@misc{lyu2023macaw,
  title={Macaw-LLM: Multi-Modal Language Modeling with Image, Audio, Video, and Text Integration},
  author={Chenyang Lyu and Minghao Wu and Longyue Wang and Xinting Huang and Bingshuai Liu and Zefeng Du and Shuming Shi and Zhaopeng Tu},
  year={2023},
  eprint={2306.09093},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2306.09093}
}