Hi, I’m a Master’s student in Mathematical Engineering and I’m currently exploring PhD opportunities in Poland and looking for researchers or labs working on AI Safety/Mechanistic Interpretability.
Could anyone recommend researchers, labs, or universities in Poland that focus on these or related areas (ML/NLP)?
Thank you in advance for any guidance or recommendations.
Let us discussion on your research scope and provide you necessary information .Thank you
IYH Dear Taras Kutsyk
h/t gynvael.coldwind said "Mechanistic Interpretability - that's probably the most fun thing in AI from a reverse engineer's perspective" :D
He recommended the AI Dept. at Wroclaw University of Science and Technology
https://ai.pwr.edu.pl/
Daniyel Yaacov Bilar thanks a lot! I'll make sure to check that one out.
Friday Ameh thank you, my research scope lately has been mechanistic interpretability of language models. There aren't many people in this research area at the moment, that's why I'm mentioning some broader fields as well (AI Safety, NLP). You can also check my LinkedIn for more info on my recent work: https://www.linkedin.com/in/taras-kutsyk-135006212/
- Badges
- Science topic