I am a Research Associate at the Applied Theory for Machine Learning Research (ATMLR) Lab, IIT Hyderabad, working on “Constrained Sampling” under the supervision of Dr.J Saketha Nath.
I received a B.S.–M.S. dual degree in Mathematics, with a minor in Computer Science, from IISER Berhampur. I carried out my Master’s thesis work at IIT Hyderabad under Dr.Srijith P.K. on Non-Stationary Markov Decision Processes and Continual Reinforcement Learning. During my BS-MS, I was a recipient of the Indian Academy of Sciences(IASc-INSA-NASI) Summer Research Fellowship (2023) to work with Dr. Sudarshan Iyengar at IIT Ropar, and also worked as Summer Undergraduate Reseaerch Fellow(2022) at IIT Hyderabad

Research, My research lies at the intersection of deep generative models and reinforcement Learning. I particulary interested in foundations of diffusion models, flow-based methods, and large language models (LLMs), and their applications in vision, language, and scientific domains (e.g., molecular generation) as well as their connections to control and dynamical systems. I leverage tools from optimization and statistics to develop scalable training algorithms
Keywords: Diffusion Models, Flow-based Models, Reinforcement Learning, Optimal Transport, Stochatic Optimal Control

Beyond Core Research, I have a particular interest in Machine Learning Systems(MLSys) with a focus on developing efficient inference methods and distributed training for large deep learning models. I love Open Source and I spend time actively contributing to open source projects of my own and others (some of them are mentioned on the software page)

Outside Research, I enjoy playing Cricket, Travelling and exploring new cuisines, Reading(Non-Fiction!)

I’m actively seeking research opportunities. Feel free to reach out if you’d like to discuss collaborations, research roles, or cool open-source project ideas.

Reach out to me on: or Drop an Email

Education:

• M.S. in Mathematics and Computer Science(Minor), IISER Berhampur, 2025
  • Thesis: Non-Stationary Markov Decision Processes and Continual Reinforcement Learning Algorithms
  • Advisor: Dr.Srijith P.K., Department of AI, IIT Hyderabad
• B.S. in Mathematics and Computer Science(Minor), Indian Institute of Science Education and Research (IISER) Berhampur, INDIA

Research Interests:

• Machine Learning and Optimization
• Reinforcement Learning and Stochastic Approximation Theory
• Deep Generative Models and Sampling Methods
• Statistical Learning Theory
• Distributed ML Systems and Efficient Inference

Updates: