Papers & talks

Publications and presentations

Research in scientific machine learning, dynamical systems, inverse problems, and numerical analysis. The lists below are current through October 2026.

Papers

Journal articles

  1. Unified Learning of the Profile Function in Discrete Keller-Segel ModelsC. Chen, C. Liu, and M. Zhong · To appear in Advances in Computational Science and Engineering · arXiv:2510.23381.
  2. Dimension Domain Co-Decomposition: Solving PDEs with InterpretabilityS. Shang, M. Zhong, and R. Wang · Transactions on Machine Learning Research, 2026 · OpenReview.
  3. SEDONA-GesaRaT: A Deep Learning Accelerated Radiative Transfer Program for 3D Supernova SimulationsX. Chen, U. Braga-Neto, L. Wang, D. Kasen, Z. Liu, F. K. Röpke, M. Zhong, and D. J. Jeffery · The Astrophysical Journal, 1006(1): 86, 2026.
  4. Stability in Training PINNs for Stiff PDEs: Why Initial Conditions MatterB. Hao, C. Liu, U. Braga-Neto, L. Wang, and M. Zhong · Foundations of Data Science, 2026 · doi:10.3934/fods.2026016.
  5. A Finite Element Framework for Simulating Residential Burglary in Realistic Urban GeometriesB. Hao, K. Milly, A. Quaini, and M. Zhong · Mathematical Models and Methods in Applied Sciences, 36(5): 1019–1050, 2026.
  6. Attractive and Repulsive Interactions in the One-Dimensional Swarmalator ModelB. Hao, M. Zhong, and K. O’Keeffe · Physical Review E, 108: 064214, 2023.
  7. Stabilized Hyperbolic PDE Solver by Adding Adaptive Localized Artificial Viscosity to Physics-Informed Neural NetworksE. J. R. Coutinho, M. Dall’Aqua, L. McClenny, M. Zhong, U. Braga-Neto, and E. Gildin · Journal of Computational Physics, 489: 112265, 2023.
  8. The Emergence of Lines of Hierarchy in Collective Motion of Biological SystemsJ. Greene, E. Tadmor, and M. Zhong · Physical Biology, 20(5): 055001, 2023.
  9. Learning Theory for Inferring Interaction Kernels in Second-Order Interacting Agent SystemsJ. Miller, S. Tang, M. Zhong, and M. Maggioni · Sampling Theory, Signal Processing, and Data Analysis, 21: 21, 2023.
  10. On the Sparsity of Lasso Minimizers in Sparse Data RecoveryS. Foucart, E. Tadmor, and M. Zhong · Constructive Approximation, 57: 901–919, 2023.
  11. Data-Driven Discovery of Emergent Behaviors in Collective DynamicsM. Zhong, J. Miller, and M. Maggioni · Physica D: Nonlinear Phenomena, 411: 132542, 2020.
  12. Nonparametric Inference of Interaction Laws in Systems of Agents from Trajectory DataF. Lu, M. Zhong, S. Tang, and M. Maggioni · Proceedings of the National Academy of Sciences, 116(29): 14424–14433, 2019.
  13. A Stochastic Mortar Mixed Finite Element Method for Flow in Porous Media with Multiple Rock TypesB. Ganis, I. Yotov, and M. Zhong · SIAM Journal on Scientific Computing, 33(3): 1439–1474, 2011.

Conference and workshop papers

  1. PINNs-Based Uncertainty Quantification for Transient Stability AnalysisR. Wang, M. Zhong, K. Xu, L. G. Sánchez-Cortés, and I. de Cominges Guerra · CEEGE 2026. Best Poster Award.
  2. 3D-PINNS: A Unified Framework for Dimension-Wise Interpretability and Adaptive Domain DecompositionS. Shang, M. Zhong, and R. Wang · ICLR 2026 Workshop on AI & PDE, 2026.
  3. Noise-Based Regularized Training for Diffusion ModelsY. Shang, Y. Lu, J. Feng, M. Zhong, and Y. Yan · 19th International Conference on Machine Vision Applications, 2025.
  4. Learning Stochastic Dynamics from DataZ. Guo, I. Cialenco, and M. Zhong · ICLR Workshop on AI4DifferentialEquations in Science, 2024.
  5. Towards Saner Deep Image RegistrationB. Duan, M. Zhong, and Y. Yan · IEEE/CVF International Conference on Computer Vision, 12459–12468, 2023.
  6. Learning Interaction Variables and Kernels from Observations of Agent-Based SystemsJ. Feng, M. Maggioni, P. Martin, and M. Zhong · IFAC-PapersOnLine, 55(30): 162–167, 2022.
  7. Grassmannian Packings: Trust Region Stochastic Tuning for Matrix IncoherenceJ. Park, C. Saltijeral, and M. Zhong · 58th Annual Allerton Conference, 1–6, 2022.
  8. Learning Interaction Kernels for Agent Systems on Riemannian ManifoldsM. Maggioni, J. Miller, H. Qiu, and M. Zhong · Proceedings of the 38th International Conference on Machine Learning, PMLR 139: 7290–7300, 2021.

Book chapter

  1. Learning Collective Behaviors from ObservationJ. Feng and M. Zhong · In Explorations in the Mathematics of Data Science, 101–132, 2024.
Manuscripts under review
  1. Physics-Informed Random Feature Neural Networks for Solving PDEsC. Chen, C. Liao, and M. Zhong · September 2026 · arXiv:2609.16406.
  2. Learning Interaction Kernels from Collective Steady StatesB. Hao, M. Maggioni, and M. Zhong · September 2026 · arXiv:2609.12004.
  3. Simultaneous Inference of Environmental and Interaction Forces in Collective DynamicsN. de Silva, M. Zhong, and J. Greene · August 2026 · arXiv:2608.25181.
  4. Event-Structured Physics-Informed Neural Networks for Differentiable Critical Clearing BoundariesB. Hao, C. Hu, M. Zhong, and R. Wang · July 2026 · arXiv:2607.27681.
  5. Crime Hotspot Dynamics in Residential Burglary Models with Police ResponseB. Hao, K. Milly, A. Quaini, and M. Zhong · May 2026 · arXiv:2605.17709.
  6. Noise-Aware System Identification for High-Dimensional Stochastic DynamicsZ. Guo, I. Cialenco, and M. Zhong · October 2024 · arXiv:2411.00002.
Manuscripts in preparation or revision
  1. Machine Learning for Discovering Effective Interaction Kernels Between Celestial Bodies from EphemeridesB. Hao, M. Maggioni, J. Miller, and M. Zhong · Under revision before resubmission; earlier version: arXiv:2108.11894.
  2. Discovery of Hidden Crime Dynamics, Part I: Parametric StructuresB. Hao, A. Quaini, and M. Zhong.
  3. Learning Stochastic Dynamical Systems with Structured NoiseZ. Guo, J. Greene, and M. Zhong · Under revision before resubmission; earlier version: arXiv:2503.01077.
  4. An Integrated Framework for Learning Stochastic Differential EquationsZ. Guo, J. Greene, and M. Zhong.
  5. Identification of Diffusion and Reaction Functions from Stochastic Diffusion-Reaction PDEsZ. Guo, I. Cialenco, and M. Zhong.
  6. Label Propagation for Physics-Informed Neural Networks and Physics-Informed Gaussian ProcessesM. Zhong, D. Liu, R. Arroyave, and U. Braga-Neto · Under revision before resubmission; earlier version: arXiv:2404.05817.
Other preprints and doctoral dissertation
  1. Using Physics-Informed Neural Networks for Supernova Radiative Transfer SimulationX. Chen, D. J. Jeffery, M. Zhong, L. McClenny, U. Braga-Neto, and L. Wang · November 2022 · arXiv:2211.05219.
  2. Concurrent Emergence of Clustering, Flocking and Synchronization in Systems of Interacting AgentsT. Gerew and M. Zhong · February 2023 · arXiv:2302.06732.
  3. Time Relaxation with Iterative Modified Lavrentiev RegularizationM. Zhong · September 2018 · arXiv:1809.09517.
  4. Iterative Refinement of a Modified Lavrentiev Regularization Method for De-Convolution of the Discrete Helmholtz Type Differential FilterN. Mays and M. Zhong · January 2018 · arXiv:1801.08913.
  5. Hierarchical Reconstruction Method for Solving Ill-Posed Linear Inverse ProblemsM. Zhong · Ph.D. thesis, University of Maryland, College Park, Maryland, 2016.

Talks

Upcoming and recent invited presentations

  • Jan. 2027
    Recent Advances in Learning Collective BehaviorJoint Mathematics Meetings, Chicago, Illinois · scheduled
  • Nov. 2026
    Understanding Collective BehaviorsSIAM Mathematics of Data Science, Salt Lake City, Utah · scheduled
  • Oct. 2026
    Modeling, Simulation, and Data-Driven Discovery of Crime DynamicsSIAM NY-NJ-PA Sectional Meeting, Piscataway, New Jersey · scheduled
  • Oct. 2026
    Enhanced Training Methods for PINNs for Solving Stiff PDEs and Hyperbolic PDEsSIAM Central States, Jackson, Mississippi
  • Jul. 2026
    Discover Dynamics from Static PatternsEquation-Based Learning at SIAM Life Sciences, Cleveland, Ohio
  • May 2026
    Structure-Aware Physics-Informed Random Feature NetworksSIAM Conference on Waves and Coherence Structures, Montréal, Canada
  • May 2026
    Discover Dynamics from Static Patterns9th International Conference on Computational Harmonic Analysis, Vanderbilt University
  • Sep. 2025
    Discover Dynamics from Static PatternsSIAM TX-LA Sectional Meeting, University of Texas at Austin
  • May 2025
    Recent Advances in Efficient Learning from High-Dimensional DataNSF CompMath PIs Meeting, University of Utah
  • May 2025
    Learning Stochastic Dynamics from Structured NoiseAMS Spring Southeastern Sectional Meeting, Clemson University
  • Apr. 2024
    Learning Collective Variables and Kernels from ObservationsIMSI, University of Chicago
  • Apr. 2024
    Learning Collective Behaviors from ObservationMidwest Numerical Day, University of Iowa
Invited conference and workshop talks, 2015–2023
  • Oct. 2023
    Machine Learning of Collective BehaviorsSIAM Great Lakes, Michigan State University; and SIAM Central States, University of Nebraska-Lincoln
  • Aug. 2023
    Machine Learning of Self-Organization from ObservationICIAM 2023, Tokyo, Japan
  • July 2023
    Physics-Informed Machine Learning for Solving Stiff and Nonlinear PDEs17th U.S. National Congress on Computational Mechanics, Albuquerque, New Mexico
  • June 2023
    Learning Collective Behaviors in NetworksIDEAL Get Ready for Research Workshop, University of Illinois Chicago
  • June 2023
    Making Scientific Discoveries with Scientific Machine LearningTexas A&M Research Computing Symposium
  • May 2023
    Machine Learning of Self-Organization from ObservationBIRS Workshop: Emergent Collective Behaviors, Banff, Canada
  • May 2023
    Machine Learning of Collective Behaviors from ObservationSIAM DS23, Portland, Oregon
  • Apr. 2023
    Machine Learning of Collective Behaviors from ObservationMidwest Numerical Analysis Day, Iowa State University; and Shanks Workshop, Vanderbilt University
  • Apr. 2022
    Machine Learning of Self-Organization from ObservationThematic Einstein Semester Workshop, Berlin, Germany
  • Nov. 2021
    Machine Learning for Discovering Effective Interaction Kernels Between Celestial Bodies from EphemeridesSIAM TX-LA Sectional Meeting
  • May 2021
    Data-Driven Modeling of Celestial MechanicsSIAM Conference on Applications of Dynamical Systems
  • Apr. 2021
    Data-Driven Modeling of Celestial MechanicsEast Coast Optimization Meeting, George Mason University
  • Apr. 2021
    Data-Driven Modeling of Collective DynamicsSayas Numerics Day, University of Maryland
  • 2019
    Data-Driven Discovery of Emergent States in Collective DynamicsMid-Atlantic Numerical Analysis Day; Young Researchers Workshop on Kinetic Theory; SIAM SEAS
  • May 2019
    Data-Driven Approaches for Scientific DiscoveriesConference on Applied Mathematics, George Washington University
  • 2018
    Learning Interaction Laws from ObservationsMid-Atlantic Numerical Analysis Day; International Conference on Mathematics of Data Science; Young Researchers Workshop; CMS–AMS Joint Meeting
  • Apr. 2017
    Hierarchical Reconstruction Method for De-Convolution on Discrete Helmholtz FilterConference on Applied Mathematics, George Washington University
  • Nov. 2015
    Hierarchical Reconstruction of Sparse Solutions from Under-Determined Linear SystemsMid-Atlantic Numerical Analysis Day, Temple University
Colloquia, seminars, and industry talks
  • Mar. 2026
    Discover Dynamics from Static PatternsApplied Math Seminar, University of California, Riverside
  • Aug. 2024
    Recent Advances in Structured Learning from High-Dimensional DataData-Enabled Science Seminar, University of Houston
  • Apr. 2024
    Learning Collective Behaviors from ObservationPyData Chicago
  • Sep. 2023
    Machine Learning of Collective BehaviorsApplied Math Seminar, University at Buffalo
  • Sep. 2023
    Learning Collective Behaviors from ObservationData Science Colloquium, Rush University
  • Feb. 2023
    Machine Learning of Self-Organization from ObservationUniversity of Notre Dame; University of South Carolina; Illinois Institute of Technology
  • Oct. 2022
    Scientific Machine Learning for Knowledge DiscoveryChemical and Biological Engineering Seminar, Illinois Tech
  • Apr. 2022
    Machine Learning of Self-Organization from ObservationComputational Science Seminar, UMass Dartmouth
  • Mar. 2022
    Machine Learning of Self-Organization from ObservationUniversity of Houston; Lawrence Livermore National Laboratory
  • Jan. 2022
    Machine Learning of Self-Organization from ObservationApplied Physics Seminar, University of Nevada-Las Vegas
  • 2021
    Machine Learning of Collective Behaviors from ObservationBaylor University; Texas A&M University; University of Notre Dame; Oak Ridge National Laboratory
  • Mar. 2021
    Data-Driven Modeling of Collective DynamicsUniversity of New South Wales; Syracuse University; University of Georgia; University of Oklahoma
  • 2020
    Learning Collective Dynamics from Trajectory DataDartmouth College; Clarkson University; Illinois Tech
  • 2019
    Emergent Behaviors and Interaction Laws in Collective DynamicsUniversity of Maryland; UMBC; George Washington University
  • Oct. 2018
    Discovering Governing Laws of Interaction in Heterogeneous Agent DynamicsUniversity of Maryland
  • Nov. 2012
    Hierarchical Reconstruction of Sparse SignalsStone Ridge Technology, Bel Air, Maryland
Poster presentations
  • June 2023
    Learning Collective Behaviors from ObservationModern Applied and Computational Analysis at ICERM
  • Mar. 2023
    Learning Collective Behaviors from ObservationAAAI Spring Symposium on Computational Approaches to Scientific Discovery
  • Aug. 2022
    Making Scientific Discoveries with Scientific Machine LearningAI + Science Summer School, University of Chicago
  • July 2021
    Learning Interaction Kernels for Agent Systems on Riemannian ManifoldsICML 2021
  • May 2021
    Physics-Informed Machine Learning of Collective Behaviors from ObservationICERM Workshop on Hyperbolic Conservation Laws
  • 2020
    Learning Collective Dynamics and Emergent BehaviorsIMA Workshop; ICERM Algorithms for Dimension and Complexity Reduction; ICERM Mathematics of Reduced Order Models
  • Apr. 2019
    Learning Interaction Laws in Heterogeneous Agent DynamicsNature Conference on Emergent Materials and Devices, Chengdu, China
  • 2018
    Learning Interaction Laws in Heterogeneous Agent DynamicsCISMMS Workshop and IDIES Annual Symposium, Baltimore
  • Aug. 2017
    Learning Dynamical Interactions on Multiple Classes of AgentsICERM Workshop on Pedestrian Dynamics