Colorado School of Mines
Home Submit A Daily Blast Entry FAQ Guidelines

JavaScript is currently turned off in your browser. The Daily Blast website relies heavily on JavaScript and will not work correctly without it. Please change your settings to allow JavaScript on this site.

Academic Lectures
Towards Energy-Efficient Agentic Foundation Models

Department / Organization: Nuclear Science and Engineering

Dr. Syed Bahauddin Alam, UIUC. Energy Seminar Series, Hill Hall 202, 4 pm, Wed. 11/18

Nuclear Science and Engineering Energy Seminar Series

Towards Energy-Efficient Agentic Foundation Models: Digital Twin Solutions for Intelligent Inference in Inaccessible Locations

Dr. Syed Bahauddin Alam
Assistant Professor in Nuclear, Plasma & Radiological Engineering at UIUC

4 pm Wednesday Nov. 18
HIll Hall 202

Foundation models (FMs) offer a transformative approach to digital twins (DTs) in energy systems by enabling generalizable, compact, and energy-efficient AI that addresses the brittleness of conventional task-specific models. Current DTs often fail under sparse sensing, require costly retraining, and rely on power-hungry infrastructure, limiting their effectiveness in dynamic or constrained environments. This talk presents FM-enabled DTs enhanced with agentic AI for real-time field reconstruction, uncertainty quantification, and autonomous decision-making. Dr. Alam’s group develops neural-operator-based twins optimized for physical systems, capable of operating with millisecond latency, and can potentially be deployed on edge devices. Agentic components enable these twins to sense, reason, and act within context, forming a continuous loop between data, interpretation, and control. This work supports DOE missions in clean energy, nuclear safety, and secure infrastructure by advancing digital twins from passive replicas to intelligent, resilient, and energy-aware systems ready for real-world scientific and operational deployment.

For more information, send email to: jshafer@mines.edu

Published in Digest Date: Monday, November 16, 2026