@inproceedings{wang-etal-2026-tikmix, title = "{T}i{KM}i{X}: Efficient Semi-Dynamic Data Mixture via Data Influence for {LLM} Pre-training", author = "Wang, Yifan and Binbinliu and Liu, Fengze and Guo, Yuanfan and Deng, Jiyao and Wu, Xuecheng and Zhou, Weidong and Zhou, Xiaohuan and Wang, Taifeng", 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.261/", pages = "5777--5793", ISBN = "979-8-89176-390-6" }