Generalization to out-of-distribution (OOD) data is a capability natural to humans yet
challenging for machines to reproduce. This is because most learning algorithms strongly …

This is a comprehensive, critical, and pedagogical review of volumetric emission
tomography for combustion processes. Many flames that are of interest to scientists and …

Algorithmic reasoning requires capabilities which are most naturally understood through
recurrent models of computation, like the Turing machine. However, Transformer models …

We find that across a wide range of robot policy learning scenarios, treating supervised
policy learning with an implicit model generally performs better, on average, than commonly …

Large-scale pre-trained models (PTMs) such as BERT and GPT have recently achieved
great success and become a milestone in the field of artificial intelligence (AI). Owing to …

Graph representation learning has shown effectiveness when testing and training graph
data come from the same distribution, but most existing approaches fail to generalize under …

Fine-tuning pretrained language models (LMs) without making any architectural changes
has become a norm for learning various language downstream tasks. However, for non …

Though convolutional neural networks (CNNs) have demonstrated remarkable ability in
learning discriminative features, they often generalize poorly to unseen domains. Domain …

Deep supervised learning has achieved great success in the last decade. However, its
defects of heavy dependence on manual labels and vulnerability to attacks have driven …

Combinatorial optimization is a well-established area in operations research and computer
science. Until recently, its methods have focused on solving problem instances in isolation …