About me

I am a final-year Ph.D. candidate in Machine Learning at Mcgill University and Mila - Quebec Artificial Intelligence Institute, supervised by Prof. Siamak Ravanbakhsh and Prof. Kaleem Siddiqi. I have spent the last few years of my PhD working at the intersection of self-supervised representation learning, deep reinforcement learning, and geometric deep learning. Currently, I am focusing on two main research directions aimed at reducing the energy footprint of existing models while enhancing their expressivity and robustness. The first area involves developing a unifying framework to build and understand efficient state-based sequence models that can train in parallel. The second direction focuses on efficiently integrating geometric priors into existing foundational models to make them robust to transformations of the data.

I am currently interning at Microsoft Research in Cambridge, focusing on fine-tuning diffusion models using reinforcement learning for Material Discovery. During my PhD, I also interned at Apple and was a Visiting Researcher at ServiceNow Research and Huawei Noah’s Ark Lab. Before moving to Montreal, I briefly worked at the Samsung Research Institute in Bangalore.

I did my undergraduate studies in Electronics and Electrical Communication Engineering at the Indian Institute of Technology, Kharagpur. During my undergrad, I worked on VLSI engineering, Robotics, Computer Vision, Embedded systems, and Free-form Lens design. Besides that, I have also taken a broad set of courses ranging from Device physics to Data Structure and Algorithm design.

When I am not working, I like to spend time in nature, stargaze with my close friends and talk about life. I love mountains and lakes and have been on a few Himalayan treks.