I am a Postdoctoral Researcher at MIT EECS, advised by Prof. Tess Smidt. I completed my Doctorate in Computer Science at UC San Diego with Prof. Rose Yu, and here is my thesis.

My research primarily lies in deep learning, especially for spatiotemporal data. In particular, I’m interested in building accurate, interpretable, and generalizable deep forecasting models for large-scale real-world data. My works have been applied to forecasting spatiotemporal systems in finance, epidemiology, healthcare, traffic and physical sciences.

Currently, I’m actively working on designing equivariant neural nets that preserve (approximate) symmetries as well as symmetry-breaking factor discovery problems.

For more details, please see my Resume and Google Scholar.

Selected Publications

  • Relaxed Octahedral Group Convolution for Learning Symmetry Breaking in 3D Physical Systems
  • Rui Wang, Robin Walters, Tess E.Smidt.
    Working in progress
  • Physics-Guided Deep Learning for Dynamical Systems, A Survey
  • Rui Wang, Rose Yu.
    In submission to ACM Computing Survey
  • Koopman Neural Forecaster for Time Series with Temporal Distribution Shifts
  • Rui Wang, Yihe Dong, Sercan O Arik, Rose Yu.
    International Conference on Learning Representations (ICLR) 2023
  • Meta-Learning Dynamics Forecasting Using Task Inference
  • Rui Wang*, Robin Walters*, Rose Yu.
    Advances in Neural Information Processing Systems (NeurIPS) 2022
  • Approximately Equivariant Networks for Imperfectly Symmetric Dynamics
  • Rui Wang*, Robin Walters*, Rose Yu.
    International Conference on Machine Learning (ICML) 2022
  • Latent Space Simulation for Carbon Capture Design Optimization.
  • Brian Bartoldson, Rui Wang, Yucheng Fu, David Widemann, Sam Nguyen, Jie Bao, Zhijie Xu, Brenda Ng.
    Annual Conference on Innovative Applications of Artificial Intelligence (IAAI) 2022
  • Incorporating Symmetry into Deep Dynamics Models for Improved Generalization
  • Rui Wang*, Robin Walters*, Rose Yu.
    International Conference on Learning Representations (ICLR) 2021
  • Bridging Physics-based and Data-driven modeling for Learning Dynamical Systems
  • Rui Wang, Danielle Maddix, Christos Faloutsos, Yuyang Wang, Rose Yu.
    Annual Conference on Learning for Dynamics and Control (L4DC) 2021
  • Physics-based vs. Data-driven A Benchmark Study on COVID-19 Forecasting.
  • Rui Wang, Danielle Maddix, Christos Faloutsos, Yuyang Wang, Rose Yu.
    Best Paper Award at NeurIPS, Machine Learning in Public Health Workshop 2020
  • Towards Physics-informed Deep Learning for Turbulent Flow Prediction
  • Rui Wang, Karthik Kashinath, Mustafa Mustafa, Adrian Albert, Rose Yu.
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2020


    Research Intern

    2022.06 - 2022.10
    Google Cloud AI, Sunnyvale, CA; supervised by Yihe Dong and Sercan O.Arik.

    Machine Learning Research Intern

    2021.06 - 2021.09
    Lawrence Livermore National Laboratory, Livermore, CA; supervised by Brenda Ng.

    Applied Scientist Intern

    2020.05 - 2020.08
    Amazon Web Services, Palo Alto, CA; supervised by Danielle Maddix and Yuyang Wang.

    Machine Learning Research Intern

    2019.05 - 2019.08
    Berkeley Lab, Berkeley, CA; supervised by Karthik Kashinath, Mustafa Mustafa, and Adrian Albert.

    Data Science Co-op

    2018.07 - 2018.12
    Abiomed Inc., Danvers, MA; supervised by Chen Liu and Erik Kroeker.