Following unprecedented success on the natural language tasks, Transformers have been
successfully applied to several computer vision problems, achieving state-of-the-art results …

Deep neural networks have been well-known for their superb handling of various machine
learning and artificial intelligence tasks. However, due to their over-parameterized black-box …

The scaling of Transformers has driven breakthrough capabilities for language models. At
present, the largest large language models (LLMs) contain upwards of 100B parameters …

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 …

Neural network classifiers can largely rely on simple spurious features, such as
backgrounds, to make predictions. However, even in these cases, we show that they still …

The ubiquitous and demonstrably suboptimal choice of resizing images to a fixed resolution
before processing them with computer vision models has not yet been successfully …

Artificial neural networks (ANNs) inspired by biology are beginning to be widely used to
model behavioural and neural data, an approach we call 'neuroconnectionism'. ANNs have …

Deep neural networks (DNNs) have had extraordinary successes in classifying
photographic images of objects and are often described as the best models of biological …

Biological and artificial information processing systems form representations that they can
use to categorize, reason, plan, navigate, and make decisions. How can we measure the …

Recently, Miller et al. showed that a model's in-distribution (ID) accuracy has a strong linear
correlation with its out-of-distribution (OOD) accuracy, on several OOD benchmarks, a …