Cornell CS 6785: Deep Generative Models. Lecture 12: Score-Based Generative Models

Cornell CS 6785: Deep Generative Models. Lecture 12: Score-Based Generative Models
Presented by Prof. Kuleshov from Cornell University | Curated & Edited by Michael Ahedor
Instructor: www.cs.cornell.edu/~kuleshov/
Course Website: kuleshov-group.github.io/dgm-...
Follow us on Twitter/X here: / volokuleshov
00:00 Intro
14:08 Lecture
1:15:32 Summary

[@Geraltofrivia12gdhdbruwj]

One of the most amazing lectures. Ive never seen a lecture on generative models that is so connected like these, from simple autoregressive, to latent models, to gans, to energy-based, langevin dynamics, and finally to diffusion models, all are connected! The connectedness and story telling are so amazing! thank you Prof!

[@chenweilong2505]

Amazing Lectures! Can't wait to watch the next diffusion lecture! Awesome!

[@DrumsBah]

Presenting the unified view of Energy, Score and Diffusion models is invaluable. My coursework didnt cover generative methods beyond VAE and GANs but this presentation has been a great surrogate. Thanks!
A small correction to the proof on slide 14. I think there's possibly a rogue squared s_theta(x) in the third term.

[@micahdelaurentis6551]

why is the score function graph at around 21:00 postive after 5ish? As soon as you past the point corresponding to the mode at around 5 shouldn't it point left (be negative)? Same question for the other mode around -4