**摘要**
World-action models have emerged as a promising paradigm for robot manipulation, jointly modeling visual scene dynamics and actions to inject physical priors into policy learning. However, existing world-action models couple world prediction and action execution at the same temporal resolution, forcing the world branch to model near-term frame variations that are redundant and weakly informative.
👤 作者: Jisong Cai, Long Ling, Shiwei Chu, Zhongshan Liu, Jiayue Kang, Zhixuan Liang, Wenjie Xu, Yinan Mao, Weinan Zhang, Xiaokang Yang, Ru Ying, Ran Zheng, Yao Mu

---
🔗 **[AHA-WAM ：具有观察引导上下文路由的异步水平自适应世界动作建模](https://arxiv.org/abs/2606.09811v1)**

> AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing
🏷️ 来源: ArXiv cs.AI
⏱️ 2026-06-09 14:01