AI RESEARCH
A Simple Plug-in for Improving Eviction-Based KV Cache Compression
arXiv CS.LG
•
ArXi:2605.23258v1 Announce Type: new KV cache growth is a major bottleneck for long-context inference in large language models. Existing methods are often dominated by binary eviction or representation approximation, which may underutilize tokens that are not critical for exact retention but are still reconstructable. We present VECTOR, a plug-and-play augmentation for eviction-based pipelines that