Outcome-Conditioned End-Effector Geometry Across Vision-Language-Action Policies
Vision-language-action (VLA) policies solve the same manipulation task through different action interfaces, but task success alone does not establish whether their physical executions agree. We study cross-policy end-effector geometry in 15,000 closed-loop LIBERO rollouts from four policies. The primary clean-condition...
Xing-Yu Lin, Zhuang Li, Zhong-Run Wu et al.
· 0 citations