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
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
It is shown that ZWM can be learned from the first-person experience of a single child, rapidly generating competence across multiple physical understanding benchmarks, and shows progressive, staged emergence of capacities during learning and builds brain-like internal representations.
Khai Loong Aw, Klemen Kotar, Wanhee Lee et al.· arXiv.org· 6 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
