MMODELYST
Literature

Papers

Showing 101–200 of 1,326 notable papers
PaperTopicAuthorsPublishedHF ▲
Gemma 4 Technical ReportSpeech & audioGemma Team +39Jul 2, 202660
Multi-LCB: Extending LiveCodeBench to Multiple Programming LanguagesCodeMaria Ivanova +7Jun 18, 202660
Beyond Scalar Rewards by Internalizing Reasoning into Score DistributionsImage & video genXin Jin +10Jun 8, 202660
Why Far Looks Up: Probing Spatial Representation in Vision-Language ModelsVision & multimodalCheolhong Min +7May 28, 202660
KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning TasksCodeLorenz K. Muller +5Jun 2, 202659
Representation Forcing for Bottleneck-Free Unified Multimodal ModelsImage & video genYuqing Wang +12May 29, 202659
Self-Improving Language Models with Bidirectional Evolutionary SearchRoboticsGuowei Xu +6May 27, 202659
Video-Oasis: Rethinking Evaluation of Video UnderstandingVision & multimodalGeuntaek Lim +7Jul 2, 202658
Formalizing Latent Thoughts: Four Axioms of Thought Representation in LLMsEfficiency & systemsFahd Seddik +1May 7, 202658
GameCraft-Bench: Can Agents Build Playable Games End-to-End in a Real Game Engine?Vision & multimodalTongxu Luo +24Jun 16, 202658
minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World ModelsImage & video genMin Zhao +11May 28, 202658
SwanVoice: Expressive Long-Form Zero-Shot Speech Synthesis for Both Monologue and DialogueSpeech & audioRuiqi Li +5May 29, 202657
Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous RobotsRoboticsLing Xu +8Jul 2, 202656
From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AIAgentsYongheng Zhang +19Jun 12, 202656
Measuring Epistemic Resilience of LLMs Under Misleading Medical ContextAgentsHongjian Zhou +21Jun 10, 202656
K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean ContextsAgentsNahyun Lee +14Jun 1, 202655
OPID: On-Policy Skill Distillation for Agentic Reinforcement LearningAgentsShuo Yang +10Jun 25, 202654
World Action Models: A SurveyRoboticsQiuhong Shen +7Jun 18, 202654
LabVLA: Grounding Vision-Language-Action Models in Scientific LaboratoriesRoboticsBaochang Ren +17Jun 11, 202654
Mellum2 Technical ReportAgentsMarko Kojic +8May 29, 202654
YoCausal: How Far is Video Generation from World Model? A Causality PerspectiveImage & video genYou-Zhe Xie +5May 28, 202654
ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference OutcomesData & benchmarksQihao Zhao +10Jul 5, 202653
MolmoMotion: Forecasting Point Trajectories in 3D with Language InstructionRoboticsJianing Zhang +12Jun 17, 202653
Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent TrajectoriesAgentsJiaming Wang +10Jun 1, 202653
Scenes as Objects, Not Primitives: Instance-Structured 3D Tokenization from Unposed ViewsRoboticsMijin Yoo +5Jun 28, 202652
Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience LearningAgentsShiding Zhu +8Jun 23, 202652
ACE-Ego-0: Unifying Egocentric Human and Robotic Data for VLA PretrainingRoboticsHao Li +10Jun 15, 202652
Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory RolloutsAgentsWenbo Pan +7Jun 4, 202652
From Activation to Causality: Discovery of Causal Visual Representations in the Human BrainVision & multimodalYuval Golbari +7May 22, 202652
Dual Latent Memory in Vision-Language-Action Models for Robotic ManipulationRoboticsHongyu Qu +8Jul 8, 202651
Scaling Mixture-of-Experts Video Pretraining for Embodied IntelligenceRoboticsShuailei Ma +26Jul 8, 202651
TRL-Bench: Standardizing Cross-Paradigm Representation-Level Evaluation of Tabular EncodersCodeWei Pang +12Jun 8, 202651
SoCRATES: Towards Reliable Automated Evaluation of Proactive LLM Mediation across Domains and Socio-cognitive VariationsAgentsTaewon Yun +5Jun 4, 202651
Harness-1: Reinforcement Learning for Search Agents with State-Externalizing HarnessesAgentsPengcheng Jiang +7Jun 1, 202651
DataComp-VLM: Improved Open Datasets for Vision-Language ModelsVision & multimodalMatteo Farina +35Jun 26, 202650
EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive EnvironmentsAgentsZhilin Wang +15Jul 2, 202650
PhysisForcing: Physics Reinforced World Simulator for Robotic ManipulationRoboticsPeiwen Zhang +13Jun 26, 202650
Playful Agentic Robot LearningRoboticsJunyi Zhang +19Jun 17, 202650
SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep ResearchAgentsPu Ning +9Jun 8, 202650
Qwen-Image-Agent: Bridging the Context Gap in Real-World Image GenerationImage & video genZekai Zhang +20Jun 25, 202649
ResearchMath-14K: Scaling Research-Level Mathematics via AgentsAgentsGuijin Son +5May 27, 202649
Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action RecognitionEfficiency & systemsGeo Ahn +5Jul 2, 202648
Morphing into Hybrid Attention ModelsEfficiency & systemsDisen Lan +7Jun 29, 202648
ReFreeKV: Towards Threshold-Free KV Cache CompressionCodeXuanfan Ni +8Jun 26, 202648
Qwen-Image-2.0-RL Technical ReportImage & video genYixian Xu +27Jun 25, 202648
Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov GamesVision & multimodalShengyuan Ding +6Jun 17, 202648
CoVEBench: Can Video Editing Models Handle Complex Instructions?Vision & multimodalJiangtao Wu +9Jun 7, 202648
TUA-Bench: A Benchmark for General-Purpose Terminal-Use AgentsAgentsShoufa Chen +9Jun 26, 202647
The Verification Horizon: No Silver Bullet for Coding Agent RewardsAgentsBinghai Wang +11Jun 24, 202647
KaLM-Reranker-V1: Fast but Not Late Interaction for Compressed Document RerankingCodeXinping Zhao +9Jun 22, 202647
ArcANE: Do Role-Playing Language Agents Stay in Character at the Right Time?AgentsWoojung Song +5Jun 4, 202647
ShutterMuse: Capture-Time Photography Guidance with MLLMsVision & multimodalJiayu Li +7Jun 24, 202646
OpenThoughts-Agent: Data Recipes for Agentic ModelsAgentsNegin Raoof +39Jun 23, 202646
HarnessX: A Composable, Adaptive, and Evolvable Agent Harness FoundryAgentsTingyang Chen +13Jun 12, 202646
GENEB: Why Genomic Models Are Hard to CompareSafety & alignmentDaria Ledneva +2Jun 3, 202646
DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy PrefixesReinforcement learningCaijun Xu +3May 27, 202646
Orchestra-o1: Omnimodal Agent OrchestrationSpeech & audioFan Zhang +10Jun 10, 202645
Vision as Unified Multimodal GenerationImage & video genXiaoyang Han +16Jul 7, 202644
MANCE: Manifold Aware Concept ErasureVision & multimodalMatan Avitan +2Jul 4, 202644
Beyond IID: How General Are Tabular Foundation Models, Really?Data & benchmarksLennart Purucker +9Jun 29, 202644
MMAE: A Massive Multitask Audio Editing BenchmarkSpeech & audioZiyang Ma +37Jun 5, 202644
TIDE: Proactive Multi-Problem Discovery via Template-Guided IterationAgentsSoyeong Jeong +3Jun 3, 202644
GGT-100K: Generative Ground Truth for Generalizable Real-World Image RestorationVision & multimodalXiangtao Kong +4May 29, 202644
SkillHone: A Harness for Continual Agent Skill Evolution Through Persistent Decision HistoryAgentsZhiwei Li +1Jun 23, 202643
Improved Large Language Diffusion ModelsImage & video genShen Nie +9Jun 24, 202643
MobileForge: Annotation-Free Adaptation for Mobile GUI Agents with Hierarchical Feedback-Guided Policy OptimizationVision & multimodalGuangyi Liu +10Jun 18, 202643
Vision Pretraining for Dense Spatial PerceptionRoboticsZelin Fu +8Jul 6, 202642
Trimming the Long-Tail of Visual World Modeling EvaluationImage & video genBingxuan Li +8Jun 23, 202642
MemGUI-Agent: An End-to-End Long-Horizon Mobile GUI Agent with Proactive Context ManagementVision & multimodalGuangyi Liu +9Jun 18, 202642
Beyond Uniform Token-Level Trust Region in LLM Reinforcement LearningReinforcement learningRenjie Mao +9Jun 9, 202642
Trust Region On-Policy DistillationAgentsXingrun Xing +4May 31, 202642
How LoRA Remembers? A Parametric Memory Law for LLM FinetuningCodeZiwen Xu +6May 28, 202642
PerceptionRubrics: Calibrating Multimodal Evaluation to Human PerceptionVision & multimodalYana Wei +16Jun 26, 202641
Evolution Fine-Tuning: Learning to Discover Across 371 Optimization TasksAgentsYoung-Jun Lee +7Jun 27, 202641
Beyond Static Leaderboards: Predictive Validity for the Evaluation of LLM AgentsVision & multimodalDhaval C. Patel +39Jun 18, 202641
SCAIL-2: Unifying Controlled Character Animation with End-to-end In-Context ConditioningVision & multimodalWenhao Yan +3Jun 9, 202641
SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World TasksVision & multimodalHongcheng Gao +20Jun 8, 202641
Function2Scene: 3D Indoor Scene Layout from Functional SpecificationsVision & multimodalRuiqi Wang +6May 29, 202641
LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric RewardsAgentsNianyi Lin +3May 29, 202641
GEM: Generative Supervision Helps Embodied IntelligenceRoboticsRuowen Zhao +11May 27, 202641
Geometry-Aware Representation Denoising for Robust Multi-view 3D ReconstructionImage & video genJin Hyeon Kim +10May 25, 202641
Personalize-then-Store: Benchmarking and Learning Personalized Memory for Long-horizon AgentsAgentsYeonjun In +4May 25, 202641
ThriftAttention: Selective Mixed Precision for Long-Context FP4 AttentionCodeJoe SharrattMay 21, 202641
Multi-Block Diffusion Language ModelsImage & video genYijie Jin +10Jun 30, 202640
Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching ModelsImage & video genBowen Ping +5Jun 9, 202640
AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User ConstraintsAgentsJiayu Liu +10Jun 4, 202640
OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion TransformersImage & video genDonghyun Lee +7Jul 2, 202639
Translation as a Bridging Action: Transferring Manipulation Skills from Humans to RobotsRoboticsSijin Chen +8Jun 26, 202639
S-Agent: Spatial Tool-Use Elicits Reasoning for Spatial IntelligenceVision & multimodalYalun Dai +12Jun 18, 202639
LectūraAgents: A Multi-Agent Framework for Adaptive Personalized AI-Assisted Learning and Embodied TeachingRoboticsJaward Sesay +5Jun 15, 202639
MemTrace: Tracing and Attributing Errors in Large Language Model Memory SystemsCodeXinle Deng +17May 27, 202639
The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World IntelligenceAgentsMiniMax +206May 26, 202639
$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware RoutingImage & video genAoxi Liu +7May 25, 202639
ViQ: Text-Aligned Visual Quantized Representations at Any ResolutionVision & multimodalXumin Yu +7Jun 25, 202638
Beyond NL2Code: A Structured Survey of Multimodal Code IntelligenceVision & multimodalXuanle Zhao +18Jun 16, 202638
Unlimited OCR WorksSpeech & audioYouyang Yin +16Jun 22, 202638
Kairos: A Native World Model Stack for Physical AIRoboticsKairos Team +23Jun 16, 202638
MemDreamer: Decoupling Perception and Reasoning for Long Video Understanding via Hierarchical Graph Memory and Agentic Retrieval MechanismVision & multimodalCong Chen +9Jun 5, 202638
Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion TrackingData & benchmarksZekun Qi +12Jun 2, 202638
Task-Focused Memorization for Multimodal AgentsRoboticsTao Zou +4May 29, 202638
← PrevPage 2 of 14Next →