I’m a PhD student at the University of Sussex and a visiting researcher at NYU working on aligning language models with human preferences. I’m particularly interested in RL from human feedback (RLHF) and probabilistic programming with language models.
At NYU, I work with Ethan Perez, Sam Bowman and Kyunghyun Cho while at Sussex I’m advised by Chris Buckley and Anil Seth. I also spent time at Naver Labs Europe working on energy-based models for aligning language models. Before that, I studied cognitive science, philosophy and physics at the University of Warsaw and worked on compositional generalisation and emergent communication with Joanna Rączaszek-Leonardi and Piotr Miłoś, and on Bayesian accounts of self-organisation with Marcin Miłkowski.
Highlighted papers
-
RL with KL penalties is better viewed as Bayesian inference
Findings of EMNLP 2022
-
Energy-based models for code generation under compilability constraints
NLP4Programming workshop, ACL 2021
-
Measuring non-trivial compositionality in emergent communication
Emergent communication workshop, NeurIPS 2020
-
Developmentally motivated emergence of compositional communication via template transfer
Emergent communication workshop, NeurIPS 2019