ずんだもんのHugging Faceニュース

【本日の論文】 1. Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning https://huggingface.co/papers/2605.06130 2. Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction https://huggingface.co/papers/2605.05242 3. Continuous Latent Diffusion Language Model https://huggingface.co/papers/2605.06548 4. MiA-Signature: Approximating G...

【本日の論文】 1. Stream-R1: Reliability-Perplexity Aware Reward Distillation for Streaming Video Generation https://huggingface.co/papers/2605.03849 2. Stream-T1: Test-Time Scaling for Streaming Video Generation https://huggingface.co/papers/2605.04461 3. RLDX-1 Technical Report https://huggingface.co/papers/2605.03269 4. OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents https:/...

【本日の論文】 1. ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration https://huggingface.co/papers/2605.03042 2. OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories https://huggingface.co/papers/2605.04036 3. Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL https://huggingface.co/papers/2604.281...

【本日の論文】 1. MolmoAct2: Action Reasoning Models for Real-world Deployment https://huggingface.co/papers/2605.02881 2. From Context to Skills: Can Language Models Learn from Context Skillfully? https://huggingface.co/papers/2604.27660 3. Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs https://huggingface.co/papers/2605.00814 4. Repetition over Diversity: High-Signa...

【本日の論文】 1. UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors https://huggingface.co/papers/2605.00658 2. Web2BigTable: A Bi-Level Multi-Agent LLM System for Internet-Scale Information Search and Extraction https://huggingface.co/papers/2604.27221 3. Map2World: Segment Map Conditioned Text to 3D World Generation https://huggingface.co/papers/2605.007...

【本日の論文】 1. Heterogeneous Scientific Foundation Model Collaboration https://huggingface.co/papers/2604.27351 2. Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling https://huggingface.co/papers/2604.28185 3. Co-Evolving Policy Distillation https://huggingface.co/papers/2604.27083 4. Intern-Atlas: A Methodological Evolution Graph as Research Infrastruc...

【本日の論文】 1. Heterogeneous Scientific Foundation Model Collaboration https://huggingface.co/papers/2604.27351 2. Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling https://huggingface.co/papers/2604.28185 3. Co-Evolving Policy Distillation https://huggingface.co/papers/2604.27083 4. ExoActor: Exocentric Video Generation as Generalizable Interactive Hu...

【本日の論文】 1. Heterogeneous Scientific Foundation Model Collaboration https://huggingface.co/papers/2604.27351 2. Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling https://huggingface.co/papers/2604.28185 3. Co-Evolving Policy Distillation https://huggingface.co/papers/2604.27083 4. ExoActor: Exocentric Video Generation as Generalizable Interactive Hu...

【本日の論文】 1. GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents https://huggingface.co/papers/2604.26752 2. Large Language Models Explore by Latent Distilling https://huggingface.co/papers/2604.24927 3. RADIO-ViPE: Online Tightly Coupled Multi-Modal Fusion for Open-Vocabulary Semantic SLAM in Dynamic Environments https://huggingface.co/papers/2604.26067 4. ClawGym: A Scalabl...

【本日の論文】 1. Recursive Multi-Agent Systems https://huggingface.co/papers/2604.25917 2. Programming with Data: Test-Driven Data Engineering for Self-Improving LLMs from Raw Corpora https://huggingface.co/papers/2604.24819 3. DV-World: Benchmarking Data Visualization Agents in Real-World Scenarios https://huggingface.co/papers/2604.25914 4. AutoResearchBench: Benchmarking AI Agents on Complex S...

【本日の論文】 1. From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company https://huggingface.co/papers/2604.22446 2. World-R1: Reinforcing 3D Constraints for Text-to-Video Generation https://huggingface.co/papers/2604.24764 3. ReVSI: Rebuilding Visual Spatial Intelligence Evaluation for Accurate Assessment of VLM 3D Reasoning https://huggingface.co/papers/2604.24300 4. Tuna...

【本日の論文】 1. Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond https://huggingface.co/papers/2604.22748 2. Video Analysis and Generation via a Semantic Progress Function https://huggingface.co/papers/2604.22554 3. DiffNR: Diffusion-Enhanced Neural Representation Optimization for Sparse-View 3D Tomographic Reconstruction https://huggingface.co/papers/2604.21518 4. LLM Safety...

【本日の論文】 1. LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics https://huggingface.co/papers/2604.17295 2. WorldMark: A Unified Benchmark Suite for Interactive Video World Models https://huggingface.co/papers/2604.21686 3. UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling https://huggingface.co/pape...

【本日の論文】 1. LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics https://huggingface.co/papers/2604.17295 2. WorldMark: A Unified Benchmark Suite for Interactive Video World Models https://huggingface.co/papers/2604.21686 3. UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling https://huggingface.co/pape...

【本日の論文】 1. LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics https://huggingface.co/papers/2604.17295 2. WorldMark: A Unified Benchmark Suite for Interactive Video World Models https://huggingface.co/papers/2604.21686 3. UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling https://huggingface.co/pape...

【本日の論文】 1. LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model https://huggingface.co/papers/2604.20796 2. Near-Future Policy Optimization https://huggingface.co/papers/2604.20733 3. DR-Venus: Towards Frontier Edge-Scale Deep Research Agents with Only 10K Open Data https://huggingface.co/papers/2604.19859 4. OpenMobile: Building Open Mobile Age...

【本日の論文】 1. Tstars-Tryon 1.0: Robust and Realistic Virtual Try-On for Diverse Fashion Items https://huggingface.co/papers/2604.19748 2. CoInteract: Physically-Consistent Human-Object Interaction Video Synthesis via Spatially-Structured Co-Generation https://huggingface.co/papers/2604.19636 3. AgentSPEX: An Agent SPecification and EXecution Language https://huggingface.co/papers/2604.13346 4....

【本日の論文】 1. Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation https://huggingface.co/papers/2604.18168 2. OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation https://huggingface.co/papers/2604.18486 3. Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence https://huggingface....

【本日の論文】 1. Elucidating the SNR-t Bias of Diffusion Probabilistic Models https://huggingface.co/papers/2604.16044 2. Maximal Brain Damage Without Data or Optimization: Disrupting Neural Networks via Sign-Bit Flips https://huggingface.co/papers/2502.07408 3. PersonaVLM: Long-Term Personalized Multimodal LLMs https://huggingface.co/papers/2604.13074 4. Web Retrieval-Aware Chunking (W-RAC) for...

【本日の論文】 1. HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds https://huggingface.co/papers/2604.14268 2. DR^{3}-Eval: Towards Realistic and Reproducible Deep Research Evaluation https://huggingface.co/papers/2604.14683 3. RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework https://huggingface.co/papers/2604.15308 4. How...

【本日の論文】 1. HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds https://huggingface.co/papers/2604.14268 2. DR^{3}-Eval: Towards Realistic and Reproducible Deep Research Evaluation https://huggingface.co/papers/2604.14683 3. RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework https://huggingface.co/papers/2604.15308 4. How...

【本日の論文】 1. HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds https://huggingface.co/papers/2604.14268 2. RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework https://huggingface.co/papers/2604.15308 3. DR^{3}-Eval: Towards Realistic and Reproducible Deep Research Evaluation https://huggingface.co/papers/2604.14683 4. How...

【本日の論文】 1. Seedance 2.0: Advancing Video Generation for World Complexity https://huggingface.co/papers/2604.14148 2. GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents https://huggingface.co/papers/2604.07429 3. RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time https://huggingface.co/papers/2604.11626 4. SpatialEvo: Self-...

【本日の論文】 1. ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents https://huggingface.co/papers/2604.11784 2. KnowRL: Boosting LLM Reasoning via Reinforcement Learning with Minimal-Sufficient Knowledge Guidance https://huggingface.co/papers/2604.12627 3. Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe https://huggingf...

【本日の論文】 1. QuanBench+: A Unified Multi-Framework Benchmark for LLM-Based Quantum Code Generation https://huggingface.co/papers/2604.08570 2. The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping https://huggingface.co/papers/2604.11297 3. OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation https://huggingface.co/papers/2604.11804 4. Attention Sink i...