AugVLA-3D: Depth-Driven Feature Augmentation for Vision-Language-Action Models

作者：Zhifeng Rao, Wenlong Chen, Lei Xie, Xia Hua, Dongfu Yin, Zhen Tian, F. Richard Yu · 单位：Guangdong Laboratory of Artificial Intelligence and Digital Economy, School of Communication and Information Engineering, Shanghai Uni- versity, Shanghai, China, School of Information Technology, Carleton University, Ottawa, Canada · 会议/期刊：arXiv · 日期：2026-02-11 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 3D Vision Language Action Models