Skip to content

Lethe: Layer- and Time-Adaptive KV Cache Pruning for Reasoning-Intensive LLM Serving.

Hui Zeng, Daming Zhao, Pengfei Yang, WenXuan Hou, Tianyang Zheng, Hui Li, Weiye Ji, Jidong Zhai

VenueA*AAAI
Year2026
ProceedingsAAAI

Browse the full AAAI paper archive.