Jhomanik/Optimal-Flow-Matching

The official repository for the paper "Optimal Flow Matching: Learning Straight Trajectories in Just One Step" (NeurIPS 2024)

22
/ 100
Experimental

This is a developer tool for researchers working in machine learning and optimal transport. It provides code to implement a new method called Optimal Flow Matching (OFM), which efficiently learns direct paths between different data distributions using a single step. Researchers who develop or apply advanced machine learning models for tasks like generative modeling or data transformation would find this useful.

110 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher or practitioner exploring novel methods for generative modeling or efficient data distribution transformation, particularly those involving optimal transport.

Not ideal if you are looking for a plug-and-play solution for data analysis or a tool for general machine learning tasks without deep expertise in flow matching or optimal transport.

Machine Learning Research Optimal Transport Generative Models Flow Matching Neural Networks
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 5 / 25

How are scores calculated?

Stars

110

Forks

3

Language

Jupyter Notebook

License

Last pushed

Dec 19, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/Jhomanik/Optimal-Flow-Matching"

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