← Back to Benchmarks
simmediumvision-robotmetric · varies

DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos

Description

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 44k hours of egocentric human videos. Our data mixture r

Source

http://arxiv.org/abs/2602.06949v1