Diffusion LAIR converts reward scores across candidate images into centered advantage weights and optimizes an advantage-weighted regression objective on implicit denoising-loss improvement with quadratic penalty, outperforming pairwise baselines on SD1.5 and SDXL.
a photo of a green cup and a red pizza
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Beyond Pairwise Preferences: Listwise Reward-Aware Alignment for Diffusion Models
Diffusion LAIR converts reward scores across candidate images into centered advantage weights and optimizes an advantage-weighted regression objective on implicit denoising-loss improvement with quadratic penalty, outperforming pairwise baselines on SD1.5 and SDXL.