Course Syllabus

**Title of Course [Generative AI]**

Prefix and Number [CPTS 544]

Semester and Year [Spring 2026]

Number of Credit Hours [3]

Prerequisites [570 Machine Learning]

Course Details

Day and Time: [tbd]

Meeting Location: [tbd]

Instructor Contact Information

Instructor Name: [tbd]

Instructor Contact Information: [office location, phone, email] [tbd]

Instructor Office Hours: [click here for best practices] [tbd]

TA Name: [tbd]

TA Contact Information: [office location, phone, email]: [tbd]

TA Office Hours: [click here for best practices] [tbd]

Course Description

This course introduces the foundations and modern advances in generative artificial intelligence. Generative AI focuses on models that can learn complex data distributions and synthesize new, high-quality data such as text, images, video, and beyond. Students will study both the theoretical underpinnings and practical implementations of core generative modeling paradigms, including Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), Normalizing Flows, Diffusion Models, Large Language Models (LLMs), Generative Pre-Training, and Flow Matching. Applications discussed will span scientific discovery, creative content generation, conversational agents, and domain-specific modeling. Students will gain experience with both theoretical analysis and hands-on implementation, culminating in the ability to critically evaluate and extend state-of-the-art generative AI methods.

Course Materials

Books: [Probabilistic Machine Learning: Advanced Topics by Kevin Murphy (publicly available), no cost]

Other Materials: [Paper handouts, publicly available, no cost]

Fees: [no cost]

**Student Learning Outcomes (SLOs) [add more lines if necessary]**
Course Learning Outcomes (students will be able to:)	Activities Supporting the Learning Outcomes	Assessment of the Learning Outcomes
Understand the landscape of generative modeling including VAEs, GANs, Normalizing Flows, Diffusion Models, LLMs, Generative Pre-Training, and Flow Matching and articulate their relative strengths, limitations, and areas of application.	Homework exercises and guided discussions will reinforce core theoretical concepts in generative modeling and ensure students can articulate the assumptions and trade-offs of different approaches.	Evaluate understanding of theoretical foundations, derivations, and comparative analysis of generative modeling approaches. Grade: 30%
Design, implement, and evaluate generative models on real-world data, making appropriate modeling choices, selecting evaluation metrics (e.g., likelihood, FID, perplexity, calibration), and addressing robustness and reliability.	Programming assignments will provide hands-on experience with building and analyzing generative models, focusing on practical issues of efficiency, scalability, and statistical performance.	Assess students’ ability to implement, train, and analyze generative models, with attention to computational and statistical trade-offs. Grade: 30%
Critically engage with generative AI research, including reading, presenting, and assessing scholarly papers by identifying contributions, evaluating methodological soundness, recognizing limitations, and proposing future directions.	A semester-long project will allow students to apply generative modeling techniques to a real-world problem of their choice, demonstrating creativity, critical evaluation, and interdisciplinary relevance.	Assess the application of generative modeling to a real-world problem, including project design, execution, written report, and in-class presentation. Grade: 40%

**Course Schedule**

**[Please note that a WSU semester is 15 weeks + Thanksgiving/Spring Break. The schedule below does not include the break.]**
Dates	Lesson Topic	Assignment	Assessment
Week 1 [dates]	Course overview, motivation, applications Learning paradigms (discriminative vs. generative) High-level roadmap	Introduction	No
Week 2 [dates]	Latent variable models KL divergence, ELBO, likelihood vs. implicit models Approximate inference (variational methods, sampling)	Reading	In-class discussion
Week 3 [dates]	Encoder-decoder structure Reparameterization trick Extensions (β-VAE, hierarchical VAEs)	Reading	In-class discussion
Week 4 [dates]	Minimax optimization and adversarial training Mode collapse, stability issues Advances (DCGAN, WGAN, StyleGAN)	Reading HW1 released	In-class discussion
Week 5 [dates]	Change of variables formula Invertible neural networks RealNVP, Glow, continuous normalizing flows	Reading	In-class discussion
Week 6 [dates]	Forward/backward diffusion processes Score matching basics Denoising score matching	Reading HW2 released	In-class discussion HW1 due
Week 7 [dates]	Sampling algorithms (DDPM, DDIM) Classifier guidance, conditional diffusion Applications in image, audio, and beyond	Reading	In-class discussion Project proposal due
Week 8 [dates]	Flow matching formulation Connections to ODE/SDE flows Relation to diffusion and normalizing flows	Exam 1 Reading	In-class discussion HW2 due
Week 9 [dates]	Autoregressive modeling (PixelCNN, WaveNet) Masked prediction (BERT, MAE) Generative pre-training foundations	Reading HW3 released	In-class discussion Exam discussion
Week 10 [dates]	Transformer architecture recap Pre-training objectives (causal LM, masked LM) Scaling laws and compute/data trade-offs	Reading Project check-in (1)	In-class discussion Team discussion
Week 11 [dates]	Fine-tuning (instruction tuning, RLHF, adapters) Evaluation (perplexity, calibration, benchmarks) Deployment considerations	Reading HW4 released	In-class discussion HW3 due
Week 12 [dates]	Text-to-image (DALL·E, Stable Diffusion) Text-to-audio/video Cross-modal alignment and applications	Reading	In-class discussion
Week 13 [dates]	Hybrid models (EBMs + diffusion, flow-guided LLMs) Efficiency: distillation, quantization, low-rank adaptation Recent research highlights	Reading Project check-in (2)	In-class discussion Team discussion HW4 due
Week 14 [dates]	Responsible deployment and governance Open science and reproducibility	Exam 2 Reading	In-class discussion
Week 15 [dates]	Student project presentations	Project Peer Review Attending Presentation	In-class discussion Team discussion Exam 2 review

Expectations for Student Effort

[Describe how much time students should expect to invest in the course each week. Graduate courses should state: "For each hour of lecture equivalent, students should expect to have a minimum of two hours of work outside of class." Note that Global campus courses will automatically include credit hour equivalents in the syllabus.]

Students are expected to attend all classes in person. Zoom recordings will only be made available to students who get permission from Access Center. Missing more than 20% of the class sessions will result in a fail. For each hour of lecture equivalent, students should expect to have a minimum of three hours of work outside class.

Grading [add more lines if necessary]

Assignment Breakdown
Type of Assignment (tests, papers, etc)	Points	Percent of Overall Grade
[Homework]	[100]	[30]
[Exam]	[100]	[30]
[Project]	[100]	[40]

Grading Schema
Grade	Percent	Grade	Percent
A	[85]	C	[55]
A-	[80]	C-	[50]
B+	[75]	D+	[45]
B	[70]	D	[40]
B-	[65]	F	<40
C+	[60]

Final percent score will be rounded up to the nearest integer. In case of tie, it will be rounded up to the larger one (e.g., 89.5 will become 90; 89.25 will become 89)

Attendance and Make-Up Policy

[Provide details on how attendance affects final course grades. Indicate whether and how missed exams, laboratory sessions, etc. can be made up. Sample attendance statement: “Students should make all reasonable efforts to attend all class meetings. However, in the event a student is unable to attend a class, it is the responsibility of the student to inform the instructor as soon as possible, explain the reason for the absence (and provide documentation, if appropriate), and make up class work missed within a reasonable amount of time, if allowed. Missing class meetings may result in reducing the overall grade in the class.” ]

Academic Integrity Statement

You are responsible for reading WSU's Academic Integrity Policy, which is based on Washington State law. If you cheat in your work in this class you will

-Receive a failing grade for the assignment or exam, and possibly a failing grade for the course.

-Be reported to the Office of Student Conduct, where further university-level sanctions (including probation, suspension, or dismissal) may be imposed.

-Be reported to the Center for Community Standards

-Have the right to appeal my decision

-Not be able to drop the course of withdraw from the course until the appeals process is finished

If you have any questions about what you can and cannot do in this course, ask me.

If you want to ask for a change in my decision about academic integrity, use the form at the Center for Community Standards website. You must submit this request within 21 calendar days of the decision.