Skip to main content
Search

# SURE

1 related articles

Subscribe to updates
  1. arXiv

    Robot demos no longer need frame-by-frame matching: SURE hits 97.0% average success on LIBERO with a fifth of the training steps

    In robot manipulation demonstrations, one task often admits several feasible poses and execution speeds, yet pointwise supervision treats each demonstrated action as the single exact target. SURE adds a lightweight transposed-convolutional probabilistic action decoder to an OpenVLA-7B backbone to capture spatial uncertainty among neighboring action bins, and pairs it with Soft-DTW alignment supervision that tolerates local timing differences between demonstrations. On LIBERO it reaches 97.0% average success after 10k training steps, above the 94.3% of OpenVLA-OFT trained for 50k steps; it averages 72.2% on five RoboTwin 2.0 tasks and 57.5% on six real-world tasks.

You’re all caught up