@article{audiovlaaddingcontactaudioperceptiontovi,
  title = {Audio-VLA: Adding Contact Audio Perception to Vision-Language-Action Model for Robotic Manipulation},
  author = {Xiangyi Wei and Haotian Zhang and Xinyi Cao and Siyu Xie and Weifeng Ge and Yang Li and Changbo Wang},
  year = {2025},
  eprint = {2511.09958},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2511.09958},
}