@inproceedings{mmdiffusionlearningmultimodaldiffusion,
  title = {MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation},
  author = {Ludan Ruan and Yiyang Ma and Huan Yang and Huiguo He and Bei Liu and Jianlong Fu and Nicholas Jing Yuan and Qin Jin and Baining Guo},
  year = {2022},
  booktitle = {CVPR 2023 1},
  eprint = {2212.09478},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2212.09478v2},
}