One-Policy-Fits-All: Geometry-Aware Action Latents for Cross-Embodiment Manipulation

作者：Juncheng Mu, Sizhe Yang, Hojin Bae, Feiyu Jia, Qingwei Ben, Boyi Li, Huazhe Xu, Jiangmiao Pang · 单位：Shanghai AI Laboratory, Tsinghua University, The Chinese University of Hong Kong, University of Science and Technology of China, NVIDIA · 会议/期刊：ICRA 2026 · 日期：2026-03-15 · 来源：Bottlenecks / Generalization / Cross-Embodiment Generalization