Flow Matching

This is what pi0 uses.

Flow matching is a training method used to learn a mapping from a source distribution to a target distribution by approximating the underlying vector field.

The paper:

• https://arxiv.org/pdf/2210.02747

Resources

• https://mlg.eng.cam.ac.uk/blog/2024/01/20/flow-matching.html
• https://diffusionflow.github.io/
• https://www.youtube.com/watch?v=DDq_pIfHqLs&ab_channel=Jia-BinHuang
• https://www.youtube.com/watch?v=7cMzfkWFWhI

Flow matching vs. Flow-Based Model?

Flow-based models care about exact probabilities. Flow matching cares about how to move from one distribution to another.

Related

• Normalizing Flow