A distillation method that supervises a student on its own samples using teacher refinements compared in a frozen DINOv2 feature space, reporting preference-metric gains on a FLUX.1-dev to SD3.5-Medium transfer.
International Conference on Learning Representations , volume=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Any-OPD: Heterogeneous On-Policy Distillation for Flow-Matching Models via Representation-Space Bridging
A distillation method that supervises a student on its own samples using teacher refinements compared in a frozen DINOv2 feature space, reporting preference-metric gains on a FLUX.1-dev to SD3.5-Medium transfer.