@inproceedings{mao-etal-2024-visually,
    title = "Visually Guided Generative Text-Layout Pre-training for Document Intelligence",
    author = "Mao, Zhiming  and
      Bai, Haoli  and
      Hou, Lu  and
      Shang, Lifeng  and
      Jiang, Xin  and
      Liu, Qun  and
      Wong, Kam-Fai",
    editor = "Duh, Kevin  and
      Gomez, Helena  and
      Bethard, Steven",
    booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.naacl-long.264/",
    doi = "10.18653/v1/2024.naacl-long.264",
    pages = "4713--4730"
}