Cross-Embodiment Causal Transfer from Human Videos to Robot Manipulation
CBST (Causal-Beam-Guided Subtask Transfer) transfers cross-embodiment knowledge from human manipulation videos to robot world-action models. It learns manipulation-related representations from human videos, grounds them into task-level semantic variables using robot demonstrations, then uses causal-beam constraints to select context-dependent retained dependencies. These semantic conditions let the robot generate actions from its own observations without human–robot motion correspondence. Experiments show improved task success over world-action model baselines.
