Where the Score Lives: A Wavelet View of Diffusion 事件

Where the Score Lives: A Wavelet View of Diffusion arXiv:2606.08309v1 Announce Type: cross Abstract: Score-based generative models have had remarkable success over the last decade in generating a diverse set of visually plausible images. A variety of architectures including CNNs, U-Nets, and Transformers have been used as the score-approximation network in such diffusion modeling; however, to date, relatively little is known about how these architectural choices impact generative behavior. In t