@inproceedings{zhang-etal-2026-multi-modal,
    title = "A Multi-Modal Recognition Framework for Ancient Books Integrating {D}o{RA}-{DPO} Text Recognition and {YOLO} Layout Analysis",
    author = "Zhang, Chaokun  and
      Wen, Xin  and
      Zhou, Tongtong",
    editor = "Sprugnoli, Rachele  and
      Passarotti, Marco",
    booktitle = "Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages ({LT}4{HALA} 2026) @ {LREC} 2026",
    month = may,
    year = "2026",
    address = "Palma, Mallorca (Spain)",
    publisher = "ELRA Language Resources Association (ELRA)",
    url = "https://aclanthology.org/2026.lt4hala-1.25/",
    doi = "10.63317/58pv4t9t8hmt",
    pages = "268--272"
}