@inproceedings{dong-etal-2025-scalable,
    title = "Scalable Vision Language Model Training via High Quality Data Curation",
    author = "Dong, Hongyuan  and
      Kang, Zijian  and
      Yin, Weijie  and
      LiangXiao, LiangXiao  and
      ChaoFeng, ChaoFeng  and
      Jiao, Ran",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.acl-long.1595/",
    pages = "33272--33293",
    ISBN = "979-8-89176-251-0"
}