[Site under construction]
I am currently a PhD student working with Prof. Biplab Sikdar at the National University of Singapore. I graduated with a B.Tech in Electrical Engineering and M.Tech in Artificial Intelligence from Indian Institute of Technology (IIT) Bombay in July 2025. There, I worked with Prof. Abir De on information retrieval using learned permutation matrices and exploring graph summarization using information theoreitc techniques. Part of this work has recently been accepted at AISTATS 2026.
In the past, I have worked on firmware attestation in IoT, explored neuromorphic computing for AI, and interned under Prof. Oliver Bringmann on developing an edge-device-compatible framework involving temporal convolutions and viterbi decoding for seizure detection.
My broad research focus at the moment is to use machine learning as an interpretable efficient tool to cover for inefficient parts of complex algorithms. To that end, I try to develop frameworks that work closely with theory, and use machine learning in key areas with a targeted purpose, not simply as large end-to-end black-boxes.
You can find a list of my publications here, and explore my projects on my GitHub.
Some Links
News & Updates
- Mar 2026 Preprint: "PEANUT: Perturbations by Eigenvector Alignment for Attacking Graph Neural Networks Under Topology-Driven Message Passing" uploaded to arxiv (arXiv:2603.26136)
- Jan 2026 Paper: "Learning Right Monotone Permutation Matrices for Neural Subsequence Search" accepted at the 29th International Conference on Artificial Intelligence and Statistics (AISTATS) 2026
- Nov 2025 Workshop Paper: "Masked Diffusion Models are Secretly Learned-Order Autoregressive Models" accepted at the EurIPS 2025 Workshop on Principles of Generative Modeling (PriGM)
- Aug 2025 Started PhD at the National University of Singapore with Prof. Biplab Sikdar
- Jul 2025 Graduated from IIT Bombay with a Dual Degree in Electrical Engineering and Aritificial Intelligence
- Nov 2024 Paper: "Swarm-Net: Firmware Attestation in IoT Swarms Using Graph Neural Networks and Volatile Memory" published at the IEEE Internet of Things Journal
- Mar 2024 Paper: "Energy-Efficient Seizure Detection Suitable for Low-Power Applications" published at the International Joint Conference on Neural Networks (IJCNN) 2024
- May 2023 Summer internship under Prof. Oliver Bringmann at the University of Tübingen, Germany