@inproceedings{li-etal-2025-commit,
    title = "{C}o{MMIT}: Coordinated Multimodal Instruction Tuning",
    author = "Li, Xintong  and
      Wu, Junda  and
      Yu, Tong  and
      Wang, Rui  and
      Wang, Yu  and
      Chen, Xiang  and
      Gu, Jiuxiang  and
      Yao, Lina  and
      McAuley, Julian  and
      Shang, Jingbo",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.582/",
    pages = "11533--11547",
    ISBN = "979-8-89176-332-6"
}