Research map / Image generation / Fast diffusion sampling
Score-Based Generative Models Detect Manifolds
Jakiw Pidstrigach
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use pretrained DDPM++ drift instead of exact empirical drift | reverse SDE · CIFAR-10 | distance to training examples | Improved |
| perturb empirical drift with constant vector (1,...,1) | reverse SDE with empirical drift · CIFAR-10 | distance to closest training image: 0 -> 0.07 | Hurt |
| perturb the drift with a constant error vector (0,-1) | reverse SDE · unit circle S1 | support of sample distribution | No clear effect |
| poor prior approximation N(m, I) instead of p1 | reverse SDE · unit circle S1 | uniformity of samples | Hurt |
| use perturbed drift instead of DDPM++ drift | reverse SDE · CIFAR-10 | martingale integral at t to 1 | Improved |
Closest papers by meaning
- Approximation and Generalization Abilities of Score-based Neural Network Generative Models for Sub-Gaussian Distributions (NeurIPS 2025 · similarity 0.87)
- Algorithm- and Data-Dependent Generalization Bounds for Diffusion Models (NeurIPS 2025 · similarity 0.87)
- What Secrets Do Your Manifolds Hold? Understanding the Local Geometry of Generative Models (ICLR 2025 · similarity 0.87)
- Beyond Log-Concavity and Score Regularity: Improved Convergence Bounds for Score-Based Generative Models in W2-distance (ICML 2025 · similarity 0.87)
- When and how can inexact generative models still sample from the data manifold? (NeurIPS 2025 · similarity 0.87)
- Global Well-posedness and Convergence Analysis of Score-based Generative Models via Sharp Lipschitz Estimates (ICLR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
