Quantifying Error Propagation and Model Collapse in Diffusion Models
Machine learning models are increasingly trained or fine-tuned on synthetic data. Recursively training on such data has been observed to significantly degrade performance in a wide range of tasks, often characterized by a progressive drift away from the target distribution.
By Nail B. Khelifa, Richard E. Turner, Ramji VenkataramananarXiv - stat.ML
Read the full story
Originally published by arXiv - stat.ML on Nov 5, 2026.
Comments
Sign in to join the discussion.