109
EMAG: Self-Rectifying Diffusion Sampling with Exponential Moving Average Guidance
arXiv:2512.17303v1 Announce Type: new
Abstract: In diffusion and flow-matching generative models, guidance techniques are widely used to improve sample quality and consistency. Classifier-free guidance (CFG) is the de facto choice in modern systems and achieves this by contrasting conditional and u…
Abstract: In diffusion and flow-matching generative models, guidance techniques are widely used to improve sample quality and consistency. Classifier-free guidance (CFG) is the de facto choice in modern systems and achieves this by contrasting conditional and u…