Method DriftKV-cache compression

Tracked

PruneHal

PruneHal: Reducing Hallucinations in Multi-modal Large Language Models through Adaptive KV Cache Pruning

KV-cache compression · first seen Oct 22, 2025

current frontier — recent, not yet superseded in the knowledge base

0 papers critique it · 0 beat it on benchmarks

Newer alternatives

Recent methods in the same sub-problem, not yet superseded in the knowledge base.