Constitutive modeling enables the mathematical description of the behavior of different materials such as metals, polymers, composites, soft biological tissue, or active materials. Conventional modeling approaches face challenges regarding highly nonlinear, inelastic, or multiphysical behavior. This can be traced back to a lack of flexibility of conventional constitutive models. To address this, in recent years, the formulation of material models using highly flexible machine learning (ML) methods such as neural networks, Gaussian processes and symbolic regression has gained momentum. It is widely agreed that ML-based constitutive models should be formulated to fulfill mechanical conditions such as thermodynamic consistency and objectivity, which can be coined as physics-augmented, physics-enhanced, or physics-constrained ML modeling. By that, the flexibility of ML-methods is combined with a sound mechanical basis. This minisymposium seeks to gather researchers working at the intersection of mechanics and machine learning to address current challenges and explore emerging trends. Topics of interest include, but are not limited to: • Constitutive modeling based on ML-methods such as neural networks and Gaussian processes • Modeling of material behavior including: (i) energy conservation and dissipation (e.g., viscoelasticity, plasticity, damage, fracture, …), (ii) multiphysics (e.g., thermo-, magneto-, or electromechanics), and (iii) parametric dependencies • Fulfillment of physical conditions, interpretability, sparsity, and uncertainty quantification • Calibration of constitutive models to (full-field) experimental data • Efficient and structure-preserving implementation in numerical schemes such as multiscale simulation and topology optimization