@article{unifiedmodelforimagevideoaudioand,
  title = {UnIVAL: Unified Model for Image, Video, Audio and Language Tasks},
  author = {Mustafa Shukor and Corentin Dancette and Alexandre Rame and Matthieu Cord},
  year = {2023},
  eprint = {2307.16184},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2307.16184v2},
}