The performance of Large Language Models (LLMs) on downstream tasks ofte...
We introduce Three Towers (3T), a flexible method to improve the contras...
We introduce a challenging decision-making task that we call active
acqu...
Principled Bayesian deep learning (BDL) does not live up to its potentia...
We propose Active Surrogate Estimators (ASEs), a new method for
label-ef...
We challenge a common assumption underlying most supervised deep learnin...
We introduce active testing: a new framework for sample-efficient model
...
When humans observe a physical system, they can easily locate objects,
u...