@inproceedings{liang-etal-2025-single, title = "Single-to-mix Modality Alignment with Multimodal Large Language Model for Document Image Machine Translation", author = "Liang, Yupu and Zhang, Yaping and Zhang, Zhiyang and Zhao, Yang and Xiang, Lu and Zong, Chengqing and Zhou, Yu", 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/acl25-workshop-ingestion/2025.acl-long.606/", pages = "12391--12408", ISBN = "979-8-89176-251-0" }