arXiv AI
Feature Selective Model Collapse in Diffusion Models: Total Replacement versus Fixed-Budget Training
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Jul 17
Escaping Model Collapse via Synthetic Data Verification: Near-term Improvements and Long-term Convergence
arXiv:2510. 16657v3 Announce Type: replace-cross Abstract: Synthetic data has been increasingly used to train frontier generative models.
arXiv Machine Learning
Jun 10
The Emergence of Reproducibility and Generalizability in Diffusion Models
arXiv:2310. 05264v5 Announce Type: replace Abstract: In this work, we investigate an intriguing and prevalent phenomenon of diffusion models which we term as "consistent model reproducibility": given the same starting noise input and a deterministic sampler, different diffusion models often yield remarkably similar outputs.
arXiv AI
Aug 25
Reviewing Model Collapse and Countermeasures
arXiv:2608.21366v1 Announce Type: new Abstract: Driven by massive amounts of web-scale data, generative AI (GenAI) has achieved remarkable progress, enabling various applications in diverse sectors....
arXiv Machine Learning
Jun 17
Recursive Learning Without Collapse: A Weighting-Based Stabilization Framework
arXiv:2502. 18049v5 Announce Type: replace-cross Abstract: Recent studies identified an intriguing phenomenon in recursive generative model training known as model collapse, where models trained on data generated by previous models exhibit severe performance degradation.
arXiv Machine Learning
Aug 4
Pseudorandom Streams within Diffusion Models Act as Learnable Inputs That Affect Generation Quality
arXiv:2608. 02575v1 Announce Type: new Abstract: Diffusion models rely on stochastic inputs, yet on finite-precision hardware, the "randomness" they consume is realized as deterministic numerical orbits generated by pseudorandom rules.
arXiv Machine Learning
Aug 19
Abra: Scaling Diffusion Image Training
The paper introduces Abra, a family of flow‑matching transformers used to systematically study scaling laws for text‑to‑image diffusion models across three orders of magnitude in compute. It finds that diffusion models scale predictably like language models but need far more data, with compute optimality occurring at roughly 200 image tokens per parameter—ten times the optimal ratio for large language models. The study also shows that diffusion models are robust to overtraining, that more data is preferable to larger models, and that scaling predictability extends to generative quality, optimal CFG settings, representation quality, and training curve shapes.