Is fixed-schedule KV caching superseded?

fixed-schedule KV caching (KV-cache compression): cited as a baseline — critiqued by newer work, not yet beaten on a benchmark here. 1 paper(s) critique it, 0 beat it on benchmarks — #142 of 234 most-superseded. Sub-problem: cluster led by Fast-dLLM. Newer alternatives in the same sub-problem include WaveFilter.

KV-cache compression

fixed-schedule KV caching

Superseded baseline#142 of 234 most-superseded

Cited as a baseline — critiqued by newer work, not yet beaten on a benchmark here

1 papers critique it · 0 beat it on benchmarks

What papers say

Verbatim critique sentences, each from a paper that cites fixed-schedule KV caching as a baseline.

Such fixed-period policies leave performance on the table: they recompute when nothing has changed and miss updates precisely when rapid semantic revisions occur.

— Attention Is All You Need for KV Cache in Diffusion LLMs

What to use instead

Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.

WaveFilterWaveFilter: Enhancing the Long-Context Capability of Diffusion LLMs via Wavelet-Guided KV Cache Filtering
May 30, 2026