Deep learning approaches to anomaly detection (AD) have recently improved the state of
the art in detection performance on complex data sets, such as large collections of images or …

Deep learning has triggered the current rise of artificial intelligence and is the workhorse of
today's machine intelligence. Numerous success stories have rapidly spread all over …

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

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 …

Inspired by progress in large-scale language modeling, we apply a similar approach
towards building a single generalist agent beyond the realm of text outputs. The agent …

Abstract Out-of-distribution (OOD) detection is critical to ensuring the reliability and safety of
machine learning systems. For instance, in autonomous driving, we would like the driving …

Reinforcement learning from human feedback (RLHF) is an effective technique for aligning
large language models (LLMs) to human preferences, but gathering high-quality human …

Language Models (LMs) often cannot be deployed because of their potential to harm users
in hard-to-predict ways. Prior work identifies harmful behaviors before deployment by using …

AI models are increasingly applied in high-stakes domains like health and conservation.
Data quality carries an elevated significance in high-stakes AI due to its heightened …

Abstract Trustworthy Artificial Intelligence (AI) is based on seven technical requirements
sustained over three main pillars that should be met throughout the system's entire life cycle …