Shows / ずんだもんのHugging Faceニュース

ずんだもんのHugging Faceニュース

ksterx · ja · 248 episodes

Hugging Face Trending Papersの要約を毎日日本語で配信。

Website ↗

Episodes

ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-10-25)
【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…
Oct 25, 2026·4m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-10-24)
【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…
Oct 24, 2026·2m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-10-23)
【本日の論文】 1. StreamEval: Evaluating Interactive Streaming Video Generation Models https://huggingface.co/papers/2610.28402 2. SpatialScout: Can VLM Agents…
Oct 23, 2026·2m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-10-22)
【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…
Oct 22, 2026·5m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-10-21)
【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…
Oct 21, 2026·5m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-10-20)
【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…
Oct 20, 2026·3m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-10-19)
【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…
Oct 19, 2026·2m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-10-18)
【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…
Oct 17, 2026·4m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-10-17)
【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…
Oct 17, 2026·5m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-10-16)
【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…
Oct 16, 2026·4m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-10-15)
【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…
Oct 15, 2026·3m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-10-14)
【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…
Oct 14, 2026·3m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-10-13)
【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…
Oct 13, 2026·3m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-10-12)
【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…
Oct 12, 2026·3m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-10-03)
【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…
Oct 3, 2026·3m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-10-02)
【本日の論文】 1. The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation…
Oct 2, 2026·3m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-10-01)
【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…
Oct 1, 2026·3m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-09-30)
【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…
Sep 30, 2026·4m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-09-29)
【本日の論文】 1. FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders…
Sep 29, 2026·2m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-09-28)
【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…
Sep 28, 2026·2m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-09-27)
【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…
Sep 27, 2026·3m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-09-26)
【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…
Sep 26, 2026·3m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-09-25)
【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…
Sep 25, 2026·4m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-09-24)
【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…
Sep 24, 2026·3m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-09-23)
【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…
Sep 23, 2026·2m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-09-22)
【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…
Sep 22, 2026·3m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-09-21)
【本日の論文】 1. DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression https://huggingface.co/papers/2609.19969 2. Can MiniMax-H3 Reason About the Physical…
Sep 20, 2026·3m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-09-20)
【本日の論文】 1. DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression https://huggingface.co/papers/2609.19969 2. Can MiniMax-H3 Reason About the Physical…
Sep 19, 2026·3m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-09-19)
【本日の論文】 1. DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression https://huggingface.co/papers/2609.19969 2. SoL-Pi: Recursively Scaling…
Sep 18, 2026·2m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-09-18)
【本日の論文】 1. LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence https://huggingface.co/papers/2609.17488 2. ScienceIDE: Turning…
Sep 18, 2026·3m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-09-17)
【本日の論文】 1. Continual Learning Mechanisms Compose for Long-Horizon Memorization https://huggingface.co/papers/2609.06986 2. AI for Games in the Foundation Model…
Sep 17, 2026·4m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-09-16)
【本日の論文】 1. Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation https://huggingface.co/papers/2609.11638 2. Atria Dawn: The Dawn of Agentic…
Sep 16, 2026·3m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-09-15)
【本日の論文】 1. DataFlex-RL: An Evaluation Platform for RLVR Data Policies https://huggingface.co/papers/2609.06107 2. Benchmark Radar: A Living Database and Search…
Sep 15, 2026·4m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-09-14)
【本日の論文】 1. NCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction…
Sep 14, 2026·5m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-09-13)
【本日の論文】 1. NCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction…
Sep 12, 2026·4m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-09-12)
【本日の論文】 1. NCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction…
Sep 11, 2026·4m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-09-11)
【本日の論文】 1. Show-Harness: Just a VLM Agent Can Play Robots https://huggingface.co/papers/2609.10522 2. AgentGrad: Intervention-guided Prompt Optimization for…
Sep 10, 2026·3m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-09-10)
【本日の論文】 1. NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness https://huggingface.co/papers/2609.08183 2. AuK…
Sep 9, 2026·3m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-09-09)
【本日の論文】 1. Unlocking Lossless Speedups in LLMs via Discrete Diffusion https://huggingface.co/papers/2609.04010 2. FlowBalance: Verifier-Grounded…
Sep 8, 2026·4m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-09-08)
【本日の論文】 1. Bilevel Coordinated Reflection: A Game-Theoretic Approach to Multi-Agent LLM Systems https://huggingface.co/papers/2609.02750 2. Iris: Climbing to…
Sep 8, 2026·5m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-09-07)
【本日の論文】 1. Compile by Training: Turning Natural-Language Specifications into Local Neural Functions https://huggingface.co/papers/2609.04199 2…
Sep 6, 2026·3m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-09-06)
【本日の論文】 1. Compile by Training: Turning Natural-Language Specifications into Local Neural Functions https://huggingface.co/papers/2609.04199 2…
Sep 5, 2026·4m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-09-05)
【本日の論文】 1. Compile by Training: Turning Natural-Language Specifications into Local Neural Functions https://huggingface.co/papers/2609.04199 2…
Sep 4, 2026·3m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-09-04)
【本日の論文】 1. Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills https://huggingface.co/papers/2609.02749 2. HarnessDev: Can LLMs Create and Evolve…
Sep 3, 2026·3m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-09-03)
【本日の論文】 1. StudentSim: Training LLM-based Student Simulators https://huggingface.co/papers/2609.01591 2. Qwen-Drive-1.0: An Initial Step towards a…
Sep 2, 2026·3m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-09-02)
【本日の論文】 1. Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement https://huggingface.co/papers/2608.31046 2. DreamX-Creator…
Sep 1, 2026·4m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-09-01)
【本日の論文】 1. LoopArena: Benchmarking Models as Runtime Controllers for Loop Engineering https://huggingface.co/papers/2608.28281 2. Beyond Data Scaling…
Sep 1, 2026·3m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-08-31)
【本日の論文】 1. Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models https://huggingface.co/papers/2608.25518 2. PAWBench: How…
Aug 31, 2026·3m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-08-30)
【本日の論文】 1. Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models https://huggingface.co/papers/2608.25518 2. PAWBench: How…
Aug 30, 2026·4m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-08-29)
【本日の論文】 1. Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models https://huggingface.co/papers/2608.25518 2. PAWBench: How…
Aug 29, 2026·4m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-08-28)
【本日の論文】 1. PAWBench: How Far Are We from Probabilistically Aligned World Modeling? https://huggingface.co/papers/2608.27345 2. Training Agents to Evolve with…
Aug 28, 2026·4m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-08-27)
【本日の論文】 1. FrontierChallenge: Evaluating Scientific Workflow Completion https://huggingface.co/papers/2608.24979 2. VBVR-Pro: A Scalable and Verifiable Suite…
Aug 27, 2026·3m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-08-26)
【本日の論文】 1. Apodex 1.1: Scaling Agentic Intelligence for Complex Work https://huggingface.co/papers/2608.23283 2. EchoWM: Open and Enterable Omnimodal World…
Aug 25, 2026·3m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-08-25)
【本日の論文】 1. Let's Scale Step by Step: Compute-Efficient Hyperparameter Transfer for Large-Scale Mixture-of-Experts https://huggingface.co/papers/2608.20061 2…
Aug 24, 2026·4m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-08-24)
【本日の論文】 1. EnvHarness: Awakening Static Worlds for Agent Learning https://huggingface.co/papers/2608.19880 2. FACET: Preserving Source Intent and Executable…
Aug 23, 2026·3m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-08-23)
【本日の論文】 1. EnvHarness: Awakening Static Worlds for Agent Learning https://huggingface.co/papers/2608.19880 2. FACET: Preserving Source Intent and Executable…
Aug 22, 2026·3m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-08-22)
【本日の論文】 1. EnvHarness: Awakening Static Worlds for Agent Learning https://huggingface.co/papers/2608.19880 2. FACET: Preserving Source Intent and Executable…
Aug 21, 2026·4m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-08-21)
【本日の論文】 1. SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation https://huggingface.co/papers/2608.17426 2. Zetta ζ: An Efficient…
Aug 20, 2026·3m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-08-20)
【本日の論文】 1. Demystifying Agent Skills: Why They Work-Until They Don't https://huggingface.co/papers/2608.14036 2. Agentic ESOpt: Fine-Tuning Long-Horizon LLM…
Aug 19, 2026·3m
ずんだもんのHugging Faceニュース
Daily AI Papers Briefing (2026-08-19)
【本日の論文】 1. HarnessEval-W: Agentifying the Evaluation of Visual Worlds https://huggingface.co/papers/2608.16859 2. StateM: Reaching 95.3% Raw Accuracy, or a…
Aug 18, 2026·3m