default search action
BibTeX record conf/aaai/ZengZYHZLJZ26
@inproceedings{DBLP:conf/aaai/ZengZYHZLJZ26,
author = {Hui Zeng and
Daming Zhao and
Pengfei Yang and
WenXuan Hou and
Tianyang Zheng and
Hui Li and
Weiye Ji and
Jidong Zhai},
editor = {Sven Koenig and
Chad Jenkins and
Matthew E. Taylor},
title = {Lethe: Layer- and Time-Adaptive {KV} Cache Pruning for Reasoning-Intensive
{LLM} Serving},
booktitle = {Fortieth {AAAI} Conference on Artificial Intelligence, Thirty-Eighth
Conference on Innovative Applications of Artificial Intelligence,
Sixteenth Symposium on Educational Advances in Artificial Intelligence,
{AAAI} 2026, Singapore, January 20-27, 2026},
pages = {28103--28112},
publisher = {{AAAI} Press},
year = {2026},
url = {https://doi.org/10.1609/aaai.v40i33.40036},
doi = {10.1609/AAAI.V40I33.40036},
timestamp = {Tue, 07 Apr 2026 20:21:18 +0200},
biburl = {https://dblp.org/rec/conf/aaai/ZengZYHZLJZ26.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.