Artificial General Intelligence (AGI) 1 is an important and sometimes controversial concept in
computing research, used to describe an AI system that is at least as capable as a human at …

We propose a framework for classifying the capabilities and behavior of Artificial General
Intelligence (AGI) models and their precursors. This framework introduces levels of AGI …

What spatial frequency information do humans and neural networks use to recognize
objects? In neuroscience, critical band masking is an established tool that can reveal the …

This paper revisits the simple, long-studied, yet still unsolved problem of making image
classifiers robust to imperceptible perturbations. Taking CIFAR10 as an example, SOTA …

This paper develops an in-depth treatment concerning the problem of approximating the
Gaussian smoothing and the Gaussian derivative computations in scale-space theory for …

The vulnerability of deep neural networks to adversarial perturbations has been widely
perceived in the computer vision community. From a security perspective, it poses a critical …

As AI systems become increasingly powerful, the need for safe AI has become more
pressing. Humans are an attractive model for AI safety: as the only known agents capable of …

The rapid proliferation of large language models (LLMs) invites the possibility of a new
marketplace for behavioral and psychological data that signals intent. This brief article …

Deep neural networks, trained on large amounts of data, have become a highly successful
tool for a variety of cognitive tasks. In many of those, they exceed human performance in …

Traditionally, adversarial examples have been defined as imperceptible perturbations that
fool deep neural networks. This thesis challenges this view by examining unrestricted …