Large language models have led to state-of-the-art accuracies across several tasks.
However, training these models efficiently is challenging because: a) GPU memory capacity …

Recent work argues that robust training requires substantially larger datasets than those
required for standard classification. On CIFAR-10 and CIFAR-100, this translates into a …

Here we present a machine learning framework and model implementation that can learn to
simulate a wide variety of challenging physical domains, involving fluids, rigid solids, and …

Traditionally multi-object tracking and object detection are performed using separate
systems with most prior works focusing exclusively on one of these aspects over the other …

Artificial intelligence (AI) and 5G system have been two hot technical areas that are
changing the world. On the deep convergence of computing and communication, networking …

In static monitoring cameras, useful contextual information can stretch far beyond the few
seconds typical video understanding models might see: subjects may exhibit similar …

Data augmentation has been widely adopted for object detection in 3D point clouds.
However, all previous related efforts have focused on manually designing specific data …

Over the past decade, the dominance of deep learning has prevailed across various
domains of artificial intelligence, including natural language processing, computer vision …

Recently the LARS and LAMB optimizers have been proposed for training neural networks
faster using large batch sizes. LARS and LAMB add layer-wise normalization to the update …

Kronecker-factored Approximate Curvature (K-FAC) has recently been shown to converge
faster in deep neural network (DNN) training than stochastic gradient descent (SGD); …