@inproceedings{suri-etal-2025-visdom,
    title = "{V}is{D}o{M}: Multi-Document {QA} with Visually Rich Elements Using Multimodal Retrieval-Augmented Generation",
    author = "Suri, Manan  and
      Mathur, Puneet  and
      Dernoncourt, Franck  and
      Goswami, Kanika  and
      Rossi, Ryan A.  and
      Manocha, Dinesh",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Ingest-2025-COMPUTEL/2025.naacl-long.310/",
    pages = "6088--6109",
    ISBN = "979-8-89176-189-6"
}