Improving and Generalizing Flow-Based Generative Models with Minibatch Optimal Transport

Improving and Generalizing Flow-Based Generative Models with Minibatch Optimal Transport

Valence Labs via YouTube Direct link

- Q+A

10 of 10

10 of 10

- Q+A

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Improving and Generalizing Flow-Based Generative Models with Minibatch Optimal Transport

Automatically move to the next video in the Classroom when playback concludes

  1. 1 - Intro
  2. 2 - Background on diffusion + flow models
  3. 3 - Why do diffusion models beat CNFs?
  4. 4 - Main idea: how can we train a CNF like a diffusion model?
  5. 5 - Flow matching
  6. 6 - Conditional flow matching
  7. 7 - Properties of flow depend on the choice of the probability path
  8. 8 - Score and flow matching
  9. 9 - Main takeaways
  10. 10 - Q+A

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.