@inproceedings{monteiro-etal-2024-xc,
    title = "{XC}-Cache: Cross-Attending to Cached Context for Efficient {LLM} Inference",
    author = "Monteiro, Joao  and
      Marcotte, {\'E}tienne  and
      Noel, Pierre-Andre  and
      Zantedeschi, Valentina  and
      Vazquez, David  and
      Chapados, Nicolas  and
      Pal, Christopher  and
      Taslakian, Perouz",
    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/add-emnlp-2024-awards/2024.findings-emnlp.896/",
    doi = "10.18653/v1/2024.findings-emnlp.896",
    pages = "15284--15302"
}