ずんだもんのHugging Faceニュース

【本日の論文】 1. Vidu S1: A Real-Time Interactive Video Generation Model https://huggingface.co/papers/2607.03118 2. Video-Oasis: Rethinking Evaluation of Video Understanding https://huggingface.co/papers/2603.29616 3. Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition https://huggingface.co/papers/2601.16211 4. UniClawBench: A Universal B...

【本日の論文】 1. Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning https://huggingface.co/papers/2607.07708 2. Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation https://huggingface.co/papers/2607.07608 3. Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence https://huggingface.co/papers/2...

【本日の論文】 1. RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation https://huggingface.co/papers/2607.06559 2. AlayaWorld: Long-Horizon and Playable Video World Generation https://huggingface.co/papers/2607.06291 3. RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation https://huggingface.co/papers/2607.06558 4. Hierarchical Sparse Attention Done Right: Towar...

【本日の論文】 1. OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers https://huggingface.co/papers/2607.04033 2. UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning https://huggingface.co/papers/2607.04425 3. ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog https://huggingface.co/papers/2607.04438 4. PixWorld:...

【本日の論文】 1. The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning https://huggingface.co/papers/2606.29526 2. Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots https://huggingface.co/papers/2607.02501 3. OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transforme...

【本日の論文】 1. Program-as-Weights: A Programming Paradigm for Fuzzy Functions https://huggingface.co/papers/2607.02512 2. AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents https://huggingface.co/papers/2607.02255 3. EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments https://huggingface.co/papers/2607.02440 4. Morphing into Hybrid Attention Models htt...

【本日の論文】 1. Program-as-Weights: A Programming Paradigm for Fuzzy Functions https://huggingface.co/papers/2607.02512 2. AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents https://huggingface.co/papers/2607.02255 3. EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments https://huggingface.co/papers/2607.02440 4. Morphing into Hybrid Attention Models htt...

【本日の論文】 1. Program-as-Weights: A Programming Paradigm for Fuzzy Functions https://huggingface.co/papers/2607.02512 2. EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments https://huggingface.co/papers/2607.02440 3. AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents https://huggingface.co/papers/2607.02255 4. Morphing into Hybrid Attention Models htt...

【本日の論文】 1. PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception https://huggingface.co/papers/2606.28322 2. ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving https://huggingface.co/papers/2607.00466 3. TurboServe: Serving Streaming Video Generation Efficiently and Economically https://huggingface.co/papers/2606.19271 4. MemSyco-Bench: Benchmarki...

【本日の論文】 1. Orca: The World is in Your Mind https://huggingface.co/papers/2606.30534 2. Dockerless: Environment-Free Program Verifier for Coding Agents https://huggingface.co/papers/2606.28436 3. DOPD: Dual On-policy Distillation https://huggingface.co/papers/2606.30626 4. BlockPilot: Instance-Adaptive Policy Learning for Diffusion-based Speculative Decoding https://huggingface.co/papers/260...

【本日の論文】 1. LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling https://huggingface.co/papers/2606.18023 2. Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients https://huggingface.co/papers/2606.18216 3. ACE-Ego-0: Unifying Egocentric Human and Robotic Data for VLA Pretraining https://huggingface.co/papers/2606.17200 4. GameCraft-Bench: Can Agents Bui...

【本日の論文】 1. JoyAI-VL-Interaction: Real-Time Vision-Language Interaction Intelligence https://huggingface.co/papers/2606.14777 2. Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories https://huggingface.co/papers/2606.11176 3. Geometric Action Model for Robot Policy Learning https://huggingface.co/papers/2606.17046 4. DreamX-World 1.0: A General-Purpose Interactive Worl...

【本日の論文】 1. OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data https://huggingface.co/papers/2606.13432 2. APPO: Agentic Procedural Policy Optimization https://huggingface.co/papers/2606.12384 3. Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents https://huggingface.co/papers/2606.06036 4. From Chatbot to Digital Colleague: The Paradigm Shift Toward Pe...

【本日の論文】 1. EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments https://huggingface.co/papers/2606.13681 2. MiniMax Sparse Attention https://huggingface.co/papers/2606.13392 3. WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces https://huggingface.co/papers/2606.09426 4. SpatialClaw: Rethinking Action Interface for Ag...

【本日の論文】 1. EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments https://huggingface.co/papers/2606.13681 2. MiniMax Sparse Attention https://huggingface.co/papers/2606.13392 3. WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces https://huggingface.co/papers/2606.09426 4. SpatialClaw: Rethinking Action Interface for Ag...

【本日の論文】 1. EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments https://huggingface.co/papers/2606.13681 2. SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning https://huggingface.co/papers/2606.13673 3. MiniMax Sparse Attention https://huggingface.co/papers/2606.13392 4. InterleaveThinker: Reinforcing Agentic Interleaved Generation https://hu...

【本日の論文】 1. Redesign Mixture-of-Experts Routers with Manifold Power Iteration https://huggingface.co/papers/2606.12397 2. Toward Generalist Autonomous Research via Hypothesis-Tree Refinement https://huggingface.co/papers/2606.11926 3. Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application https://huggingface.co/pape...

【本日の論文】 1. ABot-Earth 0.5: Generative 3D Earth Model https://huggingface.co/papers/2606.09967 2. Kwai Keye-VL-2.0 Technical Report https://huggingface.co/papers/2606.10651 3. Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution https://huggingface.co/papers/2606.10917 4. Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts https://hug...

【本日の論文】 1. SWE-Explore: Benchmarking How Coding Agents Explore Repositories https://huggingface.co/papers/2606.07297 2. On the Geometry of On-Policy Distillation https://huggingface.co/papers/2606.07082 3. Agents' Last Exam https://huggingface.co/papers/2606.05405 4. LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents https://huggingface.co/papers/2606.0608...

【本日の論文】 1. Your UnEmbedding Matrix is Secretly a Feature Lens for Text Embeddings https://huggingface.co/papers/2606.07502 2. SoCRATES: Towards Reliable Automated Evaluation of Proactive LLM Mediation across Domains and Socio-cognitive Variations https://huggingface.co/papers/2606.05563 3. GENEB: Why Genomic Models Are Hard to Compare https://huggingface.co/papers/2606.04525 4. MMAE: A Mass...

【本日の論文】 1. Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution https://huggingface.co/papers/2606.06492 2. ArcANE: Do Role-Playing Language Agents Stay in Character at the Right Time? https://huggingface.co/papers/2606.05553 3. TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration https://huggingface.co/papers/2606.04743 4. AdaPlanBen...

【本日の論文】 1. Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution https://huggingface.co/papers/2606.06492 2. ArcANE: Do Role-Playing Language Agents Stay in Character at the Right Time? https://huggingface.co/papers/2606.05553 3. TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration https://huggingface.co/papers/2606.04743 4. AdaPlanBen...

【本日の論文】 1. Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution https://huggingface.co/papers/2606.06492 2. ArcANE: Do Role-Playing Language Agents Stay in Character at the Right Time? https://huggingface.co/papers/2606.05553 3. TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration https://huggingface.co/papers/2606.04743 4. AdaPlanBen...

【本日の論文】 1. Audio Interaction Model https://huggingface.co/papers/2606.05121 2. Cosmos 3: Omnimodal World Models for Physical AI https://huggingface.co/papers/2606.02800 3. Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories https://huggingface.co/papers/2606.02060 4. Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Le...

【本日の論文】 1. OCC-RAG: Optimal Cognitive Core for Faithful Question Answering https://huggingface.co/papers/2606.00683 2. From Activation to Causality: Discovery of Causal Visual Representations in the Human Brain https://huggingface.co/papers/2605.23895 3. Trust Region On-Policy Distillation https://huggingface.co/papers/2606.01249 4. Humanoid-GPT: Scaling Data and Structure for Zero-Shot Mot...