作者：Hao Li, Ziqin Wang, Zi-han Ding, Shuai Yang, Yilun Chen, Yang Tian, Xiaolin Hu, Tai Wang, Dahua Lin, Feng Zhao, Si Liu, Jiangmiao Pang · 单位：Laboratory, Beihang University, Nanyang Technological University, Zhejiang, University, Tsinghua University, The Chinese University of Hong Kong · 会议/期刊：ICLR 2026 · 日期：2026-02-10 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Auxiliary Tasks - Visual Goal Extraction
