@inproceedings{ou-etal-2024-lossless,
    title = "Lossless Acceleration of Large Language Model via Adaptive N-gram Parallel Decoding",
    author = "Ou, Jie  and
      Chen, Yueming  and
      Tian, Prof.",
    editor = "Yang, Yi  and
      Davani, Aida  and
      Sil, Avi  and
      Kumar, Anoop",
    booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 6: Industry Track)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2024.naacl-industry.2/",
    doi = "10.18653/v1/2024.naacl-industry.2",
    pages = "10--22"
}