Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation
On-policy distillation (OPD) adapts diffusion models by querying a teacher along trajectories generated by the current student, but how it should behave under classifier-free guidance (CFG), a default component of modern diffusion systems, remains poorly understood. Existing OPD methods naturally extend velocity matching to the CFG-composed prediction, directly matching teacher and student guided velocities. We show that this objective is under-identified at the branch level: positive- and negat
Record details
Published: 27 July 2026
Source: arXiv cs.AI
Category: Research
Topics: Regulation · Children & education
Retrieved: 28 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Weak-to-Strong On-Policy Distillation
HuggingFace Daily Papers · 27 July 2026
Pass the Baton: Trajectory-Relayed On-Policy Distillation
HuggingFace Daily Papers · 27 July 2026
A Framework for Developing University Policies on Generative AI Governance: A Cross-national Comparative Study
arXiv cs.CY · 28 July 2026
A principled way to think about AI in education: guidance for educators and policy makers based on goals, models of human learning, and use of technologies
arXiv cs.CY · 27 July 2026
Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation
HuggingFace Daily Papers · 26 July 2026
Pictura: Perspective-View Self-Play at Scale for Driving
arXiv cs.AI · 28 July 2026
How to cite this record
ethics.ai (27 July 2026), “Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation,” evidence record 14027, https://ethics.ai/record/14027 (originally published by arXiv cs.AI).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.