VLA Models Are More Generalizable Than You Think: Revisiting Physical and Spatial Modeling

作者：Weiqi Li, Quande Zhang, Ruifeng Zhai, Liang Lin, Guangrun Wang · 单位：Sun Yat-sen University, Guangdong Key Laboratory of Big Data Analysis and Processing, X-Era AI Lab · 会议/期刊：arXiv · 日期：2025-12-02 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models for Generalization / Environment/Language Changes