Impressive performance on point cloud semantic segmentation has been ach...
We consider the sampling problem from a composite distribution whose
pot...
Textual adversarial attacks can discover models' weaknesses by adding
se...
Attention-based vision models, such as Vision Transformer (ViT) and its
...
Light field salient object detection (SOD) is an emerging research direc...
The knowledge distillation uses a high-performance teacher network to gu...
Federated learning (FL) is a collaborative learning paradigm for
decentr...
To defend the inference attacks and mitigate the sensitive information
l...
We propose a sampling algorithm that achieves superior complexity bounds...
To mitigate the privacy leakages and communication burdens of Federated
...
Offline safe RL is of great practical relevance for deploying agents in
...
Low-rank compression is an important model compression strategy for obta...
The recently proposed Vision transformers (ViTs) have shown very impress...
Graph neural networks (GNNs) are a class of effective deep learning mode...
Safety comes first in many real-world applications involving autonomous
...
Long short-term memory (LSTM) is a type of powerful deep neural network ...
Tucker decomposition is one of the SOTA CNN model compression techniques...
Despite of the superb performance on a wide range of tasks, pre-trained
...
Text editing, such as grammatical error correction, arises naturally fro...
Recent works have revealed that Transformers are implicitly learning the...
Visual reinforcement learning (RL), which makes decisions directly from
...
A key challenge of continual reinforcement learning (CRL) in dynamic
env...
Neural network (NN)-based methods have emerged as an attractive approach...
As the number of devices connected to the Internet of Things (IoT) incre...
We study the problem of sampling from a target distribution in ℝ^d
whose...
Safe reinforcement learning (RL) has achieved significant success on
ris...
Safe reinforcement learning aims to learn the optimal policy while satis...
Unsupervised domain adaptation (UDA) aims to enhance the generalization
...
One of the key challenges in visual Reinforcement Learning (RL) is to le...
Named entity recognition (NER) is an essential task in natural language
...
The dynamic job-shop scheduling problem (DJSP) is a class of scheduling ...
The integration of Reinforcement Learning (RL) and Evolutionary Algorith...
Researchers are increasingly focusing on intelligent games as a hot rese...
The powerful learning ability of deep neural networks enables reinforcem...
Advanced tensor decomposition, such as Tensor train (TT) and Tensor ring...
Offline reinforcement learning (RL) tries to learn the near-optimal poli...
With the development of Edge Computing and Artificial Intelligence (AI)
...
Multi-view clustering is an important yet challenging task in machine
le...
Data-driven dynamic models of cell biology can be used to predict cell
r...
Noise injection-based regularization, such as Dropout, has been widely u...
Recently deep neural networks have been successfully applied in channel
...
In recent studies, Lots of work has been done to solve time series anoma...
Unsupervised domain adaptation (UDA) aims to train a target classifier w...
MOBA games, e.g., Honor of Kings, League of Legends, and Dota 2, pose gr...
We present JueWu-SL, the first supervised-learning-based artificial
inte...
In unsupervised domain adaptation (UDA), a classifier for the target dom...
In unsupervised domain adaptation (UDA), classifiers for the target doma...
Type 2 diabetes (T2DM), one of the most prevalent chronic diseases, affe...
In the unsupervised open set domain adaptation (UOSDA), the target domai...
Recently, the vulnerability of DNN-based audio systems to adversarial at...