Tengjin Weng

πŸ‘‹ About Me

Tengjin Weng (he/him)
PhD Student in Computer Science
Shenzhen University, China πŸ‡¨πŸ‡³

My research focuses on medical image analysis, semi-supervised learning, and multimodal reasoning, with an emphasis on annotation ambiguity, pseudo-label robustness, and efficient supervision. I am particularly interested in developing algorithms that are both practical and reliable in real-world clinical settings.

πŸŽ“ Education

  • πŸ§‘β€πŸŽ“ Ph.D. Student, Shenzhen University, 2024 – Present
  • πŸŽ“ M.S., Zhejiang Sci-Tech University, 2021 – 2024
  • πŸŽ“ B.S., Wenzhou University 2017-2021

πŸ“ Selected Publications

2025

Tengjin Weng, Jingyi Wang, Wenhao Jiang, Zhong Ming
VisNumBench: Evaluating Number Sense of Multimodal Large Language Models
In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2025


2024

Tengjin Weng, Yang Shen, Kai Jin, Yaqi Wang, Zhiming Cheng, Yunxiang Li, Gewen Zhang, Shuai Wang
Enhancing Point Annotations with Superpixel and Confident Learning for Semi-supervised OCT Fluid Segmentation
Biomedical Signal Processing and Control, 2024

Tengjin Weng, Yang Shen, Zhidong Zhao, Zhiming Cheng, Shuai Wang
Accurate Segmentation of Optic Disc and Cup from Multiple Pseudo-labels by Noise-aware Learning
The 2024 IEEE International Conference on Computer Supported Cooperative Work in Design (CSCWD)