About
Yunhao Li
PhD student at The Hong Kong Polytechnic University, specializing in Medical Image Analysis, Computer Vision, and trustworthy AI with peer-reviewed work on reliable clinical imaging.
My research centers on Computer Vision, Medical Image Analysis, and Multimodal Learning, with an emphasis on dependable methods for clinical decision support. I aim to translate algorithmic advances into measurable contributions for medical science and human health.
Publications
Understanding Surgical Triplet Videos Through Transferable Visual Models from Natural Language Supervision
.Yunhao Li, Aoying Wang, Qiong Wang, Jinpeng Hu, Ying Hu, Yan Pang.
SegTom: A 3D Volumetric Medical Image Segmentation Framework for Thoracoabdominal Multi-Organ Anatomical Structures
.Yan Pang, Yunhao Li , Jiaming Liang, Hao Chen, Ying Hu, Qiong Wang.
Efficient Breast Lesion Segmentation from Ultrasound Videos Across Multiple Source-limited Platforms
.Yan Pang, Yunhao Li , Teng Huang, Jiaming Liang, Ziyu Ding, Hao Chen, Baoliang Zhao, Ying Hu, Zheng Zhang, Qiong Wang.
Online Self-distillation and Self-modeling for 3D Brain Tumor Segmentation
.Yan Pang, Yunhao Li , Teng Huang, Jiaming Liang, Zhen Wang, Changyu Dong, Dongyang Kuang, Ying Hu, Hao Chen, Tim Lei, Qiong Wang.
Optimized Breast Lesion Segmentation in Ultrasound Videos Across Varied Resource-Scant Environments
.Yunhao Li , Chen Zibin, Yan Junming, Ding Ziyu, Li Jie ,Pei Xiaoqing, Zhang Zheng, Qiong Wang, Yan Pang.
IPM: An Intelligent Component for 3D Brain Tumor Segmentation Integrating Semantic Extractor and Pixel Refiner
.Yunhao Li , Caiyan Tan, Mingdu Zhang, Xi Zhang, Teng Huang ,Xiao-Qing Pei, Yan Pang.
Slim UNETR: Scale hybrid transformers to efficient 3D medical image segmentation under limited computational resources
.Yan Pang, Jiaming Liang, Teng Huang, Hao Chen, Yunhao Li , Dan Li, Lin Huang, Qiong Wang.
CAM-PC: A novel method for camouflaging point clouds to counter adversarial deception in remote sensing
.Bo Wei, Teng Huang, Xi Zhang, Jiaming Liang, Yunhao Li , Cong Cao, Dan Li, Yongfeng Chen, Huagang Xiong, Feng Jiang, Xiqiu Zhang.
AgileNet: A Rapid and Efficient Breast Lesion Segmentation Method for Medical Image Analysis
.Jiaming Liang, Teng Huang, Dan Li, Ziyu Ding, Yunhao Li , Lin Huang, Qiong Wang, Xi Zhang.
Programming Skills
Full-stack delivery across research prototypes and production systems, with a focus on reliable ML, developer experience, and thoughtful tooling choices.
AI & Data
Train and fine-tune CV/LLM models, ship evaluation loops, and keep datasets reproducible.
Backend & Services
Design APIs and async pipelines with observability, caching, and resource-aware deployment.
System Glue
Bridge research and product: prompt tooling, feature flags, and rollouts tied to metrics.
Collaboration
Mentor teams, write docs, and keep coding standards consistent for safer shipping.
How I build
Practical workflows that keep experiments measurable and services shippable.
- •Start with measurable prototypes, then instrument tracing/metrics before scaling models or infra.
- •Prefer lightweight adapters, retrieval, and dataset curation over brute-force training.
- •Ship services with automated testing, containerization, and staged rollout paths for resilience.
CI/CD pipelines with containerized services, feature flags for safe rollout, and dashboards to watch model drift.
Collaborating with the community to strengthen LLM and CV tooling.
Education
Work Experience
ML Researcher & Data Analyst
China Post Bank
- Developed AI-driven finance data precision recommendation model for customer marketing.
- Designed and implemented a model training engine for automatic rolling training and optimization
- Contributed to a 15% increase in performance for China Post Bank GuangZhou.
