@inproceedings{xu-etal-2024-vision,
    title = "Vision-Flan: Scaling Human-Labeled Tasks in Visual Instruction Tuning",
    author = "Xu, Zhiyang  and
      Feng, Chao  and
      Shao, Rulin  and
      Ashby, Trevor  and
      Shen, Ying  and
      Jin, Di  and
      Cheng, Yu  and
      Wang, Qifan  and
      Huang, Lifu",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.findings-acl.905/",
    doi = "10.18653/v1/2024.findings-acl.905",
    pages = "15271--15342"
}