Published multiple papers covering topics such as networks of LLMs, bandits, and controlling federated learning, including 'Information Diffusion and Preferential Attachment in a Network of Large Language Models' and 'Blocked Sparse Linear Bandits'.
Research Experience
Interned at Morgan Stanley's Machine Learning Research Group, where he developed a mixture of tokens generation method to improve verifiable reinforcement learning in large language models. Interned at Adobe Research in the summer of 2024, working on developing high-dimensional sparse bandits algorithms for efficient data annotation, proving regret bounds, and applying this algorithm to improve the efficiency of supervised fine-tuning of large language models.
Education
Currently a Ph.D. candidate at the School of Electrical and Computer Engineering at Cornell University, advised by Prof. Vikram Krishnamurthy. Expected to graduate in May 2026. Completed Bachelor's degree at IIT Guwahati with a major in Electronics and Communication Engineering and a minor in Computer Science.
Background
Research interests include reinforcement learning, distributed optimization, and networks of LLMs. Focuses on improving the training and networking of large language models.
Miscellany
Enjoys reading all kinds of books, learning new topics and skills, discussing and debating, and playing racquet sports like Badminton & Squash.