@inproceedings{wang-etal-2025-inference,
    title = "Inference Compute-Optimal Video Vision Language Models",
    author = "Wang, Peiqi  and
      Peng, ShengYun  and
      Zhang, Xuewen  and
      Yu, Hanchao  and
      Yang, Yibo  and
      Huang, Lifu  and
      Liu, Fujun  and
      Wang, Qifan",
    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/ingestion-acl-25/2025.acl-long.117/",
    pages = "2345--2374",
    ISBN = "979-8-89176-251-0"
}