@inproceedings{yu-chai-2025-evolkv, title = "{E}vol{KV}: Evolutionary {KV} Cache Compression for {LLM} Inference", author = "Yu, Bohan and Chai, Yekun", 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://aclanthology.org/2025.findings-emnlp.88/", pages = "1673--1689", ISBN = "979-8-89176-335-7" }