ChatPaper

AI論文ランキング

この1週間、世界のAI研究者が注目した論文をやさしく解説

  1. 1

    OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding

    🔥 5662026-10-13深く読むarXiv 原文
  2. 2

    Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation

    🔥 4512026-10-15深く読むarXiv 原文
  3. 3

    Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation

    🔥 3332026-10-14深く読むarXiv 原文
  4. 4

    Player-1: Learning to Play from Synthetic Experience

    🔥 2852026-10-14深く読むarXiv 原文
  5. 5

    HexaShell: A Thin Harness for Exploring the Limits of VLM Agents as Robot Coding Agents

    🔥 2842026-10-16深く読むarXiv 原文
  6. 6

    OpenGCUA: Toward a Fully Open Stack for Generalist Computer Use

    🔥 2662026-10-15深く読むarXiv 原文
  7. 7

    Beyond Domain-Routed Supervision: Cross-Teacher Guarding for Multi-Teacher On-Policy Distillation

    🔥 2382026-10-09深く読むarXiv 原文
  8. 8

    Has GPT-6-Astra Achieved Embodied Intelligence?

    🔥 2362026-10-15深く読むarXiv 原文
  9. 9

    Scaling Parameter-Efficient Fine-Tuning for Brain Encoding

    🔥 2332026-10-19深く読むarXiv 原文
  10. 10

    FDE-Gym: The Last Mile of AI Delivery

    🔥 2292026-10-15深く読むarXiv 原文
  11. 11

    Focused Omni-Modal GUI Agents

    🔥 2242026-10-19深く読むarXiv 原文
  12. 12

    RoTA-Bench: Evaluating 3D Spatial Reasoning through Interactive Projection Alignment

    🔥 1982026-10-14深く読むarXiv 原文
  13. 13

    Self-Evolving Agent Harness

    🔥 1882026-10-13深く読むarXiv 原文
  14. 14

    Matrix-Game 4.0: Harnessing Video Models for Real-Time Playable Game Worlds

    🔥 1782026-10-20深く読むarXiv 原文
  15. 15

    Ropedia W0: Scaling Loco-Manipulation World Models across Embodiments with Human Experience

    🔥 1762026-10-19深く読むarXiv 原文
  16. 16

    BizBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business

    🔥 1692026-10-14深く読むarXiv 原文
  17. 17

    OR-License: Evaluating LLM Agents as Real-World Operations Research Practitioners

    🔥 1672026-10-16深く読むarXiv 原文
  18. 18

    PAR: Progress-Aligned Recurrence for Length Generalization in State Tracking

    🔥 1472026-10-20深く読むarXiv 原文
  19. 19

    Learning to Think and Explore in 3D World

    🔥 1442026-10-15深く読むarXiv 原文
  20. 20

    MJev-Spatial: System One Spatial Intelligence via Native Attention Matching

    🔥 1412026-10-15深く読むarXiv 原文