PNAPO augments preference data with prior noise pairs and uses straight-line interpolation to create a tighter surrogate objective for offline alignment of rectified flow models.
Tuning timestep-distilled diffusion model using pairwise sample optimization.arXiv preprint arXiv:2410.03190
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
baseline 1
citation-polarity summary
fields
cs.CV 2years
2026 2representative citing papers
citing papers explorer
-
Offline Preference Optimization for Rectified Flow with Noise-Tracked Pairs
PNAPO augments preference data with prior noise pairs and uses straight-line interpolation to create a tighter surrogate objective for offline alignment of rectified flow models.
- D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models