Skip to main content
Search

Jiaming Tang

1 related articles

Subscribe to updates
  1. arXiv

    A 27B open-weight model learns to run robots in simulation: 18 of 30 real dual-arm trials succeed, base model none

    The open-weight reasoning model Qwen3.8-27B barely succeeded at robot tasks before, reaching 1.6% on LIBERO. The researchers built the PEAR training engine and trained it with robot-use reinforcement learning in simulation to output end-effector poses directly, without demonstrations or perception tools. After training it reaches 74.4% on LIBERO and succeeds in 18 of 30 trials on a real dual-arm robot it never saw, against none for the base model.

You’re all caught up