@article{reformulatingvisionlanguagefoundation,
  title = {Reformulating Vision-Language Foundation Models and Datasets Towards Universal Multimodal Assistants},
  author = {Tianyu Yu and Jinyi Hu and Yuan YAO and Haoye Zhang and Yue Zhao and Chongyi Wang and Shan Wang and Yinxv Pan and Jiao Xue and Dahai Li and Zhiyuan Liu and Hai-Tao Zheng and Maosong Sun},
  year = {2023},
  eprint = {2310.00653},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2310.00653v1},
}