← 研踪 PaperTrailCVF · CVPR 2026:cvf:41ebc90ef7ffaffcfac55944c558ebcf · 记录 #1
C^2FG: Control Classifier-Free Guidance via Score Discrepancy Analysis
Gao, JiayangZheng, TianyiZou, JiayangYang, FengxiangLiu, ShiceFan, LuyaoZhang, ZheyuZhang, HaoChen, JinweiJiang, Peng-TaoLi, BoWang, Jia 来源日期（仅到年份） 2026
来源记录日期 2026
雷达观测 2026-11-05 04:11
摘要
Classifier-Free Guidance (CFG) is a cornerstone of modern conditional diffusion models, yet its reliance on the fixed or heuristic dynamic guidance weight is predominantly empirical and overlooks the inherent dynamics of the diffusion process. In this paper, we provide a rigorous theoretical analysis of the Classifier-Free Guidance. Specifically, we establish strict upper bounds on the score discrepancy between conditional and unconditional distributions at different timesteps based on the diffusion process.This finding explains the limitations of fixed-weight strategies and establishes a principled foundation for time-dependent guidance. Motivated by this insight, we introduce **Control Classifier-Free Guidance (C^2FG)**, a novel, training-free, and plug-in method that aligns the guidance strength with the diffusion dynamics via an exponential decay control function. Extensive experiments demonstrate that C^2FG is effective and broadly applicable across diverse generative tasks, while also exhibiting orthogonality to existing strategies.
论文发现出处
这些页面提供论文线索，不代表同行评审或质量认证。
观测到的版本
平台记录号代表本站观测到的元数据变化，不是作者修订号。来源日期仅到月份或年份时，按该月或该年首日存档。
记录 #1 · 2026 · 最新观测版本
C^2FG: Control Classifier-Free Guidance via Score Discrepancy Analysis
Classifier-Free Guidance (CFG) is a cornerstone of modern conditional diffusion models, yet its reliance on the fixed or heuristic dynamic guidance weight is predominantly empirical and overlooks the inherent dynamics of the diffusion process. In this paper, we provide a rigorous theoretical analysis of the Classifier-Free Guidance. Specifically, we establish strict upper bounds on the score discrepancy between conditional and unconditional distributions at different timesteps based on the diffusion process.This finding explains the limitations of fixed-weight strategies and establishes a principled foundation for time-dependent guidance. Motivated by this insight, we introduce **Control Classifier-Free Guidance (C^2FG)**, a novel, training-free, and plug-in method that aligns the guidance strength with the diffusion dynamics via an exponential decay control function. Extensive experiments demonstrate that C^2FG is effective and broadly applicable across diverse generative tasks, while also exhibiting orthogonality to existing strategies.
查看此版本解读 →查看此版本原文 ↗