AI alignment aims to make AI systems behave in line with human intentions and values. As
AI systems grow more capable, so do risks from misalignment. To provide a comprehensive …

Domain-specific hardware is becoming a promising topic in the backdrop of improvement
slow down for general-purpose processors due to the foreseeable end of Moore's Law …

Driven by improved architectures and better representation learning frameworks, the field of
visual recognition has enjoyed rapid modernization and performance boost in the early …

Abstract Out-of-distribution (OOD) detection has received much attention lately due to its
practical importance in enhancing the safe deployment of neural networks. One of the …

The emerging paradigm of federated learning (FL) strives to enable collaborative training of
deep models on the network edge without centrally aggregating raw data and hence …

Deep neural networks excel at finding hierarchical representations that solve complex tasks
over large datasets. How can we humans understand these learned representations? In this …

In response to recent criticism of gradient-based visualization techniques, we propose a new
methodology to generate visual explanations for deep Convolutional Neural Networks …

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 …

Many important transition points in the history of science have been moments when science
“zoomed in.” At these points, we develop a visualization or tool that allows us to see the …

With the recent wave of progress in artificial intelligence (AI) has come a growing awareness
of the large-scale impacts of AI systems, and recognition that existing regulations and norms …