I'm Zichun 👋

I work on medical image analysis, medical large language models (MLLMs), and 3D volumetric understanding and analysis. I’m especially interested in problems where perception, reasoning, and spatial grounding come together in medical data 🧠

• Medical image segmentation and analysis
• Medical large language models and multimodal learning
• 3D volumetric understanding and reasoning
• Vision-language modeling for clinical applications
• Grounded perception in complex medical scenes

• Developing MLLM-based methods for medical image understanding
• Exploring reasoning and grounding for volumetric medical data
• Improving 3D perception, localization, and segmentation in clinical scenarios

You are visitor ✨