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 …

Convolutional neural networks (CNNs) were inspired by early findings in the study of
biological vision. They have since become successful tools in computer vision and state-of …

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 …

Test-time training adapts to a new test distribution on the fly by optimizing a model for each
test input using self-supervision. In this paper, we use masked autoencoders for this one …

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 …

Abstract Machine-learning models for medical tasks can match or surpass the performance
of clinical experts. However, in settings differing from those of the training dataset, the …

Large pre-trained models such as CLIP or ALIGN offer consistent accuracy across a range of
data distributions when performing zero-shot inference (ie, without fine-tuning on a specific …

Abstract 3D object detection is an important task in autonomous driving to perceive the
surroundings. Despite the excellent performance, the existing 3D detectors lack the …

Although current deep learning-based face forgery detectors achieve impressive
performance in constrained scenarios, they are vulnerable to samples created by unseen …

A model must adapt itself to generalize to new and different data during testing. In this
setting of fully test-time adaptation the model has only the test data and its own parameters …