🚨 PhD position alert! 🚨 I'm hiring a fully funded PhD student to work on mechanistic interpretability at UvA Amsterdam. If you're interested in reverse engineering modern deep learning architectures, please apply: vacatures.uva.nl/UvA/job/PhD-Po…

Very excited and grateful to receive an ERC Consolidator grant #ERCCoG on Counterfactuals in Minds and Machines! Are you interested in a postdoc or Ph.D. at Max Planck Institute for Software Systems? Please get in touch by email European Research Council (ERC) Max Planck Society

🛬In Vancouver. Would love to meet new people working on causality, game theory and/or all human-centric aspects of ML. Ping me to have a coffee ☕ or come find me at the CaLM workshop presenting some new exciting work: arxiv.org/abs/2409.17027 P.S. I am on the academic job market

Let's talk causality and LLMs! Come find us at the posters in East Hall C. 11:30-12:00 & 14:30-15:00. #NeurIPS2024

This is such an awesome collection of people/topics in responsible computing! Hope we all find our academic homes. Thanks Gautam Kamath, Jonathan Ullman and Adam for the initiative!

🚀 🇬🇷 A year in the making! I’ve just completed a set of 21 lectures in Machine Learning, in Greek, designed for high school students. The course introduces key ML concepts, coding in Python & PyTorch, and real-world AI applications. #MachineLearning #AI #EdTech #Greece

January was cool! Here's a quick update: - I submitted my PhD thesis 🎉 - Our work on counterfactual generation in LLMs (shorturl.at/nmfdh) got accepted at CLeaR-Conference on Causal Learning and Reasoning! - We released a new preprint on causality + evaluation of LLMs (shorturl.at/j2Fq4). See below👇

Together with Manuel Gomez-Rodriguez, adishs, Krishna Gummadi, Goran Radanovic and Nina Grgić-Hlača, we have multiple open positions postdocs in AI, Computing, and Society at the MPI for Software Systems! Apply by May 13 via the new Max Planck Postdoc Program! mpg.de/en/max-planck-…

Presenting this today at 17:00 in Hall 4 #6

New PhD position at UvA AMLab on learning concepts with theoretical guarantees using #causality and #RL with me, Frans Oliehoek (TU Delft) and Herke van Hoof 💥 Deadline: 15 June werkenbij.uva.nl/en/vacancies/p…

Upon graduation, I paused to reflect on what my PhD had truly taught me. Was it just how to write papers, respond to brutal reviewer comments, and survive without much sleep? Or did it leave a deeper imprint on me — beyond the metrics and milestones? Turns out, it did. A

Giving this one a boost, since it was treated poorly by the algorithm. TL;DR: if you're using an LLM API, you could be getting overcharged and there's no way for you to know. See arxiv.org/abs/2505.21627 for more.