The Two Phases of Transfer Learning

I like to think about kind of there being two phases and some of the talks that I've given recently, I sort of called a neural knowledge acquisition phase and the neural knowledge mobilization phase. Thinking of it as the pre-training is sort of like us trying to put as much knowledge as we can into a base machine learning or neural net model. And my more recent research has been more interested in that sort of second phase and trying to see whether we can do something better than fine-tuning. So how do we take this pre-trained model and extract the right information from it to solve well some downstream tasks?