Wang Ziyue

Wang Ziyue

National University of Singapore

I am a M.Eng student at Department of Electrical and Coomputer Engineering, National University of Singapore, supervised by Prof. Yueming Jin. Before that, I received my B.Eng degree from Harbin Institute of Technology (Shenzhen), advised by Prof. Yongbing Zhang.

My research interests include computer vision techniques—particularly image and video segmentation—and agentic AI systems, with a focus on their applications in medical domains such as radiology, surgery, and pathology. I have published more than 10 papers at the top conferences and journals with total google scholar citations 750+ (You can also use google scholar badge ).

🔥 News

  • 2026.06   Actively seeking Ph.D positions in medical AI and agentic AI in 2026 Fall. If you’re interested in collaboration, feel free to reach out!
  • 2025.05:  🎉🎉 Our paper “ReSurgSAM2: Referring Segment Anything in Surgical Video via Credible Long-term Tracking” has been early accepted by MICCAI 2025 (top 9%).
  • 2025.04:  🎉🎉 Our paper “The Four Color Theorem for Cell Instance Segmentation” has been accepted by ICML 2025.
  • 2025.03:  🎉🎉 Our paper “Seine: Structure encoding and interaction network for nuclei instance segmentation” has been accepted by IEEE JBHI.
  • 2025.02:  🎉🎉 Our paper “Medical sam adapter: Adapting segment anything model for medical image segmentation” has been accepted by MedIA.
  • 2024.12:  🎉🎉 Our paper “Multi-scale Context Intertwining for Panoramic Renal Pathology Segmentation” has been accepted by ICASSP 2025.
  • 2024.12:  🎉🎉 Our paper “Dawn: Domain-adaptive weakly supervised nuclei segmentation via cross-task interactions” has been accepted by IEEE TCSVT.
  • 2024.5:  🎉🎉 Our paper “Dynamic pseudo label optimization in point-supervised nuclei segmentation” has been early accepted by MICCAI 2024 (top11%).
  • 2024.2:  🎉🎉 Our paper “Boundary-aware Contrastive Learning for Semi-supervised Nuclei Instance Segmentation” has been accepted by MIDL 2024 (Oral).

📝 Selected Publications

Under Review
sym

Medagent-pro: Towards evidence-based multi-modal medical diagnosis via reasoning agentic workflow

Ziyue Wang, Junde Wu, Linghan Cai, Chang Han Low, Xihong Yang, Qiaxuan Li, Yueming Jin

  • We present an evidence-based reasoning agentic system with both quantitative and qualitative evidence for explainable medical diagnosis.
Under Review
sym

Surgraw: Multi-agent workflow with chain-of-thought reasoning for surgical intelligence

Chang Han Low, Ziyue Wang, Tianyi Zhang, Zhitao Zeng, Zhuo Zhu, Evangelos B. Mazomenos, Yueming Jin

  • We present a CoT-driven multi-agent framework for accurate and interpretable analysis of surgical vision tasks.
Under Review
sym

Structure Matters: Revisiting Boundary Refinement in Video Object Segmentation

Guanyi Qin, Ziyue Wang, Daiyun Shen, Haofeng Liu, Hantao Zhou, Junde Wu, Runze Hu, Yueming Jin

  • We propose a novel boundary amendment video object segmentation method with inherent structure refinement
MedIA (IF=10.7)
sym

Medical sam adapter: Adapting segment anything model for medical image segmentation

Junde Wu, Ziyue Wang, Mingxuan Hong, Wei Ji, Huazhu Fu, Yanwu Xu, Min Xu, Yueming Jin

  • We present a simple yet effective adaptation technique, to extend SAM to medical domain.
  • Received over 600 citations on google scholar.
MICCAI25 (CCF-B)
sym

Dynamic pseudo label optimization in point-supervised nuclei segmentation

Ziyue Wang, Ye Zhang, Yifeng Wang, Linghan Cai, Yongbing Zhang

  • We present a framework leverage CAM to achieve accurate weak-supervised nuclei segmentation.
MIDL24 (Oral)
sym

Boundary-aware Contrastive Learning for Semi-supervised Nuclei Instance Segmentation

Ye Zhang, Ziyue Wang, Yifeng Wang, Hao Bian, Linghan Cai, Hengrui Li, Lingbo Zhang, Yongbing Zhang

  • We proposes a boundary-aware contrastive learning network to denoise the boundary noise for semi-supervised nuclei segmentation.

🎖 Honors and Awards

  • 2023.10 Second-class academic schorlarship of undergraduate (top 10%).
  • 2022.10 Second-class academic schorlarship of undergraduate (top 10%).
  • 2022.10 11th of the NeurIPS22 Cellseg challenge among 500 teams, Paper here
  • 2022.6 11th of the MIDOG2022 challenge of MICCAI2023, Paper here

📖 Educations

  • 2024.08 - 2026.06 (now), M.Eng. Student (Master by Research) at Department of Electrical and Coomputer Engineering, National University of Singapore, supervised by Prof. Yueming Jin.
  • 2020.09 - 2024.07, B.Eng. Student at Department of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), supervised by Prof. Yongbing Zhang.

💻 Internships

  • 2021.10 - 2024.06, Research Assistant in Harbin Institute of Technology (Shenzhen) and Tsinghua Shenzhen International Graduate School, supervised by Prof. Yongbing Zhang.