Tess Smidt

Tess Smidt is an Associate Professor of Electrical Engineering and Computer Science at MIT. Tess earned her SB in Physics from MIT in 2012 and her PhD in Physics from the University of California, Berkeley in 2018. Her research focuses on machine learning that incorporates physical and geometric constraints, with applications to materials design. Prior to joining the MIT EECS faculty, she was the 2018 Alvarez Postdoctoral Fellow in Computing Sciences at Lawrence Berkeley National Laboratory and a Software Engineering Intern on the Google Accelerated Sciences team where she developed Euclidean symmetry equivariant neural networks which naturally handle 3D geometry and geometric tensor data.

AI2050 Project

Smidt’s project builds AI systems that understand and respect the deep structure of the physical world, its symmetries, hierarchies, and complex dynamics. By designing models that are aware of physical laws and operate across multiple scales, from atoms to galaxies, they aim to create tools that not only predict physical behavior but help scientists explore, control, and design it. These symmetry-aware AI models will enable breakthroughs in materials discovery, fluid dynamics, and cosmology by making abstract scientific principles actionable, interpretable, and generative, paving the way for AI to become a true partner in scientific reasoning and innovation.