For a long time, researchers have sought artificial intelligence (AI) that matches or exceeds
human intelligence. AI agents, which are artificial entities capable of sensing the …

This article surveys and organizes research works in a new paradigm in natural language
processing, which we dub “prompt-based learning.” Unlike traditional supervised learning …

Language is essentially a complex, intricate system of human expressions governed by
grammatical rules. It poses a significant challenge to develop capable AI algorithms for …

Building models that can be rapidly adapted to novel tasks using only a handful of annotated
examples is an open challenge for multimodal machine learning research. We introduce …

AI is undergoing a paradigm shift with the rise of models (eg, BERT, DALL-E, GPT-3) that are
trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …

To cope with real-world dynamics, an intelligent system needs to incrementally acquire,
update, accumulate, and exploit knowledge throughout its lifetime. This ability, known as …

It has become common to publish large (billion parameter) language models that have been
trained on private datasets. This paper demonstrates that in such settings, an adversary can …

Incrementally learning new information from a non-stationary stream of data, referred to as
'continual learning', is a key feature of natural intelligence, but a challenging problem for …

The mainstream paradigm behind continual learning has been to adapt the model
parameters to non-stationary data distributions, where catastrophic forgetting is the central …

Test-time domain adaptation aims to adapt a source pre-trained model to a target domain
without using any source data. Existing works mainly consider the case where the target …