Feature Selective Model Collapse in Diffusion Models: Total Replacement versus Fixed-Budget Training
Model collapse arises when generative models are trained on synthetic data produced by earlier models. The phenomenon has attracted considerable attention because of its societal and technical implications. However, previous studies have reached seemingly contradictory conclusions: replacing real data with synthetic data causes collapse (Shumailov et al.), yet accumulating real data alongside…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.