Pulkit Verma

Pulkit is a Postdoctoral Associate in the Interactive Robotics Group at CSAIL and AeroAstro, MIT, working with Prof. Julie Shah. He completed his Ph.D. at the School of Computing and Augmented Intelligence at Arizona State University, advised by Prof. Siddharth Srivastava. During his Ph.D., he was also affiliated with UC Berkeley’s Center for Human-Compatible Artificial Intelligence and ASU’s Center for Human, Artificial Intelligence, and Robot Teaming. He earned his M.Tech. from the Department of Computer Science & Engineering at IIT Guwahati, where he was advised by Prof. Pradip K. Das.

Pulkit’s primary interests lie in AI safety, AI planning, action-model learning, interpretability, and the analysis of abstractions. His research focuses on ensuring the safe and reliable behavior of AI agents. Currently, he is investigating the minimal set of requirements an AI system needs to enable users to assess and understand the limits of its safe operability.

In the past, he has worked in the areas of bio-inspired robotics, speech processing, and the Internet of Things.

You can learn more about Pulkit’s work at his website.