Symmetry breaking and nonlocality phase transitions occur nearly simultaneously during diffusion model generation in modern transformers.
Title resolution pending
6 Pith papers cite this work, alongside 30 external citations. Polarity classification is still indexing.
6
Pith papers citing it
30
external citations · external index
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
A time-dilation schedule makes the mode-probability learning phase survive in high dimension, and the learned flow autoencoder recovers the mixture's p and σ² in two separate phases.
Rank-constrained denoising score matching yields a spectral tradeoff: lower training error with increasing rank, but test error may increase beyond a threshold set by the data subspace dimension and sample size.
Under the common-cause hypothesis, the nonlocality window is contained in the speciation window, and both sharpen to a single critical time in the large-system limit, verified analytically in Gaussian mixtures.
The paper links phase-transition behavior in continuous generative samplers to projection caustics in the data geometry and introduces the Critical Boundary Detector as a diagnostic tool.
A review that groups AI methods for cancer spatial omics into data-driven, constraint-based, and mechanistic modeling paradigms, calling for more interpretable models and mouse-model-generated perturbational data.
citing papers explorer
-
Concurrence of Symmetry Breaking and Nonlocality Phase Transitions in Diffusion Models
Symmetry breaking and nonlocality phase transitions occur nearly simultaneously during diffusion model generation in modern transformers.
-
Phase-aware Training Schedule Simplifies Learning in Flow-Based Generative Models
A time-dilation schedule makes the mode-probability learning phase survive in high dimension, and the learned flow autoencoder recovers the mixture's p and σ² in two separate phases.
-
Denoising Score Matching in Diffusion Models: The Effect of Rank Constraints on Generalization
Rank-constrained denoising score matching yields a spectral tradeoff: lower training error with increasing rank, but test error may increase beyond a threshold set by the data subspace dimension and sample size.
-
Breakdown of Local Denoising as Semantic Speciation
Under the common-cause hypothesis, the nonlocality window is contained in the speciation window, and both sharpen to a single critical time in the large-system limit, verified analytically in Gaussian mixtures.
-
The Geometry of Phase Transitions in Generative Dynamics via Projection Caustics
The paper links phase-transition behavior in continuous generative samplers to projection caustics in the data geometry and introduces the Critical Boundary Detector as a diagnostic tool.
-
Emerging AI Approaches for Cancer Spatial Omics
A review that groups AI methods for cancer spatial omics into data-driven, constraint-based, and mechanistic modeling paradigms, calling for more interpretable models and mouse-model-generated perturbational data.