Author

Keon Kim

View on Semantic Scholar

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Jul 2026

MemDecay: Region-Aware KV Cache Eviction for Efficient LLM Agent Inference

These results establish semantic prompt structure as a robust signal for KV-cache management while clarifying how it should be combined with attention-based importance.

Venkatesha Matam, Keon Kim · 1 citation