While large language models (LLMs) have demonstrated impressive capabilities across
tasks in language understanding and interactive decision making, their abilities for …

Reasoning is a fundamental aspect of human intelligence that plays a crucial role in
activities such as problem solving, decision making, and critical thinking. In recent years …

Large language models can encode a wealth of semantic knowledge about the world. Such
knowledge could be extremely useful to robots aiming to act upon high-level, temporally …

Recent advances in large language models (LLMs) have transformed the field of natural
language processing (NLP). From GPT-3 to PaLM, the state-of-the-art performance on …

In coming decades, artificial general intelligence (AGI) may surpass human capabilities at
many critical tasks. We argue that, without substantial effort to prevent it, AGIs could learn to …

In recent years, much progress has been made in learning robotic manipulation policies that
follow natural language instructions. Such methods typically learn from corpora of robot …

We study few-shot prompting of pretrained large language models (LLMs) towards solving
PDDL planning problems. We are interested in two questions:(1) To what extent can LLMs …

We present a retrospective on the state of Embodied AI research. Our analysis focuses on
13 challenges presented at the Embodied AI Workshop at CVPR. These challenges are …

Despite widespread use of LLMs as conversational agents, evaluations of performance fail
to capture a crucial aspect of communication: interpreting language in context--incorporating …

Large pre-trained models exhibit distinct and complementary capabilities dependent on the
data they are trained on. Language models such as GPT-3 are capable of textual reasoning …