Research map / Image generation / Fast diffusion sampling
A Variational Perspective on Diffusion-Based Generative Models and Score Matching
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Sample diffusion time from a debiased distribution instead of uniform with weighted DSM (ablation) | Score-based model likelihood training · MNIST and CIFAR10 | bits-per-dim ELBO | Helped |
| Parameterize drift a instead of score s_theta directly (ablation) | Score-based model · MNIST and CIFAR10 | bits-per-dim ELBO | Helped |
| Train continuous-time flow (sigma=0) vs plug-in reverse SDE with score matching, compare per runtime | Swiss roll generative model · Swiss roll | negative ELBO convergence | No clear effect |
Closest papers by meaning
- Training Diffusion-based Generative Models with Limited Data (ICML 2025 · similarity 0.91)
- Nearest Neighbour Score Estimators for Diffusion Generative Models (ICML 2024 · similarity 0.91)
- Dimension-free Score Matching and Time Bootstrapping for Diffusion Models (NeurIPS 2025 · similarity 0.91)
- Generative Fractional Diffusion Models (NeurIPS 2024 · similarity 0.90)
- What’s the score? Automated Denoising Score Matching for Nonlinear Diffusions (ICML 2024 · similarity 0.90)
- One-Step Diffusion Distillation through Score Implicit Matching (NeurIPS 2024 · similarity 0.90)
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.