@inproceedings{dong-etal-2026-utilize,
    title = "How to Utilize Complementary Vision-Text Information for 2{D} Structure Understanding",
    author = "Dong, Jiancheng  and
      Jia, Pengyue  and
      Xu, Derong  and
      Cheng, Jiawei  and
      Peng, Jingyu  and
      Zhang, Chao  and
      Liu, Bowen  and
      Sun, Xin  and
      Su, Lixin  and
      Wang, Shuaiqiang  and
      Yin, Dawei  and
      Zhao, Xiangyu",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-main.2081/",
    pages = "47398--47416",
    ISBN = "979-8-89176-459-0"
}