Recursively Trained Diffusion Models: Limiting Collapse Distribution and Spectral Characterization
stat.ML, cs.LG
Submitted: 2026-06-11
Updated: 2026-11-05
Terminology
Sources
- Self-Improving Diffusion Models with Synthetic Data
- Probabilistic plugging of airways by sliding mucus films
- A Tale of Tails: Model Collapse as a Change of Scaling Laws
- Reinforced Self-Training (ReST) for Language Modeling
- Quantifying Error Propagation and Model Collapse in Diffusion Models
- Stochastic Runge-Kutta Methods: Provable Acceleration of Diffusion Models
- Analyzing and Mitigating Model Collapse in Rectified Flow Models
Related papers
- Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks
- Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors
- Quantifying Error Propagation and Model Collapse in Diffusion Models
- Behavior of prediction performance metrics with rare events
- Statistical Inference and Learning for Shapley Additive Explanations (SHAP)
- Control Variate Design for Score-Function Gradient Estimators in Importance-Weighted Variational Inference