Psychologists and neuroscientists extensively rely on computational models for studying
and analyzing the human mind. Traditionally, such computational models have been hand …

We survey applications of pretrained foundation models in robotics. Traditional deep
learning models in robotics are trained on small datasets tailored for specific tasks, which …

This work identifies 18 foundational challenges in assuring the alignment and safety of large
language models (LLMs). These challenges are organized into three different categories …

Large transformer models trained on diverse datasets have shown a remarkable ability to
learn in-context, achieving high few-shot performance on tasks they were not explicitly …

We introduce a value-based RL agent, which we call BBF, that achieves super-human
performance in the Atari 100K benchmark. BBF relies on scaling the neural networks used …

Research in Fairness, Accountability, Transparency, and Ethics (FATE) 1 has established
many sources and forms of algorithmic harm, in domains as diverse as health care, finance …

A growing body of evidence suggests that neural networks employed in deep reinforcement
learning (RL) gradually lose their plasticity, the ability to learn from new data; however, the …

Large transformer models powered by diverse data and model scale have dominated
natural language modeling and computer vision and pushed the frontier of multiple AI areas …

Transformer has been considered the dominating neural architecture in NLP and CV, mostly
under supervised settings. Recently, a similar surge of using Transformers has appeared in …

Transformer models exhibit in-context learning: the ability to accurately predict the response
to a novel query based on illustrative examples in the input sequence, which contrasts with …