The U.S. criminal legal system increasingly relies on software output to...
Although the fairness community has recognized the importance of data,
r...
In this work, we study the pandemic course in the United States by
consi...
For machine learning systems to be reliable, we must understand their
pe...
Improvements to Zambia's malaria surveillance system allow better monito...
In performative prediction, predictions guide decision-making and hence ...
We propose a new framework for 2-D interpreting (features and samples)
b...
We build four new test sets for the Stanford Question Answering Dataset
...
Consequential decision-making incentivizes individuals to adapt their
be...
We introduce a general approach, called test-time training, for improvin...
Excessive reuse of test data has become commonplace in today's machine
l...
Consequential decision-making typically incentivizes individuals to beha...
We prove stable recurrent neural networks are well approximated by
feed-...
We present Deep Voice 3, a fully-convolutional attention-based neural
te...
We present Deep Voice 3, a fully-convolutional attention-based neural
te...
Rapid progress has been made towards question answering (QA) systems tha...
We introduce a technique for augmenting neural text-to-speech (TTS) with...
We present Deep Voice, a production-quality text-to-speech system constr...
Path queries on a knowledge graph can be used to answer compositional
qu...