Nexus Sampling combines iterative Nexus scoring with weighted reservoir sampling to evict KV cache tokens, theoretically dominating top-K selection in retaining subtly important tokens and empirically matching dense attention within 1% at 80% eviction on LongBench.
how much can we shrink the cache before accuracy breaks?
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
-
Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets
Nexus Sampling combines iterative Nexus scoring with weighted reservoir sampling to evict KV cache tokens, theoretically dominating top-K selection in retaining subtly important tokens and empirically matching dense attention within 1% at 80% eviction on LongBench.