作者：Yuxiang Lu, Zhe Liu, Xianzhe Fan, Zhenya Yang, Jinghua Hou, Junyi Li, Kaixin Ding, Hengshuang Zhao · 单位：The University of Hong Kong, ACE Robotics · 会议/期刊：arXiv · 日期：2026-03-19 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Efficiency / Inference Acceleration
