Awesome Robotics Manipulation · full_paper

StreamingVLA: Streaming Vision-Language-Action Model with Action Flow Matching and Adaptive Early Observation

作者：Yiran Shi, Dongqi Guo, Tianchen Zhao, FengGao, Liangzhi Shi, Chao Yu, ZhiJian Mo, Qihua Xiao, XiaoShuai Peng, Qingmin Liao, Yu Wang · 单位：Tsinghua University, Lenovo Group Ltd · 会议/期刊：arXiv · 日期：2026-03-30 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Efficiency / Inference Acceleration

视觉语言动作流匹配机器人学习
新标签打开 AlphaXiv新标签打开 Paper
StreamingVLA: Streaming Vision-Language-Action Model with Action Flow Matching and Adaptive Early Observation figure
AlphaXiv 中文论文页面（可滚动查看）