Deep Generative Models
Updates
-
[Sep 16] Homework 1 has been posted on Canvas under the Assignments section. Please review the instructions in the problem set and submit your solutions on Gradescope.
- Homework 1 due: 09/29/2026, 12:00 PM (Noon) Eastern Time.
- Quiz 1 (in-person): 09/29/2026, 1:45 PM Eastern Time, AGH 203.
If you have any questions, feel free to reach out via Ed Discussion or come to office hours.
-
[Sep 15] The most recent recording can always be accessed through Canvas → Class Recordings. Please note that this website may be updated with a slight delay.
-
[Sep 9] Slides and recordings have moved to the Course Schedule page.
Course Description
Generative models have found widespread applications in science and engineering. Recent progress in deep learning has enabled the application of generative models to complex high-dimensional data such as images, videos, text and speech. This course will cover state-of-the-art deep generative models, including variational autoencoders (VAEs), auto-regressive models, diffusion models, and generative adversarial networks (GANs). The course will also illustrate various applications of deep generative models to image and video generation, text and speech generation, image captioning, text-to-image generation, and inverse problems.
