by __rito__ on 3/3/25, 6:27 AM
Our MIT class “6.S184: Introduction to Flow Matching and Diffusion Models” is now available on YouTube!
We teach state-of-the-art generative AI algorithms for images, videos, proteins, etc. together with the mathematical tools to understand them.
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!
From: https://x.com/peholderrieth
by szvsw on 3/3/25, 11:38 AM
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…
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!
by arolihas on 3/3/25, 4:35 PM
by ipnon on 3/3/25, 9:38 AM
Does anyone have a collection of all public courses on latest AI techniques?
by schmorptron on 3/3/25, 11:07 AM
I'm incredibly grateful for MIT OCW and consorts. I'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.
by fumeux_fume on 3/3/25, 2:51 PM
I'm so happy to find this here. LLMs seem to have diverted a lot of attention away from this incredibly useful technique.
by ddingus on 3/4/25, 12:34 AM
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?
Thanks and appreciated in advance.
by bicepjai on 3/3/25, 11:25 PM
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
by whoisnnamdi on 3/3/25, 6:25 PM
Great for MIT to be putting out such timely and relevant content for free!
by coolThingsFirst on 3/3/25, 11:58 AM
Thank you so much, what other OCW courses exist on modern AI?
by jnkml on 3/3/25, 8:51 AM
This is exactly what I was looking for! Thanks for sharing
by whiplash451 on 3/3/25, 8:08 AM
Well done, folks. Congrats!
by Verlyn139 on 3/3/25, 8:34 AM
Nice