@inproceedings{zhang-etal-2026-hermes, title = "{HERMES}: {KV} Cache as Hierarchical Memory for Efficient Streaming Video Understanding", author = "Zhang, Haowei and Yang, Shudong and Fu, Jinlan and Ng, See-Kiong and Qiu, Xipeng", 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.381/", pages = "8411--8430", ISBN = "979-8-89176-390-6" }