Training-Free Generative Sampling via Moment-Matched Score Smoothing
stat.ML, cs.LG
Submitted: 2026-05-14
Updated: 2026-11-06
Terminology
Sources
- Score-Based Generative Modeling through Stochastic Differential Equations
- DiffWave: A Versatile Diffusion Model for Audio Synthesis
- Imagen Video: High Definition Video Generation with Diffusion Models
- GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation
- Sharp Generalization Bounds for Foundation Models with Asymmetric Randomized Low-Rank Adapters
- Why Diffusion Models Don't Memorize: The Role of Implicit Dynamical Regularization in Training
- Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions
- Convergence of denoising diffusion models under the manifold hypothesis
- An analysis of the noise schedule for score-based generative models
- Progressive Distillation for Fast Sampling of Diffusion Models
- Denoising Diffusion Implicit Models
- Diffusion Models on the Edge: Challenges, Optimizations, and Applications
- Diffusion Models and the Manifold Hypothesis: Log-Domain Smoothing is Geometry Adaptive
- Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study
- Closed-Form Diffusion Models
- Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
- Progressive Growing of GANs for Improved Quality, Stability, and Variation
- Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
- Decoupled Weight Decay Regularization
- Gaussian Error Linear Units (GELUs)
Related papers
- Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks
- Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors
- Quantifying Error Propagation and Model Collapse in Diffusion Models
- Behavior of prediction performance metrics with rare events
- Statistical Inference and Learning for Shapley Additive Explanations (SHAP)
- Control Variate Design for Score-Function Gradient Estimators in Importance-Weighted Variational Inference