Pattern formation in trained diffusion models emerges from out-of-equilibrium phase transitions driven by instabilities in low-frequency denoising modes linked to data symmetries and architectural constraints.
Sampling with flows, diffusion, and autoregressive neural networks from a spin-glass perspective.Proceedings of the National Academy of Sciences, 121(27):e2311810121
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Conditional normalizing flows approximate intractable likelihoods arising from cell division history to conclude that glc3 is mostly inactive under nutrient stress in yeast, with brief transient expression.
citing papers explorer
-
How Out-of-Equilibrium Phase Transitions can Seed Pattern Formation in Trained Diffusion Models
Pattern formation in trained diffusion models emerges from out-of-equilibrium phase transitions driven by instabilities in low-frequency denoising modes linked to data symmetries and architectural constraints.
-
Inherited or produced? Inferring protein production kinetics when protein counts are shaped by a cell's division history
Conditional normalizing flows approximate intractable likelihoods arising from cell division history to conclude that glc3 is mostly inactive under nutrient stress in yeast, with brief transient expression.