Shashank Kirtania

Bio

I am a PhD student at the University of Michigan, Ann Arbor advised by (Prof. Gabriel Poesia). I love abstractions. They are the strange inventions of the mind that allow us to move through a world far too large and complicated to understand directly. We turn experiences into concepts, concepts into rules, and rules into reusable ideas. We recognize a pattern once, give it a name, and suddenly we can see it everywhere.
I am interested in whether machines can do the same. My research explores how AI systems can learn abstractions from experience: discovering concepts, programs, and reusable structures that allow them to generalize beyond what they have seen. I am particularly interested in the connection between learning and programming—how experiences can become abstractions, and how those abstractions can become the building blocks of increasingly rich models of the world. For fun, I do lot of things and I am almost always interested to try soemthing new lately I have been learning tennis.
Previously, I was a Research Fellow (Pre-Doctoral) at Microsoft Research India, where I was part of the program synthesis group (PROSE) and the AI4Code team. I was privileged to work with Aditya Kanade, Ashish Tiwari, Gustavo Soares, Arjun Radhakrishna, Sumit Gulwani, and Arun Iyer.

Publications

Most recent publications on Google Scholar.
^‡ indicates equal contribution.

• Selected
• All

Train of Thought

A collection of trains of thought and lines of research, inspired by Kartik Chandra and Shubhra Mishra.

CV

Full Resume in PDF.

• University of Michigan, Ann Arbor 2026-

  CS PhD
  
• Microsoft Research India 2023 - 2026

  ML Resident
  AI4Code
• Wadhwani AI 2023 - 2023

  Research Engineer, Intern