arXiv cs.CV
· Papers
Probing Diffusion Denoising Dynamics for Contrastive Representation Learning
arXiv:2607.09067v1 Announce Type: new Abstract: Text-to-image diffusion models exhibit unprecedented generative capability and contain rich intermediate representations that can be useful for discriminative vision tasks. Motivated by this observation, we study a focused question: how can the denoising dynamics of a pre