Diffusion trajectory distillation is reframed as operator merging, yielding an optimal variance-driven merging strategy via Pareto dynamic programming in the linear Gaussian case and unavoidable approximation errors from exponential mixture growth in the nonlinear case.
Diffusion models generate images like painters: an analytical theory of outline first, details later
5 Pith papers cite this work. Polarity classification is still indexing.
verdicts
UNVERDICTED 5representative citing papers
Analytic solution of full-batch gradient flow for linear and convolutional denoisers in diffusion models yields a universal inverse-variance spectral law for learning times of eigenmodes.
SiLD is a score-matching framework that learns both manifold projection and intrinsic density from a single objective, with proven sample complexity depending only on intrinsic dimension.
Generative models learn rules before memorizing data, creating an innovation window whose width depends on dataset size and rule complexity, observed in both diffusion and autoregressive architectures.
DP-DMD preserves sample diversity in few-step image synthesis by applying a teacher-derived target-prediction objective to the first distillation step and standard DMD loss to the rest.
citing papers explorer
-
Toward Theoretical Insights into Diffusion Trajectory Distillation via Operator Merging
Diffusion trajectory distillation is reframed as operator merging, yielding an optimal variance-driven merging strategy via Pareto dynamic programming in the linear Gaussian case and unavoidable approximation errors from exponential mixture growth in the nonlinear case.
-
An Analytical Theory of Spectral Bias in the Learning Dynamics of Diffusion Models
Analytic solution of full-batch gradient flow for linear and convolutional denoisers in diffusion models yields a universal inverse-variance spectral law for learning times of eigenmodes.
-
Provably Learning Diffusion Models under the Manifold Hypothesis: Collapse and Refine
SiLD is a score-matching framework that learns both manifold projection and intrinsic density from a single objective, with proven sample complexity depending only on intrinsic dimension.
-
The two clocks and the innovation window: When and how generative models learn rules
Generative models learn rules before memorizing data, creating an innovation window whose width depends on dataset size and rule complexity, observed in both diffusion and autoregressive architectures.
-
Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesis
DP-DMD preserves sample diversity in few-step image synthesis by applying a teacher-derived target-prediction objective to the first distillation step and standard DMD loss to the rest.