Siu Wun "Tony" Cheung

I am a staff research scientist in the Center for Applied Scientific Computing at Lawrence Livermore National Laboratory. Prior to joining LLNL, I obtained my PhD in Mathematics from Texas A&M University in 2020. My research leverages numerical analysis, data science, and machine learning to enable high-fidelity, accelerated simulations, predictions, and inference of complex multiscale physics systems, spanning electronic structures, molecular dynamics, energetic materials, fusion plasmas, and subsurface geoscience. My core interests include finite element methods, multiscale methods, model reduction, and representation learning, with recent expansions into generative modeling. I am a core member of the libROM team and a co-organizer of the DDPS seminars. I am always open to discussing research, please feel free to get in touch.
Date Updates
November 2026 In SIAM MDS26, I will co-chair a minisymposium and present our work on local model reduction for anisotropic diffusion in magnetized plasmas.
July 2026 Our survey on hyper-reduction for nonlinear finite element simulations is published in ACME.
July 2026 In WCCM-ECCOMAS 2026, I will co-chair a minisymposium and present our work on reduced order modeling for first-principle molecular dynamics.
July 2026 Our paper on thermodynamics-informed dynamics identification from noisy data is published in CMAME.
July 2026 Our paper on supervised contrastive code-problem alignment is published in LLM4Code proceedings.
June 2026 In USNC-TAM26, I will present our work on data-driven finite element methods.
May 2026 Our paper on the position of foundation models for computational science is published in CISE.
April 2026 In LLM4Code 2026, I will present our work on supervised contrastive code-problem alignment.
April 2026 Our paper on scalable reduced oder model for Navier-Stokes flow is published in IJNME.
February 2026 Our preprint on reduced order model for first-principles molecular dynamics is available on arXiv.
January 2026 Our preprint on adaptive RBF-KAN is available on arXiv.
October 2025 In SIAM CSS 2025, I will co-chair a minisymposium and present our work on thermodynamics-informed latent space dynamics identification.
September 2025 In SIAM TXLA 2025, I will co-chair a minisymposium and present our work on reduced order modeling for Lagrangian hydrodynamics and density functional theory.
September 2025 Our paper on theory and numerics of subspace approximation of eigenvalue problems is published in AMC.
September 2025 Our preprint on model order reduction for quantum molecular dynamics is available on arXiv.
August 2025 Our preprint on energy conservative hyper-reduction of Lagrangian hydrodynamics is available on arXiv.
July 2025 Our preprint on the position of foundation models for computational science is featured in HPCwire headline story.
July 2025 In USNCCM18, I will present our work on reduced order modeling for first-principle molecular dynamics.
March 2025 In SIAM CSE25, I will co-chair a minisymposium and present our work on reduced order modeling for density functional theory.
January 2025 In JMM 2025, I will give an overview talk on our open-source software libROM.
October 2024 In SIAM MDS24, I will give a talk on reduced order modeling for density functional theory.
August 2024 Our paper on physics-aware localized reduced order models for Rayleigh-Taylor instability was honored with LLNL 2024 Director’s Excellence in Publication Award.
July 2024 In WCCM-PANACM 2024, I will give an overview talk on our open-source software libROM.
July 2024 Our paper on S-optimal point selection algorithm for hyper-reduction is published in SISC.
July 2024 Our paper on non-intrusive surrogate modeling for pore collapse dynamics is published in SHOC.
July 2024 Our paper on thermodynamics-informed latent space dynamics identification with neural networks is published in CMAME.
June 2024 Our paper on generative modeling for stratigraphic geology is published in PETGEO.
March 2024 Our book chapter on latent space dynamics identification is available on arXiv.
August 2023 In ICIAM2023, I will co-chair a minisymposium and present our work on S-OPT point selection algorithm for hyper-reduction.
July 2023 In USNCCM17, I will give an overview talk on our open-source software libROM.
March 2023 In SIAM CSE23, I will present our work on reduced order models for Lagrangian hydrodynamics.
Februrary 2023 Our paper on residual-driven adaptive discontinuous Galerkin multiscale model reduction method is published in MMS.
January 2023 Our paper on multiscale model reduction method for nonlinear multicontinuum flow is published in JCP.
December 2022 A recording of my recent presentation in 2nd MFEM Community Workshop, is now available on Youtube.
October 2022 Our paper on physics-aware localized reduced order models for Rayleigh-Taylor instability is published in JCP.
September 2022 In SIAM MDS22, I will present our work on reduced order models for Lagrangian hydrodynamics.
May 2022 In MWNAD 2022, I will present our work on multiscale methods for physical processes in high contrast heterogeneous porous media.
April 2022 In SIAM UQ22, I will present our work on reduced order models for Lagrangian hydrodynamics.
November 2021 Our paper on reduced order models for Lagrangian hydrodynamics is published in CMAME.
November 2021 Our paper on an explicit discontinuous Galerkin multiscale model reduction scheme for wave propagation is published in MMS.
November 2021 Our paper on an non-local upscaling for multicontinuum flow is published in JCAM.
October 2021 Our paper on iterative oversampling multiscale model reduction method is published in AMC.
July 2021 In USNCCM16, I will present our work on reduced order model simulation for hydrodynamic instability.
June 2021 In SIAM GS21, I will present our work on multiscale and upscaling methods for multicontinuum flow.
May 2021 In PETER 2021 NMH, I will present our work on reduced order model simulation for hydrodynamic instability.
December 2020 Our paper on discontinuous Galerkin based multiscale model reduction method is published in MMS.
July 2020 I am excited to start my new journey in CASC at LLNL.

Experience

Appointments
Lawrence Livermore National Laboratory
Staff Research Scientist
Postdoctoral Research Scientist
Livermore, CA
May 2023 - Present
Jul. 2020 - Apr. 2023
ExxonMobil Upstream Integrated Solutions
Research Engineer Intern
Spring, TX
May 2019 - Aug. 2019
Oak Ridge National Laboratory
REU Intern
Oak Ridge, TN
Jun. 2013 - Aug. 2013
Education
Texas A&M University
PhD in Mathematics
College Station, TX
2020
The Chinese University of Hong Kong
MPhil in Mathematics
BSc in Mathematics
Hong Kong
2016
2014

Research

Research interests
Numerical analysis
Multiscale methods
Model reduction
Representation learning
Generative modeling
Publications & preprints
  1. Siu Wun Cheung, Youngsoo Choi, Jean-Luc Fattebert, Jonas Kaufman, and Daniel Osei-Kuffuor.
    A reduced order model approach for first-principles molecular dynamics computations.
    arXiv preprint arXiv:2602.22390.

  2. Shao-Ting Chiu, Siu Wun Cheung, Ulisses Braga-Neto, Chak Shing Lee, and Rui Peng Li.
    Free-RBF-KAN: Kolmogorov-Arnold networks with adaptive radial basis functions for efficient function learning.
    arXiv preprint arXiv:2601.07760.

  3. Siu Wun Cheung, Youngsoo Choi, Jean-Luc Fattebert, and Daniel Osei-Kuffuor.
    Model order reduction for quantum molecular dynamics.
    arXiv preprint arXiv:2509.07340.

  4. Chris Vales, Siu Wun Cheung, Dylan Matthew Copeland, and Youngsoo Choi.
    Machine-precision energy conservative quadrature hyperreduction of Lagrangian hydrodynamics.
    arXiv preprint arXiv:2508.21279.

  5. Youngsoo Choi, Siu Wun Cheung, Youngkyu Kim, Ping-Hsuan Tsai, Alejandro N. Diaz, Ivan Zanardi, Seung Whan Chung, Dylan Matthew Copeland, Coleman Kendrick, William Anderson, Traian Iliescu, and Matthias Heinkenschloss.
    Defining foundation models for computational science: A call for clarity and rigor.
    arXiv preprint arXiv:2505.22904.

  6. Christophe Bonneville, Xiaolong He, April Tran, Jun Sur Park, William Fries, Daniel A Messenger, Siu Wun Cheung, Yeonjong Shin, David M Bortz, Debojyoti Ghosh, Jiun-Shyan Chen, Jonathan Belof, and Youngsoo Choi.
    A comprehensive review of latent space dynamics identification algorithms for intrusive and non-intrusive reduced-order-modeling.
    arXiv preprint arXiv:2403.10748.

  7. Axel Larsson, Minji Kim, Chris Vales, Sigrid Adriaenssens, Dylan Matthew Copeland, Youngsoo Choi, and Siu Wun Cheung.
    Hyper-reduction methods for accelerating nonlinear finite element simulations: open source implementation and reproducible benchmarks.
    Archives of Computational Methods in Engineering, (2026), doi:10.1007/s11831-026-10749-7.

  8. Jun Sur Richard Park, Auroni Huque Hashim, Siu Wun Cheung, Youngsoo Choi, and Yeonjong Shin.
    WGFINNs: Weak formulation-based GENERIC formalism informed neural networks.
    Computer Methods in Applied Mechanics and Engineering, 461 (2026), 119213.

  9. Siu Wun Cheung and Harshitha Menon.
    Learning functional equivalence via supervised contrastive code-problem alignment.
    LLM4Code '26: Proceedings of the 3rd International Workshop on Large Language Models For Code (2026), 51-58.

  10. Youngsoo Choi, Siu Wun Cheung, Youngkyu Kim, Ping-Hsuan Tsai, Alejandro N. Diaz, Ivan Zanardi, Seung Whan Chung, Dylan Matthew Copeland, Coleman Kendrick, William Anderson, Traian Iliescu, and Matthias Heinkenschloss.
    Rigor over hype: what foundation model should mean in computational science.
    Computing in Science & Engineering, (2026), doi:10.1109/MCSE.2026.3695442.

  11. Seung Whan Chung, Siu Wun Cheung, Youngsoo Choi, Pratanu Roy, Thomas Roy, Tiras Y. Lin, Du T. Nguyen, Christopher Hahn, Eric B. Duoss, and Sarah E. Baker.
    A scalable reduced-order model for the steady Navier–Stokes equations.
    International Journal for Numerical Methods in Engineering, 127-7 (2026), e70314.

  12. Siu Wun Cheung, Youngsoo Choi, Seung Whan Chung, Jean-Luc Fattebert, Coleman Kendrick, and Daniel Osei-Kuffuor.
    Theory and numerics of subspace approximation of eigenvalue problems.
    Applied Mathematics and Computation, 511 (2026), 129722.

  13. Jun Sur Richard Park, Siu Wun Cheung, Youngsoo Choi, and Yeonjong Shin.
    tLaSDI: Thermodynamics-informed latent space dynamics identification.
    Computer Methods in Applied Mechanics and Engineering, 429 (2024), 117144.

  14. Jessica T. Lauzon, Siu Wun Cheung, Yeonjong Shin, Youngsoo Choi, Dylan Matthew Copeland, and Kevin Huynh.
    S-OPT: a points selection algorithm for hyper-reduction in reduced order models.
    SIAM Journal on Scientific Computing, 46-4 (2024), B474-B501.

  15. Siu Wun Cheung, Amit Kushwaha, Huafei Sun, and Xiao-Hui Wu.
    Stochastic representation and conditioning of process-based geological model by deep generative and recognition networks.
    Petroleum Geoscience, 30 (2024), petgeo2022-032.

  16. Siu Wun Cheung, Youngsoo Choi, H. Keo Springer, and Teeratorn Kadeethum.
    Data-scarce surrogate modeling of shock-induced pore collapse process.
    Shock Waves, 34 (2024), 237-256.

  17. Qing Wan, Siu Wun Cheung, and Yoonsuck Choe.
    AdjointBackMapV2: Precise reconstruction of arbitrary CNN unit's activation via adjoint operators.
    Neural Networks, 170 (2024), 55-71.

  18. Sai-Mang Pun and Siu Wun Cheung.
    Online adaptive algorithm for constraint energy minimizing generalized multiscale discontinuous Galerkin method.
    Multiscale Modeling & Simulation, 23 (2023), 168-193.

  19. Tina Mai, Siu Wun Cheung, and Jun Sur Richard Park.
    Constraint Energy Minimizing Generalized Multiscale Finite Element Method for multi-continuum Richards equations.
    Journal of Computational Physics, 477 (2023), 111915.

  20. Siu Wun Cheung, Youngsoo Choi, Dylan Matthew Copeland, and Kevin Huynh.
    Local Lagrangian reduced-order modeling for Rayleigh-Taylor instability by solution manifold decomposition.
    Journal of Computational Physics, 472 (2023), 111655.

  21. Jingyan Zhang and Siu Wun Cheung.
    Analysis of non-local multicontinuum upscaling for dual continuum model.
    Journal of Computational and Applied Mathematics, 406 (2022), 113873.

  22. Siu Wun Cheung, Eric Chung, Yalchin Efendiev, Wing Tat Leung, and Sai-Mang Pun.
    Iterative oversampling technique for constraint energy minimizing generalized multiscale finite element method in the mixed formulation.
    Applied Mathematics and Computation, 415 (2022), 126622.

  23. Dylan Matthew Copeland, Siu Wun Cheung, Kevin Huynh, and Youngsoo Choi.
    Reduced order models for Lagrangian hydrodynamics.
    Computer Methods in Applied Mechanics and Engineering, 388 (2022), 114259.

  24. Jun Sur Richard Park, Siu Wun Cheung, and Tina Mai.
    Multiscale simulations for multi-continuum Richards equations.
    Journal of Computational and Applied Mathematics, 397 (2021), 113648.

  25. Siu Wun Cheung, Eric T. Chung, Yalchin Efendiev, and Wing Tat Leung.
    Explicit and energy-conserving constraint energy minimizing generalized multiscale discontinuous Galerkin method for wave propagation in heterogeneous media.
    Multiscale Modeling & Simulation, 19 (2021), 1736-1759.

  26. Siu Wun Cheung, Eric Chung, and Wing Tat Leung.
    Constraint energy minimizing generalized multiscale discontinuous Galerkin method.
    Journal of Computational and Applied Mathematics, 380 (2020), 112960.

  27. Jun Sur Richard Park, Siu Wun Cheung, Tina Mai, and Viet Ha Hoang.
    Multiscale simulations for upscaled multi-continuum flows.
    Journal of Computational and Applied Mathematics, 374 (2020), 112782.

  28. Siu Wun Cheung, Eric T. Chung, Yalchin Efendiev, Wing Tat Leung, and Maria Vasilyeva.
    Constraint energy minimizing generalized multiscale finite element method for dual continuum model.
    Communications in Mathematical Sciences, 18 (2020), 663-685.

  29. Yating Wang, Siu Wun Cheung, Eric T. Chung, Yalchin Efendiev, and Min Wang.
    Deep multiscale model learning.
    Journal of Computational Physics, 406 (2020), 109071.

  30. Min Wang, Siu Wun Cheung, Eric T. Chung, Maria Vasilyeva, and Yuhe Wang.
    Generalized multiscale multicontinuum model for fractured vuggy carbonate reservoirs.
    Journal of Computational and Applied Mathematics, 366 (2020), 112370.

  31. Siu Wun Cheung, Eric T. Chung, Yalchin Efendiev, Eduardo Gildin, Yating Wang, and Jingyan Zhang.
    Deep global model reduction learning in porous media flow simulation.
    Computational Geosciences, 24 (2020), 261-274.

  32. Min Wang, Siu Wun Cheung, Wing Tat Leung, Eric T. Chung, Yalchin Efendiev, and Mary Wheeler.
    Reduced-order deep learning for flow dynamics. The interplay between deep learning and model reduction.
    Journal of Computational Physics, 401 (2020), 108939.

  33. Maria Vasilyeva, Eric T. Chung, Siu Wun Cheung, Yating Wang, and Georgy Prokopev.
    Nonlocal multicontinua upscaling for multicontinua flow problems in fractured porous media.
    Journal of Computational and Applied Mathematics, 355 (2019), 258-267.

  34. Siu Wun Cheung and Nilabja Guha.
    Dynamic data-driven Bayesian GMsFEM.
    Journal of Computational and Applied Mathematics, 353 (2019), 72-85.

  35. Min Wang, Siu Wun Cheung, Eric Chung, Yalchin Efendiev, Wing Tat Leung, and Yating Wang.
    Prediction of discretization of GMsFEM using deep learning.
    Mathematics, 7 (2019), 412.

  36. Jingyan Zhang, Siu Wun Cheung, Yalchin Efendiev, Eduardo Gildin, and Eric T. Chung.
    Deep model reduction-model learning for reservoir simulation.
    SPE Reservoir Simulation Conference (2019), 193912-MS.

  37. Siu Wun Cheung and Eric T. Chung.
    An embedded SDG method for the convection-diffusion equation.
    International Journal of Numerical Analysis and Modeling, 16 (2019), 255-275.

  38. Siu Wun Cheung, Eric Chung, and Hyea Hyun Kim.
    A mass conservative scheme for fluid-structure interaction problems by the staggered discontinuous Galerkin method.
    Journal of Scientific Computing, 74 (2018), 1423–1456.

  39. Yalchin Efendiev, Wing Tat Leung, Siu Wun Cheung, Nilabja Guha, Viet Ha Hoang, and Bani Mallick.
    Bayesian multiscale finite element methods. Modeling missing subgrid information probabilistically.
    International Journal for Multiscale Computational Engineering, 15 (2017), 175–197.

  40. Siu Wun Cheung, Eric Chung, Hyea Hyun Kim, and Yue Qian.
    Staggered discontinuous Galerkin methods for the incompressible Navier–Stokes equations.
    Journal of Computational Physics, 302 (2015), 251-266.

  41. Yiwei Zhao, Siu Wun Cheung, Ying Wai Li, and Markus Eisenbach.
    Performance of replica-exchange Wang-Landau sampling for the 2D Ising model: a brief survey.
    Physics Procedia, 57 (2014), 43-47.

Softwares

libROM: a free, lightweight, scalable C++ library for data-driven physical simulation methods
C++ implementation of dynamic mode decomposition, proper orthogonal decompsition, hyper-reduction, and matrix manifold interpolation for building parametric reduced order models
pylibROM: Python wrapper of libROM
Python implementation of dynamic mode decomposition, proper orthogonal decompsition, hyper-reduction, and matrix manifold interpolation for building parametric reduced order models
LaghosROM: reduced order models for Lagrangian hydrodynamics
Development of projection-based reduced order models, based on proper orthogonal decompsition, hyper-reduction, and indicator-based localization, for accelerating compressible gas dynamics simulations such as Sedov blast wave and Rayleigh-Taylor instability
MGmolROM: reduced order models for electronics structure calculations and molecular dynamics
Development of projection-based reduced order models, based on proper orthogonal decompsition, tensor basis for electronic density, and equivariance with respect to rigid body motions, for reducing the complexity of density functional theory and molecular dynamics simulations of atomistic systems
tLaSDI: thermodynamics-informed latent space dynamics identification
Development of non-intrusive reduced order models, based on autoencoder compression and neural network representation of GENERIC formalism structures, for enforcing thermodynamic consistency in the inferred dynamics

Presentations

Seminars
NCSU Computational and Applied Mathematics Seminar
Raleigh, NC, Apr. 2026
UTRGV-TAMUCC Joint Seminar on Integrable Systems and Nonlinear Mechanics
Virtual, Mar. 2026
TAMUCC Mathematics Department Seminar
Virtual, Mar. 2026
UARK Applied Mathematics Seminar
Virtual, Nov. 2025
TTU Applied Mathematics and Machine Learning Seminar
Virtual, Apr. 2024
UCSB Applied Math/PDE/DS Seminar
Virtual, Oct. 2023
CUHK SIAM Student Chapter Seminar
Hong Kong, Jan. 2020
CUHK Mathematics Department Seminar
Hong Kong, Dec. 2018
Conference sessions & workshops
SIAM Conference on Mathematics of Data Science 2026
Salt Lake City, UT, Nov. 2026
17th World Congress on Computational Mechanics
Munich, Jul. 2026
20th U.S. National Congress on Theoretical and Applied Mechanics
Pasadena, CA, Jun. 2026
2026 IEEE/ACM 48th International Conference on Software Engineering
Rio de Janeiro, Apr. 2026
Arizona-Livermore Days
Tucson, AZ, Feb. 2026
SIAM Central States Sectional Meeting 2025
Fayetteville, AR, Oct. 2025
SIAM Texas-Louisiana Sectional Meeting 2025
Austin, TX, Sep. 2025
18th U.S. National Congress on Computational Mechanics
Chicago, IL, Jul. 2025
SIAM Conference on Computational Science and Engineering 2025
Fort Worth, TX, Mar. 2025
Joint Mathematics Meetings 2025
Seattle, WA, Jan. 2025
SIAM Conference on Mathematics of Data Science 2024
Atlanta, GA, Oct. 2024
16th World Congress on Computational Mechanics
Vancouver, Jul. 2024
10th International Congress on Industrial and Applied Mathematics
Tokyo, Aug. 2023
17th U.S. National Congress on Computational Mechanics
Albuquerque, NM, Jul. 2023
SIAM Conference on Computational Science and Engineering 2023
Amsterdam, Mar. 2023
6th Annual Sandia Machine Learning and Deep Learning Workshop
Virtual, Oct. 2022
2nd MFEM Community Workshop
Virtual, Oct. 2022
SIAM Conference on Mathematics of Data Science 2022
San Diego, CA, Sep. 2022
Midwest Numerical Analysis Day 2022
Ann Arbor, MI, May 2022
6th Coastal Bend Mathematics & Statistics Conference
Virtual, Apr. 2022
SIAM Conference on Uncertainty Quantification 2022
Atlanta, GA, Apr. 2022
16th U.S. National Congress on Computational Mechanics
Virtual, Jul. 2021
SIAM Conference on Mathematical & Computational Issues in the Geosciences 2021
Virtual, Jun. 2021
12th International Conference on New Models and Hydrocodes for Shock Wave Physics
Virtual, Mar. 2021
SIAM Conference on Mathematics of Data Science 2020
Virtual, May 2020
SIAM Conference on Mathematical & Computational Issues in the Geosciences 2019
Houston, TX, Mar. 2019
Finite Element Rodeo 2018
Houston, TX, Feb. 2018