@inproceedings{zhang-etal-2024-visual-question,
    title = "Visual Question Decomposition on Multimodal Large Language Models",
    author = "Zhang, Haowei  and
      Liu, Jianzhe  and
      Han, Zhen  and
      Chen, Shuo  and
      He, Bailan  and
      Tresp, Volker  and
      Xu, Zhiqiang  and
      Gu, Jindong",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.findings-emnlp.107/",
    doi = "10.18653/v1/2024.findings-emnlp.107",
    pages = "1926--1949"
}