I am a Machine Learning MSc student at the University of Tübingen, working in the Health-NLP group Tübingen.
Interests: I am interested in the intersection of Deep Learning and Natural Language Processing to develop AI systems that are capable, trustworthy, and socially beneficial. As AI technologies advance, I want to contribute to addressing the societal risks and ensure equitable benefits by improving scientific understanding and effective governance approaches.
Bio: I graduated with distinction in Computer Science from the University of Tübingen in 2022, ranking in the top 5% of my class. During my studies, I worked as a machine learning engineer at RAWLAB, a startup specializing in engineering data processing, where I applied machine learning models to time-series analysis. I am currently writing my Master's thesis on representation engineering in Large Language Models, supervised by Seyed Ali Bahrainian and Carsten Eickhoff from the Health-NLP group at the University of Tübingen, and Dmitrii Krasheninnikov and David Krueger from the Krueger AI Safety Lab at the University of Cambridge.
Feel free to reach out to me via mail!
@InProceedings{Braun2022BSCTHESIS,
author = {Joschka Braun},
title = {Verbal Epistemic Uncertainty Estimation for Numeric Values with GPT-3},
booktitle = {BSc Thesis at Univesity of Tübingen},
year = {2022},
}
@InProceedings{Braun2024,
author = {Joschka Braun and Seyed Ali Bahrainian},
title = {Enhancing Topical Relevance in Abstractive Summaries through Reweighting Logits of Topic-Relevant Tokens},
booktitle = {Research project under the supervision of Seyed Ali Bahrainian},
year = {2024},
}
This website is based on the template of Michael Niemeyer. Check out his Github repository for instructions on how to use it.