The purpose of this project is to continue developing physics informed Machine Learning (ML) methods to accelerate and/or complement state-of-the-art simulation methods for Soft-Matter flows. Following our work of the previous year, we are considering three characteristic problems: (A) simulating entangled polymer melt flows, (B) inferring the solution of Stokes flow problems given partial and/or noisy data, and (C) teaching active particles how to navigate non-uniform flows using local hydrodynamic signals. For topics (A-B) we are considering more complex flows, for topic (C) we are investigating how to target more complex collective behaviours. Throughout, we have continued our work to improve the robustness and scalability of our numerical methods, with the aim of studying the large-scale and complex systems observed in real-life Soft-Matter systems.