Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model

作者：Fuhao Li, Wenxuan Song, Han Zhao, Jingbo Wang, Pengxiang Ding, Donglin Wang, Long Zeng, B Haoang Li · 单位：The Hong Kong University of Science and Technology (Guangzhou), Tsinghua University, Westlake University, Zhejiang University South China University of Technology · 会议/期刊：ICLR 2026 · 日期：2025-10-14 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 3D Vision Language Action Models