新研究推进自动驾驶和机器人领域的世界行动模型

报道来源 [3]

1. arXiv cs.CV TIER_1 English(EN) · Tianze Xia, Lijun Zhou, Kaixin Xiong, Jingfeng Yao, Yu Zhu, Zhenxin Zhu, Bing Wang, Guang Chen, Hangjun Ye, Wenyu Liu, Haiyang Sun, Xinggang Wang · 2026-06-29 04:00

   ReWorld: Learning Better Representations for World Action Models

   arXiv:2606.27504v1 Announce Type: new Abstract: World Action Models (WAMs) model future environment evolution under action conditioning, offering a scalable paradigm for autonomous driving. However, existing approaches focus largely on model architecture design, and how a WAM can…

2. arXiv cs.CV TIER_1 English(EN) · Kai Wang, Zhaopeng Gu, Yixiang Chen, Yuan Xu, Qisen Ma, Peng Su, Zhaowen Li, Yan Huang, Liang Wang · 2026-06-29 04:00

   DIM-WAM: World-Action Modeling with Diverse Historical Event Memory

   arXiv:2606.27677v1 Announce Type: cross Abstract: World-action models have shown promising robot-manipulation performance by jointly predicting future visual states and actions. However, existing methods mainly rely on short-term history and short-horizon future prediction, which…

3. arXiv cs.CV TIER_1 English(EN) · Liang Wang · 2026-06-26 03:17

   DIM-WAM：具有多样化历史事件记忆的世界动作建模

   World-action models have shown promising robot-manipulation performance by jointly predicting future visual states and actions. However, existing methods mainly rely on short-term history and short-horizon future prediction, which is insufficient for long-horizon tasks whose corr…