Archived News

  2025

  • 08/2025 News: A 3M collaborative research project led by the CIMS Lab was recently featured in the University of Minnesota News: [Research & Innovation Office] [CEGE].
  • 08/2025 Events: We successfully concluded the workshop GenAI4Science: Integrating Scientific Knowledge into Generative AI at UMN (Aug 13–14, 2025). Dr. He delivered a featured talk on Physics-Constrained Differentiable Modeling and Inverse Design with Latent Machine Learning and also served as a panelist in the GenAI in Materials session. The workshop was recorded and shared on the DSI YouTube channel..
  • 08/2025 Outreach: We successfully hosted an fantastic lecture on Physical AI in Engineering Science and hands-on computer labs as part of our STEM summer program, engaging 20 motivated high school students. Special thanks to our PhD students Binyao and Zihan for their excellent preparation of codes and demonstrations that made the event memorable!
  • 07/2025 Events: The CIMS Lab has three presentations at USNCCM-18 in Chicago, July 20–24, showcasing Advances in Differentiable and AI-Augmented Mechanics [News]:
    • Guo, Binyao et al., Attention-Enhanced Fourier Neural Operators for Robust Constitutive Modeling of History-Dependent Nonlinear Materials [Abstract]
    • Lin, Zihan et al., A Latent Diffusion Model-Coupled Differentiable Physics Simulator for Inverse Modeling of Heterogeneous Media [Abstract]
    • Du, Honghui et al., A Differentiable Meshfree Method for Nonlinear Mechanics and Geomechanics Modeling [Abstract]
  • 07/2025 Publications: Two recent preprints:
    • Guo, Lin et al., History-Aware Neural Operator: Robust Data-Driven Constitutive Modeling of Path-Dependent Materials [Preprint]
    • Du et al., JAX-MPM: A Learning-Augmented Differentiable Meshfree Framework for GPU-Accelerated Lagrangian Simulation and Geophysical Inverse Modeling [Preprint]
  • 05/2025 Events: Dr. He presented recent advancements in a differentiable Eulerian–Lagrangian framework (JAX-MPM) for nonlinear mechanics and landslide hazard modeling at the 2025 ASCE Engineering Mechanics Institute (EMI) Conference.
  • 05/2026 Events: We welcome you to participate in our mini-symposium, "Advancements of Data-Driven Methods in Computational Mechanics" (Mini-Symposia Code: v2vyb), co-organized by Professors Nikolaos Vlassis, Jiun-Shyan Chen, WaiChing Sun, and myself. The symposium will take place at the 2025 ASCE Engineering Mechanics Institute (EMI) Conference in Anaheim, California, from May 27–30, 2025.
  • 03/2025 Awards: Our group receives 3M Research Grant to advance generative AI for polymer discovery. We sincerely thank 3M and our collaborators for their generous support. [News]
  • 03/2025 Announcements: Our group is officially named the Computational Intelligence and Multiphysics Simulation Lab (CIMS Lab). [News]
  • 01/2025 Events: Dr. He delivered a Seminar in the Department of Aerospace Engineering and Mechanics on the topic of Differentiable Computational Mechanics. [News]

  2024

  • 12/2024 Publications: Our paper, which focuses on advancing the differentiable meshfree method with GPU acceleration for modeling nonlinear elasticity problems and characterization of heterogeneous mechanical properties, has been published in Engineering with Computers [Link]. Tutorial code is available on GitHub. 
  • 12/2024 Awards: Binyao was awarded the ADC Graduate Fellowship by the Data Science Initiative, which will support his research on AI-Enabled Multiphysics Design and Simulations.
  • 11/2024 Events: Recent updates from IMECE 2024 in Portland, OR:
    Our group was involved in two talks:
    1. "A Neural Network-Enhanced Differentiable Meshfree Method for Computational Mechanics"
    2. "Neural Topology Optimization Based on Differential Programming with Principled Constrained Optimization"
    Also, congratulations to Honghui for receiving the ASME Applied Mechanics Division's Robert M. and Mary Haythornthwaite Foundation Student Travel Award for the work on "Neural-Integrated Meshfree Method for computational mechanics". [See more]

  • 09/2024 Events: Thank Prof. Wada for inviting me to present at the workshop "Deep and Machine Learning Methodology in the Context of Application to Computational Engineering" during IWACOM-IV in Kitakyushu, Japan. I’m excited to share my work and engage with colleagues on advancements in this area.

  • 09/2024 Events: Dr. He delivered a seminar on differentiable solid mechanics and geophysics, titled "Neural-Integrated and Data-Driven Approaches for Computational Modeling in Solid Mechanics and Geophysics," at NUS, NTU and A*STAR in Singapore. [News]

  • 07/2024 Announcement : This year, IMECE 2024 is introducing a new "Best Paper Competition" to recognize the top 10 AI/Deep Learning-related papers presented at the conference. I am thrilled to have been invited to serve on the ASME AI/Deep Learning Best Paper Honors Committee. I encourage you to nominate outstanding AI papers from your fields, and I’m excited to see the innovative work that will be submitted! [See Link]

  • 07/2024 Publications: Our new paper, "Differentiable Neural-Integrated Meshfree Method for Forward and Inverse Modeling of Finite Strain Hyperelasticity," is now available on arXiv. In this paper, we discuss how to accurately simulate nonlinear elastic materials, such as rubbers, biotissues, and beam structures under large deformation, by a novel machine learning method, while bypassing the use of consistent tangent stiffness and Newton's method conventionally required in FEM solvers. Additionally, the same framework can handle complex material identification for biological tissues. Check it out here!

  • 07/2024 Short course: In the upcoming WCCM 2024 / PANACM 2024 conference, we are co-organizing a short course titled "Machine Learning for Solid Mechanics". Qizhi He will deliver a lecture and a lab on Manifold Learning and Data-Driven Computing for Nonlinear Solid Mechanics. 

  • 04/2024 Publications: Congratulations to Honghui for publishing the paper "Neural-Integrated Meshfree (NIM) Method" in Computer Methods in Applied Mechanics and Engineering. This novel framework integrates symbolic basis functions, meshfree discretization, and physics-informed machine learning to efficiently solve PDEs in computational mechanics. Feel free to check the paper in Link. We also look forward to reporting the GPU-enabled NIM for nonlinear elasticity soon!

  2023

  2022

  • 12/2022 Events: Dr. He gave a seminar talk about Reduced Order Modeling and Physics-Constrained Deep Surrogate Model at University of Illinois Urbana-Champaign.

  • 11/2022 Events: PhD student Honghui presented his recent studies on "efficient meshfree method and CO2 density-driven flow modeling by using physics-informed neural networks" in the Structures Seminar at the Department of Civil, Environmental, ang Geo- Engineering.

  • 11/2022 Events: Dr. He gave a talk titled "Data-Assisted Computational Mechanics: From Reduced Order Modeling to Physics-Constrained Deep Surrogate Model" in Solid Mechanics Research Seminar at the Department of Aerospace Engineering and Mechanics.

  • 08/2022 News: Dr. He was appointed as the CTS Faulty Scholar of the Center for Transportation Studies. He also recently joined the organizer team for the "CSE DSI Machine Learning Seminar Series sponsored by the College of Science and Engineering.

  • 08/2022 Publications: A collaborative work with UC San Diego's teams is accepted for publication in the ASME-Journal of Biomechanical Engineering. Congratulations! 

  • 08/2022 Welcome: Welcome to new CEGE graduate student Honghui Du to join He Group!

  • 06/2022 Awards: Our lab received a UMII seed grant award (Medium) to develop a novel knowledge-augmented machine learning tool for a fast and reliable defect prediction in 3D printing. Congratulations!

  • 01/2022 Announcements: The research lab on Computing, Intelligence, Mechanics are launched at the University of Minnesota!