Hello, I'm
Jingxuan Kang
PhD Student at Imperial College London
Supervised by Prof. Chen Qin. My research focuses on computer vision and machine learning — cross-modal learning, data-efficient visual understanding, and vision-language models.
Research Interests
Vision-Language Models
Advancing multimodal understanding through attention-based selection and alignment mechanisms.
Cross-Modal Learning
Bridging modalities through knowledge alignment, enabling transfer across visual and linguistic domains.
Data-Efficient Learning
Leveraging language semantics and pre-trained models to learn effectively from limited visual data.
Medical Imaging
Applying computer vision to autonomous catheterization, X-ray analysis, and surgical guidance.
Publications
Loading publications from Google Scholar...
Could not load publications. View on Google Scholar →
Contact
Imperial College London, UK