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
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
World-action models (WAM) predict future states to guide robot actions, enabling learning from both action-free video and action-labeled interaction. Most inherit pretrained video generators, leaving WAM pretraining and scaling underexplored. We introduce Genie Envisioner Act 2.0 (GE-Act 2.0), a world-action model whos...
Ren-Hang Liu, Wen-Zhi Zhao, Zhuo Yang et al.· 7 citations· ⚡4
BEE is introduced, an intervention-adaptive framework for real-world RL on a frozen VLA that lets the policy go BEyond Expert imitation, and a Correction Model predicts how a human would correct a given VLA proposal and how consistent the correction is along each action dimension.
Wei-Hui Zhao, Xiao Yan, Zu-Nian Wan et al.· 0 citations
Genie Envisioner Act 2.0 (GE-Act 2.0) is introduced, a world-action model whose trainable generative and action components are all initialized from scratch on manipulation data, and its components are jointly trained with knowledge-aligned selective optimization (KASO), which reduces mismatched supervision.
AgiBot Research Team, Ren-Hang Liu, Wen-Zhi Zhao et al.· 4 citations· ⚡1
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.