AI alignment aims to make AI systems behave in line with human intentions and values. As
AI systems grow more capable, so do risks from misalignment. To provide a comprehensive …

Transformers, originally devised for natural language processing (NLP), have also produced
significant successes in computer vision (CV). Due to their strong expression power …

Large language models (LLMs) are shown to possess a wealth of actionable knowledge that
can be extracted for robot manipulation in the form of reasoning and planning. Despite the …

With the emergence of Large Language Models (LLMs) and Vision Foundation Models
(VFMs), multimodal AI systems benefiting from large models have the potential to equally …

Reinforcement learning from human feedback (RLHF) is a technique for training AI systems
to align with human goals. RLHF has emerged as the central method used to finetune state …

This paper presents an experimental study regarding the use of OpenAI's ChatGPT for
robotics applications. We outline a strategy that combines design principles for prompt …

Large language models (LLMs) have demonstrated exciting progress in acquiring diverse
new capabilities through in-context learning, ranging from logical reasoning to code-writing …

Large language models (LLMs) trained on code-completion have been shown to be capable
of synthesizing simple Python programs from docstrings [1]. We find that these code-writing …

Transformer-based large language models (LLMs) provide a powerful foundation for natural
language tasks in large-scale customer-facing applications. However, studies that explore …

Existing learning-based autonomous driving (AD) systems face challenges in
comprehending high-level information, generalizing to rare events, and providing …