World-action models jointly learn robot policies and predict future observations, making the representation space an interface between control and prediction. We study the design of this space through controlled comparisons, finding that neither reconstruction fidelity nor pre-trained perceptual features alone ensure e...
Hao-Yi Jiang, Liu Liu, Xin-Jiang Wang et al.· 1 citation
It is argued that instruction-following evaluation should be text-indispensable: multiple actions should be visually and physically plausible, while only one should be consistent with the language instruction.
Mengao Zhao, Ziang Li, Chaodong Huang et al.· 2 citations
EmbodiedGen V2 is established as scalable simulation infrastructure for training, evaluating, and deploying embodied policies, and is established as a generative, editable, and reusable simulation pipeline.
Xin-Jie Wang, Liu Liu, Taojun Ding et al.· arXiv.org· 3 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.