In long-horizon manipulation, a robot may need to take different actions under identical observations, depending on task progress and the outcomes of earlier attempts. We refer to this ambiguity as decision aliasing. Resolving it requires the policy to maintain memory of its execution history. To reduce the cost of pro...
Xuan-Zhuo Liu, Chuan-Kang Li, Mao-Qing Yao et al.· 0 citations
As egocentric video becomes increasingly available for embodied learning, an important research question is how to turn this low-cost, scalable source of data into robot manipulation capabilities. Egocentric videos naturally provide rich context for high-level task understanding, while real-robot demonstrations with wr...
Ke-Ru Zhou, Zhi-Rui Fang, Xin-Run Xu et al.· 0 citations
This work introduces Rollback, a policy improvement paradigm that turns world models from passive simulators into counterfactual engines, and builds a scalable training system that unifies distributed world-model search with asynchronous real-robot execution, forming a self-reinforcing cycle.
Jia-Yi Luo, Yang Zhang, Li-Liang Chen et al.· 0 citations
Genie Sim PanoWorld is presented, a two-stage feed-forward pipeline that bridges generation and reconstruction via an explicit, trajectory-controllable panoramic video, and outperforms geometry-conditioned baselines in both panoramic video generation and downstream 3D reconstruction.
Yongxin Su, Linjie Hou, Feng Wang et al.· arXiv.org· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.