MEKAWIRE
ExpertarXiv

Fast-VLA: You Only Think Once for Robot Manipulation

Kehong Gong, Guanli Hou, Xiaoxu Zheng, Qi Wang, Mingxi Xu, Anbang Zhai, Xiaoyu He, Mingyuan Zhang, Michael Bi Mi
Original paper Read the full paper (PDF)
From the abstract

Vision-language-action (VLA) policies commonly place a multi-billion-parameter model inside the feedback loop, repeatedly recomputing task context whenever they predict a new action chunk. Yet task understanding changes far more slowly than the robot state.

From the abstract. Our summary is in progress.