I am a post-doc in the NLP group under the ELIAI program. My research combines symbolic reasoning and machine learning, or “Neurosymbolic Learning”. I’ve done work on differentiable fuzzy logics and optimization with discrete latent variables. I developed the Storchastic PyTorch library, which implements many gradient estimation methods. I recently developed A-NeSI, a highly scalable Neurosymbolic method that uses neural networks for symbolic inference. At Edinburgh, I continue to work on neural networks with discrete latent variables. Furthermore, I am a program chair of the NeSy 2025 conference.