@inproceedings{mehta-etal-2025-unifying,
    title = "Unifying Mixture of Experts and Multi-Head Latent Attention for Efficient Language Models",
    author = "Mehta, Sushant  and
      Dandekar, Raj  and
      Dandekar, Rajat  and
      Panat, Sreedath",
    editor = "Charpentier, Lucas  and
      Choshen, Leshem  and
      Cotterell, Ryan  and
      Gul, Mustafa Omer  and
      Hu, Michael Y.  and
      Liu, Jing  and
      Jumelet, Jaap  and
      Linzen, Tal  and
      Mueller, Aaron  and
      Ross, Candace  and
      Shah, Raj Sanjay  and
      Warstadt, Alex  and
      Wilcox, Ethan Gotlieb  and
      Williams, Adina",
    booktitle = "Proceedings of the First BabyLM Workshop",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.babylm-main.3/",
    pages = "42--51",
    ISBN = "TODO"
}