@inproceedings{zemlyanskiy-etal-2024-memory,
    title = "{MEMORY}-{VQ}: Compression for Tractable {I}nternet-Scale Memory",
    author = "Zemlyanskiy, Yury  and
      de Jong, Michiel  and
      Vilnis, Luke  and
      Ontanon, Santiago  and
      Cohen, William  and
      Sanghai, Sumit  and
      Ainslie, Joshua",
    editor = "Duh, Kevin  and
      Gomez, Helena  and
      Bethard, Steven",
    booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Author-page-Marten-During-lu/2024.naacl-short.64/",
    doi = "10.18653/v1/2024.naacl-short.64",
    pages = "737--744"
}