PEAfowl: Perception-Enhanced Multi-View Vision-Language-Action for Bimanual Manipulation

作者：Qingyu Fan, Zhaoxiang Li, Yi Lu, Wang Chen, Qiu Shen, Xiao-xiao Long, Yinghao Cai, Tao Lu, Shuo Wang, Xun Cao · 单位：Institute of Automation, Chinese Academy of Sciences, Nanjing University · 会议/期刊：arXiv · 日期：2026-01-25 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 3D Vision Language Action Models