@article{towardbuildinggeneralfoundationmodelsfor,
  title = {Toward Building General Foundation Models for Language, Vision, and Vision-Language Understanding Tasks},
  author = {Xinsong Zhang and Yan Zeng and Jipeng Zhang and Hang Li},
  year = {2023},
  eprint = {2301.05065},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2301.05065v2},
}