MIT 6.S184: Introduction to Flow Matching and Diffusion Models

Our MIT class “6.S184: Introduction to Flow Matching and Diffusion Models” is now available on YouTube!<p>We teach state-of-the-art generative AI algorithms for images, videos, proteins, etc. together with the mathematical tools to understand them.<p>Flow and diffusion models are mathematically demanding subjects - which is why many lectures restrict themselves to teaching high level intuition. Here, we give a mathematically rigorous and self-contained introduction yet aimed at beginners in AI. We hope you will like it!<p>From: <a href="https:&#x2F;&#x2F;x.com&#x2F;peholderrieth" rel="nofollow">https:&#x2F;&#x2F;x.com&#x2F;peholderrieth</a>

Conditional normalizing flows are one of the most beautiful solutions to inverse design problems that I’ve come across, if you have the data to train them. Something about the notion of carefully deforming a base distribution by pushing and pulling its probability mass around until it’s in the right location by using bijective functions (which themselves have very clever constructions) is just so elegant…<p>I’ve had some trickiness trying to get them to work when some of the targets are continuous and some categorical, but regardless just a really cool method… really nailed it on the name imo!

Cool course, can&#x27;t wait to go through it! I noticed that this is focused strictly on continuous spaces, but there&#x27;s a lot of cool stuff going on in discrete diffusion. Any plans for a follow up? I couldn&#x27;t help but notice that the course teacher Peter just came out with a paper for discrete diffusion too.<p><a href="https:&#x2F;&#x2F;x.com&#x2F;peholderrieth&#x2F;status&#x2F;1891846309952282661" rel="nofollow">https:&#x2F;&#x2F;x.com&#x2F;peholderrieth&#x2F;status&#x2F;1891846309952282661</a><p><a href="https:&#x2F;&#x2F;github.com&#x2F;kuleshov-group&#x2F;awesome-discrete-diffusion-models">https:&#x2F;&#x2F;github.com&#x2F;kuleshov-group&#x2F;awesome-discrete-diffusion...</a>

Does anyone have a collection of all public courses on latest AI techniques?

I&#x27;m incredibly grateful for MIT OCW and consorts. I&#x27;ve been using it as a secondary resource for my subjects and learning about the same topic in two different ways is incredibly helpful, especially hard to grasp ones.

I&#x27;m so happy to find this here. LLMs seem to have diverted a lot of attention away from this incredibly useful technique.

Would one of you, who is familiar with this topic, help me understand the primary use case(s) along with a few words, just your overall take on these techniques?<p>Thanks and appreciated in advance.

Thanks again. Past decade has been golden era for deep learning education. I love the fights of who will make high quality learning content free

Great for MIT to be putting out such timely and relevant content for free!

Thank you so much, what other OCW courses exist on modern AI?

This is exactly what I was looking for! Thanks for sharing

Well done, folks. Congrats!

Nice