VaSE improves KV cache eviction accuracy for reasoning models by over 4% versus prior eviction methods at 4x compression through value-magnitude protection and stochastic diversity.
arXiv preprint arXiv:2509.05165 , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Value-Aware Stochastic KV Cache Eviction for Reasoning Models
VaSE improves KV cache eviction accuracy for reasoning models by over 4% versus prior eviction methods at 4x compression through value-magnitude protection and stochastic diversity.