@inproceedings{zhao-etal-2025-multimodal-foundation,
    title = "Can Multimodal Foundation Models Understand Schematic Diagrams? An Empirical Study on Information-Seeking {QA} over Scientific Papers",
    author = "Zhao, Yilun  and
      Wang, Chengye  and
      Li, Chuhan  and
      Cohan, Arman",
    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/display_plenaries/2025.findings-acl.957/",
    pages = "18598--18631",
    ISBN = "979-8-89176-256-5"
}