@inproceedings{ke-etal-2024-dl,
    title = "{DL}-{QAT}: Weight-Decomposed Low-Rank Quantization-Aware Training for Large Language Models",
    author = "Ke, Wenjing  and
      Li, Zhe  and
      Li, Dong  and
      Tian, Lu  and
      Barsoum, Emad",
    editor = "Dernoncourt, Franck  and
      Preo{\c{t}}iuc-Pietro, Daniel  and
      Shimorina, Anastasia",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track",
    month = nov,
    year = "2024",
    address = "Miami, Florida, US",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2024.emnlp-industry.10/",
    doi = "10.18653/v1/2024.emnlp-industry.10",
    pages = "113--119"
}