The role of injected noise in diffusion model generalization
Diffusion models trained on distinct datasets can produce highly similar samples when prompted with the same noise input, suggesting that they learn a generalized data distribution.
By Vincent Emmerling, Felix G\"unther, David KappelarXiv cs.LG
Read the full story
Originally published by arXiv cs.LG on Nov 5, 2026.
Comments
Sign in to join the discussion.