Preprint
Sep 2026
PhysBrain 1.5: From Vision-Language Models to Physical Foundation Models
Qualitative examples show the PhysBrain 1.5 model's ability to produce end-effector trajectories and predict future scenes through spatially aligned RGB, depth, and robot-mask outputs.
DeepCybo Team, Yue Bin, Hai-Peng Cao et al.
· 0 citations