Biography
I am a Master’s in Computer Science student at USC, and I am expected to graduate in May 2025. Before coming to USC, I completed my undergraduate studies at HUST where I was guided by Prof. Xianzhi Li and earned a BEng in Computer Science and Technology in June 2023.
My research experience is mainly in computer vision and generative AI. I am fortunate to work with Prof. Huaizu Jiang from Northeastern University (NEU), and with Prof. Zhengzhong Tu from Texas A&M University (TAMU).
Interests
- 3D Computer Vision
- Generative AI
- Trust worthy AI
- Machine Learning
Education
MS in Computer Science, 2025 (expected)
University of Southern California
BEng in Computer Science and Technology, 2023
Huazhong University of Science and Technology
Experience
- Presented a novel perspective for protecting personal images from malicious editing, focusing on making biometric features unrecongnizable post editing.
- Developed a new algorithm, FaceLock, that incorporates facial recognition models and feature embedding penalties to effectively protect against diffusion-based image editing.
- Conducted a crucial analysis of the quantitative evaluation metrics commonly used in image editing tasks, exposing their vulnerabilities and highlighting the potential for manipulation to achieve deceptive results.
Research Assistant
- Introduced SNAP, the first unified segmentation model capable of working across different point cloud domains including, part-level, indoor, and outdoor domains.
- Developed SNAP as a versatile model, supporting multiple prompt types, including points, bounding boxes, and text, to enable flexible object segmentation.
- Achieved state-of-the-art performance on multiple benchmark datasets and demonstrated SNAP’s utility as a semi-automated labeling tool for real-world applications.
Assistant Algorithm Engineer
- Worked on a 3D Instance Segmentation project aiming to combine the strengths of Clustering- and Transformer-based methods.
- Worked on modifying the indoor scene instance segmentation model to improve performance on outdoor scene datasets.
Worked on a Few-shot 3D Indoor Scene Instance Segmentation project.
