作者：Xuanran Zhai, Zekai Huang, Longyan Wu, Qianyou Zhao, Qiaojun Yu, Jieji Ren, Ce Hao, Harold Soh · 单位：National University of Singapore, Beijing Zhongguancun Academy, Shanghai Innovation Institute, Shanghai AI Laboratory, Shanghai Jiao Tong University, Fudan University, Smart Systems Institute, NUS · 会议/期刊：arXiv · 日期：2026-03-04 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Auxiliary Tasks - Text Goal Extraction
