@inproceedings{zhang-etal-2025-dam, title = "{DAM}: Dynamic Attention Mask for Long-Context Large Language Model Inference Acceleration", author = "Zhang, Hanzhi and Fan, Heng and Sha, Kewei and Huang, Yan and Feng, Yunhe", editor = "Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Pilehvar, Mohammad Taher", booktitle = "Findings of the Association for Computational Linguistics: ACL 2025", month = jul, year = "2025", address = "Vienna, Austria", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/landing_page/2025.findings-acl.242/", pages = "4663--4676", ISBN = "979-8-89176-256-5" }