I am a PhD student at the Hasso Plattner Institute (HPI), working with Prof. Gerard de Melo. My research lies at the intersection of vision-language models, computer vision, and vector graphics. I am interested in studying where current VLMs fall short in visually and relationally complex settings, and in teaching models to generate and reason with visual content in ways that more closely resemble how humans think and communicate.

I am currently working with Prof. Yael Vinker and Prof. Antonio Torralba (MIT CSAIL) on a project to enable sketching capabilities in the model's reasoning process, with the goal of building systems that can explain concepts visually and collaborate with students in a shared whiteboard space. I also worked with Prof. Andres Sevtšuk (MIT DUSP) on a project to detect social interactions in semantically complex urban scenes, with the goal of mapping which areas of modern cities are more socially vibrant than others.