Crimson AI NewsA CrimsonLingua Network service
EN ع
← Back to news
Research paper Hugging Face

Any-OPD: New Framework Enables On-Policy Distillation Between Any Flow-Matching Models

AI By Crimson AI Hugging Face Papers 5 August 2026 · 00:00 12 views
Share: X Telegram

Researchers introduce Any-OPD, the first framework for on-policy distillation between arbitrary pairs of latent flow-matching generators, enabling a 12B teacher to boost a 2.5B student's performance without shared architecture or latents.

Any-OPD: New Framework Enables On-Policy Distillation Between Any Flow-Matching Models

Key points

On-policy distillation, where a teacher model corrects samples generated by the student, traditionally requires both models to share the same latent space, architecture, and timestep schedule. This assumption breaks when distilling between different model families, such as distilling a large model into a smaller one from a different lineage. The standard recipes fail: teacher latents cannot serve as targets in a foreign coordinate system, per-pixel losses against a teacher that stochastically re-draws local detail lead to blur or divergence, and timestep indices lose meaning across mismatched schedules.

To address this, researchers present Any-OPD, the first framework for on-policy distillation between arbitrary pairs of latent flow-matching generators. Any-OPD treats the teacher purely as a black-box sampler and connects the two models at exactly one point: a frozen, model-agnostic vision representation in which their independently decoded outputs are compared. This sidesteps every assumption about latents, features, or architecture.

Trajectory correspondence is recovered by matching continuous noise levels instead of step indices. A brief anchoring phase, where teacher samples are re-encoded through the student's own VAE, ensures the on-policy gradient measures sample quality rather than domain mismatch.

In experiments, distilling the 12B FLUX.1-dev into the 2.5B SD3.5-Medium, Any-OPD lifts the student's PickScore from 0.846 to 0.884 and HPSv3 from 9.12 to 10.97, rivaling the teacher at a fifth of its size. Direct latent regression fails to train at all in this setting.

MetricBefore DistillationAfter Any-OPD
PickScore0.8460.884
HPSv39.1210.97
Source
Hugging Face · Hugging Face Papers
Related news
Research paper
Hugging Face 31 Aug 2026

Hugging Face Unveils StepGuard: Step-Level Guardrails for Safer AI Agents

StepGuard, a new step-level guard model from Hugging Face, audits agent actions before execution, reducing attack success rates by...

1
Research paper
Hugging Face 31 Aug 2026

Hugging Face Researchers Unveil ABot-Recon for Stable Long-Horizon 3D Reconstruction

ABot-Recon, a new streaming 3D reconstruction model from Hugging Face, achieves stable long-horizon performance using only local t...

1
Research paper
Hugging Face 31 Aug 2026

ContextPilot: Teaching Agents Proactive Context Management via Fine-Grained RL

Hugging Face researchers introduce ContextPilot, a framework that enhances long-horizon agent reasoning by expanding context-editi...

1