Pıer
TidesCurrentsHarbor LightsLabBottlesAshore
Pıer

Navigation

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

External links

GitHubCloudborne ↗

© 2026 Pier.

WatchingResearchWatching0 independent reports0

Flux-OPD: On-Policy Distillation with Evolving Contexts

First seen · 7/31/2026, 12:00 PMLatest activity · 7/31/2026, 12:00 PM

Flux-OPD addresses open-ended language-model training where verifiable rewards are scarce by using contexts as preference supervision that evolves with student performance. The paper decomposes the reverse-KL objective and argues that the student is distilled toward the geometric mean of context-conditioned teachers, while a conflict term captures disagreement among those teachers. Flux-OPD injects contextual differences into a context-free teacher anchor and scales them by the conflict signal. The abstract reports improvements over existing OPD paradigms on open-ended tasks, but gives no numerical results, benchmark names, or implementation details.

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. AggregatorarXiv7/30, 07:11 PMnot independent
    Flux-OPD: On-Policy Distillation with Evolving Contexts
  2. AggregatorHuggingFace Daily Papers7/31, 12:00 PMnot independentRepresentative
    Flux-OPD: On-Policy Distillation with Evolving Contexts