AI RESEARCH
When Models Don't Collapse: On the Consistency of Iterative MLE
arXiv CS.LG
•
ArXi:2505.19046v3 Announce Type: replace-cross The widespread use of generative models has created a feedback loop, in which each generation of models is trained on data partially produced by its predecessors. This process has raised concerns about model collapse: A critical degradation in performance caused by repeated