Diffusion models have emerged as a powerful new family of deep generative models with
record-breaking performance in many applications, including image synthesis, video …

Since the onset of the COVID-19 pandemic, there has been a growing interest in studying
epidemiological models. Traditional mechanistic models mathematically describe the …

Node features of graph neural networks (GNNs) tend to become more similar with the
increase of the network depth. This effect is known as over-smoothing, which we …

Position encoding has recently been shown to be effective in transformer architecture. It
enables valuable supervision for dependency modeling between elements at different …

The conjoining of dynamical systems and deep learning has become a topic of great
interest. In particular, neural differential equations (NDEs) demonstrate that neural networks …

Autonomous driving systems have witnessed significant development during the past years
thanks to the advance in machine learning-enabled sensing and decision-making …

Abstract We propose Graph-Coupled Oscillator Networks (GraphCON), a novel framework
for deep learning on graphs. It is based on discretizations of a second-order system of …

Continuous-time dynamic graphs naturally abstract many real-world systems, such as social
and transactional networks. While the research on continuous-time dynamic graph …

Partial differential equations (PDEs) are commonly derived based on empirical
observations. However, recent advances of technology enable us to collect and store …

Fueled by the availability of more data and computing power, recent breakthroughs in cloud-
based machine learning (ML) have transformed every aspect of our lives from face …