@inproceedings{xi-etal-2025-samplemix, title = "{S}ample{M}ix: A Sample-wise Pre-training Data Mixing Strategy by Coordinating Data Quality and Diversity", author = "Xi, Xiangyu and Kong, Deyang and Yang, Jian and Yang, Jiawei and Chen, Zhengyu and Wang, Wei and Wang, Jingang and Cai, Xunliang and Zhang, Shikun and Ye, Wei", editor = "Christodoulopoulos, Christos and Chakraborty, Tanmoy and Rose, Carolyn and Peng, Violet", booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025", month = nov, year = "2025", address = "Suzhou, China", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.741/", doi = "10.18653/v1/2025.findings-emnlp.741", pages = "13736--13758", ISBN = "979-8-89176-335-7" }