@inproceedings{yang-etal-2026-curated, title = "From Curated Data to Scalable Models: Continual Pre-training of Dense and {M}o{E} Large Language Models for {T}ibetan", author = "Yang, Lei and Pan, Leiyu and Xiong, Bojian and Jin, Renren and Zhang, Shaowei and Chen, Yue and Shi, Ling and Zhou, Jiang and Wu, Junru and Wang, Zhen and Peng, Jianxiang and Xiao, Juesi and Dong, Tianyu and Han, Zhuowen and Chen, Zhuo and Ren, Yuqi and Xiong, Deyi", editor = "Liakata, Maria and Moreira, Viviane P. and Zhang, Jiajun and Jurgens, David", booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)", month = jul, year = "2026", address = "San Diego, California, United States", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1866/", pages = "40167--40182", ISBN = "979-8-89176-390-6" }