Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
TorchCFM: a Conditional Flow Matching library
| Date | Stars |
|---|---|
| 2026-07-24 | 2544 |
| 2026-07-25 | 2545 |
| 2026-07-28 | 2545 |
| 2026-07-30 | 2545 |
| 2026-08-06 | 2545 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center"> # TorchCFM: a Conditional Flow Matching library <!---[](https://papers.nips.cc/paper/2020) --> <!---[](https://github.com/atong01/conditional-flow-matching/graphs/contributors) --> [](https://arxiv.org/abs/2302.00482) [](https://arxiv.org/abs/2307.03672) [](https://pytorch.org/get-started/locally/) [](https://pytorchlightning.ai/) [](https://hydra.cc/) [](https://black.readthedocs.io/en/stable/) [](https://github.com/pre-commit/pre-commit) [](https://github.com/atong01/conditional-flow-matching/actions/workflows/test.yaml) [](https://codecov.io/gh/atong01/conditional-flow-matching/) [](https://github.com/atong01/conditional-flow-matching/actions/workflows/code-quality-main.yaml) [](https://github.com/atong01/conditional-flow-matching#license) <a href="https://github.com/ashleve/lightning-hydra-template"><img alt="Template" src="https://img.shields.io/badge/-Lightning--Hydra--Template-017F2F?style=flat&logo=github&labelColor=gray"></a> [](https://pepy.tech/project/torchcfm) [](https://pepy.tech/project/torchcfm) </div> ## Description Conditional Flow Matching (CFM) is a fast way to train continuous normalizing flow (CNF) models. CFM is a simulation-free training objective for continuous normalizing flows that allows conditional generative modeling and speeds up training and inference. CFM's performance closes the gap between CNFs and diffusion models. To spread its use within the machine learning community, we have built a library focused on Flow Matching methods: TorchCFM. TorchCFM is a library showing how Flow Matching methods can be trained and used to deal with image generation, single-cell dynamics, tabular data and soon SO(3) data. <p align="center"> <img src="assets/169_generated_samples_otcfm.png" width="600"/> <img src="assets/8gaussians-to-moons.gif" /> </p> The density, vector field, and trajectories of simulation-free CNF training schemes: mapping 8 Gaussians to two moons (above) and a single Gaussian to two moons (below). Action matching with the same architecture (3x64 MLP with SeLU activations) underfits with the ReLU, SiLU, and SiLU activations as suggested in the [example code](https://github.com/necludov/jam), but it seems to fit better under our training setup (Action-Matching (Swish)). The GIF above is produced by the `examples/2D_tutorials/model-comparison-plotting.ipynb` notebook: [](https://colab.research.google.com/github/atong01/conditional-flow-matching/blob/master/examples/2D_tutorials/model-comparison-plotting.ipynb). We also have included an example of unconditional MNIST generation in `examples/image
Excerpt of 13,885 characters
Read on GitHub
Kilian · United States
172
Alexander Tong · Austria
112
8
8
University of Edinburgh · United Kingdom
5
Imahn Shekhzadeh
4
2
1
1
Mukunda Rao Katta · Open to opportunities
1
1
Paul Maria Scheikl · Germany
1
Alex Morehead · Lawrence Berkeley National Laboratory · United States
1
Scott H. Hawley · Belmont University, Hyperstate Music · Tunisia
1
1
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:41a805c431aecd61, topic:pytorch