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
The results establish goal-conditioned state comparison as an explicit formulation of egocentric spatiotemporal reasoning for task-progress understanding as part of a unified framework for diagnosing and improving order-robust task-progress understanding.
Xiao-Da Yang, Can Wang, Yu-Xiang Liu et al.· arXiv.org· 0 citations
OPIS is introduced, an input-grounded benchmark that strictly anchors the assessment to a fixed set of object instances from the initial observation for evaluating multi-object memory in video world models and demonstrates that preserving the particular object instances in the input is considerably harder than generati...
Hao Wang, Tao Yu, Liu-Zhou Zhang et al.· arXiv.org· 1 citation
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
Across in-domain and distribution-shifted settings, allocating additional test-time computation substantially improves next-subtask prediction accuracy, and these gains translate into higher closed-loop success on long-horizon robot manipulation tasks.