DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos (opens in new tab)

arXiv:2602.06949v1 Announce Type: cross Abstract: Being able to simulate the outcomes of actions in varied environments will revolutionize the development of generalist agents at scale. However, modeling these world dynamics, especially for dexterous robotics tasks, poses significant challenges due to limited data coverage and scarce action labels. As an endeavor towards this end, we introduce DreamDojo, a foundation world model that learns diverse interactions and dexterous controls from 44...