Biography
I am a first-year M.S. student at Institute of Media, Information, and Network (min), Shanghai Jiao Tong University, advised by Prof. Hongkai Xiong and Prof. Wenrui Dai. I received my bachelor’s degree in Electronic Science and Technology from SJTU.
I have a keen interest in machine learning and interpretable artificial intelligence. My goal is to identify the fundamental optimization goal of deep learning and construct interpretable machine learning systems through mathematical derivations. Specifically, I aim to establish objective metrics to measure model performance and mathematically deduce the factors that contribute to model performance, guiding the design of neural network architectures.
Download my CV.
- Machine Learning
- Interpretable AI
- Computer Vision
M.S. in Information and Communication Engineering, 2023
SJTU
B.S. in Electronic Science and Technology (major) and Computer Science and Technology (minor), 2019
SJTU
Research Experience
Advised by Prof. Hongkai Xiong and Prof. Wenrui Dai, my researches include:
- Proposed ICPNet, a unified model capable of representing networks with arbitrary depths with fixed-point iteration layers and any activation function with Chebyshev polynomials, and verified its great properties. (submission for ECCV 2024)
- Validated the high similarity properties of parameter matrices in LoRa, thereby constructed low-rank decomposition which reduced the required parameter quantity for fine-tuning as well as enhanced performance.
Advised by Prof. Quanshi Zhang, my researches include:
- Used high-dimensional matrix analysis to clarify the challenges in adversarial training. (Accepted by AAAI 2024)
- Derived the dynamics characteristics in interactive learning. (Preparing for submission)
- Designed experimental methods to analyze the robustness of various complexity concepts.
Advised by Prof. Chongyang Zhang, my researches include:
- Developped Swin Transformer based model to implemente instance segmentation of workpiece welding area.
- Designed a space-time filter to remove false positive samples in pedestrian detection.
- Developped YOLOv5-based model to detect tower crane, recognize dangerous tower crane, and label electronic fence.
Competitions
Honors and Awards
Skills
Python, C++, Matlab, LaTeX, Linux, PyTorch, NumPy, Anaconda, Git, OpenCV
calculus, linear algebra, probability statistics
mandarin (native), English (fluent)
Activities and Leaderships
Contributions include:
- Third Place in the Team Category at the Tizong Cup in 2021.
- Second Place in the Team Category at the School Sports Meet in 2022.
Contributions include:
- Second Place in the Men’s 4$\times$100-Meter Relay at the School Sports Meet in 2020.
- First Place in the Men’s 4$\times$100-Meter Relay at the 2021 Track and Field Athletics Meet.