Theory and Applications of Generative Models
-
Instructor: Yao-Liang Yu
-
Email: yaoliang.yu@uwaterloo.ca
-
Time and location:
- M 10:00-12:50, DC 2585
-
Office hour: by email appointment
Lectures (Tentative)
| Date | Topic | Slides | Notes | |
| 01 | Sep 14, 2026 | Transport | ||
| 02 | Sep 21, 2026 | Diffusion | ||
| 03 | Sep 28, 2026 | Flow | ||
| 04 | Oct 05, 2026 | Discrete | ||
| reading week | ||||
| reading week | ||||
| 05 | Oct 19, 2026 | Training | ||
| 06 | Oct 26, 2026 | Inference | ||
| 07 | Nov 02, 2026 | Guidance | ||
| 08 | Nov 09, 2026 | Distillation | ||
| 09 | Nov 16, 2026 | Memorization | ||
| 10 | Nov 23, 2026 | Deconvolution | ||
| 11 | Nov 30, 2026 | Purification | ||
| 12 | Dec 07, 2026 | Finance | ||
| !!! | Dec 18, 2026 | Final Project | ||
Evaluations
Each student will give two presentations in the second part of the course, together worth 30%. We reserve 20% for course participation (engaging in discussion, asking questions, additional readings / experimentations, etc.).
There will be a final course project that
- relates to generative models (either algorithmic, theoretical or applied)
- allows you to learn something new (and hopefully significant)
- is interesting and nontrivial, preferably publishable
Project template: download zip
Project proposal: You need to submit a project proposal (10%) by November 9, 2026. Please elaborate the following:
- What is the project about? What is the goal?
- Initial literature search: what has been done? What remains open?
- Feasibility study: convince us your proposal is within reach. If possible, include simple toy examples or quick experiments.
- Dataset, evaluation and computing (if applicable): make sure you have all the resource for your project. Talk to me if you need help.
Please write your proposal using the provided template and limit yourself to 2 pages + 1 page solely for figures and tables (if needed) + 1 page solely for reference.
Project report: You need to submit a project report (40%) by December 18, 2025 that summarizes all your findings (empirical, algorithmic, theoretical). We expect there is an introduction section, a background section, a main result section, and a conclusion section. Depending on your project, you may include an experimental section and/or discussion section. Please always give proper citations to prior work or results. Be precise and concise. We expect the report to be at most 8 pages (excluding references). Your project report will be evaluated by its clarity, significance, rigor, presentation, and completeness.
Textbook
There is no required textbook, but the following fine text is recommended.
- Max Welling, Sirui Lu and Lars Holdijk. Generative AI and Stochastic Thermodynamics. Cambridge University Press, 2026.
Resource
- Colab
- Canada Compute, require a faculty (e.g., supervisor) sponsor
Use of Artificial Intelligence Tools
The use of generative AI tools (such as ChatGPT, Claude, Gemini, GitHub Copilot, and similar tools) is permitted in this course as a learning aid. However, all submitted work must reflect your own understanding and intellectual effort. You are responsible for completing the assigned work independently and for being able to explain and justify everything you submit.
AI tools may be used, for example, to clarify concepts, obtain feedback on your work, improve writing, or assist with debugging. They should not be used to generate solutions or substantial portions of an assignment that you then submit as your own work.
Whenever you use an AI tool in completing an assignment, you must include a brief declaration stating which tool(s) you used and how you used them. If you did not use any AI tools, no declaration is necessary.
You remain fully responsible for the correctness, originality, and integrity of all work you submit. Undeclared or inappropriate use of AI may be treated as a violation of the course’s academic integrity requirements.
Policy
Academic Integrity: In order to maintain a culture of academic integrity, members of the University of Waterloo community are expected to promote honesty, trust, fairness, respect and responsibility. Check the university website for more information.
Grievance: A student who believes that a decision affecting some aspect of his/her university life has been unfair or unreasonable may have grounds for initiating a grievance. Read Policy 70, Student Petitions and Grievances, Section 4. When in doubt please be certain to contact the department’s administrative assistant who will provide further assistance.
Discipline: A student is expected to know what constitutes academic integrity to avoid committing an academic offence, and to take responsibility for his/her actions. A student who is unsure whether an action constitutes an offence, or who needs help in learning how to avoid offences (e.g., plagiarism, cheating) or about “rules” for group work/collaboration should seek guidance from the course instructor, academic advisor, or the undergraduate Associate Dean. For information on categories of offences and types of penalties, students should refer to Policy 71, Student Discipline. For typical penalties check Guidelines for the Assessment of Penalties.
Appeals: A decision made or penalty imposed under Policy 70 (Student Petitions and Grievances) (other than a petition) or Policy 71 (Student Discipline) may be appealed if there is a ground. A student who believes he/she has a ground for an appeal should refer to Policy 72 (Student Appeals).
Note for Students with Disabilities: The Office for Persons with Disabilities (OPD), located in Needles Hall, Room 1132, collaborates with all academic departments to arrange appropriate accommodations for students with disabilities without compromising the academic integrity of the curriculum. If you require academic accommodations to lessen the impact of your disability, please register with the OPD at the beginning of each academic term.
Mental Health: If you or anyone you know experiences any academic stress, difficult life events, or feelings like anxiety or depression, we strongly encourage you to seek support.
On-campus Resources
- Campus Wellness https://uwaterloo.ca/campus-wellness/
- Counselling Services: counselling.services@uwaterloo.ca / 519-888-4567 ext 32655 / Needles Hall North 2nd floor, (NH 2401)
- MATES: one-to-one peer support program offered by Federation of Students (FEDS) and Counselling Services: mates@uwaterloo.ca
- Health Services service: located across the creek from Student Life Centre, 519-888-4096.
Off-campus Resources
- Good2Talk (24/7): Free confidential help line for post-secondary students. Phone: 1-866-925-5454
- Here 24/7: Mental Health and Crisis Service Team. Phone: 1-844-437-3247
- OK2BME: set of support services for lesbian, gay, bisexual, transgender or questioning teens in Waterloo. Phone: 519-884-0000 extension 213
Diversity: It is our intent that students from all diverse backgrounds and perspectives be well served by this course, and that students’ learning needs be addressed both in and out of class. We recognize the immense value of the diversity in identities, perspectives, and contributions that students bring, and the benefit it has on our educational environment. Your suggestions are encouraged and appreciated. Please let us know ways to improve the effectiveness of the course for you personally or for other students or student groups. In particular:
- We will gladly honour your request to address you by an alternate/preferred name or gender pronoun. Please advise us of this preference early in the semester so we may make appropriate changes to our records.
- We will honour your religious holidays and celebrations. Please inform of us these at the start of the course.
- We will follow AccessAbility Services guidelines and protocols on how to best support students with different learning needs.