Pıer
TidesCurrentsHarbor LightsLabBottlesAshore
Pıer

Navigation

  • Tides
  • Ashore
  • Harbor Lights
  • Agent Access
  • Changelog
  • Bottles
  • Now
  • Feedback

External links

GitHubCloudborne ↗

© 2026 Pier.

WatchingResearchWatching0 independent reports0

KVpop: Key-Value Cache Compression with Predictive Online Pruning

First seen · 7/7/2026, 12:00 PMLatest activity · 7/7/2026, 12:00 PM

KVpop introduces a learned, fixed-budget KV-cache eviction policy that directly supervises keep-or-drop decisions. Its scorer is trained with a future-attention target that can be computed without materializing dense attention maps. The method also adds a delayed memory-based scorer, postponing scoring for a fixed number of steps to use near-future context. On AIME and HMMT mathematical reasoning with Qwen3-4B, KVpop reportedly retains 98% of full-attention performance at 75% KV-cache compression and 97% at 88% compression. Qwen3-8B achieves near-full teacher performance, according to the abstract.

Event heat · last 24 hours

No heat snapshots are available in the last 24 hours.

No heat snapshots are available in the last 24 hours.

Reporting Timeline

  1. AggregatorHuggingFace Daily Papers7/7, 12:00 PMnot independentRepresentative
    KVpop: Key-Value Cache Compression with Predictive Online Pruning