Skip to main content
Search

Haisen He

1 related articles

Subscribe to updates
  1. arXiv

    Robots learn to act from the present by training on later frames: HSD reaches 98.50% on LIBERO and lifts real-robot success from 24.17% to 37.50%

    A robot must choose an action before it sees the outcome, while a demonstration records what followed the move. Hindsight Self-Distillation (HSD) trains a teacher that sees both current and later frames to pass two targets to a student, its denoising action predictions and its visual summaries, and the student reads only current frames at deployment. The student averages 98.50% success on LIBERO and 92.31% on RoboTwin 2.0, and across six real-world bimanual tasks success rises from 24.17% with Fast-WAM to 37.50%.

You’re all caught up