ViPO: Visual Preference Optimization at Scale

ArXi:2604.24953v1 Announce Type: new While preference optimization is crucial for improving visual generative models, how to effectively scale this paradigm remains largely unexplored. Current open-source preference datasets contain conflicting preference patterns, where winners excel in some dimensions but underperform in others. Naively optimizing on such noisy datasets fails to learn preferences, hindering effective scaling.