As artificial intelligence (AI) transitions from research to deployment, creating the appropriate
datasets and data pipelines to develop and evaluate AI models is increasingly the biggest …

High-entropy alloys (HEAs) have attracted extensive interest due to their exceptional
mechanical properties and the vast compositional space for new HEAs. However …

Abstract We introduce the Segment Anything (SA) project: a new task, model, and dataset for
image segmentation. Using our efficient model in a data collection loop, we built the largest …

Multimodal datasets are a critical component in recent breakthroughs such as CLIP, Stable
Diffusion and GPT-4, yet their design does not receive the same research attention as model …

Widely observed neural scaling laws, in which error falls off as a power of the training set
size, model size, or both, have driven substantial performance improvements in deep …

Vision transformers (ViT) have demonstrated impressive performance across numerous
machine vision tasks. These models are based on multi-head self-attention mechanisms that …

The hidden costs of artificial intelligence, from natural resources and labor to privacy and
freedom What happens when artificial intelligence saturates political life and depletes the …

We have now entered the era of trillion parameter machine learning models trained on
billion-sized datasets scraped from the internet. The rise of these gargantuan datasets has …

Data is the driving force of machine learning, with the amount and quality of training data
often being more important for the performance of a system than architecture and training …

Abstract Domain generalization (DG) methods aim to achieve generalizability to an unseen
target domain by using only training data from the source domains. Although a variety of DG …