Pıer
TidesCurrentsHarbor LightsLabBottlesAshore
Pıer

Navigation

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

External links

GitHubCloudborne ↗

© 2026 Pier.

WatchingResearchWatching0 independent reports0

CADENCE: Closing the Reasoning Gap via Coverage-Adaptive On-Policy Distillation

First seen · 7/30/2026, 12:00 PMLatest activity · 7/30/2026, 12:00 PM

CADENCE is an on-policy distillation framework designed to address cold-start collapse, state-agnostic KL scheduling, and sparse binary rewards. Its DRIFT objective mixes forward- and reverse-KL surrogates per token, while COVA adapts the transition using student coverage, FTB emphasizes high-entropy forking tokens, and CCD supplies numerical-proximity partial credit. On GSM8K and MATH-500, a 0.5B student reached 69.8% GSM8K pass@1 after distillation from a 1.5B teacher, compared with 48.7% pretrained, and experiments ran on a single 64GB Apple Mac Studio.

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. AggregatorarXiv7/19, 04:16 AMnot independent
    CADENCE: Closing the Reasoning Gap via Coverage-Adaptive On-Policy Distillation
  2. AggregatorHuggingFace Daily Papers7/30, 12:00 PMnot independentRepresentative
    CADENCE: Closing the Reasoning Gap via Coverage-Adaptive On-Policy Distillation