Research
Welcome! I'm a first year graduate student (MS in Machine Learning) at Carnegie Mellon University in the School of Computer Science School of Computer Science. I am currently working on theoretical motivations of flow-based models with applications to Neural PDEs advised by Prof. Andrej Risteski. Previously, I was a Research Assistant in the Department of Electrical and Communication Engineering at the Indian Institute of Science (IISc) advised by Prof. Prathosh A.P. where my research was focused on integrating numerous symmetries into neural networks, specifically for generative models. This exploration spans both discrete and continuous groups, focusing on understanding the impact of integrating group symmetries. I also had the opportunity to collaborate with Aditya Gopalan at IISc, on our latest work on unified symmetry learning for discrete groups. My publications can be found here.
News
- Jan 2024: Our paper on A Unified Framework for Discovering Discrete Symmetries is accepted at AISTATS 2024.
- Jan 2023: Our paper on Neural Discovery of Permutation Subgroups is accepted at AISTATS 2023.
- Aug 2023: Serving as a Teaching Assistant for the Advanced Deep Representation Learning (E1-285) course during the Fall 2023 semester.
- June 2023: Selected for the AIS - Lie groups and Lie algebras (2023) at the Indian Institute of Science.
I am highly motivated to explore the intersection of invariant learning and generative models. My long-term goal is to develop data-driven methodologies for understanding, modeling, and recreating the visual world. Personally, I am enthusiastic about our current work on flow-based models and neural operators for modeling partial differential equations using neural networks.
See my Research Overview page for more details on my research interests. You can find my latest CV here.