Get the latest news
Subscribe to receive updates from the School of Data Science.
Postdoctoral Researcher
Xinlun Cheng
Postdoctoral Research Associate
School of Data Science
Email: xc7ts@virginia.edu
Additional Contact Information
Website: chengxinlun.github.io/
Office: 108 Cresap, Rm. 103
Xinlun Cheng is a postdoctoral research associate in the School of Data Science. He is currently working in professor Stephen Baek's Visual Intelligence Lab on developing new algorithm and training strategies in physics-informed machine learning (PIML), especially for improving Physics-aware Recurrent Convolutional neural networks (PARCv2).
Prior to becoming a postdoc in 2024, Cheng had been involved in research in Baek's lab for two years and worked on development of PARCv2, application of PARCv2 on various computational fluid dynamics problems, and comparison with other PIML models. He was also involved in data mining large sky survey databases with the UVA Department of Astronomy.
Cheng holds a Ph.D. in astronomy from the University of Virginia. He also holds a B.S. in physics from Tsinghua University and a M.S. in data science from UVA.
Education
- Ph.D. in Astronomy, University of Virginia
- M.S. in Data Science, University of Virginia
- B.S. in Physics, Tsinghua University
Selected Publications
Cheng, X., Nguyen, P., et al. 2024, IJMF, 104, 877. Physics-Aware Recurrent Convolutional Neural Networks for Modeling Multiphase Compressible Flows.
Nguyen, P., Cheng, X., et al. 2024, ICML. PARCv2: Physics-Aware Recurrent Convolutional Neural Networks for Spatiotemporal Dynamics Modeling
Cheng, X., Zhang, Sheng., et al. 2023, Physical Review Research, 5, 3, 033188. Convolutional neural networks for large-scale dynamical modeling of itinerant magnets.
Bozsik, S., Cheng, X., Kuncham, M., Mitchell, E. (alphabetical ordering) 2022, IEEE Systems and Information Engineering Design Symposium (SIEDS). Democratizing Housing Affordability Data: Open Data and Data Journalism in Charlottesville, Virginia.