Hauptinhalt

Topinformationen

Begleitseminar zum Studienprojekt: Exploring Physical Understanding in LLMs (Part I)

8.3203

Dozenten

Beschreibung

This is an interdisciplinary seminar accompanying a study project. The seminar will help maintaining the study project's structure, which I report also below.

Note: Prerequisites are good programming skills and at least an introductor level understanding of Deep Learning (applied to either for Computer Vision or NLP).

We have received a high volume of interest in this project and to that end, we are compelled to conduct a selection process to provide a meaningful organization and supervision for all participants. As part of the selection process, we will be requesting applicants to submit a brief essay that introduces themselves and their motivation for participating in the project. This will help us to better understand each candidate and determine the best fit for the program. More information on that will be announced around two weeks before the course starts.

Structure:
The project will be structured into three main phases, with weekly meetings focusing on different aspects of learning and research:

Part 1 - Background Learning:
Introduction to LLMs and their capabilities in next-word prediction and multimodal learning. Students will receive learning packages covering the foundational theories and the evolution of LLMs.
Deliverables: Each student will prepare a brief presentation summarizing the key concepts and their implications for understanding physical reality.

Part 2 - Literature Review:
Focus on discussing seminal and recent papers that are pivotal to understanding the current landscape of LLMs’ cognitive abilities, especially in physical understanding. This phase includes identifying gaps in the current research.
Deliverables: In small groups, students will present summaries and critiques of selected papers, highlighting methodologies, findings, and areas needing further exploration.

Part 3 - Research Operationalization and Benchmark Development:
Small groups will operationalize research questions based on identified gaps from the literature review. This phase will involve hands-on work with the GRAP evaluation benchmark as detailed in the paper available at https://arxiv.org/abs/2311.09048
Deliverables: Each group will develop enhancements or new features for the GRAP benchmark, aiming to address specific challenges in evaluating the physical understanding of LLMs. The project concludes with groups presenting their proposed solutions and implementations.

Weitere Angaben

Ort: 93/E12
Zeiten: Di. 14:00 - 16:00 (wöchentlich)
Erster Termin: Dienstag, 29.10.2024 14:00 - 16:00, Ort: 93/E12
Veranstaltungsart: Seminar (Offizielle Lehrveranstaltungen)