About
Hi, my name is Yunhao Li. I am currently pursuing a Master of Science in Artificial Intelligence at Guangzhou University. My research interests focus on Computer Vision, Medical Image Analysis and Multimodal Learning. I have strong hands-on skills, proficient in tools like PyTorch, Transformers, AutoGluon, and server-side technologies including Vue, FastAPI, and Spring Cloud. My achievements include multiple national competition awards and patents. Ultimately, I aim to help others reach their full their potential through 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.
Publications
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.
PRCVCCF-C
Programming Skills
- AI & Data: PyTorch, Transformers, AutoGluon, Pandas, Matplotlib, OpenCV
- Server: Vue, FastAPI, Spring Cloud, MySQL, RabbitMQ, K8S, kubesphere, CI/CD
- Contribute to LLaMA-Factory
Chinese-LLaMA-Alpaca
Education
- Master of Artificial Intelligence
GuangZhou University- Major in Artificial Intelligence
- Advisor: Yan Pang
- GPA 3.61/4
- Bachelor in Computer Science
Guilin University of Electronic Technology- Major in Computer Science
- GPA 4.15/5
Honors & Awards
- First Prize in the National Guangzhou Pazhou Algorithm Competition
- Lead AI and backend teams develop an Artificial Intelligence Security Assessment platform.
- Implemented 20+ adversarial attack, 10+ defense algorithms, integrated image & text classification, object detection models
- Third Prize in the National China Collegiate Computing Contest-AI Track
- Developed an Intelligent Construction Site Monitoring System for Helmet Detection and Tracking.
- Implemented Helmet Detection and Tracking Pipeline by Vue, FastAPI, and YOLO.
- Second Prize in the National 9th "China Software Cup"
- Developed a Real-Time Vehicle Recognition and Tracking System for Traffic Light Scenarios.
- Implemented Traffic Light Visual Processing Pipeline by YOLO, DeepTrack, and Vue, tracking cars and pedestrians.
- Second Prize in the National Competition at the RoboMaster
- Led computer vision algorithm team to build real-time target recognition and tracking system for edge devices.
- Co-work with the Mechanical Design and Circuit Design Department to build robots.
- Second Prize in the National 9th "China Education Robot Competition"
- Developed computer vision systems enable robots to recognize and navigate around obstacles and identify specific markers accurately.
- Train object detection models that run on edge devices.