@inproceedings{hu-etal-2025-mlwq,
    title = "{MLWQ}: Efficient Small Language Model Deployment via Multi-Level Weight Quantization",
    author = "Hu, Chun  and
      He, Junhui  and
      Wu, Shangyu  and
      He, Yuxin  and
      Xue, Chun Jason  and
      Li, Qingan",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.408/",
    pages = "8078--8088",
    ISBN = "979-8-89176-332-6"
}