Dr Jian-Xun Wang
Associate Professor at the Sibley School of Mechanical and Aerospace Engineering
Cornell University
Friday, Nov 21st at 3:00pm
L105 WEB
ABSTRACT: Forward and inverse problems are fundamental to computational mechanics but remain computationally demanding: high-fidelity simulations are costly, while traditional surrogates often lack generality and uncertainty awareness. Generative modeling offers a new paradigm by directly learning probability distributions of complex spatiotemporal systems, enabling both predictive simulation and data-driven inference within a unified framework. In this talk, I will highlight recent advances in generative modeling for mechanics, showing how diffusion-based and neural field methods enable scalable, uncertainty-aware solutions for forward prediction, inverse inference, and data assimilation. Applications in turbulence and biomechanics will illustrate how generative models can act as probabilistic forward and inverse solvers, advancing digital twins and paving the way toward foundation models for computational mechanics.
BIO: Dr. Wang is an Associate Professor at the Sibley School of Mechanical and Aerospace Engineering at Cornell University. Previously, he held the position of Robert W. Huether Collegiate Associate Professor in the Department of Aerospace and Mechanical Engineering at the University of Notre Dame. He received his Ph.D. in Aerospace Engineering from Virginia Tech in 2017 and completed a postdoctoral training at UC Berkeley before joining Notre Dame as a tenure-track Assistant Professor in 2018. He is a recipient of the NSF CAREER and ONR YIP awards and currently serve as Associate Editor for Journal of Computational Physics and Vice Chair of the USACM Technical Thrust Areas on Data-Driven Modeling.
Dr. Wang’s research at the interface of scientific machine learning, computational fluid, solid, and thermal dynamics, data assimilation, and uncertainty quantification, with the goal of advancing predictive modeling and decision-making for complex physical systems.