Minimizing averaged squared Lipschitzness of the drift produces interpolation schedules that improve numerical accuracy and mitigate mode collapse in generative models, with closed-form optima for Gaussians and validation on stochastic PDEs.
Gotta go fast when generating data with score-based models
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
citation-role summary
background 3
method 1
citation-polarity summary
representative citing papers
First dedicated survey organizing diffusion and flow matching models for tabular data synthesis, imputation, anomaly detection, and related tasks, covering literature from 2015 to 2026 and highlighting open problems.
Latent Consistency Models enable high-fidelity text-to-image generation in 2-4 steps by directly predicting solutions to the probability flow ODE in latent space, distilled from pre-trained LDMs.
Diffusion models solve noisy (non)linear inverse problems via approximated posterior sampling that blends diffusion steps with manifold gradients without strict consistency projection.
Organizing diffusion model design choices yields SOTA FID of 1.79 on CIFAR-10 with only 35 network evaluations per image and similar gains on ImageNet-64.
Progressive distillation halves sampling steps repeatedly in diffusion models, reaching 4 steps with FID 3.0 on CIFAR-10 from 8192-step samplers.
A new error-damping estimator for compositional score matching enables stable amortized inference on hierarchical Bayesian models with over 750,000 parameters using fewer than one full model simulation on large problems.
Moment-matched GMM kernels in DDIM yield lower FID and higher IS than Gaussian kernels at small sampling steps on CelebA-HQ, FFHQ, ImageNet, and Stable Diffusion tasks.
DPM-Solver++ enables high-quality guided sampling of diffusion models in 15-20 steps via data-prediction ODE solving and multistep stabilization.
LA-SR extracts real LR patches from depth-varying regions in single images and uses vision-language models with linguistic content and quality losses for unpaired super-resolution.
OTCache uses optimal transport to interpolate caching schedules between a graph-based reference and an Optuna-optimized anchor, delivering 3.66x-4.7x speedups on FLUX.1, Qwen-Image and HunyuanVideo with improved fidelity.
LISA adds a likelihood-score alignment loss to the side branch of dual-branch controllable generators, accelerating convergence and improving results across image/video tasks with negligible extra cost.
SteinDiff applies Stein-derived residual corrections at each step to stabilize large-step inference in diffusion probability flow ODEs without retraining or reference samples.
citing papers explorer
-
Lipschitz-Guided Design of Interpolation Schedules in Generative Models
Minimizing averaged squared Lipschitzness of the drift produces interpolation schedules that improve numerical accuracy and mitigate mode collapse in generative models, with closed-form optima for Gaussians and validation on stochastic PDEs.
-
Diffusion and Flow Matching Models for Tabular Data: A Survey
First dedicated survey organizing diffusion and flow matching models for tabular data synthesis, imputation, anomaly detection, and related tasks, covering literature from 2015 to 2026 and highlighting open problems.
-
Compositional amortized inference for large-scale hierarchical Bayesian models
A new error-damping estimator for compositional score matching enables stable amortized inference on hierarchical Bayesian models with over 750,000 parameters using fewer than one full model simulation on large problems.