Any3D-VLA: Enhancing VLA Robustness via Diverse Point Clouds

作者：Xianzhe Fan Shengliang Deng Xiaoyang Wu, Yuxiang Lu, Zhuoling Li, Mi Yan Yujia Zhang, Zhizheng Zhang, He Wang Hengshuang Zhao · 单位：School of Computing and Data Science, The University of Hong Kong, Hong Kong SAR, China · 会议/期刊：arXiv · 日期：2026-01-31 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 3D Vision Language Action Models