AI RESEARCH
Error as Signal: Stiffness-Aware Diffusion Sampling via Embedded Runge-Kutta Guidance
arXiv CS.CV
•
ArXi:2603.03692v2 Announce Type: replace Classifier-Free Guidance (CFG) has established the foundation for guidance mechanisms in diffusion models, showing that well-designed guidance proxies significantly improve conditional generation and sample quality. Autoguidance (AG) has extended this idea, but it relies on an auxiliary network and leaves solver-induced errors unaddressed. In stiff regions, the ODE trajectory changes sharply, where local truncation error (LTE) becomes a critical factor that deteriorates sample quality.