100 short videos (at most 180 s), each with one multiple-choice question and the responses of five open-source video reasoning models (Video-Thinker, Open-o3 Video, VideoChat-R1, VideoChat-R1.5, ...
LIBERO spatial, object, goal and 10 suites: 1,695 successful replay episodes, 274,008 frames, 10 Hz. Derived from LIBERO demonstrations for layout-conditioned robot policy training. GT and DA3 share ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results