Biography
I am a first-year MSML student at Carnegie Mellon University. I work at the intersection of scene understanding, self-supervised learning and robotics. Some of the problems that interest me are:
- learning actionable representations from scenes encompassing multiple modalities like images, videos, depth maps and 3D data.
- understanding scenes at different levels of abstraction, from pixel level all the way up to the image level
- understanding hierarchical relationships among the abstractions, and leveraging them for tasks in robotics.
Previously, I was employed full-time at Samsung Research, Seoul, where I designed a framework, called Map View to extract vectorized home layouts from floorplan images in the wild. Here is our solution showcased at CES 2024 . I have also been a research fellow at the Vector Institute for AI , where I worked with Prof. Sanja Fidler leveraging inter‑image relationships for object‑centric self‑supervised learning.
I graduated from Indian Institute of Technology Kanpur in May 2021, majoring in Electrical Engineering with minors in Machine Learning. I worked on natural language processing, optimization algorithms, stochastic modelling, and wireless networks during my undergraduate days.
For details, check my CV (short) and CV .
- Computer Vision
- Self/Weakly-Supervised Learning
- Scene Understanding
- Reinforcement Learning
MS in Machine Learning, 2026
Carnegie Mellon University
Btech in Electrical Engineering with Minors in Machine Learning, 2021
Indian Institute of Technology Kanpur
Recent Publications
Featured Publications
Projects
