Reading Group

The reading group in the WiSe24/25 will be every week on Monday evenings, starting on the 21st of October. We meet at 7pm in MAR 0.015 .
Down below you find the list of papers with their respective date. Please read the paper before attending as we will use the time to discuss the contents.
We will use the semester to explore LLMs and mechanistic interpretability. At first, we are going to learn the basics of natural language processing and the transformer architecture. Then we will have a look at scaling these models, modern training techniques and self improvement. Afterwards, we will switch topics and focus on mechanistic interpretability.

Past Papers

Mechanistic Interpretability

Host: Lorenz Hufe

Sometimes everybody needs to know what is going on inside a (language) model

LLMs and Language Modeling

Host: Raphael Reinauer

Long story short, we read papers about language models and language modeling

Deep Q-Learning

Host: Jarek Liesen

Introduction to deep reinforcement learning by exploration of many relevant and foundational papers