GAISE Lab
Generative AI for Science and EngineeringAbout the GAISE Lab
The Generative AI for Science and Engineering (GAISE) lab aims to advance scientific discovery and engineering innovation through state-of-the-art generative AI methods, with a particular emphasis on nuclear energy and material sciences. The lab’s primary objective is to develop foundational models integrating heterogeneous graph data, large-scale simulations, digital twins, and expert domain knowledge into comprehensive AI-driven analytical frameworks. These models will support rapid material discovery, autonomous operations, and intelligent safeguards that are critical to advanced energy systems such as nuclear fission and fusion.
The lab will foster interdisciplinary collaboration among experts in nuclear engineering, artificial intelligence, and computational materials science, driving ecosystem growth and workforce development. Ultimately, our integrative approach positions the lab to significantly contribute to energy security and dominance in both Texas and the United States.
Meet Our Team
Dr. Yang Liu
Director Department of Nuclear Engineering
Dr. Shuiwang Ji
Co-Director Department of Computer Science and Engineering
Dr. Raymundo Arroyave
Department of Materials Science and Engineering
Dr. Xiaofeng Qian
Department of Materials Science and EngineeringResearch
Large Language Model-based Nuclear Foundation Model
Advanced nuclear technologies, recognized as reliable energy sources for AI-driven data centers, are gaining momentum in the United States, particularly in Texas. Deploying these systems requires a streamlined licensing process and robust safeguards to ensure operational safety and security. To address this, we propose developing a Nuclear Foundation Model (NFM), utilizing large language model (LLM) to integrate diverse data streams for effective anomaly detection, material accountancy, and cyber-threat identification.
Graph Network Foundation Model for Materials Science
Rapid materials discovery requires accurate, efficient prediction of key properties like energy, atomic forces, and stress tensors from atomic structures. Existing methods either offer computational efficiency with limited precision (invariant models) or precise symmetry capture but high computational cost (equivariant models). Our proposed foundation model integrates these strengths, significantly enhancing accuracy and computational efficiency for diverse materials science applications.
Contact Us
Reach our team via email.