AI systems need exact descriptions of tasks to be performed.

Deep learning sometimes appears to work in unexpected ways.

Current test-time adaptation (TT A) approaches aim to adapt a machine learning model to environments that change continuously.

Code is at this URL.

We explore online learning in episodic Markov decision processes on non-stationary environments (changing losses and probability transitions).

Surgical video-language pretraining (VLP) faces unique challenges due to the knowledge domain gap and the scarcity of multi-modal data.