Geng’s research focuses on distributed sensing, learning, and decision-making, with an emphasis on dependency analysis and multimodal fusion in environments with limited communication bandwidth and power. His work also includes collaborative and interpretable human-AI decision-making to enhance shared situational awareness in high-stakes fields like healthcare.

Oubre’s research applies AI techniques to 1) extract information from time-series sensor data and 2) model human motion and behavior. His expertise lies in the application of these techniques to identify subtle disease signs, better assess disease progression and therapeutic efficacy, and develop ecologically valid assessments of natural behavior.

Zhang works in the broad areas of knowledge learning from images/ video/ audio and multimodal data fusion, multimedia security and forensics, geoinformatics (aerial and Lidar image analysis), and applied biomedical informatics. Her research has a wide spectrum of applications in biomedical image/ video/ language machine learning, intelligent video surveillance, image spam and paper-ballot fraud detection, and multi-modal fusion leveraging foundational large models.

Son’s research focuses on developing advanced neural network architectures, such as Graph Neural Networks and Equivariant Neural Networks, to accurately model molecular interactions while preserving symmetries like permutation, rotation, and translation invariance. By integrating Generative AI and Multimodal Protein Representation Learning, his work enables efficient drug discovery and repurposing through the creation of novel ligands and the identification of repurposed drugs with optimized protein-binding affinities.

Tian’s primary research interests are in computer vision and machine learning, particularly in neural network compression (e.g., pruning and knowledge distillation) and adversarial AI. These techniques have broad applications in areas such as autonomous driving, neural architecture search, mobile and edge computing, and healthcare.

Wang applies AI techniques to 1) analyze cellular structures and 2) solve challenges in broad data science across disciplines, such as medical image analysis. He has developed cutting-edge algorithms and methodologies in machine learning and deep learning, which are the two cornerstones of modern AI.

Li’s research focuses on trustworthy AI and enhancing the robustness of models against adversarial threats. She is exploring the potential of AI techniques to address security challenges in domains like cybersecurity and IoT security. Her research also aims to promote the application of trustworthy AI in other areas, including healthcare and education.