News and Updates
October 2025
10-28-2025 - I was invited to present at the AI4EIC 2025 Workshop at MIT (October 27–29), where I introduced the design of production-oriented RAG pipelines, including RAG4EIC, the first end-to-end RAG system for nuclear physics developed by our team. The talk emphasized data strategy and benchmarking—outlining a framework for generating high-quality datasets to support reliable RAG deployment, with a focus on uncertainty-aware ML systems for decision-critical applications. Check out the tutorial here and the presentation for generating high quality dataset for Nuclear Physics.
Meeting Details | Slides 1 2
10-17-2025 - I was invited to design and teach a tutorial on Convolutional Neural Networks and Generative Artificial Intelligence for the nuclear physics community at the APS Division of Nuclear Physics (DNP) 2025 meeting, under the Data Science Division. The tutorial showcased state-of-the-art deep learning and generative modeling methodologies and their strategic applications to nuclear physics data analysis and large-scale computational workflows. Checkout the tutorial at DNP Tutorials
Meeting Details 1 2 | Tutorials
September 2025
09-30-2025 - Got promoted as Research Scientist in the department of Data Science at College of William & Mary. Will continue to work on the Phase-II of the AID2E project. The project aims to now create an integrated LLM assisted framework for distributed design optmization focusing on the Electron Ion Collider and beyond. The integration of LLM will make the system more robust an fault taulrent for running complex workflows.
July 2025
07-30-2025 - Hosted a topical meeting on RAG4EIC to explore open-source LLM integration and agent-based workflows for enhanced scientific reasoning in the EIC community.
June 2025:
11-08-2025 - Delivered a lecture at AI4Fusion School titled “From Bayesian Regression to Gaussian Process” — a thorough introduction to Bayesian methods for scientific machine learning.
06-08-2025 - Delivered a lecture series at HUGS 2025 on AI-driven optimization and LLM applications in nuclear and particle physics.