Article

ARPG scales dexterous manipulation via action representation pretraining

ARPG proposes separating action representation learning from action generation: first pretrain an action representation encoder on large-scale human manipulation data, then freeze that encoder and train a 130M-parameter generative backbone in its representation space to learn task-conditioned action distributions.

Part of the event: ARPG: Action Representation Pretraining and Generation

This page provides a summary and source link only.