STREAM: Stochastic Riemannian Flow Matching with Anisotropic Decoder for Digital Histopathology Image Generation

Excerpt

arXiv:2606.07036v2 Announce Type: replace-cross Abstract: Synthetic histopathology image generation addresses patient-privacy concerns and the growing data demands of foundation models. Existing state-of-the-art histopathology generative models use pretrained Vision Foundation Models (VFMs) as conditioning signals. We show this yields conditioning-dominated diversity: on TCGA-BRCA, 62-75% of their output diversity is attributable to the conditioning signal rather than the learned latent space, w