معرفی
Ke Yan is an Associate Professor in the Department of Computer Science at the National University of Singapore's College of Design and Engineering. With extensive research output from 2021-2026, their work spans computer vision, artificial intelligence, and multimodal learning systems.
- National University of Singapore (Primary Affiliation)
- Collaborations with University of Electronic Science and Technology of China
- Research ties with Tencent Youtu Lab in Shanghai
Research focuses on advancing computer vision techniques, particularly in medical image analysis, vision-language integration, and fault diagnosis systems. Their work bridges theoretical AI development with practical applications in healthcare, industrial systems, and environmental monitoring. Notable contributions include novel approaches to multimodal learning, medical image segmentation with sparse annotations, and improving reliability of large vision-language models.
Recent publication trends (2024-2026) demonstrate increasing focus on multimodal systems, with significant contributions to vision-language model reliability, medical AI applications, and efficient transfer learning techniques. Their work frequently addresses critical challenges like hallucination mitigation in large models and sparse data scenarios in medical imaging.
As an advisor, they mentor multiple researchers including Junlong Du, Shouhong Ding, and Zhiwen Lin, with whom they frequently collaborate on cutting-edge computer vision projects. Their research group maintains strong industry connections, particularly with Tencent's AI research division.
The research is conducted within NUS's computer vision and AI research ecosystem, collaborating with multiple laboratories focused on multimodal intelligence and practical AI deployment in real-world systems.
