arXiv 2609.34981 · cs.CV · 2026-09-28
What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling
Renping Zhou, Zanlin Ni, Zihao Fan, Guohao Fu, Zeyu Liu, Hao Shi, Jie Zhang, Chi Bene Chen 等 11 人
Tsinghua-LeapLab
在最新榜 #45 本站收录于 2026-10-21
一句话要点
实证发现：只在潜空间预测未来的世界-动作模型会丢掉泛化优势，显式生成未来画面仍有价值。
Finds latent world-action models lose the generalisation benefits of explicitly generating future frames at test time.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库 项目页
主题与学科
同主题：机器人与具身
- Has GPT-6-Astra Achieved Embodied Intelligence? ▲459
- In-Context Learning for Robots: Methods and Applications ▲388
- HexaShell: A Thin Harness for Exploring the Limits of VLM Agents as Robot Coding Agents ▲313
- GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives ▲310
- Ropedia W0: Scaling Loco-Manipulation World Models across Embodiments with Human Experience ▲179
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-22。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。