[2603.03281] CFG-Ctrl: Control-Based Classifier-Free Diffusion Guidance

Computer Science > Computer Vision and Pattern Recognition arXiv:2603.03281 (cs) [Submitted on 3 Mar 2026] Title:CFG-Ctrl: Control-Based Classifier-Free Diffusion Guidance Authors:Hanyang Wang, Yiyang Liu, Jiawei Chi, Fangfu Liu, Ran Xue, Yueqi Duan View a PDF of the paper titled CFG-Ctrl: Control-Based Classifier-Free Diffusion Guidance, by Hanyang Wang and 5 other authors View PDF HTML (experimental) Abstract:Classifier-Free Guidance (CFG) has emerged as a central approach for enhancing semantic alignment in flow-based diffusion models. In this paper, we explore a unified framework called CFG-Ctrl, which reinterprets CFG as a control applied to the first-order continuous-time generative flow, using the conditional-unconditional discrepancy as an error signal to adjust the velocity field. From this perspective, we summarize vanilla CFG as a proportional controller (P-control) with fixed gain, and typical follow-up variants develop extended control-law designs derived from it. However, existing methods mainly rely on linear control, inherently leading to instability, overshooting, and degraded semantic fidelity especially on large guidance scales. To address this, we introduce Sliding Mode Control CFG (SMC-CFG), which enforces the generative flow toward a rapidly convergent sliding manifold. Specifically, we define an exponential sliding mode surface over the semantic prediction error and introduce a switching control term to establish nonlinear feedback-guided correction....