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 …

Understanding the structure of real data is paramount in advancing modern deep-learning
methodologies. Natural data such as images are believed to be composed of features …

Fine-tuning large pre-trained models has become the de facto strategy for developing both
task-specific and general-purpose machine learning systems, including developing models …

Abstract Text-to-image (T2I) diffusion models notably the unCLIP models (eg DALL-E-2)
achieve state-of-the-art (SOTA) performance on various compositional T2I benchmarks at …

As training datasets become increasingly drawn from unstructured, uncontrolled
environments such as the web, researchers and industry practitioners have increasingly …

Transformers trained on huge text corpora exhibit a remarkable set of capabilities, eg,
performing simple logical operations. Given the inherent compositional nature of language …

We obtain the first analytic, interpretable and predictive theory of creativity in convolutional
diffusion models. Indeed, score-based diffusion models can generate highly creative images …

Diverse studies in systems neuroscience begin with extended periods of training known as'
shaping'procedures. These involve progressively studying component parts of more …

The literature on text-to-image generation is plagued by issues of faithfully composing
entities with relations. But there lacks a formal understanding of how entity-relation …

Transformers have shown impressive capabilities across various tasks, but their
performance on compositional problems remains a topic of debate. In this work, we …