Master's candidate in Operations Research at Nankai University, specializing in developing robust and interpretable AI for Healthcare.
My research focuses on developing AI solutions for healthcare challenges
I am a Master of Science candidate in Operations Research at Nankai University, advised by Prof. Jianda Han and Prof. Weiguang Huo. My research focuses on AI4Healthcare, Computer Vision, LLMs.
I have contributed to several national research projects, including the National Natural Science Foundation of China project on "Cooperative Control of Lower Limb Exoskeletons for Complex Gait Prediction and Assistance" and the National Key Research and Development Program of China project on "Efficient Human-Machine Synergistic Control via Neuro-Muscular-Skeletal Integration".
Key projects and research contributions
Developed a patented, expert-level deep learning framework to predict Parkinson's severity from smartphone videos. This system successfully distinguishes subtle medication effects at a physician-level resolution and discovers novel digital biomarkers sensitive to disease progression.
Proposed the IMU2SKE framework to accurately predict Freezing of Gait (FoG) from monocular videos. Leveraged IMU-guided hierarchical contrastive learning to significantly enhance prediction accuracy from 79.5% to 83.2%.
Enhanced VLM geometric reasoning (Qwen2-VL-7B) by building a 3,000-pair image-text dataset for Supervised Fine-Tuning (SFT), achieving an 18% accuracy increase. Developed inference acceleration techniques using SFT and Group Relative Policy Optimization (GRPO).
npj Digital Medicine (IF=15.1, SCI, JCR Q1, Rank 1/188 in Health Care Sciences & Services)
2025 IEEE International Conference on Cyborg and Bionic Systems
China Invention Patent, 202511317738.5
Academic and professional journey
Advised by Prof. Jianda Han and Prof. Weiguang Huo. GPA: 88.99/100
Built a voice appointment agent and a dietary comment LLM (Base: Qwen2.5-VL-7B) to improve efficiency for medical staff.
Developed a high-definition portrait generation system (Unreal Engine MetaHuman) and improved model accuracy using diffusion models (DDPM) for data generation.
Developed human body/face beauty model and algorithm, with several models and algorithms serving 2M+ photographers.
GPA: 3.67/4.0
Areas of expertise and technical competencies
Recognition for academic and research excellence
Third place in the competitive AI challenge focused on video generation and understanding.
Recognition for excellence in operations research and optimization methodologies.
Academic Competition Special Scholarship (Top 10%) and Second-class Gongneng Scholarship (Top 20%).
Recognition for innovative AI solutions in the Huawei Ascend ecosystem.