Staff profile

• Minye Shao’s research focuses on medical artificial intelligence, medical image analysis, and general computer vision, with an emphasis on Unified Multimodal Reasoning, Understanding, and Generation. His work centers on probabilistic distribution modeling, representation learning, and cross-modal semantic alignment across vision, language, and biomedical data, aiming to develop principled and scalable foundation models for reliable medical understanding, generation, and decision-making. His research interests further extend to medical multimodal and generative foundation models, Medical AI agents, and AI for Science, particularly in emerging directions such as AI-driven drug discovery (AIDD) and AI-driven virtual cell (AIVC), where multimodal foundation models and generative reasoning can be applied to protein structure modeling, molecular generation, and multi-omics integration.

Conference Paper

• TRACE: Temporally Reliable Anatomically-Conditioned 3D CT Generation with Enhanced Efficiency
  
  Shao, M., Miao, X., Duan, H., Wang, Z., Chen, J., Huang, Y., Deng, J., Wu, X., Long, Y., & Zheng, Y. (2026). TRACE: Temporally Reliable Anatomically-Conditioned 3D CT Generation with Enhanced Efficiency. In Medical Image Computing and Computer Assisted Intervention – MICCAI 2025 (pp. 627-637). Springer Nature Switzerland. https://doi.org/10.1007/978-3-032-04965-0_59

Journal Article

• Rethinking Brain Tumor Segmentation from the Frequency Domain Perspective
  
  Shao, M., Wang, Z., Duan, H., Huang, Y., Zhai, B., Wang, S., Long, Y., & Zheng, Y. (2025). Rethinking Brain Tumor Segmentation from the Frequency Domain Perspective. IEEE Transactions on Medical Imaging. Advance online publication. https://doi.org/10.1109/tmi.2025.3579213