@inproceedings{wang-etal-2024-compression,
    title = "When Compression Meets Model Compression: Memory-Efficient Double Compression for Large Language Models",
    author = "Wang, Weilan  and
      Mao, Yu  and
      Dongdong, Tang  and
      Hongchao, Du  and
      Guan, Nan  and
      Xue, Chun Jason",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Author-page-Marten-During-lu/2024.findings-emnlp.988/",
    doi = "10.18653/v1/2024.findings-emnlp.988",
    pages = "16973--16983"
}