@inproceedings{zhao-etal-2026-vtcbench,
    title = "{VTCB}ench: Can Vision-Language Models Understand Long Contexts with Vision-Text Compression?",
    author = "Zhao, Hongbo  and
      Wang, Meng  and
      Zhu, Fei  and
      Liu, Wenzhuo  and
      Ni, Bolin  and
      Zeng, Fanhu  and
      Meng, Gaofeng  and
      Zhang, Zhaoxiang  and
      Liu, Cheng-Lin",
    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.145/",
    pages = "3349--3379",
    ISBN = "979-8-89176-459-0"
}