +8Jun 11, 202621
Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection SamplingAgentsYucheng Li +16Jun 10, 202621
A Geometric Account of Activation Steering through Angle-Norm DecompositionSafety & alignmentGeorgii Aparin +1Jun 4, 202621
Watch, Remember, Reason: Human-View Video Understanding with MLLMsSpeech & audioJiahao Meng +14Jun 5, 202621
Rethinking Continual Experience Internalization for Self-Evolving LLM AgentsAgentsJingwen Chen +9Jun 3, 202621
Decentralized Instruction Tuning: Conflict-Aware Splitting and Weight MergingVision & multimodalMinsik Choi +1Jun 1, 202621
Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM AgentsAgentsMinhua Lin +16May 28, 202621
LongDS-Bench: On the Failure of Long-Horizon Agentic Data AnalysisAgentsKewei Xu +6May 28, 202621
Xetrieval: Mechanistically Explaining Dense RetrievalCodeZhixin Cai +9May 28, 202621
KVpop -- Key-Value Cache Compression with Predictive Online PruningCodeLukas Hauzenberger +7Jul 6, 202620
ACID: Action Consistency via Inverse Dynamics for Planning with World ModelsRoboticsGawon Seo +2Jul 2, 202620
Are We Measuring Strategy or Phrasing? The Gap Between Surface- and Approach-Level Diversity in LLM Math ReasoningReinforcement learningSangmook Lee +5Jun 29, 202620
MultiHashFormer: Hash-based Generative Language ModelsData & benchmarksHuiyin Xue +2Jun 26, 202620
Semantic Browsing: Controllable Diversity for Image GenerationImage & video genSara Dorfman +4Jun 22, 202620
SkillHarness: Harnessing Safe Skills for Computer-Use AgentsAgentsYurun Chen +3Jun 2, 202620
JanusMesh: Fast and Zero-Shot 3D Visual Illusion Generation via Cross-Space DenoisingImage & video genSiang-Ling Zhang +3Jun 18, 202620
The Reward Was in Your Data All Along: Correcting Flow Matching with Discriminator-Guided RLVision & multimodalNicolas Beltran-Velez +6Jun 17, 202620
LLM Agents Can See Code RepositoriesVision & multimodalDongjian Ma +5Jun 12, 202620
VideoMDM: Towards 3D Human Motion Generation From 2D SupervisionImage & video genAmir Mann +3Jun 11, 202620
Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional FieldsAgentsLiya Zhu +39Jun 9, 202620
UnpredictaBench: A Benchmark for Evaluating Distributional Randomness in LLMsData & benchmarksAmirhossein Abaskohi +6Jun 4, 202620
ZipSplat: Fewer Gaussians, Better SplatsVision & multimodalAlexander Veicht +3Jun 3, 202620
PEEK: Picking Essential frames via Efficient Knowledge distillationVision & multimodalKillian Steunou +4May 29, 202620
Recovering Policy-Induced Errors: Benchmarking and Trajectory Synthesis for Robust GUI AgentsAgentsTianpeng Bu +9May 28, 202620
← PrevPage 4 of 14Next →