作者：Chengyang Li, Kaiyi Xiong, Yuan Xu, Lei Qian, Yizhou Wang, Wentao Zhu · 单位：Shanghai Jiao Tong University, Eastern Institute of Technology, Ningbo, Peking University, ShanghaiTech University · 会议/期刊：arXiv · 日期：2026-04-24 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Auxiliary Tasks - Visual Goal Extraction
