Loop-ViT is a vision model that thinks in loops, so it can take more steps on hard puzzles and stop early on easy ones.
TTCS is a way for a model to teach itself during the test by first making easier practice questions that are similar to the real hard question and then learning from them.
This paper shows how to keep training a language model while it is solving one hard, real problem, so it can discover a single, truly great answer instead of many average ones.
Robots usually learn by copying many demonstrations, which is expensive and makes them brittle when things change.