RoboStream: Weaving Spatio-Temporal Reasoning with Memory in Vision-Language Models for Robotics

作者：Yuzhi Huang, ♠ Jie Wu, Weijue Bu, Ziyi Xiong, Gaoyang Jiang, Ye Li, Kangye Ji, Shuzhao Xie, Yue Huang, Chenglei Wu, Jingyan Jiang, Zhi Wang · 单位：Shenzhen International Graduate School, Tsinghua University, China University of Mining and Technology, Shenzhen Technology University, Huazhong University of Science and Technology, Xiamen University · 会议/期刊：arXiv · 日期：2026-03-13 · 来源：High-Level Structured Planning / 3D Representation-based Planning / Point Cloud