The advent of machine learning (ML) is actively revolutionizing the realm of computational solid mechanics, creating a platform for the development of novel methods with unprecedented efficiency. Nonetheless, several limitations still hinder the direct incorporation of purely ML-based methods in industry-level engineering problems, including the need to generate vast datasets, their limited generalizability beyond the training regime, their numerical sensitivity to the choice of hyperparameters, and more. To this end, there is a growing momentum towards hybrid modeling paradigms which integrate ML-based techniques with conventional numerical methods. The aim of these hybrid frameworks is to capitalize on the strengths of both worlds: the robustness and rigor of conventional methods (such as FEM, BEM, VEM, etc.) and the flexibility and speed of machine learning, ultimately targeting large-scale, multi-physics, real-world solid mechanics problems. In this minisymposium, we invite new contributions focused on hybrid solvers combining ML tools with existing numerical methods, topics of interest include but not limited to: • Novel combinations of ML-tools (networks, operators, etc.) with the Finite Element Method, Boundary Element Method, Virtual Element Method, meshless approaches, and more. • Fusion of ML-methods into multi-scale (FE2) modeling, to accelerate solid mechanics simulations across different length scales. • Efficient and robust pathways to extrapolate the ML predictive capability beyond the bounds of the training regime (unseen geometries, loading conditions, timeframes, etc.). • Challenges and opportunities in the utilization of ML-methods for the solution of coupled multi-physics problems, including fracture, corrosion, thermo-hydro-mechanic-chemical coupling, and more. • Complementing numerical methods of failure analysis with physics-augmented machine learning, with applications on phase-field fracture, continuum damage, peridynamics, cohesive zone models, etc. • Stochastic analysis and uncertainty quantification of such hybrid methods.