Awesome Robotics Manipulation · full_paper

ActiveVLA: Injecting Active Perception into Vision-Language-Action Models for Precise 3D Robotic Manipulation

作者：Zhenyang Liu, Yongchong Gu, Yikai Wang, Xiangyang Xue, Yanwei Fu · 单位：Fudan University Shanghai Innovation Institute Nanyang Technological University · 会议/期刊：arXiv · 日期：2026-01-13 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 3D Vision Language Action Models

三维表征视觉语言动作感知机器人学习操作
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Code
ActiveVLA: Injecting Active Perception into Vision-Language-Action Models for Precise 3D Robotic Manipulation figure
AlphaXiv 中文论文页面（可滚动查看）