Vision and language are the two foundational senses for humans, and they build up our
cognitive ability and intelligence. While significant breakthroughs have been made in AI …

We introduce new methods for 1) accelerating and 2) stabilizing training for large language-
vision models. 1) For acceleration, we introduce SwitchBack, a linear layer for int8 quantized …

Foundation models are rapidly being developed for computational pathology applications.
However, it remains an open question which factors are most important for downstream …

In previous literature, backward error analysis was used to find ordinary differential
equations (ODEs) approximating the gradient descent trajectory. It was found that finite step …

Large Language Models (LLMs) have become ubiquitous across various domains,
transforming the way we interact with information and conduct research. However, most high …

In recent years, advances in the large-scale pretraining of language and text-to-image
models have revolutionized the field of machine learning. Yet, integrating these two …

Artificial intelligence and machine learning have shown great promise in their ability to
accelerate novel materials discovery. As researchers and domain scientists seek to unify …

SGD performs worse than Adam by a significant margin on Transformers, but the reason
remains unclear. In this work, we provide an explanation of SGD's failure on Transformers …

Most advanced unsupervised anomaly detection (UAD) methods rely on modeling feature
representations of frozen encoder networks pre-trained on large-scale datasets, eg …

The number of parameters in large transformers has been observed to grow exponentially.
Despite notable performance improvements, concerns have been raised that such a …