University of Washington

Who would disagree that, if all people are mortal and Socrates is a person, Socrates must be mortal? GPT-3, for one. Recent work shows that bigger language models are not necessarily better when it comes to logical reasoning.

A CLIP model whose weights were the mean of an ensemble of fine-tuned models performed as well as the ensemble and better than its best-performing constituent.

Researchers discovered a new way to reduce memory requirements when training large machine learning models. Tim Dettmers and colleagues at University of Washington released 8-bit optimizers that store gradient statistics as 8-bit values, while maintaining the same accuracy.

To understand a movie scene, viewers often must remember or infer previous events and extrapolate potential consequences. New work improved a model’s ability to do the same.

Models that interpret the interplay of words and images tend to be trained on richer bodies of text than images. Recent research worked toward giving such models a more balanced knowledge of the two domains.

In 2020, I hope the AI community will grapple with issues of fairness in ways that tangibly and directly benefit disadvantaged populations.

One of the largest open datasets for training face recognition systems has its roots in a popular photo-sharing service. Companies that have used this data could find themselves liable for millions in legal recompense.

Less than a month after XLNet overtook BERT, the pole position in natural language understanding changed hands again. RoBERTa is an improved BERT pretraining recipe that beats its forbear, becoming the new state-of-the-art language model — for the moment.