@inproceedings{li-etal-2024-enhanced,
    title = "Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data",
    author = "Li, Yanda  and
      Zhang, Chi  and
      Yu, Gang  and
      Yang, Wanqi  and
      Wang, Zhibin  and
      Fu, Bin  and
      Lin, Guosheng  and
      Shen, Chunhua  and
      Chen, Ling  and
      Wei, Yunchao",
    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/fix-sig-urls/2024.findings-acl.864/",
    doi = "10.18653/v1/2024.findings-acl.864",
    pages = "14512--14531"
}