Fall 2025

CSE 510 GenAI (Lecture)
Section: SREY
Instructor: Sreyasee Das Bhattacharjee
Description: This course is intended for Computer Science students who are interested in understanding the fundamental issues, challenges and techniques that are associated with recent advances in Generative Artificial Intelligence (Generative AI). The course will discuss the history and properties of basic Generative AI systems including foundational probabilistic principles of generative models, their learning algorithms, and several state-of-the-art model families, which include variational autoencoders, generative adversarial networks, autoregressive models, flow based models, energy based models, and diffusion models. The course will be a combination of lectures, discussions, hands-on activities and projects. During the entire course, students will also learn about different applications in domains like computer vision, natural language processing, healthcare, etc.
Prereqs: CSE 574, or, CSE555, or equivalent graduate level courses on AI topics
Instruction Mode: In person
Class #: 23173
Dates: 08/25/2025 - 12/08/2025
Days, Time: TR, 3:30PM-4:50PM
Location: Frnczk 454, North Campus
Credit Hours: 1-3
Enrollment: 3/20 (0/20 seats reserved: force registration only) (Active)
Info:
CSE 610 Introduction to AI for Health (Lecture)
Section: XU
Instructor: Wenyao Xu
Description: Course Description This course explores the transformative applications of artificial intelligence in healthcare settings. Students will examine how AI technologies are reshaping various domains of healthcare, from wearable devices and public health initiatives to critical care environments and mental health services. The curriculum covers cutting-edge topics including electronic health records, medical imaging analysis, chronic disease management, physician burnout prediction, causal machine learning for health outcomes, large language models in clinical settings, and essential considerations for security and privacy in health AI systems. Through a project-based approach, students will gain hands-on experience developing and implementing AI solutions for real-world healthcare challenges. The course emphasizes both technical competency and critical evaluation of AI technologies in the health sector. Students will work in collaborative teams to design, iterate, and present their projects while also developing individual critique skills to thoughtfully assess AI implementations in healthcare contexts. Assessment Structure Assessment is primarily based on team projects (60%), which include a proposal and presentation (10%), two progressive demonstrations (5% each), and a final demonstration with comprehensive report (40%). Individual critiques and material reading of healthcare AI applications comprise 35% of the grade, with class participation accounting for the remaining 5%. Note that final scores will NOT be curved. Collaboration Guidelines While project components should be completed collaboratively within designated teams, all critique assignments must be completed independently with no collaboration permitted.
Notes: Welcome to contact the instructor if students have any questions for selecting this course.
Instruction Mode: In person
Class #: 23192
Dates: 08/25/2025 - 12/08/2025
Days, Time: F, 9:00AM-11:50AM
Location: Davis 113A, North Campus
Credit Hours: 3
Enrollment: 3/25 (Active)
Info:
CSE 708 Programming Massively Parallel Computers (Seminar)
Section: MILL
Instructor: Russ Miller
Description: The focus of this course is experimental (hands-on) parallel computing. Each student is responsible for a semester-long project of their choosing. Seminars are graded S/U. Grade is based on the project, as well as two formal talks, using presentation software (e.g., PowerPoint), that covers your project, including a definition and justification of the problem, sequential and parallel solution strategies, and a significant set of running times on large parallel systems that allow for an analysis and explanation of Amdahl's and Gustafson's speedups. In particular, the first talk provides a brief explanation of the proposed project, goals, expectations, and a timeline of the work to be performed. The second talk provides a summary of accomplishments. Students are encouraged to look at the final talks from previous semesters, available on my website. Historically, it has been the case that a successfully completed project satisfies the requirement for a project in the M.S. program. Please check with the grad coordinator to see if this is still the case. (The student who completes the project successfully is responsible for filling out the proper paperwork and presenting it to Dr. Miller for a signature.) NB: There will be a cap on the number of students allowed to enroll in the course, so that those who are enrolled will have a full experience and educational opportunity.
Instruction Mode: Remote: real time
Class #: 19922
Dates: 08/25/2025 - 12/08/2025
Days, Time: T, 5:00PM-7:50PM
Location: Remote
Credit Hours: 1-3
Enrollment: 3/20 (Active)
Info:
CSE 710 Advanced Seminar on Foundation Models (Seminar)
Section: LOKH
Instructor: Vishnu Lokhande
Description: This course will explore the cutting-edge field of foundation models, which have transformed contemporary machine learning on a wide range of tasks after being trained on enormous volumes of raw data. We will examine the fundamental ideas that underpin the effectiveness or shortcomings of these models in this advanced course, with a focus on their reliability and trustworthiness. Students will engage with recent developments in the literature, focusing on vision-language models, and will also explore large language models and vision-audio models. Depending on time, the course may extend into the application of these models in generating visual, audio, and video content. The course will be structured with both readings of critical papers and expert-led presentations. Throughout the semester, each student will give one or two lectures. They must turn in a draft of their slide deck at least 24 hours in advance. Students will also have the chance to embark on a research project that will result in a 5-page paper written in the NeurIPS style.
Notes: https://docs.google.com/document/d/1m2LqhlYzaxL8KoXpd1tXg3cN2m6YW0T9hnIrETftCRk/pub
Instruction Mode: In person
Class #: 22473
Dates: 08/25/2025 - 12/08/2025
Days, Time: W, 4:00PM-6:40PM
Location: Davis 113A, North Campus
Credit Hours: 1-3
Enrollment: 15/20 (Active)
Info:
CSE 715 Design and Implementation of Applications for Computing with Private Data (Seminar)
Section: MBLA
Instructor: Marina Blanton
Description: The course involves learning about cryptographic techniques that enable secure computation on private data and using them to build privacy-preserving applications that handle private data from multiple sources. The introductory portion of the course will cover several techniques that permit privacy-preserving computation. Consequently, a number of different applications and the corresponding secure computation protocols will be presented and discussed. This will involve reading the assigned articles and presenting them in class.

Another component of the course consists of experimenting with secure multi-party computation tools. Students will become familiar with writing programs for computing on private data, transforming them into secure computation protocols, and executing them on sample data. An important part of the course is the course project that asks students to create their own application and present it at the end of the semester.

The content heavily relies on cryptographic techniques and thus familiarity with security and/or cryptography concepts will make reading the literature easier.
Instruction Mode: In person
Class #: 23093
Dates: 08/25/2025 - 12/08/2025
Days, Time: T, 2:00PM-4:50PM
Location: Baldy 106, North Campus
Credit Hours: 1-3
Enrollment: 6/20 (Active)
Info: