I am currently a post-doc at LaBRI, working with Nathanaël Fijalkow on Safe AI through formal methods. I am interested in language models, reinforcement learning and interpretability.
In 2023-2024, I was an ATER (aka teaching assistant) at Université Paris Cité, doing my research at IRIF.
I was a PhD student at LIX, École Polytechnique and at LMF, Université Paris-Saclay, where I worked with Eric Goubault and Jean Goubault-Larrecq on topological models of multi-agent logic and distributed computing.
The best way to contact me is by sending an e-mail to: roman (AT) knzv.me
Here is my CV.
I do some film photography, see my instagram. This is how I look like.
