Multimodal AI for Medical Understanding
This direction explores multimodal large-model systems for medical assistance, including joint image-text understanding, diagnostic consistency, triage support, and visual grounding.
Yingjin Li
MPhil student at HKUST(GZ), working on computer vision, multimodal learning, industrial anomaly detection, and diffusion models.
- Guangzhou, China
- The Hong Kong University of Science and Technology (Guangzhou)
- Website
- Google Scholar
- GitHub