SOURCE-LINKED INTELLIGENCE

PathGuide: Dynamic Classifier-Free Guidance via On-Policy Transport Alignment

arXiv · AI, language, vision and robotics · article · Aug 29, 2026 · UTC

While modern generative models excel at modeling complex data, precise inference-time control in conditional generation remains a critical challenge. Classifier-free guidance (CFG) is a primary mechanism for such control, yet it is typically treated as a static tuning parameter. In flow-based models, however, the guidance scale fundamentally dictates the velocity field and the resulting probability path, making guidance selection a dynamic path-optimization problem. We introduce PathGuide, a framework that reformulates scalar CFG selection as an on-policy transport problem. Leveraging the weak

Read original source ↗ Open in workspace

recordType

paper

region

Global