Beyond Mean Attention: Diversity-Aware, Layer-Wise Scoring for KV Cache Eviction
A unified score, $\mu_i+\lambda_1\sigma_i+\lambda_2\mathrm{corr}(i,S)$, is studied, adding attention dispersion across window queries and redundancy relative to selected tokens to test whether this relevance-diversity balance should vary with depth.
Tian-Fang Xie, Wei Zhu
· 0 citations