Fuzzy rough sets combine the principles of fuzzy sets (Zadeh, 1965) and rough sets (Pawlak, 1982). Fuzzy sets handle vague information by acknowledging that membership to certain concepts varies by degree, whereas rough sets address potentially inconsistent information by offering lower and upper approximations of a concept. These two frameworks can be integrated from multiple perspectives, leading to a hybrid theory with applications across a broad range of machine learning problems, including classification, instance and feature selection. In this project, we will continue explore both the foundations (e.g., granular approximations, relationship to topological data analysis) and applications (e.g., in natural language processing) of fuzzy-rough hybridization.