Starting from the resurgence of deep learning, vision-language models (V...
Reasoning is a cognitive process of using evidence to reach a sound
conc...
This paper offers a new perspective to ease the challenge of domain
gene...
Graph Neural Networks (GNNs) have achieved state-of-the-art performance ...
Images taken under the low-light condition often contain blur and satura...
Instruction tuning has significantly advanced large language models (LLM...
Oversmoothing is a common phenomenon in graph neural networks (GNNs), in...
While contrastive self-supervised learning has become the de-facto learn...
We uncover a systematic bias in the evaluation paradigm of adopting larg...
The rapid development of digital economy has led to the emergence of var...
Traffic simulation is a crucial tool for transportation decision-making ...
Efficient traffic management is crucial for maintaining urban mobility,
...
In this note, we consider the problem of robust learning mixtures of lin...
Anomaly detection aims to distinguish abnormal instances that deviate
si...
Generating persona consistent dialogue response is important for develop...
While multilingual neural machine translation has achieved great success...
The prevalence of large-scale graphs poses great challenges in time and
...
Multi-task learning for various real-world applications usually involves...
Halftoning aims to reproduce a continuous-tone image with pixels whose
i...
Stereo image super-resolution aims to improve the quality of high-resolu...
Uncertainty propagation across different domains is of fundamental impor...
The main challenge in domain generalization (DG) is to handle the
distri...
In this work, we study how the generalization performance of a given
dir...
Federated Recommender Systems (FedRecs) are considered privacy-preservin...
Research on debiased recommendation has shown promising results. However...
Click-through prediction (CTR) models transform features into latent vec...
Semantic segmentation has recently achieved notable advances by exploiti...
The virtual machine consolidation problem (VMCP) attempts to determine w...
Recent studies demonstrate that Graph Neural Networks (GNNs) are vulnera...
Graph Neural Networks (GNNs) as deep learning models working on
graph-st...
Training a large-scale deep neural network in a large-scale dataset is
c...
A coupled hybridizable discontinuous Galerkin (HDG) and boundary integra...
In this paper, we provide a detailed description of our system at CAMRP-...
Recent years have seen a surge in research on dynamic graph representati...
We present masked graph autoencoder (MaskGAE), a self-supervised learnin...
Deep graph learning has achieved remarkable progresses in both business ...
Graph Convolutional Networks (GCNs) achieve an impressive performance du...
In recent years, the rise of deep learning and automation requirements i...
Graph contrastive learning (GCL), as a popular approach to graph
self-su...
Recently, graph convolutional networks (GCNs) have shown to be vulnerabl...
Recently, deep learning has been successfully applied to the single-imag...
As Abstract Meaning Representation (AMR) implicitly involves compound
se...
Recent studies in deepfake detection have yielded promising results when...
Recent segmentation methods, such as OCR and CPNet, utilizing "class lev...
Label smoothing and vocabulary sharing are two widely used techniques in...
Recent evolution in deep learning has proven its value for CT-based lung...
Machine learning, especially deep learning is gaining much attention due...
Deep graph learning (DGL) has achieved remarkable progress in both busin...
In the real world, the degradation of images taken under haze can be qui...
Abstract Meaning Representation (AMR) parsing translates sentences to th...