AI RESEARCH
On the Limits of Latent Reuse in Diffusion Models
arXiv CS.LG
•
ArXi:2605.13448v1 Announce Type: cross Diffusion models are often trained in low-dimensional latent spaces, which are then reused for related but shifted datasets. In this work, we study when such latent reuse remains reliable under distribution shift. We consider a source-target setting in which both datasets are approximately low-dimensional but may lie near different subspaces.