Audio-VLA: Adding Contact Audio Perception to Vision-Language-Action Model for Robotic Manipulation

作者：Xiangyi Wei, Haotian Zhang, Xinyi Cao, Siyu Xie, Weifeng Ge, Yang Li, Changbo Wang · 单位：School of Computer Science and Technology, East China Normal University, School of Data Science and Engineering, East China Normal University, School of Software Engineering, East China Normal University, School of Computer Science, Fudan University · 会议/期刊：arXiv · 日期：2025-11-13 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / Audio-based Action Models