@inproceedings{wang-etal-2024-world,
    title = "World to Code: Multi-modal Data Generation via Self-Instructed Compositional Captioning and Filtering",
    author = "Wang, Jiacong  and
      Wu, Bohong  and
      Jiang, Haiyong  and
      Xun, Zhou  and
      Xiao, Xin  and
      Guo, Haoyuan  and
      Xiao, Jun",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.emnlp-main.265/",
    doi = "10.18653/v1/2024.emnlp-main.265",
    pages = "4608--4623"
}