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.

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.


Postdoctoral Researcher

2023.08 - Present
Massachusetts Institute of Technology; supervised by Prof. Tess Smidt.

Research Intern

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

Machine Learning Research Intern

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

Applied Scientist Intern

2020.05 - 2020.08
Amazon Web Services; supervised by Danielle Maddix and Yuyang Wang.

Machine Learning Research Intern

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

Data Science Co-op

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

Selected Publications

  • Discovering Symmetry Breaking in Physical Systems with Relaxed Group Convolution
  • Rui Wang, Elyssa Hofgard, Han Gao, Robin Walters, Tess E.Smidt.
    International Conference on Machine Learning (ICML) 2024
  • Physics-Guided Deep Learning for Dynamical Systems
  • Rui Wang, Rose Yu.
    ACM Computing Surveys
  • 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
  • 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
  • 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