نسخة أولية وصول مفتوح
SAGE: Subspace Alignment for Classifier-Free Guidance in Mixture-of-Experts Diffusion Models
Diffusion Transformers with Mixture-of-Experts (MoE) routing are a leading recipe for scaling generative models. Classifier-Free Guidance (CFG) is essential for generation quality, yet excessively high guidance scales trigger collapse. We identify a previously unreported failure mode in their combination: the two CFG b …