GENERATIVE AI

Class overview

Generative AI are unsupervised machine learning methods that can create a wide variety of data, such as images, videos, audio, text, and 3D models. Deep generative models are the fundamental tools behind generative AI. They combine the generality of probabilistic reasoning with the scalability of deep learning. This course will study the probabilistic foundations and learning algorithms in generative AI, including variational autoencoders, generative adversarial networks, autoregressive models, normalizing flow, and diffusion models. This is a graduate-level course with an emphasis on mathematical principles as well as practical know-how. The course will be a combination of lectures, student presentations, and team projects.

Lecturer: Qi (Rose) Yu (roseyu@ucsd.edu)

TA: Bo Zhao (bozhao@ucsd.edu), Hansen Lillemark (hlillemark@ucsd.edu)
Time: 2:00 pm - 3:30 pm PT Tue, Thur
Location: Remote (to accommdate international students who faced visa challenges)
Canvas: https://canvas.ucsd.edu/courses/68703
Piazza: https://piazza.com/ucsd/fall2025/cse291
Office Hours:

Rose Yu | EBU3B 4216 | Mon 4:00 - 5:00 pm or by appointment
TBD

Syllabus

Week 1 (Sep 25) Introduction and deep learning recap

Week 2 (Sep 30/Oct 2) Generative AI background Oct 2: HW 1 release

Week 3 (Oct 7/Oct 9) Autogressive Models Oct 7: Project poposal release

Week 4 (Oct 14/Oct 16) Variational Autoencoder Oct 16: HW 1 due; Oct 19: Project Proposal Due

Week 5 (Oct 21/Oct 23) Generative Adversarial networks Oct 21: Milestone release; Oct 23: HW 2 release

Week 6 (Oct 27/Oct 39) Normalizing Flow

Week 7 (Nov 4/Nov 6) Energy-Based Model Nov 4: HW2 due; Nov 9: Project Milestone Due

Week 8 (Nov 13) Diffusion Models Nov 11: Final report release; Nov 13: HW3 release

Week 9 (Nov 18/Nov 20) Large Language Models

Week 10 (Nov 25) GenAI Evaluation Nov 26: HW3 due; Dec 30; presentation due

Week 11 (Dec 2) Final project poster presentation Dec 7th: Project Final Report Due

Lectures

Lecture Slides

Latex Template

Class Assessment

30 % homework (10% x 3)
50 % project
- 5 % proposal
- 15 % milestone report
- 20 % final report
- 10 % final presentation
20 % paper reading

Resources

Project Related

Project Page

Reading Materials

FAQ

Q: What are the pre-requisites?

Familiarity with statistical inference and deep learning.
Have taken at least an equivalent of CSE 250A and CSE 253.
Proficiency in Python.

Q: Can masters/undergraduates take this course?

This a graduate level audience.
Exceptional masters/undergraduates are welcome.

About me

My Chinese name is Qi Yu. That is also the instructor name in the registrar's office. I publish under the name Rose Yu. You can learn more about my research at my personal website.