Semi-DPO applies semi-supervised learning to noisy preference data in diffusion DPO by training first on consensus pairs then iteratively pseudo-labeling conflicts, yielding state-of-the-art alignment with complex human preferences.
This is significantly more efficient than the 19 Published as a conference paper at ICLR 2026 standard Diffusion-DPO baseline, which necessitates192 GPU hours
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
-
Learning from Noisy Preferences: A Semi-Supervised Learning Approach to Direct Preference Optimization
Semi-DPO applies semi-supervised learning to noisy preference data in diffusion DPO by training first on consensus pairs then iteratively pseudo-labeling conflicts, yielding state-of-the-art alignment with complex human preferences.