Tess Smidt

Tess Smidt is an Assistant Professor in the Department of Electrical Engineering and Computer Science at the Massachusetts Institute of Technology (MIT). Her research focuses on Artificial Intelligence, Machine Learning, and applications in materials science and quantum devices. She leads innovative work on equivariant neural networks for physical system modeling.

Her primary research interests include developing symmetry-preserving machine learning models for understanding complex physical systems, creating high-performance computational methods for materials discovery, and advancing quantum material design through computational approaches. The research combines fundamental computer science principles with practical applications in physics and chemistry.

Analysis of recent publications reveals strong trends in developing novel equivariant neural network architectures for scientific applications. Key focus areas include molecular dynamics simulations, materials property prediction, and symmetry-aware learning frameworks. The work consistently bridges theoretical machine learning advances with experimental validation in physical sciences.

While no awards are mentioned in available information, the publications demonstrate significant contributions to machine learning for science. The research involves collaboration across disciplines, particularly in computational physics and materials science.

Professor Smidt leads a research group at MIT developing computational tools for scientific discovery. Current projects explore applications of equivariant models across quantum materials, protein dynamics, and cosmological data analysis, demonstrating the breadth of these computational approaches.