Jeongeun Park

World-action pretraining now learns from task-paired human demonstrations: the model sees one demonstration's video and actions and predicts another demonstration's actions and future frames, separating scene appearance from task interaction. Previously, within-video next-frame prediction let context and target share scene, viewpoint and collection source, so the model could rely on appearance cues instead of transferable interactions. On MimicDroid, cross-video pretraining raises Cosmos Policy's average success from 40.9% to 68.3% and the unseen-layout level from 18.3% to 40.8%, without matched robot demonstrations.

World-action pretraining now learns from task-paired human demonstrations: the model sees one demonstration's video and actions and predicts another demonstration's actions and future frames, separating scene appearance from task interaction. Previously, within-video next-frame prediction let context and target share scene, viewpoint and collection source, so the model could rely on appearance cues instead of transferable interactions. On MimicDroid, cross-video pretraining raises Cosmos Policy's average success from 40.9% to 68.3% and the unseen-layout level from 18.3% to 40.8%, without matched robot demonstrations.