Flow-induced crystallization in polymers is an important problem in both fundamental polymer science and industrial polymer processing. The key process of flow-induced nucleation occurs on a very rapid time scale and on a highly localized lengthscale and so is extremely difficult to observe directly in experiments. However, recent advances in molecular dynamics (MD) simulations mean that flow-induced nucleation can be simulated at an achievable computational cost. Such studies offer unrivalled time and lengthscale resolution of the nucleation process. Nevertheless, the computational cost of MD places considerable constraints on the range of molecular weights, temperature, and polydispersity that can be studied. In this review, I will discuss recent progress, describe how future work might resolve or work around the constraints of molecular simulation, and examine how multiscale modeling could translate molecular insight into improved polymer processing. (C) 2019 The Society of Rheology.