[HN Gopher] MIT 6.S184: Introduction to Flow Matching and Diffus...
       ___________________________________________________________________
        
       MIT 6.S184: Introduction to Flow Matching and Diffusion Models
        
       Author : __rito__
       Score  : 374 points
       Date   : 2025-03-03 06:27 UTC (1 days ago)
        
 (HTM) web link (diffusion.csail.mit.edu)
 (TXT) w3m dump (diffusion.csail.mit.edu)
        
       | __rito__ wrote:
       | 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
        
         | kla-s wrote:
         | Thank you, for making the effort of making this so accessible!
         | Danke :)
        
         | amelius wrote:
         | Thanks!
         | 
         | By the way, I was trying to go through the MIT Optics [1]
         | course, but the audio/video quality is ... terrible. Could
         | somebody fix that? (Maybe with diffusion models? ;)
         | 
         | [1] https://ocw.mit.edu/courses/2-71-optics-
         | spring-2009/resource...
        
         | actualwitch wrote:
         | Youtube link to playlist:
         | https://www.youtube.com/watch?v=GCoP2w-Cqtg&list=PL57nT7tSGA...
        
         | krosaen wrote:
         | > Flow and diffusion models are mathematically demanding
         | subjects - which is why many lectures restrict themselves to
         | teaching high level intuition.
         | 
         | I appreciate this - I hope norms develop to clearly identify
         | whether learning materials / courses are about intuition or
         | deeper applications that don't shy away from full
         | prerequisites. They both have their place, but can be hard to
         | find the latter amidst the sea of introductory materials that
         | merely give intuition.
        
         | lastdong wrote:
         | Awasemoness! Since my undergrad days (it was a long time ago),
         | I've found myself turning to MIT classes to help me grasp some
         | challenging subjects. It's been such a great resource!
        
       | whiplash451 wrote:
       | Well done, folks. Congrats!
        
       | Verlyn139 wrote:
       | Nice
        
       | jnkml wrote:
       | This is exactly what I was looking for! Thanks for sharing
        
       | ipnon wrote:
       | Does anyone have a collection of all public courses on latest AI
       | techniques?
        
         | coolThingsFirst wrote:
         | This
        
         | esafak wrote:
         | Just start an "awesome AI courses" repo on GitHub and invite
         | PRs. Or update these:
         | 
         | https://github.com/luspr/awesome-ml-courses
         | 
         | https://github.com/owainlewis/awesome-artificial-intelligenc...
        
       | schmorptron wrote:
       | 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.
        
       | szvsw wrote:
       | 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!
        
       | coolThingsFirst wrote:
       | Thank you so much, what other OCW courses exist on modern AI?
        
       | fumeux_fume wrote:
       | I'm so happy to find this here. LLMs seem to have diverted a lot
       | of attention away from this incredibly useful technique.
        
       | arolihas wrote:
       | Cool course, can't wait to go through it! I noticed that this is
       | focused strictly on continuous spaces, but there's a lot of cool
       | stuff going on in discrete diffusion. Any plans for a follow up?
       | I couldn't help but notice that the course teacher Peter just
       | came out with a paper for discrete diffusion too.
       | 
       | https://x.com/peholderrieth/status/1891846309952282661
       | 
       | https://github.com/kuleshov-group/awesome-discrete-diffusion...
        
       | whoisnnamdi wrote:
       | Great for MIT to be putting out such timely and relevant content
       | for free!
        
       | bicepjai wrote:
       | 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
        
       | ddingus wrote:
       | 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.
        
         | x1000 wrote:
         | It's the fundamentals that underly Stable Diffusion, Dalle, and
         | various other SOTA image generation models, video, and audio
         | generation models. They've also started taking off in the field
         | of robotics control [1]. These models are trained to
         | incrementally nudge samples of pure noise onto the
         | distributions of their training data. Because they're trained
         | on noised versions of the training set, the models are able to
         | better explore, navigate, and make use of the regions near the
         | true data distribution in the denoising process. One of the
         | biggest issues with GANs is a thing called "mode collapse" [2].
         | 
         | [1] https://www.physicalintelligence.company/blog/pi0
         | 
         | [2] https://en.wikipedia.org/wiki/Mode_collapse
        
       ___________________________________________________________________
       (page generated 2025-03-04 23:02 UTC)