Haixu Wu

Logo

wuhx23@mails.tsinghua.edu.cn

About Me

I am currently a Ph.D. student (from fall, 2020) in School of Software, Tsinghua University, under the supervision of Prof. Mingsheng Long.
My research interests lie in deep learning and scientific machine learning, especially sequence modeling, physical world modeling and PDE solving. The goal of my research is to create strong foundation models through scientific inspiration and theoretical support for modeling our ever-changing world, solving challenging science problems and advancing practical applications.

Google Scholar / Semantic Scholar / GitHub / CV

Education

Highlights

Preprints

  1. Unisolver: PDE-Conditional Transformers Are Universal PDE Solvers
    Zhou Hang*, Yuezhou Ma*, Haixu Wu#, Haowen Wang, Mingsheng Long#
    arXiv 2024

  2. Deep Time Series Models: A Comprehensive Survey and Benchmark
    Yuxuan Wang*, Haixu Wu*, Jiaxiang Dong*, Yong Liu, Mingsheng Long#, Jianmin Wang
    arXiv 2024

  3. Metadata Matters for Time Series: Informative Forecasting with Transformers
    Jiaxiang Dong*, Haixu Wu*, Yuxuan Wang*, Li Zhang, Jianmin Wang, Mingsheng Long#
    arXiv 2024

Journal Articles

  1. Interpretable Weather Forecasting for Worldwide Stations with a Unified Deep Model
    Haixu Wu, Hang Zhou, Mingsheng Long#, Jianmin Wang#
    Nature Machine Intelligence 2023 / PDF / Code / Slides (Cover Article, WAIC Youth Outstanding Paper Nomination)

  2. PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning
    Yunbo Wang*, Haixu Wu*, Jianjin Zhang, Zhifeng Gao, Jianmin Wang, Philip S. Yu, Mingsheng Long#
    TPAMI 2022 / PDF / Code (ESI Highly Cited Paper, Hot Paper)

  3. ModeRNN: Harnessing Spatiotemporal Mode Collapse in Unsupervised Predictive Learning
    Zhiyu Yao, Yunbo Wang, Haixu Wu, Jianmin Wang, Mingsheng Long#
    TPAMI 2023 / PDF / Code

Conference Proceedings

  1. RoPINN: Region Optimized Physics-Informed Neural Networks
    Haixu Wu, Huakun Luo, Yuezhou Ma, Jianmin Wang, Mingsheng Long#
    NeurIPS 2024 / PDF / Code / Slides

  2. DeepLag: Discovering Deep Lagrangian Dynamics for Intuitive Fluid Prediction
    Qilong Ma*, Haixu Wu*, Lanxiang Xing, Shangchen Miao, Mingsheng Long#
    NeurIPS 2024 / PDF / Code / Slides

  3. TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables
    Yuxuan Wang*, Haixu Wu*, Jiaxiang Dong, Yong Liu, Yunzhong Qiu, Haoran Zhang, Jianmin Wang, Mingsheng Long#
    NeurIPS 2024 / PDF / Code / Slides

  4. Transolver: A Fast Transformer Solver for PDEs on General Geometries
    Haixu Wu, Huakun Luo, Haowen Wang, Jianmin Wang, Mingsheng Long#
    ICML 2024 / PDF / Code / Slides / Poster (Spotlight Paper)

  5. HelmFluid: Learning Helmholtz Dynamics for Interpretable Fluid Prediction
    Lanxiang Xing*, Haixu Wu*, Yuezhou Ma, Jianmin Wang, Mingsheng Long#
    ICML 2024 / PDF / Code / Slides

  6. TimeSiam: A Pre-Training Framework for Siamese Time-Series Modeling
    Jiaxiang Dong*, Haixu Wu*, Yuxuan Wang, Yunzhong Qiu, Li Zhang, Jianmin Wang, Mingsheng Long#
    ICML 2024 / PDF / Code / Slides

  7. Mobile Attention: Mobile-Friendly Linear-Attention for Vision Transformers
    Zhiyu Yao, Jian Wang, Haixu Wu, Jingdong Wang, Mingsheng Long#
    ICML 2024 / PDF / Code

  8. iTransformer: Inverted Transformers Are Effective for Time Series Forecasting
    Yong Liu*, Tengge Hu*, Haoran Zhang*, Haixu Wu, Shiyu Wang, Lintao Ma, Mingsheng Long#
    ICLR 2024 / PDF / Code / Slides (Spotlight Paper, Citation Rank 14th in ICLR 2024)

  9. TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting
    Shiyu Wang*, Haixu Wu*, Xiaoming Shi, Tengge Hu, Huakun Luo, Lintao Ma, James Y. Zhang, Jun Zhou
    ICLR 2024 / PDF / Code / Slides

  10. SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling
    Jiaxiang Dong*, Haixu Wu*, Haoran Zhang, Li Zhang, Jianmin Wang, Mingsheng Long#
    NeurIPS 2023 / PDF / Code (Spotlight Paper)

  11. Solving High-Dimensional PDEs with Latent Spectral Models
    Haixu Wu, Tengge Hu, Huakun Luo, Jianmin Wang, Mingsheng Long#
    ICML 2023 / PDF / Code / Slides

  12. TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis
    Haixu Wu*, Tengge Hu*, Yong Liu*, Hang Zhou, Jianmin Wang, Mingsheng Long#
    ICLR 2023 / PDF / Code / Slides (Citation Rank 11th in ICLR 2023)

  13. Non-stationary Transformers: Rethinking the Stationarity in Time Series Forecasting
    Yong Liu*, Haixu Wu*, Jianmin Wang, Mingsheng Long#
    NeurIPS 2022 / PDF / Code / Slides

  14. Supported Policy Optimization for Offline Reinforcement Learning
    Jialong Wu, Haixu Wu, Zihan Qiu, Jianmin Wang, Mingsheng Long#
    NeurIPS 2022 / PDF / Code / Slides

  15. Flowformer: Linearizing Transformers with Conservation Flows
    Haixu Wu, Jialong Wu, Jiehui Xu, Jianmin Wang, Mingsheng Long#
    ICML 2022 / PDF / Code / Slides

  16. Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy
    Jiehui Xu*, Haixu Wu*, Jianmin Wang, Mingsheng Long#
    ICLR 2022 / PDF / Code / Slides (Spotlight Paper, Citation Rank 15th in ICLR 2022)

  17. Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting
    Haixu Wu, Jiehui Xu, Jianmin Wang, Mingsheng Long#
    NeurIPS 2021 / PDF / Code / Slides (PaperDigest Most Influential Paper)

  18. MotionRNN: A Flexible Model for Video Prediction with Spacetime-Varying Motions
    Haixu Wu*, Zhiyu Yao*, Jianmin Wang, Mingsheng Long#
    CVPR 2021 / PDF / Appendix / Code / Slides

* Equal Contribution, # Corresponding Author

System and Applications

Experience

Selected Awards