Why do large language models sometimes output factual inaccuracies and
e...
Active learning is perhaps most naturally posed as an online learning
pr...
Models that can actively seek out the best quality training data hold th...
This work introduces the Eigen Memory Tree (EMT), a novel online memory ...
Algorithmic reasoning requires capabilities which are most naturally
und...
Intrinsic rewards play a central role in handling the
exploration-exploi...
Noise contrastive learning is a popular technique for unsupervised
repre...
There is an increasing need for effective active learning algorithms tha...
Meta-materials are an important emerging class of engineered materials i...
In many real-world deployments of machine learning systems, data arrive
...
We design a new algorithm for batch active learning with deep neural net...
Domain adaptation addresses the problem created when training data is
ge...