SOURCE-LINKED INTELLIGENCE

ECOKV: Geometry-Aware KV Cache Eviction via Complementary Diversity Metrics

arXiv · AI, language, vision and robotics · article · Sep 6, 2026 · UTC

Although multimodal Large Language Models (MLLMs) excel in diverse tasks, their scalability remains limited by the memory and computational overhead of KV cache storage. Recent KV cache eviction approaches incorporate a cosine similarity-based diversity metric with importance metrics to selectively retain critical key-value pairs. However, cosine similarity involves normalization that discards magnitude information, and it often yields uniformly high similarity values across layers due to the anisotropy property of hidden representations. In our study ECOKV, we rigorously deconstruct the capab

Read original source ↗ Open in workspace

recordType

paper

region

Global