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.
Boost your human image gen- eration model via direct preference optimization.arXiv preprint arXiv:2405.20216
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative 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.