@inproceedings{akhauri-etal-2024-shadowllm,
    title = "{S}hadow{LLM}: Predictor-based Contextual Sparsity for Large Language Models",
    author = "Akhauri, Yash  and
      AbouElhamayed, Ahmed F.  and
      Dotzel, Jordan  and
      Zhang, Zhiru  and
      Rush, Alexander M.  and
      Huda, Safeen  and
      Abdelfattah, Mohamed S.",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.emnlp-main.1068/",
    doi = "10.18653/v1/2024.emnlp-main.1068",
    pages = "19154--19167"
}