Rethinking Personalized Generation: Test-Time Alignment via Factorized Ranking Models
This work uses empirical studies to reveal the existence of a massive, untapped performance headroom for personalized generation through test-time alignment, and proposes a parameter-efficient framework utilizing million-parameter scale multi-layer perceptron (MLP) ranking models.
Qi-Yao Ma, Jun-Shan Zhang, Zhe Zhao
· 0 citations