@inproceedings{chen-etal-2025-advancing,
    title = "Advancing General Multimodal Capability of Vision-language Models with Pyramid-descent Visual Position Encoding",
    author = "Chen, Zhanpeng  and
      Li, Mingxiao  and
      Chen, Ziyang  and
      Du, Nan  and
      Li, Xiaolong  and
      Zou, Yuexian",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/acl25-workshop-ingestion/2025.findings-acl.327/",
    pages = "6324--6341",
    ISBN = "979-8-89176-256-5"
}