About Me

Guangze Shi is currently a Ph.D. candidate in the College of Computer Science and Technology at Taiyuan University of Technology, advised by Professor Mingqiang Wei. His research has been published in leading conferences and journals, including ICML, CVPR, MICCAI, Medical Image Analysis (MedIA), Pattern Recognition (PR), and IEEE Journal of Biomedical and Health Informatics (J-BHI).

His research focuses on computer vision and medical image analysis, with particular interests in foundation models, prompt-based image segmentation, domain generalization, and multimodal learning. His recent work explores efficient adaptation and prompt optimization for foundation segmentation models, as well as AI-driven analysis of pathological images and multimodal medical data.

📜 Research Area

• Computer Vision:

Foundation model, Domain generalization

• Medical Data Analytics:

Pathological image analysis, Multimodal data analysis

💻 Research Experiences

• 2018.09 - 2022.07: B.ENG. in Software Engineering, Taiyuan University of Technology, China
• 2023.09 - 2025.07: M.ENG. in Big Data Technology and Engineering, Taiyuan University of Technology, China
• 2025.09 - Present: Ph.D candidate in Computer Science and Technology, Taiyuan University of Technology, China

📝 Publications

2026

• [1] Guangze Shi, Yingjie Mi, Jia Shen, Feixue Shao, Jiarui Cao, Yexin Lai, Xueyu Liu*, Rui Wang, Yongfei Wu, Mingqiang Wei*. PromptPilot: Game-Theoretic Multi-Agent Prompt Optimization for Segment Anything, International Conference on Machine Learning (ICML), 2026. (CCF A)
• [2] Xueyu Liu, Xiaoyi Zhang, Meilin Liu, Guangze Shi, Jia Shen, Yujie Wang, Cai Zhao, Ziyuan He, Yongfei Wu*, Mingqiang Wei, Yongle Chen*. Attack for Defense: Adversarial Agents for Point Prompt Optimization Empowering Segment Anything Model, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026. (CCF A)
• [3] Hangbei Cheng, Xiaorong Dong, Jia Shen, Guangze Shi, Xueyu Liu, Jianan Zhang, Xuetao Ma, Mingqiang Wei, Liansheng Wang, Junxin Chen, Yongfei Wu*. FMaMIL: Synergistic Spatial-Frequency Mamba Multi-Instance Learning for Weakly Supervised Pathology Lesion Segmentation, Pattern Recognition (PR), 2026. (SCI Q1-TOP)
• [4] Shuqi Xia, Guangze Shi, Jiarui Cao, Aoyuan Shi, Meilin Liu, Xiaoyi Zhang, Yujie Wang, Xueyu Liu*, Cai Zhao, Ziyuan He, Yongfei Wu, Mingqiang Wei. Instruction-Focus-Prompt: Semantics-Driven Structural Prompts for Universal SAM Segmentation, IEEE/CVF Conference on Computer Vision and Pattern Recognition Findings (CVPR Findings), 2026.
• [5] Yansong Zhang, Hangbei Cheng, Jianan Zhang, Guangze Shi, Xueyu Liu, Lijie Shi, Junxin Chen, Yongfei Wu*. Automatic Prompt Generation via Reinforcement Learning Guided Contrastive Purification for Label-Free SAM Segmentation, Biomedical Signal Processing and Control (BSPC), 2026.
• [6] Helin Wang, Guangze Shi, Xueyu Liu*, Jianan Zhang, Sheng Chen, Jiashuo Shi, Yu-ang Li, Guanghui Yue, Yongfei Wu*. Explainable AI in Medicine: A Comprehensive Narrative Review of Methods, Applications, and Future Directions, Expert Systems, 2026. (Review)

2025:

• [1] Guangze Shi, Ying Wang, Yongfei Wu*, Xueyu Liu*, Jia Shen, Hao Meng, Yexin Lai, Weixia Han, Yan Hu, Mingqiang Wei. Al-driven Quantitative Analysis of Pathological images for Membranous Nephropathy across Macro and Micro Modalities, IEEE Journal of Biomedical and Health Informatics (IEEE J-BHI), 2025. (SCI Q2-TOP)
• [2] Xueyu Liu, Guangze Shi, Rui Wang, Yexin Lai, Jianan Zhang, Weixia Han, Min Lei, Ming Li, Xiaoshuang Zhou, Yongfei Wu*, Chen Wang, Wen Zheng. Segment Any Tissue: One-Shot Reference Guided Training-Free Automatic Point Prompting for Medical Image Segmentation (MedIA), 2025. (SCI Q1-TOP)
• [3] Xueyu Liu, Rui Wang, Yexin Lai, Guangze Shi, Feixue Shao, Fang Hao, Jianan Zhang, Jia Shen, Yongfei Wu*, Wen Zheng. Plug-and-Play PPO: An Adaptive Point Prompt Optimizer Making SAM Greater. Conference on Computer Vision and Pattern Recognition (CVPR), 2025. (CCF A)
• [4] Jia Shen, Jun Zhang, Xueyu Liu*, Yunfei Zhang, Guangze Shi, Fiexue Shao, Hangbei Cheng, Yongfei Wu*. Fourier Transform-Based Shape Constrained Framework for Generalizable Medical Image Segmentation, Chinese Conference on Pattern Recognition and Computer Vision (PRCV), 2025. (CCF C)

2024:

• [1] Xueyu Liu, Guangze Shi, Rui Wang, Yexin Lai, Jianan Zhang, Lele Sun, Quan Yang, Yongfei Wu*, MIng Li, Weixia Han, Wen Zheng. Feature-prompting GBMSeg: One-Shot Reference Guided Training-Free Prompt Engineering for Glomerular Basement Membrane Segmentation. International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2024. (CCF B)
• [2] Zihao Mi, Xueyu Liu, Jianan Zhang, Guangze Shi, Yidi Li, Yongfei Wu*. Multi-instance Curriculum Learning for Histopathology Image Classifications with Hard Negative Mining and Positive Augmentation. IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2024. (CCF B)

  2022:

• [1] Xueyu Liu, Ming Li, Yongfei Wu*, Yilin Chen, Fang Hao, Daoxiang Zhou, Chen Wang, Chuanfeng Ma, Guangze Shi, Xiaoshuang Zhou. An efficient glomerular object locator for renal whole slide images using proposal-free network and dynamic scale evaluation method. AI Communications, 2022. (SCI Q4)

🎖 Certifications and Awards

• “Huawei Cup” The 22th China Post-Graduate Mathematical Contest in Modeling, 2025, National Third Prize.
• 12th “Challenge Cup” China College Students Entrepreneurship Competition, 2020, National Second Prize.