Sequential models, such as Recurrent Neural Networks and Neural Ordinary...
Trajectory generation and trajectory prediction are two critical tasks f...
Polymer simulation with both accuracy and efficiency is a challenging ta...
Human emotion understanding is pivotal in making conversational technolo...
Recently significant progress has been made in vehicle prediction and
pl...
Graph Neural Networks (GNNs) have shown remarkable performance on
graph-...
Multi-agent applications have recently gained significant popularity. In...
A real-world text corpus sometimes comprises not only text documents but...
Robot-based assembly in construction has emerged as a promising solution...
Multi-agent patrolling is a key problem in a variety of domains such as
...
Neural networks (NNs) playing the role of controllers have demonstrated
...
To model the indeterminacy of human behaviors, stochastic trajectory
pre...
Predicting the future trajectories of surrounding vehicles based on thei...
When the traffic stream is extremely congested and surrounding vehicles ...
Due to the exponential growth of scientific publications on the Web, the...
Connectivity technology has shown great potentials in improving the safe...
In real-world applications, deep learning models often run in non-statio...
Diverse data formats and ontologies of task-oriented dialogue (TOD) data...
This paper studies the problem of stochastic continuum-armed bandit with...
Existing graph contrastive learning (GCL) typically requires two forward...
Data augmentation has been widely used to improve generalization in trai...
Modern Building Automation Systems (BASs), as the brain that enables the...
It is quite challenging to ensure the safety of reinforcement learning (...
With the increment of interest in leveraging machine learning technology...
Low-light image enhancement is an inherently subjective process whose ta...
Deep learning-based source dehazing methods trained on synthetic dataset...
Predicting the trajectories of surrounding objects is a critical task in...
We study node representation learning on heterogeneous text-rich network...
Graph contrastive learning (GCL) is the most representative and prevalen...
The robustness of deep neural networks has received significant interest...
Researches have been devoted to making connected and automated vehicles
...
Federated learning (FL) has attracted growing attention via data-private...
Trajectory generation and prediction are two interwoven tasks that play
...
In model-based reinforcement learning for safety-critical control system...
Neural networks have shown great promises in planning, control, and gene...
Neural network based planners have shown great promises in improving
per...
There has been a recent surge of interest in designing Graph Neural Netw...
Building loads consume roughly 40
countries, a significant part of which...
As people spend up to 87
Ventilation, and Air Conditioning (HVAC) system...
We propose POLAR, a polynomial arithmetic framework that
leverages polyn...
As Artificial Intelligence as a Service gains popularity, protecting
wel...
Vision-and-Language (VL) pre-training has shown great potential on many
...
The infrastructure-vehicle cooperative autonomous driving approach depen...
In the development of advanced driver-assistance systems (ADAS) and
auto...
While connected vehicle (CV) applications have the potential to revoluti...
Data quantity and quality are crucial factors for data-driven learning
m...
Texts appearing in daily scenes that can be recognized by OCR (Optical
C...
This paper introduces the Ninth Dialog System Technology Challenge (DSTC...
Graph neural networks (GNNs) have been shown with superior performance i...
Federated learning (FL) is a promising approach for training decentraliz...