KV-Kaizen: Learning Context-Adaptive Cache Compression Choices

Sep 25, 2026·

Joao Monteiro

,

Louis Béthune

,

Anastasiia Filippova

Sonia Laguna

Sonia Laguna

,

David Grangier

,

Marco Cuturi

· 0 min read

Type

Conference paper

Publication

Preprint - Arxiv

Last updated on Sep 25, 2026

Sonia Laguna

Authors

Research @Apple MLR
PhD in Machine Learning @ETH Zurich

← Cyclostationary Phase Conditioning for Medical Time Series Diffusion Sep 25, 2026

DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures Aug 20, 2026 →