NLP seminar: Large Language Models
Place: Delta, 2047 (no online participation)
Time: Friday 12.15-13.45
Coordinators: Emil Kalbaliyev, Kairit Sirts
Questions: emil.kalbaliyev@ut.ee
This semester's seminar will focus on the algorithms and methods for LLMs. Our discussions will revolve around papers or blog posts.
Organization
We will discuss one topic per week. The topics are broken down into subcategories based on sections of papers, such as related work, experiment setup, and results. Before each seminar:
- Skim the assigned papers (see Topics) and select a subtopic of interest here (log into courses to see the link)
- Dig deeper into the selected topic (read parts of the paper more closely, go through relevant related works, or use open-source models).
- Submit a half-page overview of your findings by Friday morning (at 9) before the seminar. The overview can be in free format (bullet points, thoughts, references with notes, etc.), but it should help you remember what you learned and explain it to others.
- Participate actively during the seminar; be ready to explain what you learned. While it's not obligatory, if you wish, you can create visual aids, such as a presentation with figures and tables from paper, to share with the group. Please submit these along with your review, or be prepared to share them directly from your computer.
The first seminar (September 13) is introductory and explains the course topic and organization.
Requirements / Grading
Passing requirements:
- Submit an overview for at least eight seminars.
- Participate actively in at least eight seminars (excluding the first introductory seminar).