MCG-NJU/FlowBack

[AAAI 2026] Flowing Backwards: Improving Normalizing Flows via Reverse Representation Alignment

24
/ 100
Experimental

This project helps machine learning researchers and practitioners improve the performance of image generation and classification tasks. By enhancing Normalizing Flows (NFs), it takes raw image datasets as input and produces high-quality synthetic images and more accurate classification models. Researchers and engineers in computer vision and generative AI will find this useful for advancing state-of-the-art models.

Use this if you are developing or applying generative models, specifically Normalizing Flows, and need to improve the quality of generated images or the accuracy of image classification.

Not ideal if you are looking for an out-of-the-box solution for general image editing, object detection, or other computer vision tasks not related to generative modeling or representation learning.

generative-ai image-synthesis computer-vision machine-learning-research representation-learning
No Package No Dependents
Maintenance 6 / 25
Adoption 5 / 25
Maturity 13 / 25
Community 0 / 25

How are scores calculated?

Stars

14

Forks

Language

Python

License

Apache-2.0

Last pushed

Dec 09, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/MCG-NJU/FlowBack"

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