@inproceedings{chai-etal-2026-state,
    title = "State-Conditioned Visual Evidence Retrieval for Fine-Grained Perception in Document Vision-Language Models",
    author = "Chai, Mingxu  and
      Liu, Chenyu  and
      Shen, Ziyu  and
      Zhang, Jiazheng  and
      Zhang, Kaidi  and
      Kang, Jihua  and
      Gui, Tao  and
      Zhang, Qi",
    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.868/",
    pages = "20078--20095",
    ISBN = "979-8-89176-459-0"
}