@inproceedings{wang-etal-2026-e2e,
    title = "{E}2{E}-{V}is{RAG}: End-to-End Visual Retrieval-Augmented Generation with Differentiable Retrieval",
    author = "Wang, Zehua  and
      Zhang, Zhaojin  and
      Weng, Xiaolong  and
      Chen, Yanzhi  and
      Xiong, Ying  and
      Tang, Buzhou",
    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.1030/",
    pages = "23670--23683",
    ISBN = "979-8-89176-459-0"
}