Picture for Kaishun Wu

Kaishun Wu

DSA and IoT, Hong Kong University of Science and Technology, Guangzhou

Efficient Mixture-of-Expert for Video-based Driver State and Physiological Multi-task Estimation in Conditional Autonomous Driving

Add code
Oct 28, 2024
Viaarxiv icon

Enhancing Inertial Hand based HAR through Joint Representation of Language, Pose and Synthetic IMUs

Add code
Jun 03, 2024
Viaarxiv icon

PhysMLE: Generalizable and Priors-Inclusive Multi-task Remote Physiological Measurement

Add code
May 10, 2024
Viaarxiv icon

CODA: A COst-efficient Test-time Domain Adaptation Mechanism for HAR

Add code
Mar 22, 2024
Viaarxiv icon

Advancing Generalizable Remote Physiological Measurement through the Integration of Explicit and Implicit Prior Knowledge

Add code
Mar 11, 2024
Viaarxiv icon

On Designing Multi-UAV aided Wireless Powered Dynamic Communication via Hierarchical Deep Reinforcement Learning

Add code
Dec 13, 2023
Figure 1 for On Designing Multi-UAV aided Wireless Powered Dynamic Communication via Hierarchical Deep Reinforcement Learning
Figure 2 for On Designing Multi-UAV aided Wireless Powered Dynamic Communication via Hierarchical Deep Reinforcement Learning
Figure 3 for On Designing Multi-UAV aided Wireless Powered Dynamic Communication via Hierarchical Deep Reinforcement Learning
Figure 4 for On Designing Multi-UAV aided Wireless Powered Dynamic Communication via Hierarchical Deep Reinforcement Learning
Viaarxiv icon

Self-Convinced Prompting: Few-Shot Question Answering with Repeated Introspection

Add code
Oct 10, 2023
Viaarxiv icon

Task-Oriented Integrated Sensing, Computation and Communication for Wireless Edge AI

Add code
Jun 11, 2023
Viaarxiv icon

MMLN: Leveraging Domain Knowledge for Multimodal Diagnosis

Add code
Feb 09, 2022
Figure 1 for MMLN: Leveraging Domain Knowledge for Multimodal Diagnosis
Figure 2 for MMLN: Leveraging Domain Knowledge for Multimodal Diagnosis
Figure 3 for MMLN: Leveraging Domain Knowledge for Multimodal Diagnosis
Figure 4 for MMLN: Leveraging Domain Knowledge for Multimodal Diagnosis
Viaarxiv icon

Faster and Safer Training by Embedding High-Level Knowledge into Deep Reinforcement Learning

Add code
Oct 22, 2019
Figure 1 for Faster and Safer Training by Embedding High-Level Knowledge into Deep Reinforcement Learning
Figure 2 for Faster and Safer Training by Embedding High-Level Knowledge into Deep Reinforcement Learning
Figure 3 for Faster and Safer Training by Embedding High-Level Knowledge into Deep Reinforcement Learning
Figure 4 for Faster and Safer Training by Embedding High-Level Knowledge into Deep Reinforcement Learning
Viaarxiv icon