@inproceedings{zhao-etal-2026-vincicoder,
    title = "{V}inci{C}oder: Unifying Multimodal Code Generation via Coarse-to-fine Visual Reinforcement Learning",
    author = "Zhao, Xuanle  and
      Jiang, Deyang  and
      Zeng, Zhixiong  and
      Chen, Lei  and
      Yang, Haoyue  and
      Qiu, Haibo  and
      Huang, Jing  and
      Zhong, Yufeng  and
      Zheng, Liming  and
      Cao, Yilin  and
      Ma, 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.2266/",
    pages = "51529--51544",
    ISBN = "979-8-89176-459-0"
}