Course Overview


Instructor: Kilian Weinberger

Contact: kqw4@cornell.edu

Faculty Office Hours: Bowers 475, Mondays 9:45–10:45am

Course Staff:

Credits: 4.0 credits (3.0 for lecture, 1.0 for independent research project)

Prerequisites: CS 4780 or CS 5780 or equivalents, or permission of the instructor

Time and Location: Tuesdays and Thursdays, 14:55–16:10 (27 lectures total)

Course overview: This course covers advanced topics in machine learning, focusing on recent developments in large language models, multimodal models, and their applications. Students will engage with cutting-edge research through presentations, discussions, and a final project.

Course Structure


Weekly Schedule
Class Session Structure (Thursdays)
  1. Quiz on the paper and previous class (10 minutes)
  2. 30-minute presentation by the team
  3. 30-minute group discussion with role presentations
  4. Optional post-class quiz (5 minutes)
Social Reading Groups

Every main presenter will lead a Perusall group for pre-class paper annotation. Groups consist of one Presenter, one Archaeologist, one Academic Researcher, one Industry Expert, one Ethicist, and six other students without specific roles (11 people total).

Course Topics


This course covers the following main topics in advanced machine learning:

  1. LLM Foundations: Tokenization, positional embeddings, attention, causal language modeling, in-context learning
  2. LLM Extensions: Quantization, adapters, mixture of experts, context window, parallelism, distillation, attention-free architectures
  3. To be announced

Schedule


The course follows this tentative schedule. Topics and dates may change.

Date Style Topic
Tuesday, August 26, 2025 Lecture Introduction
Thursday, August 28, 2025 Lecture Introduction
Tuesday, September 2, 2025 Overview LLM Foundations
Thursday, September 4, 2025 Paper LLM Foundations
Tuesday, September 9, 2025 Overview LLM Extensions
Thursday, September 11, 2025 Paper LLM Extensions

Roles


Students will rotate through various roles throughout the semester:

Each student assigned to a role should prepare 2–3 slides and present for ~5–6 minutes, except for the Hacker, who provides a Jupyter Notebook instead of slides.

Weekly Assignment: By 10 PM the day before each Thursday class, all students must submit a review on CMT here.

Role Sign-ups

Sign up for roles using this Google Sheets link. Please sign up as soon as possible.

Presenter Responsibilities

Presenters are also responsible for creating quizzes used to assess the class’s understanding of the material.

Acknowledgment

The role-playing aspect of this course has evolved from an initial design by Alec and Eitan Grinspun at Columbia University.

Grading


Note: The role-playing aspect of the course is a significant part of participation and presentations. Students are expected to fully engage with roles, prepare thoroughly, and contribute meaningfully to discussions.

Final Project


The final project engages students in research related to course topics.

Project Guidelines:

Course Policies


Attendance and Participation

Regular attendance and active participation are essential.

Academic Integrity

All students must adhere to the Cornell University Code of Academic Integrity.

Late Work Policy

Given the collaborative nature of assignments, late work is generally not accepted without prior approval.

Accommodations for Students with Disabilities

If you are registered with Student Disability Services, please meet with the instructor as soon as possible to discuss accommodations. All such appointments are confidential.

Diversity and Inclusion

We are committed to an inclusive learning environment that values diversity and fosters respect for all individuals.

The Microsoft CMT service was used for managing the peer-reviewing process for this conference. This service was provided for free by Microsoft and they bore all expenses, including costs for Azure cloud services as well as for software development and support.