Dhruv Shah

Dhruv Shah is an Assistant Professor of Electrical and Computer Engineering at Princeton University, where he directs the Princeton Robotic Intelligence and SysteMs (PRISM) group, and a Research Scientist at Google DeepMind, where he leads Gemini Robotics Post-Training. He earned his PhD in EECS from UC Berkeley under the supervision of Sergey Levine. His research focuses on the intersection of machine learning and robotics, with emphasis on large-scale robot learning, foundation models for visual navigation, and out-of-distribution generalization. He is best known for his work on generalist robot navigation models including ViNT, ViKiNG, NoMaD, and GNM.