Generative AI

10-423 + 10-623 + 10-723, Fall 2025
School of Computer Science
Carnegie Mellon University

Assignments

There will be 5 homework assignments (and a special extra assignment for 10-623 and 10-723 only). The assignments will consist of both theoretical and programming problems. Homework assignments will be released via a Piazza announcement explaining where to find the handout, LaTeX template, etc.

  • Homework 0: PyTorch Primer
    [Handout] [Overleaf]
  • Homework 1: Large Language Models
    [Handout] [Overleaf]
  • Homework 2: Image Generation
  • Homework 3: Applying and Adapting LLMs
  • Homework 4: Multimodal Foundation Models
  • Homework 623: (10-623 and 10-723 only)

Tentative release dates and due dates are listed on the Schedule page.

Quizzes

There will be 5 quizzes (plus an additional quiz for 10-723 students only).

  • Quiz 1 (Lectures 1 - 4)
  • Quiz 2 (Lectures 5 - 9)
  • Quiz 3 (Lectures 9 - 12)
  • Quiz 4 (Lectures 12 - 15)
  • Quiz 5 (Lectures 16 - 20)
  • Quiz723 (Lecture 21 - 24) for 10-723 students only

Exams

There will be one exam.

  • Midterm Exam

Project

The course project affords an opportunity to apply generative modeling to a real-world machine learning problem in your domain of interest. The work will be completed in the last 4 weeks of the course, written up in a report, and presented at the poster session. Students will submit several deliverables throughout the semester. The (tentative) deadlines for each component of the project are listed on the Schedule page.

  1. Team Formation: Each team will consist of 3 people. Teams must be specified in advance of the proposal deadline.
  2. Proposal: The proposal will describe the task, dataset, methods, and goals for the project.
  3. Midway report: The midway report presents each group a chance to present their progress partway through the project’s duration.
  4. Final report: The final report will describe the methods that were used and the present experimental results that illustrate a contrast between competing methods.
  5. Final poster: The final poster should summarize the accomplishments of the project. (Students are required to attend the final poster session.)