@inproceedings{gao-etal-2026-scaling,
    title = "Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding",
    author = "Gao, Sensen  and
      Zhao, Shanshan  and
      Jiang, Xu  and
      Duan, Lunhao  and
      Chng, Yong Xien  and
      Chen, Qing-Guo  and
      Luo, Weihua  and
      Zhang, Kaifu  and
      Bian, Jia-Wang  and
      Gong, Mingming",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.204/",
    pages = "4458--4489",
    ISBN = "979-8-89176-390-6"
}