Mission.
I am interested in building AI models that move closer to human-like visual understanding and reasoning. My research investigates abstract visual reasoning through challenging visual puzzles, using neuro symbolic approaches such as program synthesis. Central to my work are structured concept representations and programmatic abstractions, which enable interpretable reasoning and stronger generalization. Recently, I have focused on challenging visual reasoning benchmarks such as the Bongard Problems, as well as on developing methods for inducing real-world visual concepts through program synthesis.

Student Projects & Theses - Bachelor and Master.
I currently do not have the capacity to take on new students for supervision.

Timeline.