Adult semantic memory has been traditionally conceptualized as a relatively static memory
system that consists of knowledge about the world, concepts, and symbols. Considerable …

We give an overview of recent exciting achievements of deep reinforcement learning (RL).
We discuss six core elements, six important mechanisms, and twelve applications. We start …

Language models demonstrate both quantitative improvement and new qualitative
capabilities with increasing scale. Despite their potentially transformative impact, these new …

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 …

Large language models (LMs) offer unprecedented language generation capabilities and
exciting opportunities for interaction design. However, their highly context-dependent …

Recent efforts have incorporated large language models (LLMs) with external resources (eg,
the Internet) or internal control flows (eg, prompt chaining) for tasks requiring grounding or …

For sophisticated reinforcement learning (RL) systems to interact usefully with real-world
environments, we need to communicate complex goals to these systems. In this work, we …

We study the problem of learning a range of vision-based manipulation tasks from a large
offline dataset of robot interaction. In order to accomplish this, humans need easy and …

We present a new AI task--Embodied Question Answering (EmbodiedQA)--where an agent
is spawned at a random location in a 3D environment and asked a question (" What color is …

Large LMs such as GPT-3 are powerful, but can commit mistakes that are obvious to
humans. For example, GPT-3 would mistakenly interpret" What word is similar to good?" to …