Bayesian diffusion models memorize training data when mutual information between restricted observations and training data exceeds log dataset size, and generalize otherwise.
Theory of speciation transitions in diffusion models with general class structure.arXiv preprint arXiv:2602.04404
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
Diffusion posterior samplers produce biased outputs that can be expressed as an Ornstein-Uhlenbeck path expectation via a surrogate Gaussian path and Feynman-Kac representation, with STSL flattening the spatially varying bias term.
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.
citing papers explorer
-
An exact information theory of generalization phase transitions in Bayesian diffusion models
Bayesian diffusion models memorize training data when mutual information between restricted observations and training data exceeds log dataset size, and generalize otherwise.
-
Diffusion-Based Posterior Sampling: A Feynman-Kac Analysis of Bias and Stability
Diffusion posterior samplers produce biased outputs that can be expressed as an Ornstein-Uhlenbeck path expectation via a surrogate Gaussian path and Feynman-Kac representation, with STSL flattening the spatially varying bias term.
-
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.
- Dynamical Regimes of Discrete Diffusion Models