Shwetha Ram

SMPRO: Self-Supervised Visual Preference Alignment via Differentiable Multi-Preference Multi-Group Ranking

Direct Preference Optimization (DPO) has emerged as a simple and effective approach for aligning models with human preferences. However, existing DPO-based methods suffer from 3 key drawbacks: they rely on only a single positive-negative preference pair per question, restricting the diversity and ri