@article{minmoamultimodallargelanguagemodelfor,
  title = {MinMo: A Multimodal Large Language Model for Seamless Voice Interaction},
  author = {Qian Chen and Yafeng Chen and Yanni Chen and Mengzhe Chen and Yingda Chen and Chong Deng and Zhihao Du and Ruize Gao and Changfeng Gao and Zhifu Gao and Yabin Li and Xiang Lv and Jiaqing Liu and Haoneng Luo and Bin Ma and Chongjia Ni and Xian Shi and Jialong Tang and Hui Wang and Hao Wang and Wen Wang and Yuxuan Wang and Yunlan Xu and Fan Yu and Zhijie Yan and Yexin Yang and Baosong Yang and Xian Yang and Guanrou Yang and Tianyu Zhao and Qinglin Zhang and Shiliang Zhang and Nan Zhao and Pei Zhang and Chong Zhang and Jinren Zhou},
  year = {2025},
  eprint = {2501.06282},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2501.06282v1},
}