Juno Nam

Juno Nam is a graduate student in materials science and engineering, developing machine learning frameworks to accelerate atomistic simulations for materials discovery. His research addresses a central challenge: modeling complex materials with quantum-level accuracy over long timescales and realistic temperatures. As a MathWorks Fellow, Juno will combine generative modeling, enhanced sampling, and alchemical interpolation into a unified platform for dynamics-aware materials design. He and colleagues created LiFlow, a generative acceleration tool that extends molecular dynamics simulations by orders of magnitude and pioneered new approaches to modeling chemical disorder using machine learning interatomic potentials. Juno uses MATLAB for model optimization, symbolic differentiation, neural ODE integration, and high-dimensional data visualization. He also builds user-friendly workflows to make advanced simulations more accessible. By merging data-driven and physics-based approaches, Juno’s work could transform what’s computationally feasible in the design of next-generation materials for energy storage, catalysis, and other critical applications.