Ideally, we would like methods that train LMs only once ( i.e., one-shot) with a fixed objective, as in

Recent advances in machine learning and artificial intelligence have relied on fitting highly overparam-eterized models, notably deep neural networks, to observed data; e.g.

Pretraining CNN models (i.e., UNet) through self-supervision has become a powerful approach to facilitate medical image segmentation under low annotation regimes.

It is a variant of shuffle coding that is many orders of magnitude faster than the original and enables'one-shot' compression of single