In computer vision, generalization of neural representations is usually measured on i.i.d. data. This hides the fact that representations often struggle to generalize to non-i.i.d data and fail to overcome the biases inherent in visual datasets. I will discuss some recent work in my lab addressing the core challenges in overcoming dataset bias, including adaptation to natural domain shifts, sim2real transfer, avoiding spurious correlations, and the role of pretraining in generalizability.