MAHDI RAD

I am a principal scientist at Microsoft Spatial AI Lab in Zurich. My work focuses on how machines perceive, understand, and reason about the physical world.

Previously, I was a postdoctoral scholar at the Institute of Computer Graphics and Vision at Graz University of Technology (TUG). I received my Ph.D. with distinction from TUG, supervised by Prof. Vincent Lepetit. I earned my B.Sc. and M.Sc. in Computer Science at EPFL, Switzerland.

My research spans 3D scene understanding, object and hand pose estimation, hand–object interaction, and vision–language models (VLMs). I am particularly interested in spatial reasoning from video and efficient VLMs, alongside semi-supervised learning and domain adaptation.