This new technique enables LLMs to dynamically adjust the amount of computation they use for reasoning, based on the difficulty of the question.
A new technique enables users to compare several large models and choose the one that works best for their task.
The system automatically learns to adapt to unknown disturbances such as gusting winds.
California Institute of Technology (Caltech)
Ph.D.University of Southern California
M.Sc.Sharif University of Technology
B.Sc.