ずんだもんのHugging Faceニュース

【本日の論文】
1. VFlash: Fast, Accurate Visual Planning via Flash Primitive Decoding
https://huggingface.co/papers/2611.08449
2. From Autonomous Agents to Cognitive Symbionts: Toward AI-Augmented Human Intelligence
https://huggingface.co/papers/2611.05376
3. SLA: Scaling Spatial-Language-Action Model via Continual Pre-training
https://huggingface.co/papers/2611.08373
4. Harness-S: Learning from Sibling Harnesses for Generalizable Agent Training
https://huggingface.co/papers/2611.04277
5. Random Is Almost Enough? Stable and Low-Cost Benchmark Compression via BestRand
https://huggingface.co/papers/2611.00883

【本日の論文】
1. VFlash: Fast, Accurate Visual Planning via Flash Primitive Decoding
https://huggingface.co/papers/2611.08449
2. SLA: Scaling Spatial-Language-Action Model via Continual Pre-training
https://huggingface.co/papers/2611.08373
3. Harness-S: Learning from Sibling Harnesses for Generalizable Agent Training
https://huggingface.co/papers/2611.04277
4. Random Is Almost Enough? Stable and Low-Cost Benchmark Compression via BestRand
https://huggingface.co/papers/2611.00883
5. WeLM-Image: A Unified Image Generation Model towards Visual Intelligence
https://huggingface.co/papers/2611.07392

【本日の論文】
1. Turns Matter: Advancing Streaming Video RL via Turn-Level Credit
https://huggingface.co/papers/2611.06728
2. From Pixels to Actions - Towards Native Vision-Language-Action Policies
https://huggingface.co/papers/2611.06918
3. FrontierPhysics: Evaluating Agents for End-to-End Physics Research
https://huggingface.co/papers/2611.06910
4. What Does Multi-Turn Reinforcement Learning Really Improve in LLM Agents?
https://huggingface.co/papers/2611.06483
5. GameVerse: A Minute-Scale Gameplay Dataset for Long-Horizon Interactive World Modeling
https://huggingface.co/papers/2610.37257

【本日の論文】
1. Route Anything: A Study of Model and Policy Routing for General-Purpose AI Systems
https://huggingface.co/papers/2611.05275
2. Words Caught in the Heart: Simulating Person-Specific Expression for Self-Opaque Clients in Psychotherapy
https://huggingface.co/papers/2611.00617
3. Think Less, Locally: Local Preference Learning for Reasoning Compression
https://huggingface.co/papers/2611.04814
4. MoviEdit: Long-form Multi-Shot Video Editing Made Easy
https://huggingface.co/papers/2611.02737
5. Behind Video Generation: Observations and Insights on Multimodal Understanding from Kling
https://huggingface.co/papers/2611.04916

【本日の論文】
1. Advances in Agentic Computer Graphics
https://huggingface.co/papers/2611.01860
2. Wave Forcing: Towards Speed-of-Light Streaming Video Generation
https://huggingface.co/papers/2611.00859
3. CUA-Master: Scaling Computer-use Agents through Open-World Recursive Improvements
https://huggingface.co/papers/2611.03126
4. CoworkOS:Scaling Agent Coworkers for Real-world Automation
https://huggingface.co/papers/2611.03178
5. Video Generation Meets Agent Harness: Agentic Video Generation, Agentic World Modeling and Recursive Self-Improvement
https://huggingface.co/papers/2610.40191

【本日の論文】
1. Diagnosing the Reference Gap: What Visual Scaffolds Can and Cannot Fix in Multimodal Reasoning
https://huggingface.co/papers/2610.39419
2. DecisionRank: On-Policy Distillation for Decision-Model Rerankers
https://huggingface.co/papers/2610.42128
3. Video Generation Meets Agent Harness: Agentic Video Generation, Agentic World Modeling and Recursive Self-Improvement
https://huggingface.co/papers/2610.40191
4. DeFT-RAG: Decomposing Multi-Hop Questions into Self-Contained Sub-Questions with Reusable Answers
https://huggingface.co/papers/2610.37826
5. From Fragmentation to Fusion: A Survey and Roadmap for Omnimodal Embeddings
https://huggingface.co/papers/2611.00172

【本日の論文】
1. Look Only When Needed: Certificate-Guided Visual Routing for Efficient Diffusion VLMs
https://huggingface.co/papers/2610.36671
2. Proving and Improving the Platonic Representation Hypothesis with JEPAs
https://huggingface.co/papers/2610.39302
3. A-RSI: Adaptive Task Refresh for Zero-Data Multimodal Self-Improvement
https://huggingface.co/papers/2610.38568
4. L3G-World: Real-Time Infinite World Generation with Latent 3D Gaussian Memory
https://huggingface.co/papers/2610.40614
5. WorkFactory: Turning Professional Intents into Executable Work for Scalable Agent Training
https://huggingface.co/papers/2610.37161

【本日の論文】
1. Look Only When Needed: Certificate-Guided Visual Routing for Efficient Diffusion VLMs
https://huggingface.co/papers/2610.36671
2. Youtu-Parsing-Omni: One Encoder, One Schema, All Modalities
https://huggingface.co/papers/2610.39301
3. A-RSI: Adaptive Task Refresh for Zero-Data Multimodal Self-Improvement
https://huggingface.co/papers/2610.38568
4. Proving and Improving the Platonic Representation Hypothesis with JEPAs
https://huggingface.co/papers/2610.39302
5. L3G-World: Real-Time Infinite World Generation with Latent 3D Gaussian Memory
https://huggingface.co/papers/2610.40614

【本日の論文】
1. Intrinsic Distribution Matching
https://huggingface.co/papers/2610.39633
2. A-RSI: Adaptive Task Refresh for Zero-Data Multimodal Self-Improvement
https://huggingface.co/papers/2610.38568
3. Your Benchmark Is an Empirical Measure Over Difficulty
https://huggingface.co/papers/2610.29927
4. Look Only When Needed: Certificate-Guided Visual Routing for Efficient Diffusion VLMs
https://huggingface.co/papers/2610.36671
5. Youtu-Parsing-Omni: One Encoder, One Schema, All Modalities
https://huggingface.co/papers/2610.39301

【本日の論文】
1. Efficient Streaming Audio-Visual Target Speaker Extraction for Real-World Acoustic Scenes
https://huggingface.co/papers/2610.32749
2. OmniShowcase: Omnidirectional Subject-Consistent Video Generation from Multi-View Images
https://huggingface.co/papers/2610.35684
3. Sensorimotor Alignment: A Platonic Proxy for Embodied Policy Success
https://huggingface.co/papers/2610.31670
4. TAO: Tool-Aware Joint Scheduling for LLM-Based Agentic Serving
https://huggingface.co/papers/2610.37230
5. RealCLI: Toward a Unified Evaluation of Human-Agent Collaboration for CLI Agents
https://huggingface.co/papers/2610.22507

【本日の論文】
1. Multiscale Policy Optimization for Long-Horizon LLM Agents
https://huggingface.co/papers/2610.35013
2. ChronoReplay: One Answer Interface Is Not Enough for Streaming Spatial Intelligence
https://huggingface.co/papers/2610.34283
3. The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents
https://huggingface.co/papers/2610.36077
4. VibeVideoBench: Evaluating Multimodal Agents on Code-Driven Video Generation
https://huggingface.co/papers/2610.35864
5. PDRVLA: A Vision-Language-Action Model with Physical Dynamics Representations
https://huggingface.co/papers/2610.37381

【本日の論文】
1. Trajectory2Gym: Decision-Grounded Compositional Interaction Synthesis for Tool-Use Agents
https://huggingface.co/papers/2610.33568
2. Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure Attribution
https://huggingface.co/papers/2610.32285
3. StreamVibe: Proactive Video Agents for Evolving User Intent
https://huggingface.co/papers/2610.34662
4. DynaFlow: Learning Free-Form Multi-Agent Orchestration
https://huggingface.co/papers/2610.34467
5. InteractiveWorld: A Verifiable Human-Centric Environment for Building Better Interactive MLLM Assistants
https://huggingface.co/papers/2610.33966

【本日の論文】
1. Reading, Writing, Sharing, and Interacting with the World through Video
https://huggingface.co/papers/2610.31668
2. UserArena: Benchmarking Interactive User Simulation for Long-Horizon Shopping Agents
https://huggingface.co/papers/2610.30932
3. HiSTEVE 1.0: Harnessing Human-Interface VLA Agents for Open-World Games
https://huggingface.co/papers/2610.31162
4. RSIHub: A Composable Framework for Agent-Evolution Methods
https://huggingface.co/papers/2610.32253
5. RynnUnify: Towards Unified Embodied Brain
https://huggingface.co/papers/2610.32965

【本日の論文】
1. WeVisOne-VL: Unified Visual Perception from Objects to Pixels
https://huggingface.co/papers/2610.31329
2. Editing Images into Reusable Layers via Compositional Edit-Prior Distillation
https://huggingface.co/papers/2610.24738
3. Making MLLM Latents Matter: Factor-Aware Predictive Learning for Cinematic Video Generation
https://huggingface.co/papers/2610.30926
4. Deep Search in Real-World Web Environments
https://huggingface.co/papers/2610.30181
5. IQuest-Q1: Advancing Foundation Capabilities for Agentic CLI Systems
https://huggingface.co/papers/2610.30949

【本日の論文】
1. WeVisOne-VL: Unified Visual Perception from Objects to Pixels
https://huggingface.co/papers/2610.31329
2. Editing Images into Reusable Layers via Compositional Edit-Prior Distillation
https://huggingface.co/papers/2610.24738
3. Making MLLM Latents Matter: Factor-Aware Predictive Learning for Cinematic Video Generation
https://huggingface.co/papers/2610.30926
4. Deep Search in Real-World Web Environments
https://huggingface.co/papers/2610.30181
5. IQuest-Q1: Advancing Foundation Capabilities for Agentic CLI Systems
https://huggingface.co/papers/2610.30949

【本日の論文】
1. WeVisOne-VL: Unified Visual Perception from Objects to Pixels
https://huggingface.co/papers/2610.31329
2. Making MLLM Latents Matter: Factor-Aware Predictive Learning for Cinematic Video Generation
https://huggingface.co/papers/2610.30926
3. Deep Search in Real-World Web Environments
https://huggingface.co/papers/2610.30181
4. Editing Images into Reusable Layers via Compositional Edit-Prior Distillation
https://huggingface.co/papers/2610.24738
5. IQuest-Q1: Advancing Foundation Capabilities for Agentic CLI Systems
https://huggingface.co/papers/2610.30949

【本日の論文】
1. StreamEval: Evaluating Interactive Streaming Video Generation Models
https://huggingface.co/papers/2610.28402
2. SpatialScout: Can VLM Agents Actively Explore and Map 3D Scenes?
https://huggingface.co/papers/2610.26659
3. DONIC: Generalist Dexterous Bimanual Tracking Control from Human Demonstrations
https://huggingface.co/papers/2610.29997
4. Looking Ahead: Modeling Future Evolution in Autoregressive Video Generation
https://huggingface.co/papers/2610.29989
5. Cache Engineering for Agents
https://huggingface.co/papers/2610.28577

【本日の論文】
1. Focused Omni-Modal GUI Agents
https://huggingface.co/papers/2610.26203
2. Matrix-Game 4.0: Harnessing Video Models for Real-Time Playable Game Worlds
https://huggingface.co/papers/2610.27999
3. Ropedia W0: Scaling Loco-Manipulation World Models across Embodiments with Human Experience
https://huggingface.co/papers/2610.26855
4. PAR: Progress-Aligned Recurrence for Length Generalization in State Tracking
https://huggingface.co/papers/2610.27628
5. S-Agent 2.0: Spatial Reasoning with a General Coding Agent
https://huggingface.co/papers/2610.28354

【本日の論文】
1. Scaling Parameter-Efficient Fine-Tuning for Brain Encoding
https://huggingface.co/papers/2610.26802
2. OR-License: Evaluating LLM Agents as Real-World Operations Research Practitioners
https://huggingface.co/papers/2610.24087
3. EgoXperience: Learning World-Grounded Egocentric Representations from Human Experience
https://huggingface.co/papers/2610.26625
4. MemT-1.0: Towards Memory-Native Evolution
https://huggingface.co/papers/2610.26825
5. Holi-World: Building Holistic World Intelligence from Human-Ego Experience
https://huggingface.co/papers/2610.26549

【本日の論文】
1. HexaShell: A Thin Harness for Exploring the Limits of VLM Agents as Robot Coding Agents
https://huggingface.co/papers/2610.23479
2. Has GPT-6-Astra Achieved Embodied Intelligence?
https://huggingface.co/papers/2610.22471
3. BizBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business
https://huggingface.co/papers/2610.20424
4. Learning to Think and Explore in 3D World
https://huggingface.co/papers/2610.21783
5. Into the Unknown: Benchmarking AI agents on open scientific research problems
https://huggingface.co/papers/2610.19159

【本日の論文】
1. Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation
https://huggingface.co/papers/2610.21601
2. OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding
https://huggingface.co/papers/2610.18829
3. MJev-Spatial: System One Spatial Intelligence via Native Attention Matching
https://huggingface.co/papers/2610.22276
4. OpenGCUA: Toward a Fully Open Stack for Generalist Computer Use
https://huggingface.co/papers/2610.22200
5. FDE-Gym: The Last Mile of AI Delivery
https://huggingface.co/papers/2610.22350

【本日の論文】
1. Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation
https://huggingface.co/papers/2610.21601
2. OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding
https://huggingface.co/papers/2610.18829
3. MJev-Spatial: System One Spatial Intelligence via Native Attention Matching
https://huggingface.co/papers/2610.22276
4. OpenGCUA: Toward a Fully Open Stack for Generalist Computer Use
https://huggingface.co/papers/2610.22200
5. FDE-Gym: The Last Mile of AI Delivery
https://huggingface.co/papers/2610.22350

【本日の論文】
1. OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding
https://huggingface.co/papers/2610.18829
2. Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation
https://huggingface.co/papers/2610.21601
3. OpenGCUA: Toward a Fully Open Stack for Generalist Computer Use
https://huggingface.co/papers/2610.22200
4. FDE-Gym: The Last Mile of AI Delivery
https://huggingface.co/papers/2610.22350
5. RoTA-Bench: Evaluating 3D Spatial Reasoning through Interactive Projection Alignment
https://huggingface.co/papers/2610.17665

【本日の論文】
1. Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation
https://huggingface.co/papers/2610.20571
2. Player-1: Learning to Play from Synthetic Experience
https://huggingface.co/papers/2610.20584
3. Beyond Domain-Routed Supervision: Cross-Teacher Guarding for Multi-Teacher On-Policy Distillation
https://huggingface.co/papers/2610.13521
4. Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents
https://huggingface.co/papers/2610.20344
5. More Methods, Better Agents? A Reality Check on Self-Distillation in Agentic Reinforcement Learning
https://huggingface.co/papers/2610.19789

【本日の論文】
1. Jeva: System One Models from First Principles
https://huggingface.co/papers/2610.18773
2. Agent-Reflex: Teaching Language Agents to Act Reflectively
https://huggingface.co/papers/2610.17953
3. VideoJev: System One Model for Video Understanding and Interaction
https://huggingface.co/papers/2610.18615
4. Urbex: Agentic Spatial Grounding for City-Scale 3D Scenes
https://huggingface.co/papers/2610.18356
5. Tev: Scaling Long-Horizon Agentic Environments with Dense Progress Rewards
https://huggingface.co/papers/2610.18868

【本日の論文】
1. GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives
https://huggingface.co/papers/2609.39601
2. Thinking Inertia: LLMs Keep Thinking When Told Not To
https://huggingface.co/papers/2610.11765
3. AgentSWE: Can Coding Agents Build the Agent You Actually Want?
https://huggingface.co/papers/2610.13361
4. Scaling Agentic Data for Long-Horizon Terminal Intelligence
https://huggingface.co/papers/2610.13166
5. VIS-Ground: Video Interactive Storytelling with Contextual Grounding
https://huggingface.co/papers/2610.09326

【本日の論文】
1. Systematic Multi-Agent Vision-and-Language Navigation: Formulation, Benchmark, and Method
https://huggingface.co/papers/2609.35965
2. Multi-Stream Attention Residuals
https://huggingface.co/papers/2610.13630
3. Thinking Inertia: LLMs Keep Thinking When Told Not To
https://huggingface.co/papers/2610.11765
4. T3lescope: Arbitrary-Resolution High-Fidelity Generative Surface Reconstruction from Images
https://huggingface.co/papers/2610.03308
5. SpatialASM: Internalizing Active Mentalization for Spatial Reasoning
https://huggingface.co/papers/2610.13832

【本日の論文】
1. AgentGarten: Code Worlds for Evolving Agents
https://huggingface.co/papers/2610.12374
2. Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?
https://huggingface.co/papers/2610.08215
3. TokenRouter: Efficient Serving System for Token-Level LLM Routing
https://huggingface.co/papers/2610.12242
4. From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation
https://huggingface.co/papers/2610.06100
5. MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement
https://huggingface.co/papers/2610.11959

【本日の論文】
1. OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction
https://huggingface.co/papers/2610.01762
2. Adaptive Reward Routing: Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forward-Process RL
https://huggingface.co/papers/2609.37200
3. On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics
https://huggingface.co/papers/2609.35259
4. Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief States
https://huggingface.co/papers/2610.01415
5. Hierarchical Continuous Diffusion Language Models
https://huggingface.co/papers/2610.02193

【本日の論文】
1. The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
https://huggingface.co/papers/2609.36484
2. UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement
https://huggingface.co/papers/2609.38721
3. Rethinking Latent Visual Reasoning: Grounding Latent Reasoning in Visual Evidence
https://huggingface.co/papers/2609.34563
4. False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents
https://huggingface.co/papers/2609.39102
5. AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks
https://huggingface.co/papers/2609.38288

【本日の論文】
1. Raven: The Harness of Harnesses for Composable Agentic Intelligence
https://huggingface.co/papers/2609.33439
2. In-Context Learning for Robots: Methods and Applications
https://huggingface.co/papers/2609.36012
3. MaLiang-Harness: A Programmable Path to Image and Video Generation
https://huggingface.co/papers/2609.34309
4. Scaling Properties of Same-Family On-Policy Distillation
https://huggingface.co/papers/2609.32722
5. Omni-IO Skills: Harnessing Your Agent Omni-Native
https://huggingface.co/papers/2609.31847

【本日の論文】
1. Post-Training Leaves Behavioral Shadows on Unrelated Decisions
https://huggingface.co/papers/2609.29233
2. YuE2: Unifying Symbolic and Audio Music Generation at Frontier Quality
https://huggingface.co/papers/2609.33757
3. Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation
https://huggingface.co/papers/2609.35347
4. Groupwise Agentic Grading and Advantage Redistribution for Code Agent RL
https://huggingface.co/papers/2609.32577
5. Self-Evolving Coding Agents: From Digital Programs to Physical-World Intelligence
https://huggingface.co/papers/2609.35432

【本日の論文】
1. FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders
https://huggingface.co/papers/2609.31620
2. Disaggregated Quantization: Specializing LLM Prefill and Decode
https://huggingface.co/papers/2609.26333
3. RayOrch: Programming and Executing Lineage-Controlled Multi-Grain Dataflows for Foundation-Model Data Preparation
https://huggingface.co/papers/2609.18703
4. Block Sparse Attention with Log-Linear Complexity
https://huggingface.co/papers/2609.31093
5. InternW0-Δ: A World Action Model Bridging Predictive Dynamics and Actions with 20K+ Hours of Open Data
https://huggingface.co/papers/2609.31394

【本日の論文】
1. Training Object Permanence in World Models
https://huggingface.co/papers/2609.28654
2. Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs
https://huggingface.co/papers/2609.29845
3. WanPE: Towards Cinematic Prompt Enhancement for Modern Text-to-Video Generation
https://huggingface.co/papers/2609.30221
4. OmniEcho: Spatial Audio Understanding for Embodied Agents
https://huggingface.co/papers/2609.23407
5. Agent-Editing World Model: Rethinking World Modeling for LLM Agents
https://huggingface.co/papers/2609.28416

【本日の論文】
1. Training Object Permanence in World Models
https://huggingface.co/papers/2609.28654
2. Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs
https://huggingface.co/papers/2609.29845
3. WanPE: Towards Cinematic Prompt Enhancement for Modern Text-to-Video Generation
https://huggingface.co/papers/2609.30221
4. OmniEcho: Spatial Audio Understanding for Embodied Agents
https://huggingface.co/papers/2609.23407
5. Agent-Editing World Model: Rethinking World Modeling for LLM Agents
https://huggingface.co/papers/2609.28416

【本日の論文】
1. Training Object Permanence in World Models
https://huggingface.co/papers/2609.28654
2. Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs
https://huggingface.co/papers/2609.29845
3. WanPE: Towards Cinematic Prompt Enhancement for Modern Text-to-Video Generation
https://huggingface.co/papers/2609.30221
4. OmniEcho: Spatial Audio Understanding for Embodied Agents
https://huggingface.co/papers/2609.23407
5. Agent-Editing World Model: Rethinking World Modeling for LLM Agents
https://huggingface.co/papers/2609.28416

【本日の論文】
1. SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue
https://huggingface.co/papers/2609.26780
2. Spatial-Interactor: Learning Spatial Reasoning through Interaction with the Observable Physical World
https://huggingface.co/papers/2609.23038
3. HappyWorld-Bench
https://huggingface.co/papers/2609.24308
4. The Past Frames the Future: Memory for Autoregressive Video Generation
https://huggingface.co/papers/2609.28466
5. Just-in-Time Memory: Learning to Curate Task-Adaptive Memory for LLM Agents
https://huggingface.co/papers/2609.27334

【本日の論文】
1. The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks
https://huggingface.co/papers/2609.25804
2. RULER: Instance-aware Rubric Rewards for SVG Generation
https://huggingface.co/papers/2609.25270
3. GAE: Learning a Geometry-Native Latent Space for 3D-Consistent World Generation
https://huggingface.co/papers/2609.24981
4. All-in-One Multilingual Scene Text Recognition with Script-aware Mixture-of-Experts
https://huggingface.co/papers/2609.24058
5. Circuit Hypernetworks for Quantum-Augmented Diffusion Language Models
https://huggingface.co/papers/2609.24657

【本日の論文】
1. RRSI: Regularized Recursive Self-Improvement of Agent Harnesses
https://huggingface.co/papers/2609.24972
2. WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory
https://huggingface.co/papers/2609.24984
3. GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay
https://huggingface.co/papers/2609.25001
4. Transferring the Intelligence of VLMs to Robotic Control
https://huggingface.co/papers/2609.22966
5. OmniEdu: Open Foundation Models for Learning and Teaching
https://huggingface.co/papers/2609.23088

【本日の論文】
1. CodeMidas: Scaling Agentic Coding RL Environments from Code Itself
https://huggingface.co/papers/2609.22068
2. Grounded Skill Synthesis from Code at Scale for Agentic Intelligence
https://huggingface.co/papers/2609.05571
3. EvoOntology: A Self-Evolving Ontology Layer for Data Agents
https://huggingface.co/papers/2609.15779
4. RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents
https://huggingface.co/papers/2609.22000
5. IntBMoE: Integrating Block-Level Conditioning into Expert Composition for Full-Participation Mixture-of-Experts
https://huggingface.co/papers/2609.21346