Syllabus

Course Info

• Instructor: Aran Nayebi and Matt Gormley
• Meetings:
  • 10-423 / 10-623 / 10-723: MWF, 2:00 PM - 3:20 PM (DH 2210)
  • Lectures are on Mondays and Wednesdays.
  • Occasional recitations are on Fridays and will be listed on the schedule.
• Piazza: https://piazza.com/cmu/spring2026/10423623723
• Gradescope: https://www.gradescope.com/courses/1208127
• Lecture Livestream: See Piazza Post
• Video Recordings: Panopto
• Office Hours Queue: https://ohq.eberly.cmu.edu/

1. Course Description

From generating images and text to generating music and art, the goal of generative modeling has long been a key challenge for artificial intelligence. This course explores the techniques from machine learning and artificial intelligence that are driving the recent advances in generative modeling and foundation models. Students will understand, develop, and apply state-of-the-art algorithms that enable machines to generate realistic and creative content. Core topics will include: the fundamental mechanisms of learning; how to build generative models and other large foundation models (e.g. transformers for vision and language, diffusion models); how to train such models (pre-training, fine-tuning) and efficiently adapt them (adapters, in-context learning); how to scale up to massive datasets (multi-GPU/distributed optimization); how to employ existing models for everyday use (generating code, coding with a generative model in the loop). Students will also explore the theoretical foundations and empirical attempts to understand their inner workings as well as learn about the ways in which things can go wrong (bias, hallucination, adversarial attacks, data contamination) and ways to combat these problems. Students in the course will develop understanding of modern techniques through implementation, but they will also employ existing libraries and models to explore their generative capabilities and limitations. The course is designed for students who have completed an introductory course in machine learning or deep learning.

Learning Outcomes:

Upon completion of the course, students should be able to…

• Differentiate between different mechanisms of learning such as parameter tuning and in-context learning.
• Implement the foundational models underlying modern approaches to generative modeling, such as transformers and diffusion models.
• Apply existing models to real-world generation problems for text, code, images, audio, and video.
• Employ techniques for adapting foundation models to tasks such as fine-tuning, adapters, and in-context learning.
• Enable methods for generative modeling to scale-up to large datasets of text, code, or images.
• Use existing generative models to solve real-world discriminative problems and for other everyday use cases.
• Analyze the theoretical properties of foundation models at scale.
• Identify potential pitfalls of generative modeling for different modalities.
• Describe societal impacts of large-scale generative AI systems.

For more details about topics covered, see the Schedule page.

2. Prerequisites

Students entering the class are expected to have a pre-existing working knowledge of introductory machine learning or deep learning by taking one of (10301 or 10315 or 10601 or 10701 or 10715 or 11485 or 11685 or 11785).

You must strictly adhere to these pre-requisites! Even if CMU’s registration system does not prevent you from registering for this course, it is still your responsibility to make sure you have all of these prerequisites before you register.

3. Recommended Textbooks

The core content of this course does not follow any one textbook, but readings will be made available for free online.

4. Course Components

Grading

The requirements of this course consist of participating in lectures, quizzes, exams, homework assignments, and a project. The grading breakdown differs for 10-423 and 10-623 and 10-723. The courses are identical in their content, except that students in 10-623 will also do HW623 and students in 10-723 will do HW623 and Quiz723.

10-423:

• 30% Homework Assignments (5 total)
• 10% In-class Quizzes (6 total, but your lowest has half weight)
• 10% Programming Tests (2 total)
• 20% Exam (1 total)
• 25% Project
• 5% Participation
• On Piazza, the Top Student “Endorsed Answer” Answerers can earn bonus points

10-623:

• 30% Homework Assignments (6 total)
• 10% In-class Quizzes (6 total, but your lowest has half weight)
• 10% Programming Tests (2 total)
• 20% Exam (1 total)
• 25% Project
• 5% Participation
• On Piazza, the Top Student “Endorsed Answer” Answerers can earn bonus points

In addition to HW1 - HW4, students registered for 10-623 are required to complete HW623. This assignment will focus on understanding, explaining, and evaluating key topics from the recent literature on generative AI.

10-723:

• 30% Homework Assignments (6 total)
• 10% In-class Quizzes (6 total, equally weighted)
• 10% Programming Tests (2 total)
• 20% Exam (1 total)
• 25% Project
• 5% Participation

• On Piazza, the Top Student “Endorsed Answer” Answerers can earn bonus points

  Unlike 10-423/10-623, the in-class quizzes all receive equal weight in 10-723.

Grade cutoffs:

• ≥ 97% A+
• ≥ 93% A
• ≥ 90% A-
• ≥ 87% B+
• ≥ 83% B
• ≥ 80% B-
• ≥ 77% C+
• ≥ 73% C
• ≥ 70% C-
• ≥ 67% D+
• ≥ 63% D
• otherwise R

Each individual component (e.g. an exam) may be curved upwards at the end. As well, the cutoffs above are merely an upper bound, at the end they may be adjusted down. We expect that the number of students that receive A’s (including A+, A, A-) is at least half the number of students that take the midterm exam(s), and the number of B’s (including B+, B, B-) will be around two-thirds the number of A’s.

Homework

There will be several assignments for 10-423 (and one additional assignments for 10-623 and 10-723 only). They contain both written questions and programming. Written portions ask students to analyze why the algorithms work as they do. The programming portions will both (a) ask students to implement core algorithms from scratch and (b) apply existing libraries and models to real world problems in machine learning.

Your solutions to the programming questions must be written in Python.

More details are listed on the Coursework page.

Human Work (Slot A) and AI Assisted Work (Slot B) The most important learning you do in this course will happen by struggling through challenging problems on the homework. The following system creates every incentive to (1) do human work in order to learn in a first pass, then (2) to correct your misunderstandings through feedback, and finally (3) to practice using AI efficiently and effectively in a second, distinct pass.

For every homework there will be two deadlines: a first called Slot A (for human work), then some feedback, then a second called Slot B (for AI assisted work).

• Slot A (Human work only, limited collaboration): Submit only pure human work to Slot A, no AI assistance is permitted. We will grade your submission and inform you which questions you got incorrect.
• Slot B (AI assisted work and full collaboration permitted): Submit AI assisted work to Slot B, three days after you receive feedback on your Slot A submission. The timing is set so that you can review your mistakes and correct them (possibly with AI or human collaboration). For your Slot B submission, we will only grade the questions that were incorrect in your Slot A submission.
• For each homework problem, your score is the maximum of the Slot A and Slot B submission scores. Additional points will be awarded for getting more than 50% of the available points in Slot A. More specifically: Let \(s_{A,q}\) and \(s_{B,q}\) be the score you received for question $q$ in slot A and B respectively, and \(s_{A}\) be the total score for slot A. Let \(\mathbb{1}(\cdot)\) be the indicator function. Your final homework score will be: \(s = 0.95 \times ( \sum_{q \in HW} \max(s_{A,q}, s_{B,q}) ) + 0.05 \times \mathbb{1}(s_{A} > 0.50)\)
• If you claim that AI assisted work is pure human work (by submitting it to Slot A), you will be penalized with an Academic Integrity Violation (AIV) and a penalty, e.g. failure in the course.
• The course staff will only offer office hours and answer questions about the homework while the Slot A submission is open. We trust you won’t need us during the Slot B submission period since you can collaborate with others.
• No grace days may be used for the Slot A submission.

Quizzes

Unless otherwise noted, all quizzes are closed-book.

You are required to attend all quizzes. All quizzes will take place in-class on either Monday, Wednesday, or Friday. The exact dates are announced on the course schedule.

The quizzes are intended to be a low-stakes assessment, as compared to the exam.

For 10-423 and 10-623, when computing your final average quiz grade, your lowest quiz grade will have half the weight of the other quizzes.

Programming Tests

The programming tests are focused on programming skills for Generative AI. Unlike the exam, which is comprehensive, each programming test will focus on the programming skills you developed in the corresponding homeworks (i.e. Programming Test 1 for HW1/HW2, Programming Test 2 for HW4/HW5).

Unless otherwise noted, all programming tests are closed-book.

You are required to attend all programming tests. All tests will take place in-class on either Monday, Wednesday, or Friday. The exact dates are announced on the course schedule.

Exams

Unless otherwise noted, all exams are closed-book.

You are required to attend the exam. The exam will be given in class and the exact date announced on the course schedule.

If you have an unavoidable conflict with an exam (e.g. an exam in another course), notify us by filling out “exam conflict” form. These Exam Conflict Forms are announced on Piazza before each exam.

If your conflict is with an exam in another course, please promptly email the following people to let them know of the exam conflict:

• the instructor(s) for this course
• the education associate(s) for this course
• the instructor(s) for the other course

In the case of exam conflicts, we will discuss with the other course and suggest a resolution. One possible resolution is that we will accommodate you and will ask you to fill out the exam conflict form above. Please note that email should ONLY be used to address conflicts with an exam in another course. The definition of a final exam conflict and the standard procedures are described here: https://www.cmu.edu/hub/registrar/exams-and-grading/conflict-guidelines.html

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, which will be held during finals week.

More details are listed on the Coursework page.

Participation

Your participation grade in the course will come from activities related to the project and occassional surveys/polls.

Exit Polls

Your submission of the exit polls counts towards your participation grade. There will be one after each homework assignment and one after each exam. You will receive full credit for any exit poll filled in within one week of its release on Piazza.

Lectures

Attendance at lectures is expected. Lectures will be livestreamed and recorded for later viewing, but (because we don’t have a professional videographer) the recording may be of poor quality or technical difficulties could result in no video recording at all.

Recitations

Reciations will be on Fridays.

Attendance at recitations is required whenever there is a quiz scheduled for that day; otherwise attendance is not required, but strongly encouraged.

These sessions will be interactive and focus on problem solving. The recitations will be recorded for later viewing, but we strongly encourage you to actively participate. A problem sheet will usually be released prior to the recitation. If you are unable to attend one or you missed an important detail, feel free to stop by office hours to ask the TAs about the content that was covered. Of course, we also encourage you to exchange notes with your peers.

Office Hours

The schedule for Office Hours will always appear on the Google Calendar on the Office Hours page.

Readings

The purpose of the readings is to provide a broader and deeper foundation than just the lectures and assessments. The readings for this course are required. We recommend you read them after the lecture. Sometimes the readings include whole topics that are not mentioned in lecture; such topics will (in general) not appear on the exams, but we still encourage you to skim those portions.

5. Technologies

We use a variety of technologies:

Piazza

We will use Piazza for all course discussion. Questions about homeworks, course content, logistics, etc. should all be directed to Piazza. If you have a question, chances are several others had the same question. By posting your question publicly on Piazza, the course staff can answer once and everyone benefits. If you have a private question, you should also use Piazza as it will likely receive a faster response.

Gradescope

We use Gradescope to collect PDF submissions of open-ended questions on the homework (e.g. mathematical derivations, plots, short answers). The course staff will manually grade your submission, and you’ll receive personalized feedback explaining your final marks.

You will also submit your code for programming questions on the homework to Gradescope. In general, your code will not be evaluated by an autograder, but you are still required to submit it.

In some cases, upon uploading your PDF, Gradescope will ask you to identify which page(s) contains your solution for each problem – this is a great way to double check that you haven’t left anything out.

Regrade Requests: If you believe an error was made during manual grading, you’ll be able to submit a regrade request on Gradescope. For each homework, regrade requests will be open for only 1 week after the grades have been published. This is to encourage you to check the feedback you’ve received early!

Zoom

Lectures and recitations will be livestreamed via Zoom.

Panopto

Lecture and recitation video recordings will be available on Panopto. The link to the Video Recordings is available in the “Links” dropdown and the recitation recordings will be available.

Cloud Storage

According to SquareTrade, one in three laptops fail over three years. That means your laptop is about to malfunction, perhaps catastrophically. As such, all of your work for this class must be backed up in the cloud. For example, everyone at CMU has storage on Google Drive and so your code can be backed up there. If you do your writeups in Overleaf, you’re already set. But, if you use a tablet, make sure your app is backing up your inked PDF. If you do your work on physical paper, snap an occasional (cloud stored) photo of it.

6. General Policies

Late homework policy

Late Slot A submissions will not be accepted. These late submission policies only apply to Slot B submissions.

Late homework submissions will receive partial credit based on the number of days late (one day is a 24-hour period):

• 1 day late: 75% credit
• 2 days late: 50% credit
• 3 days late: 25% credit

You receive 6 total grace days for use on any homework assignment. We will automatically keep a tally of these grace days for you; they will be applied greedily. No assignment will be accepted more than 3 days after the deadline. This has two important implications: (1) you may not use more than 3 graces days on any single assignment (2) you may not combine grace days with the late policy above to submit more than 3 days late.

All homework submissions are electronic (see Technologies section below). As such, lateness will be determined by the latest timestamp of any part of your submission. For example, suppose the homework requires two submission uploads – if you submit the first upload on time but the second upload 1 minute late, you entire homework will be penalized for the full 24-hour period.

Late Policy for Project Deliverables

Project deliverables submitted late will still receive partial credit as follows:

• 1 day late: 90% credit
• 2 days late: 75% credit
• 3 days late: 55% credit
• 4 days late: 30% credit
• 5 days late: 0% credit

You may not use grace days for project deliverables.

Extensions

In general, we do not grant extensions on assignments or offer a different day/time for a quiz. There are several exceptions:

• Medical Emergencies: If you are sick and unable to complete an assignment or attend class, please go to University Health Services. For minor illnesses, we expect grace days or our late penalties to provide sufficient accommodation. For medical emergencies (e.g. prolonged hospitalization), students may request an extension afterwards.
• Family/Personal Emergencies: If you have a family emergency (e.g. death in the family) or a personal emergency (e.g. mental health crisis), please contact your academic adviser and/or Counseling and Psychological Services (CaPS).
• University-Approved Travel: If you are traveling out-of-town to a university approved event or an academic conference, you may request an extension for any time lost due to traveling. For university approved absences, you must provide confirmation of attendance, usually from a faculty or staff organizer of the event or via travel/conference receipts.

For any of the above situations, you may request an extension by emailing the Education Associate(s) at dpbird@andrew.cmu.edu – do not email the instructor or TAs. Please be specific about which assessment(s) you are requesting an extension for and the number of hours requested. The email should be sent as soon as you are aware of the conflict and at least 5 days prior to the deadline. In the case of an emergency, no notice is needed.

If this is a medical emergency or mental health crisis, you must also CC your CMU College Liaison and your academic advisor. Do not submit any medical documentation to the course staff. If necessary, your College Liaison and The Division of Student Affairs (DoSA) will request such documentation and they will view the health documentation and conclude whether a retroactive extension is appropriate. (If you haven’t interacted with your college liaison before, they are experienced Student Affairs staff who work in partnership with students, housefellows, advisors, faculty, and associate deans in each college to assure support for students regarding their overall Carnegie Mellon experience.)

Audit Policy

Formal auditing of this course is permitted. However, we give priority to students taking the course for a letter grade.

You must follow the official procedures for a Course Audit as outlined by the HUB / registrar. Please do not email the instructor requesting permission to audit. Instead, you should first register for the appropriate section. Next fill out the Course Audit Approval form and obtain the instructor’s signature in-person (either at office hours or immediately after class).

Auditors are required to:

1. Attend or watch all of the lectures.
2. Submit at least 2 of HW1, HW2, HW3, or HW4. You are not required to submit HW0, but if you are unable to complete HW0 you will probably be unable to complete the other assignments.

Auditors are encouraged to sit for the quizzes and exams, but should only do so if they plan to put forth actual effort in solving them.

Pass/Fail Policy

We allow you take the course as Pass/Fail. Instructor permission is not required. What letter grade is the cutoff for a Pass will depend on your specific program; we do not specify whether or not you Pass but rather we compute your letter grade the same as everyone else in the class (i.e. using the cutoffs listed above) and your program converts that letter grade to a Pass or Fail depending on their cutoff. Be sure to check with your program / department as to whether you can count a Pass/Fail course towards your degree requirements.

Accommodations for Students with Disabilities:

If you have a disability and have an accommodations letter from the Disability Resources office, please email the Education Associate(s) at dpbird@andrew.cmu.edu requesting to set up a meeting with them to discuss your accommodations and needs as early in the semester as possible. The EAs will work with you to ensure that accommodations are provided as appropriate. If you suspect that you may have a disability and would benefit from accommodations but are not yet registered with the Office of Disability Resources, I encourage you to contact them at access@andrew.cmu.edu.

7. Collaboration, AI Use, and Academic Integrity

Read this section carefully. The rules below are designed to support learning while making expectations unambiguous.

Overview: Slot A vs. Slot B

Each homework has two submissions with different collaboration rules:

• Slot A (Human Work Only):
  Individual work with limited collaboration and no AI assistance of any kind.
• Slot B (AI-Assisted & Collaborative Work):
  Full collaboration and AI assistance are permitted only to correct mistakes identified in Slot A.

The rules below apply differently depending on the slot. Violating Slot A rules is treated as an Academic Integrity Violation.

Slot A: Human Work Only (Limited Collaboration, No AI)

General Principles

• Slot A is where the primary learning happens.
• You must submit your own human-generated work.
• No generative AI tools may be used (e.g., ChatGPT, GitHub Copilot, Gemini, Claude, Cursor, code agents, etc.).
• Collaboration is encouraged and intended to support learning, not circumvent it. You may discuss homework problems with other students following the rules below.

AI Use (Slot A)

Allowed:

• An important subtlety: You may ask high-level questions to an AI tool in order to understand the concepts, but you may not directly ask an AI tool to answer a homework problem. This is a slippery slope. For this reason, although we give you this freedom, we strongly advise against learning from AI tools during the Slot A submission period.

Not allowed:

• Asking AI tools for answers to homework problems.
• Using an IDE with an AI assistant enabled (e.g. Cursor, GitHub Copilot in VSCode).
• Using a code agent (e.g. Claude Code, Codex).

Collaboration on Written Problems (Slot A)

You are encouraged to discuss ideas, but not exchange solutions.

Allowed:

• Discussing concepts and approaches at a whiteboard or chalkboard, while talking through reasoning steps to ensure mutual understanding.
• Arriving at a solution during the whiteboard/chalkboard discussion.
• Taking notes after the discussion.

Not allowed:

• Showing or sharing complete written or electronic solutions.
• Copying another student’s derivation or final answer.

Collaboration on Programming Problems (Slot A)

You are encouraged to discuss code, but not copy code.

Allowed:

• Debugging or design discussions around one open laptop.
• High-level discussion of logic, structure, or algorithmic ideas.

Not allowed:

• Two laptops open side-by-side.
• Copying, transcribing, or closely paraphrasing another student’s code.
• Taking notes while viewing someone else’s code.

Disclosure Requirement (Slot A)

• You must list all collaborators for each problem in the homework’s collaboration section.
• Failure to disclose collaboration is itself a violation.

Slot B: AI-Assisted Work and Full Collaboration Permitted

Slot B exists so you can fix mistakes and deepen understanding after receiving feedback on Slot A.

Allowed in Slot B:

• Use of generative AI tools for code, explanations, or debugging.
• Working with other students in any format (shared code, pair programming, etc.).
• Comparing solutions directly.

Restrictions:

• Slot B submissions are only graded on questions you missed in Slot A.
• Slot B work must be submitted to Slot B, not Slot A.

Important:
Submitting AI-assisted work to Slot A, or claiming AI-assisted work is human-only work, will be treated as an Academic Integrity Violation and may result in severe penalties, including failure in the course.

Timing of Slot A and Slot B Work

For the sake of everyone in the course and the course staff, please follow these timing rules:

• You must do Slot A style work during the Slot A submission period.
• You must do Slot B style work only after the Slot A submission deadline.

We have no power to enforce that you follow the above timing rules. Yet, we believe you have the self-discipline required to follow them. In order to support the learning community in this course, if you notice a peer violating these timing rules, provide them a friendly reminder of these rules and ask them to do their best to adhere to them.

Found Code and External Sources (Slot A)

You may read textbooks, lecture notes, and instructional materials to understand concepts.

• During Slot A, you must write all code and solutions from scratch, without using external code (including online code, prior solutions, or AI-generated code).
• During Slot B, external code and AI assistance are allowed.

If you encounter code relevant to an assignment during Slot A, you must disclose this in your collaboration statement.

Self-Plagiarism

• Work completed for another course may not be reused.
• If you previously took this course, you may reuse your own prior work.

Duty to Protect Your Work

Do not post homework solutions publicly, during or after the course, to protect future students.

Penalties for Violations

All Academic Integrity Violations are reported to the university.

• First violation: −100% on the assignment.
• Second violation: Failure in the course and possible dismissal from the university.

If you are ever unsure whether something is allowed, assume it is not and ask course staff before submitting.

8. Support

Take care of yourself. Do your best to maintain a healthy lifestyle this semester by eating well, exercising, avoiding drugs and alcohol, getting enough sleep and taking some time to relax. This will help you achieve your goals and cope with stress.

All of us benefit from support during times of struggle. You are not alone. There are many helpful resources available on campus and an important part of the college experience is learning how to ask for help. Asking for support sooner rather than later is often helpful.

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. Counseling and Psychological Services (CaPS) is here to help: call 412-268-2922 and visit their website at http://www.cmu.edu/counseling/. Consider reaching out to a friend, faculty or family member you trust for help getting connected to the support that can help.

If you or someone you know is feeling suicidal or in danger of self-harm, call someone immediately, day or night:

• CaPS: 412-268-2922
• Re:solve Crisis Network: 888-796-8226
• If the situation is life threatening, call the police:
  • On campus: CMU Police: 412-268-2323
  • Off campus: 911.

If you have questions about this or your coursework, please let the instructors know.

9. Diversity

We must treat every individual with respect. We are diverse in many ways, and this diversity is fundamental to building and maintaining an equitable and inclusive campus community. Diversity can refer to multiple ways that we identify ourselves, including but not limited to race, color, national origin, language, sex, disability, age, sexual orientation, gender identity, religion, creed, ancestry, belief, veteran status, or genetic information. Each of these diverse identities, along with many others not mentioned here, shape the perspectives our students, faculty, and staff bring to our campus. We, at CMU, will work to promote diversity, equity and inclusion not only because diversity fuels excellence and innovation, but because we want to pursue justice. We acknowledge our imperfections while we also fully commit to the work, inside and outside of our classrooms, of building and sustaining a campus community that increasingly embraces these core values.

Each of us is responsible for creating a safer, more inclusive environment.

Unfortunately, incidents of bias or discrimination do occur, whether intentional or unintentional. They contribute to creating an unwelcoming environment for individuals and groups at the university. Therefore, the university encourages anyone who experiences or observes unfair or hostile treatment on the basis of identity to speak out for justice and support, within the moment of the incident or after the incident has passed. Anyone can share these experiences using the following resources:

• Center for Student Diversity and Inclusion: csdi@andrew.cmu.edu, (412) 268-2150
• Report-It online anonymous reporting platform: reportit.net username: tartans password: plaid

All reports will be documented and deliberated to determine if there should be any following actions. Regardless of incident type, the university will use all shared experiences to transform our campus climate to be more equitable and just.

10. Public Release of Video Recordings

This section describes the course policies related to video recording, public release, and the Authorization and Agreement form, as mentioned in the course description.

Carnegie Mellon University plans to record audio, photos, and video of Generative AI (10-423 / 10-623 / 10-723) lectures and recitations, (the “Recordings”), with the aims of making the content of the course more widely available and contributing to public understanding of innovative learning (the “Projects”). As part of the Projects, the Recordings, or edited versions of them, may be made available to other Carnegie Mellon students, to students at other educational institutions, and to the broader public via the Internet, television, theatrical distribution, digital media, or other means. One of the ways it is expected that the Recordings, or edited versions of them, will be made publicly available is under a Creative Commons Attribution-NonCommercial-ShareAlike (CC BY-NC-SA) license. The Recordings also may be used to make other derivative works in the future. Students may elect not to appear in photos and video used in the Projects and may still participate fully in this course.

To attend this course, you will need to sign online an Acknowledgement and Authorization in the following form:

If you have any questions about the above, contact mgormley+recordings@cs.cmu.edu