@inproceedings{zhu-etal-2026-visual,
    title = "When Does Visual Generation Help Visual Understanding in Unified Multimodal Models?",
    author = "Zhu, Yubo  and
      Kan, Zhehan  and
      Yang, Jingyi  and
      Chen, Miaolin  and
      Xing, Jinbo  and
      Zhu, Kai  and
      Wang, Zijian  and
      Zhong, Sheng  and
      Tong, Wei",
    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.383/",
    pages = "8749--8788",
    ISBN = "979-8-89176-459-0"
}