MCLR: Improving Conditional Modeling in Visual Generative Models via Inter-Class Likelihood-Ratio Maximization and Establishing the Equivalence between Classifier-Free Guidance and Alignment Objectives
Published in arXiv preprint, 2026
Recommended citation: X. Li, Y. Jia, X. Li, J.A. Fessler, R. Wang, Q. Qu. (2026). "MCLR: Improving Conditional Modeling in Visual Generative Models via Inter-Class Likelihood-Ratio Maximization and Establishing the Equivalence between Classifier-Free Guidance and Alignment Objectives." arXiv preprint arXiv:2603.22364.
Download Paper