AI & ML Paradigm Shift

Establishes a formal mathematical equivalence between Classifier-Free Guidance (CFG) and alignment-based objectives, allowing for CFG-like quality without inference-time overhead.

March 25, 2026

Original Paper

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

Xiang Li, Yixuan Jia, Xiao Li, Jeffrey A. Fessler, Rongrong Wang, Qing Qu

arXiv · 2603.22364

The Takeaway

By reframing CFG as an inter-class likelihood-ratio maximization during training, practitioners can train models that possess the 'guidance' effect inherently. This eliminates the need for the double-pass sampling required by traditional CFG, potentially halving generation latency.

From the abstract

Diffusion models have achieved state-of-the-art performance in generative modeling, but their success often relies heavily on classifier-free guidance (CFG), an inference-time heuristic that modifies the sampling trajectory. From a theoretical perspective, diffusion models trained with standard denoising score matching (DSM) are expected to recover the target data distribution, raising the question of why inference-time guidance is necessary in practice. In this work, we ask whether the DSM trai