Luca Modica

I’m an industrial PhD student at Zenseact, working on reasoning in Vision Language-Action models in autonomous driving, their interpretability and faithfulness. Previously, I completed my master’s degree in Data Science and AI at Chalmers University of Technology, conducting a master’s thesis on mechanistic interpretability and factuality of multimodal speech-language models with the NLP@DSAI group. I have also been part of the social computing group at University of Turin, where I collaborated as research fellow for the FirstLife civic social network project.

My current research interests include Vision Language-Action Models, (mechanistic) interpretability of multimodal models, reasoning faithfulness and their applications in autonomous driving. In my free time, you will probably find me running, baking🍪, traveling✈️, or exploring the beutiful nature of Sweden🌲.