@inproceedings{sun-etal-2023-fusion, title = "Fusion or Defusion? Flexible Vision-and-Language Pre-Training", author = "Sun, Rongyi and Li, Ziran and Ding, Yifeng and Wang, Qifan and Wang, Jingang and Zheng, Haitao and Wu, Wei and Xian, Yunsen", editor = "Rogers, Anna and Boyd-Graber, Jordan and Okazaki, Naoaki", booktitle = "Findings of the Association for Computational Linguistics: ACL 2023", month = jul, year = "2023", address = "Toronto, Canada", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2023.findings-acl.316/", doi = "10.18653/v1/2023.findings-acl.316", pages = "5105--5119" }