Scheduled presentations:

• Physics-Informed Neural Networks for Computational (Contact) Mechanics: From Collocation to Energy-Based and Variational Formulations
  *D. Wolff (University of the Bundeswehr Munich), S. Völkl (University of the Bundeswehr Munich), T. Sahin (University of the Bundeswehr Munich), A. Popp (University of the Bundeswehr Munich)
• Physics based machine learning framework for cyclic damage evolution and fatigue lifetime-scale homogenization
  *E. Elsayed (Leibniz Universität Hannover), A. Baktheer (Leibniz Universität Hannover), F. Aldakheel (Leibniz Universität Hannover)
• Predicting the Thermo-Mechanical Behavior of Periodic Microstructures Through Spectral-Based Physics-Informed Finite Operator Learning (SPiFOL)
  *C. Gierden (Ruhr University Bochum), A. Harandi (Henkel AG & Co. KGaA), S. Rezaei (ACCESS e.V), J. Waimann (Ruhr University Bochum)
• Embedding a Physics-Constrained ML Constitutive Model Into the Finite Element Framework via an Abaqus UMAT
  *Y. He (Institut für Mechanik, Universität Kassel), Y. Heider (Institut für Mechanik, Universität Kassel)
• Finite Element-Guided Physics-Informed Operator Learning for Multiphysics Problems
  *Y. Yamazaki (Keio University), R. Asl (Technical University of Munich), M. Apel (ACCESS e.V.), M. Muramatsu (Keio University), S. Rezaei (ACCESS e.V.)
• SPLIT-PINN: Separable Probability Learning Technique via Physics-Informed Neural Networks for High-Dimensional Probabilistic Modeling
  *W. Pan (University of Wisconsin-Madison)