Pıer
TidesCurrentsHarbor LightsLabBottlesAshore
Pıer

Navigation

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

External links

GitHubCloudborne ↗

© 2026 Pier.

WatchingResearchWatching0 independent reports0

Poly-OPD: Heterogeneous Multi-Teacher On-Policy Distillation for Capability-Selectable Flow Models

First seen · 8/5/2026, 04:00 AMLatest activity · 8/5/2026, 04:00 AM

Poly-OPD is an on-policy distillation framework for combining complementary capabilities from heterogeneous text-to-image teachers. It distills FLUX.1-dev and Z-Image into a 2.5B-parameter SD3.5-Medium student despite differences in autoencoders and noise schedules. A pixel bridge re-encodes student images with a selected teacher, while frozen DINOv2 features provide cross-latent supervision. Shared attention LoRA modules and teacher-specific feed-forward adapters are organized using gradient compatibility diagnostics, and a gap-aware curriculum targets weaker compositional categories. The paper reports GenEval improving from 67.3 to 73.3 and DrawBench HPSv3 from 9.34 to 11.35.

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 Papers8/5, 04:00 AMnot independentRepresentative
    Poly-OPD: Heterogeneous Multi-Teacher On-Policy Distillation for Capability-Selectable Flow Models