GitHub - bytedance/SALMONN: SALMONN family: A suite of advanced multi-modal LLMs

The SALMONN model family consists of a series of advanced multi-modal large language models. For more details, please refer to the corresponding branches.

@inproceedings{
  sun2025videosalmonno1,
  title={{video-SALMONN-o1}: Reasoning-enhanced Audio-visual Large Language Model},
  author={Guangzhi Sun, Yudong Yang, Jimin Zhuang, Changli Tang, Yixuan Li, Wei Li, Zejun MA, Chao Zhang},
  booktitle={ICML},
  year={2025}
}

@article{tang2025video,
    title={{video-SALMONN 2: Captioning-Enhanced Audio-Visual Large Language Models}}, 
    author={Changli Tang and Yixuan Li and Yudong Yang and Jimin Zhuang and Guangzhi Sun and Wei Li and Zejun Ma and Chao Zhang},
    journal={arXiv preprint arXiv:2506.15220},
    year={2025},
}

@inproceedings{wang2024enabling,
  title={Enabling Auditory Large Language Models for Automatic Speech Quality Evaluation},
  author={Wang, Siyin and Yu, Wenyi and Yang, Yudong and Tang, Changli and Li, Yixuan and Zhuang, Jimin and Chen, Xianzhao and Tian, Xiaohai and Zhang, Jun and Sun, Guangzhi and others},
  booktitle={Proc. ICASSP},
  address={Hyderabad},
  year={2025}
}

@inproceedings{wang2024enabling,
  title={QualiSpeech: A Speech Quality Assessment Dataset with Natural Language Reasoning and Descriptions},
  author={Wang, Siyin and Yu, Wenyi and Chen, Xianzhao and Tian, Xiaohai and Zhang, Jun and Sun, Guangzhi and others},
  booktitle={Proc. ACL},
  address={Vienna},
  year={2025}
}

@inproceedings{
  sun2024videosalmonn,
  title={video-{SALMONN}: Speech-Enhanced Audio-Visual Large Language Models},
  author={Guangzhi Sun and Wenyi Yu and Changli Tang and Xianzhao Chen and Tian Tan and Wei Li and Lu Lu and Zejun MA and Yuxuan Wang and Chao Zhang},
  booktitle={Forty-first International Conference on Machine Learning},
  year={2024},
  url={https://openreview.net/forum?id=nYsh5GFIqX}
}

@inproceedings{
  tang2024salmonn,
  title={SALMONN: Towards Generic Hearing Abilities for Large Language Models},
  author={Changli Tang and Wenyi Yu and Guangzhi Sun and Xianzhao Chen and Tian Tan and Wei Li and Lu Lu and Zejun MA and Chao Zhang},
  booktitle={The Twelfth International Conference on Learning Representations},
  year={2024},
  url={https://openreview.net/forum?id=14rn7HpKVk}
}