Background & Aims The association between sarcopenia and prognosis in patients with
cirrhosis remains to be determined. In this study, we aimed to quantify the association between …

Deep learning on graphs has attracted significant interests recently. However, most of the
works have focused on (semi-) supervised learning, resulting in shortcomings including heavy …

We examine the effect of chief executive officer (CEO) compensation incentives on corporate
cash holdings and the value of cash to better understand how compensation incentives …

Agility and trajectory control are two desirable features for robotics, but they become very
challenging for soft robots without rigid structures to support rapid manipulations. Here, a …

Pretrained Foundation Models (PFMs) are regarded as the foundation for various downstream
tasks with different data modalities. A PFM (eg, BERT, ChatGPT, and GPT-4) is trained on …

Recently, ChatGPT, along with DALL-E-2 and Codex,has been gaining significant attention
from society. As a result, many individuals have become interested in related resources and …

In this paper, we present a conceptually simple while empirically powerful framework for
abstractive summarization, SimCLS, which can bridge the gap between the learning objective …

Abstractive summarization models are commonly trained using maximum likelihood estimation,
which assumes a deterministic (one-point) target distribution in which an ideal model will …

Recent years have witnessed fast developments of graph neural networks (GNNs) that have
benefited myriads of graph analytic tasks and applications. In general, most GNNs depend …

… (Yixin Liu and … Yixin Liu and Shirui Pan are with the Department of Data Science and AI,
Faculty of … Yixin Liu received the BS and MS degrees from Beihang University, Beijing, China, …