WorldBridge splits video prediction from action: one labeled demo per new task lifts success from 55.90% to 70.70%
WorldBridge separates video prediction and action generation into two experts and uses structured attention to route predicted future frames into actions, then tests what video and action supervision each contribute on RoboTwin 2.0. With only in-distribution video-action supervision, out-of-distribution task success is 25.07%; adding videos of those tasks without action labels raises it to 55.90%, and one action-labeled demonstration per task raises it to 70.70%. Under the full data setting, WorldBridge reaches 96.23% average success on RoboTwin 2.0.