The field of fluid dynamics is witnessing significant advancements with the integration of scientific machine learning (SciML) techniques. Researchers are exploring innovative approaches to improve the accuracy and efficiency of flow simulations, particularly in complex geometries and convection-dominated problems. The development of novel methods, such as geometry-adaptive models and differentiable Lagrangian shock hydrodynamics, is enabling the simulation of intricate phenomena, like blood flow dynamics and shock acceleration of density interfaces. Noteworthy papers in this area include the work on 3D Neural Operator-Based Flow Surrogates, which demonstrates improved boundary-layer accuracy and generalization capabilities, and the introduction of a geometry adaptive waveformer for cardio-vascular modeling, which shows promise in predicting blood flow dynamics in complex anatomies. Additionally, the application of physics-informed neural networks and deep operator networks to vascular flow simulations and the solution of the Helmholtz equation using neural networks are highlights of the current research landscape.