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 and 3 more
Tsinghua-LeapLab
In latest · #45 Added on 2026-10-21
One-line takeaway
Finds latent world-action models lose the generalisation benefits of explicitly generating future frames at test time.
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。
Read on arXiv PDF Hugging Face discussion Code Project page
Topics & disciplines
More on Robotics & embodied AI
- 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
About this data
Metadata from the arXiv API (verified); upvotes from Hugging Face Daily Papers; citations from Semantic Scholar. Last refreshed 2026-10-22.
The takeaway is written by AIMap from the abstract; the abstract itself is not reproduced — read the original.