Graph representation learning aims to effectively encode high-dimensional sparse graph-
structured data into low-dimensional dense vectors, which is a fundamental task that has …

In the meantime, a wide variety of terminologies, motivations, approaches, and evaluation
criteria have been developed within the research field of explainable artificial intelligence …

Through considerable effort and intuition, several recent works have reverse-engineered
nontrivial behaviors oftransformer models. This paper systematizes the mechanistic …

The past decade has seen significant progress in artificial intelligence (AI), which has
resulted in algorithms being adopted for resolving a variety of problems. However, this …

Abstract Concept Bottleneck Models (CBM) are inherently interpretable models that factor
model decisions into human-readable concepts. They allow people to easily understand …

Single-cell transcriptomics has broadened our understanding of cellular diversity and gene
expression dynamics in healthy and diseased tissues. Recently, spatial transcriptomics has …

Multimodal medical data fusion has emerged as a transformative approach in smart
healthcare, enabling a comprehensive understanding of patient health and personalized …

Abstract Artificial Neural Networks (ANNs) were firstly used to model ocean engineering
problems in the decade of 1990s. Since then, this soft-modelling technique has proved …

The continuous advancement of Artificial Intelligence (AI) has been revolutionizing the
strategy of decision-making in different life domains. Regardless of this achievement, AI …

Content and style (CS) disentanglement is a fundamental problem and critical challenge of
style transfer. Existing approaches based on explicit definitions (eg, Gram matrix) or implicit …