About Me
I am Xiaoyu Xie, a Research Scientist at Meta. I received my Ph.D. in Mechanical Engineering from Northwestern University under the supervision of Prof. Wing Kam Liu. My research focuses on integrating physics and prior knowledge into machine learning to develop interpretable and scalable AI algorithms for challenging real-world applications, such as additive manufacturing, fluid mechanics, and ads ranking systems.
Recent News
- [10/2025] Our paper “Unifying machine learning and interpolation theory via interpolating neural networks” was accepted by Nature Communications!
- [09/2024] I joined Meta as a Research Scientist.
- [06/2024] Completed a three-month internship at Amazon Annapurna Labs, focusing on optimizing distributed inference for multimodal deep learning models.
- [02/2024] Published internship paper on operator learning: “Smooth and Sparse Latent Dynamics in Operator Learning with Jerk Regularization” on arXiv.
- [06/2023] Completed a three-month Research Internship at Mitsubishi Electric Research Laboratories (MERL).
- [03/2023] Invited to give a talk on Dimensionless Learning at the CMU SciML Webinar. (Recording)
- [12/2022] Our paper “Data-driven discovery of dimensionless numbers and governing laws from scarce measurements“ was published in Nature Communications!
- [08/2022] Our team won three 1st places and two 2nd places in the AM-Bench Challenge at NIST, US!
- [06/2021] Our work was published in npj Computational Materials (Nature Partner Journal)!
Research Interests
- Scientific Machine Learning & AI for Science — Bridging the gap between physics and data-driven methods
- Data-Driven Reduced-Order Modeling — Efficient representations of high-dimensional systems
- Data-Driven Scientific Discovery — Automated discovery of physical laws and dimensionless numbers
- Computer Vision & Multimodal Learning — Integrating visual and other sensory information
Hands-on Scientific Machine Learning eBook
I am creating an interactive online eBook for Scientific Machine Learning. The book provides hands-on tutorials with code, visualizations, and video explanations for both theoretical concepts and practical implementations. All tutorials can be run directly in Google Colab or on your local machine.
Interested in collaborating on this project? Please feel free to reach out!
Education
Ph.D. in Mechanical Engineering
Northwestern University, Evanston, IL, USA
2020 – 2025
Advisor: Prof. Wing Kam Liu
M.S. in General and Fundamental Mechanics
University of Chinese Academy of Sciences, Beijing, China
Institute of Mechanics
2014 – 2017