yuPeiyu98/Diffusion-Amortized-MCMC

[NeurIPS 2023] Learning Energy-Based Prior Model with Diffusion-Amortized MCMC

23
/ 100
Experimental

This project helps researchers working with generative models to train and evaluate models for tasks like realistic image generation, reconstructing images, or detecting anomalies. It takes image datasets as input and produces trained models capable of generating new images, recreating existing ones, or identifying unusual images. The primary users are machine learning researchers and practitioners focused on advanced image synthesis and anomaly detection techniques.

Use this if you are a researcher developing or applying advanced generative models for image synthesis, reconstruction, or anomaly detection, and you need to implement or evaluate energy-based prior models with diffusion-amortized MCMC.

Not ideal if you are looking for an out-of-the-box solution for image editing or simple image classification, as this project requires deep technical expertise in machine learning and model training.

generative-modeling image-synthesis anomaly-detection machine-learning-research computer-vision
No License No Package No Dependents
Maintenance 10 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

13

Forks

Language

Python

License

Last pushed

Mar 01, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/yuPeiyu98/Diffusion-Amortized-MCMC"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.