Skip to main content

CS 9840: Probabilistic Generative AI

Summarized course website for CS 9840: Probabilistic GenAI, Winter 2026. Students will learn the theoretical foundations for generative AI.

From chatbots to image generators, Generative AI (GenAI) is reshaping the world. What algorithms and probabilistic principles power this revolution? This course introduces the theoretical and algorithmic foundations of GenAI, covering large language models (LLMs) and diffusion models, among more mature methods. We will also explore applications in AI for Science, such as drug discovery and weather forecasting.

info

Detailed course information is on OWL Brightspace (available starting Jan 2026) and the course outline.

Prerequisites

There are no formal prerequisites. But, since GenAI is inherently probabilistic, some knowledge of the following is necessary.

tip

There will be review sessions (Weeks 1 & 2). However, students who are not comfortable with these concepts are highly encouraged to independently read the D2L book, Chapter 2.

  • Probability/statistics:
    • sum, product, and Bayes' rule,
    • probability distributions (Gaussians, Categorical),
    • maximum likelihood.
  • Linear algebra:
    • vectors and matrices,
    • matrices/vectors products,
    • matrix inversion.
  • Multivariable calculus:
    • partial derivatives, gradients, Jacobians, & Hessians,
    • multivariable integration.
  • Machine learning:
    • regression, classification,
    • neural networks,
    • gradient descent,
    • familiarity with deep learning libraries (code examples are in PyTorch).

Schedule

info
  • Lecture: Tuesdays, 10 AM–12 PM.
  • Tutorial: Thursdays, 1:00 PM–2:00 PM.
  • Office hour: Thursdays, 2:00 PM–3:00 PM.

WeekDateLecture (Tue)Tutorial (Thu)Resources
1Jan 6Introduction, probability review, adminsLinear algebra & calculus reviewBishop 2024, Chapters 2 & 3; D2L, Chapter 2
2Jan 13Neural networks review & deterministic autoencodersVariational autoencodersBishop 2024, Chapter 19; D2L, Chapter 2
3Jan 20Explicit and implicit likelihood modelsProject info sessionBishop 2024, Chapters 17 & 18
4Jan 27Application: Latent space Bayesian optimizationSelected topics in GenAIKristiadi 2025, Chapter 1; Garnett 2023, Chapter 1; Gómez-Bombarelli et al., ACS 2018
5Feb 3Diffusion Models I: IntroductionStylistic scientific writing 101Bishop 2024, Chapter 20
6Feb 10Diffusion Models II: Advanced TopicsHW 1Bishop 2024, Chapter 20
7Feb 17Reading weekNo classes
8Feb 24Application: Climate modelingProject proposal deadline & HW 2Price et al., Nature 2025
9Mar 3LLMs I: ArchitecturesHW 3Bishop 2024, Chapter 12; D2L Chapter 11
10Mar 10LLMs II: Decoding and reasoningHW 4Bishop 2024, Sec. 12.3.2; D2L Sec. 10.8; Lightman et al., ICLR 2023
11Mar 17LLMs III: Finetuning and alignmentQ&A, any topics. Submit questions in advance on Slido.Bishop 2024, Chapter 12; Steinnon et al., NeurIPS 2020; Hu et al., ICLR 2022
12Mar 24Uncertainty quantification in GenAIQ&A, any topics. Submit questions in advance on Slido.Kendall and Gal, NIPS 2017
13Mar 31Project presentationsProject presentations

info
  • HW 1–4 due at 12 PM (noon) on the day of the respective tutorial.
  • Project proposal must be submitted by Thursday, Feb 26, 12 PM (noon).
  • Project presentation slides must be submitted by Monday, Mar 30, 11:59 PM. The presentation order will be drawn randomly.
  • Project final report must be submitted by Thursday, Apr 9, 11:59 PM.

References

  1. Bishop, "Deep Learning: Foundations and Concepts", Springer, 2024. [Link]
  2. Zhang, Lipton, Li, and Smola, "Dive into Deep Learning (D2L)". [Link]
  3. Garnett, Roman, "Bayesian Optimization", Cambridge University Press, 2023. [Link]
  4. Kristiadi, Agustinus, "Introduction to the Analysis of Probabilistic Decision-Making Algorithms", 2025. [Link]
  5. Gómez-Bombarelli, et al., "Automatic chemical design using a data-driven continuous representation of molecules", ACS Central Science 4(2), 2018. [Link]
  6. Price, et al., "Probabilistic weather forecasting with machine learning", Nature 637(8044), 2025. [Link]
  7. Stiennon, et al., "Learning to summarize with human feedback", NeurIPS, 2020. [Link]
  8. Lightman, et al., "Let's verify step by step." ICLR. 2023. [Link]
  9. Hu, et al., "LoRA: Low-rank adaptation of large language models", ICLR, 2022. [Link]
  10. Kendall and Gal. "What uncertainties do we need in Bayesian deep learning for computer vision?", NIPS, 2017. [Link]

Grading

Students will be asked to form groups of 2 in the early weeks of the course. All homeworks and project are to be done in group. Homework assignment sheets will be available on OWL Brightspace. Refer to the course outline for detailed information.

TypeWeightCountTotal
Homework10%440%
Project Proposal15%115%
Project Final Presentation20%120%
Project Final Report25%125%
Total--100%

Policies

  • GenAI such as LLM chatbots must not be used to generate HW solutions and reports/slides.
  • Acceptable use of GenAI: (Must be disclosed as at the end of each document.)
  • Late submissions will not be marked since HWs and project are done in a group.

Refer to the course outline for more info and other polices.