Undergraduate at Sun Yat-sen University, School of Intelligent Engineering, Shenzhen Incoming Ph.D. Student at Shanghai Artificial Intelligence Laboratory & Fudan University
Key Courses: Mobile Robot Planning and Control (100), Engineering Mathematics (98), Operations Research (97), Database Systems (96), Image Processing (95), Data Structures & Algorithms (95), Deep Learning (94), Computer Vision (93), Computer Networks (91)
🔬 Research Interests
Computer Vision
Multimodal Large Language Models (MLLMs)
📂 Projects & Research
Hybrid Disturbance Modeling under Image Compression and Adverse Environmental Effects
Co-first author; studied the impact of compression and adverse environmental effects on images.
Developed a deep learning-based hybrid disturbance restoration model for high-quality image recovery.
Led project planning and progress management in an undergraduate innovation and entrepreneurship program.
Universal Medical Image Segmentation Based on Deep Snake Algorithm
Third author; implemented a universal medical image segmentation pipeline using deep snake algorithm.
Conducted in-depth review and reproduction of SOTA methods on relevant datasets, proposed improvements, and participated in paper writing.
Visible and Infrared Dual-Modal Object Detection
Leveraged single-modal labels and teacher network pseudo-labeling for cross-modal data mining to enhance model performance.
Optimized a three-stage training strategy and contributed to code development and model tuning.
Hierarchical Decoupled Adaptation for Generalized Multimodal Representation Learning
Independently designed a two-stage training framework for multimodal large model research.
Conducted literature review, formulated research plan, implemented code and experiments.