A theoretical basis for model collapse in recursive training
Not on the map. Why?
Abstract (arXiv)
It is known that recursive training from generative models can lead to the so called `collapse' of the simulated probability distribution. This note shows that one in fact gets two different asymptotic behaviours depending on whether an external source, howsoever minor, is also contributing samples.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 7 of its 15 references that are in the map. First posted on arXiv 11 Jun 2025.
Builds on
7 of 15 references.
References · 7
- 2023The Curse of Recursion: Training on Generated Data Makes Models Forgetcited by 356
- 2023Self-Consuming Generative Models Go MADcited by 250
- 2024Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Datacited by 151
- 2024A Tale of Tails: Model Collapse as a Change of Scaling Lawscited by 130
- 2024Model Collapse Demystified: The Case of Regressioncited by 82
- 2024Rate of Model Collapse in Recursive Trainingcited by 25
- 2024Heat Death of Generative Models in Closed-Loop Learningcited by 22
Built on by
Citing papers per year: 2026: 1.
1 paper.