Rapidly increasing quality of AI-generated content makes it difficult to distinguish between
human and AI-generated texts, which may lead to undesirable consequences for society …

Diffusion models recently have been successfully applied for the visual synthesis of
strikingly realistic appearing images. This raises strong concerns about their potential for …

Disobeying the classical wisdom of statistical learning theory, modern deep neural networks
generalize well even though they typically contain millions of parameters. Recently, it has …

Low-dose computed tomography (LDCT) scans, which can effectively alleviate the radiation
problem, will degrade the imaging quality. In this paper, we propose a novel LDCT …

Geometric descriptions of deep neural networks (DNNs) have the potential to uncover core
representational principles of computational models in neuroscience. Here we examined the …

Why can pre-trained language models (PLMs) learn universal representations and
effectively adapt to broad NLP tasks differing a lot superficially? In this work, we empirically …

Objective: Graphical deep learning models provide a desirable way for brain functional
connectivity analysis. However, the application of current graph deep learning models to …

Understanding generalization in deep learning has been one of the major challenges in
statistical learning theory over the last decade. While recent work has illustrated that the …

Deep neural networks have been demonstrated to achieve phenomenal success in many
domains, and yet their inner mechanisms are not well understood. In this paper, we …

A ReLU neural network leads to a finite polyhedral decomposition of input space and a
corresponding finite dual graph. We show that while this dual graph is a coarse quantization …