Transfer operator theory is a fundamental concept in dynamical systems theory which describes the evolution of probability densities over time, thus offering a powerful lens through which the underlying dynamics of a system can be understood and predicted. KoopmanFlows leverage advanced data-driven techniques to explore and identify the leading eigenfunctions of the transfer operator in complex dynamical systems. This project aims to develop and implement a computational framework that combines state-of-the-art Artificial Intelligence/Machine Learning (AI/ML) algorithms, such as diffusion models and stochastic interpolants, with theoretical insights from dynamical systems and operator theory. By doing so, KoopmanFlows seeks to identify the slow dynamics in (biomolecular) simulations, which are often challenging to analyze using traditional methods. We will test the performance of the method, on low-dimensional model systems as well as on more complex, biomolecular systems that require high-performance computing due to the complexity of the data as well as the models. By granting this proposal for computing hours on Alvis, this project will be able to harness the power of AI methods to gain a new understanding and insights into the behavior of complex systems, allowing for advancements in various scientific and engineering domains.