Jian-Xun Wang has joined the faculty of the Sibley School of Mechanical and Aerospace Engineering as an associate professor. Wang was previously a tenured associate professor at the University of Notre Dame and his work focuses on scientific machine learning, AI-integrated physics modeling, and computational fluid dynamics.
Wang grew up in Taiyuan, Shanxi Province, China, and earned his undergraduate and master’s degrees in naval architecture and ocean engineering from Harbin Institute of Technology. “For me, it’s all about fluid dynamics and fluid-structure interaction,” he explained. “Aerospace, aeronautics, ocean—they’re all about fluid.” He later earned an M.S. in ocean engineering and a Ph.D. in aerospace engineering from Virginia Tech before completing a postdoctoral appointment in bioengineering at the University of California, Berkeley.
Wang’s career has been shaped by his drive to connect complex physics with data-driven modeling. At Virginia Tech, his doctoral research focused on data-driven, multi-scale turbulence modeling—resolving flow structures from hundreds of meters down to microns—using computationally intensive simulations and machine learning techniques. “You have to resolve the large scale down to the small scale, and that’s going to be very difficult,” Wang said. “So I was doing multi-scale modeling simulation for turbulence, leveraging sensors and experimental data to build models.”
Wanting to expand his knowledge base and intrigued by biomedical applications, Wang spent a year at UC Berkeley applying these methods to cardiovascular flows, where multi-modal data from imaging technologies like CT, MRI, and Doppler ultrasound were leveraged to build patient-specific models. “It’s very helpful to combine physics and physiological knowledge with heterogeneous biomedical data to solve problems in biomechanics and bioengineering,” he noted. “It is important to understand the physics and to develop models.”
At Cornell, Wang leads the Computational Mechanics & Scientific AI Lab (CoMSAIL), which develops next-generation computational tools by merging AI, GPU computing, and physics-based modeling. “Traditional computational mechanics software is very slow… our goal is to simulate things in real time,” Wang said. “We want to shrink simulations that take months down to real-time feedback and control.”
His team’s innovations aim to transform Computer-Aided Design and Computational Mechanics by embedding AI in ways that preserve physical laws while enhancing speed, interpretability, and accuracy. This includes applications in aerodynamics, fluid-structure interaction, thermal management, advanced manufacturing, and cardiovascular biomechanics.
A key principle of Wang’s approach is scientific machine learning, where models are trained to “respect the physics” and even extract unknown physics from data. “We don’t need to reinvent the wheel,” he said. “We want to leverage the knowledge we already know into the machine learning model, and teach the models to respect the physical law—so they don’t hallucinate.”
Wang is as passionate about teaching as he is about research. “I love to teach. That is why I chose this job,” he said. “Being around younger people helps me feel young and makes me look at the content of the class with fresh eyes each time I teach it.” At Cornell, Wang will collaborate with other faculty to integrate AI into the engineering curriculum, working with Guy Hoffman to develop new undergraduate courses of AI for engineering.
In particular, Wang plans to introduce a senior/graduate-level course that bridges machine learning and partial differential equations—connecting students’ knowledge of governing physics in thermodynamics and fluid dynamics to modern deep learning techniques. The course will explore how neural networks can be interpreted from a traditional numerical perspective, enabling students to see how physics and AI can inform one another.
While his lab is computational in nature—“our facility is a supercomputer cluster”—Wang frequently collaborates with experimentalists. He previously secured funding to build a GPU cluster at Notre Dame and plans to establish similar high-performance computing capabilities at Cornell.
Outside of research and teaching, Wang enjoys painting, a skill he began developing at age ten, and more recently, running. “It’s a way to relax… I try to run every other day,” he said. Ithaca’s trails and natural scenery were part of the draw for his move and he is looking forward to experiencing Ithaca in all the seasons.