@inproceedings{wang-etal-2024-ladic,
    title = "{L}a{D}i{C}: Are Diffusion Models Really Inferior to Autoregressive Counterparts for Image-to-Text Generation?",
    author = "Wang, Yuchi  and
      Ren, Shuhuai  and
      Gao, Rundong  and
      Yao, Linli  and
      Guo, Qingyan  and
      An, Kaikai  and
      Bai, Jianhong  and
      Sun, Xu",
    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/add-emnlp-2024-awards/2024.naacl-long.373/",
    doi = "10.18653/v1/2024.naacl-long.373",
    pages = "6699--6715"
}