@inproceedings{liu-etal-2026-compact,
    title = "Compact Multilingual Pre-training under the {B}aby{LM} 100{M}-Word Budget with Regex-Guided Tokenization and Attention Residuals",
    author = "Liu, Yihan  and
      Zhang, Tongjing  and
      Nugues, Pierre",
    editor = "Choshen, Leshem  and
      Cotterell, Ryan  and
      Gul, Mustafa Omer  and
      Jumelet, Jaap  and
      Linzen, Tal  and
      Mueller, Aaron  and
      Salhan, Suchir  and
      Shah, Raj Sanjay  and
      Warstadt, Alex  and
      Wilcox, Ethan Gotlieb",
    booktitle = "Proceedings of the Second {B}aby{LM} Workshop",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.babylm-main.32/",
    pages = "403--412",
    ISBN = "979-8-89176-475-0"
}