UBTECH details Thinker-WM, a world model unifying video, depth and robot actions

UBTECH says its Thinker-WM world model encodes RGB video, metric depth and robot actions in one shared representation, and that it ranks first on three embodied world model benchmarks in its own evaluation.

On WorldOlympiad it scored 0.740 overall, and on EWMBench it reported a total of 4.66. The model was trained on about 30,000 hours of human video, real robot data and simulation, and a technical paper is available on arXiv.