AI RESEARCH
Improving Diffusion Generalization with Weak-to-Strong Segmented Guidance
arXiv CS.CV
•
ArXi:2603.20584v1 Announce Type: new Diffusion models generate synthetic images through an iterative refinement process. However, the misalignment between the simulation-free objective and the iterative process often causes accumulated gradient error along the sampling trajectory, which leads to unsatisfactory results and a failure to generalize. Guidance techniques like Classifier Free Guidance (CFG) and AutoGuidance (AG) alleviate this by extrapolating between the main and inferior signal for stronger generalization.