@inproceedings{cheng-etal-2026-micro,
    title = "Micro Language Models Enable Instant Responses",
    author = "Cheng, Wen  and
      Chen, Tuochao  and
      Helwani, Karim  and
      Srinivasan, Sriram  and
      Zettlemoyer, Luke  and
      Gollakota, Shyamnath",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-main.141/",
    pages = "3240--3264",
    ISBN = "979-8-89176-459-0"
}