Neuroexplicit models combine neural and human-interpretable ('explicit') models to overcome the limitations that each model class has separately. They include neurosymbolic models, which combine neural and symbolic models, as well as combinations of neural and physics-based models. The Research Training Group (RTG) aims to improve the state of the art in natural language processing ('Language'), computer vision ('Vision'), and planning and reinforcement learning ('Action'), and to develop novel machine learning techniques for neuroexplicit models ('Foundations'). The goal is to contribute to a better understanding of the cross-cutting design principles of effective neuroexplicit models through interdisciplinary collaboration.