tqch/poisson-jump

Official Implementation of Paper "Learning to Jump: Thinning and Thickening Latent Counts for Generative Modeling" (ICML 2023)

28
/ 100
Experimental

This project offers a method for creating new, realistic data points from existing datasets, such as images or text. It takes your raw data, learns its underlying patterns, and then generates novel samples that resemble the original input. This is primarily useful for researchers and practitioners working with generative models, particularly in fields like machine learning research or computer vision.

No commits in the last 6 months.

Use this if you are a machine learning researcher or practitioner interested in advanced generative modeling techniques for count data or image synthesis.

Not ideal if you are looking for a straightforward, out-of-the-box solution for data augmentation or content generation without deep technical involvement.

generative-modeling machine-learning-research image-synthesis data-generation computational-statistics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 7 / 25

How are scores calculated?

Stars

10

Forks

1

Language

Python

License

MIT

Last pushed

Jun 06, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/tqch/poisson-jump"

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