Homepage
Welcome to my homepage!
- I am currently an Algorithm Engineer specializing in the pretraining and post training of large language model (LLM) and multimodal LLMs. Previously, I obtained my Master’s degree in Computer Engineering from the National University of Singapore (NUS).
- In 2024, I was fortunate to intern with Tencent WeChat in Guangzhou.
🎓I completed my undergraduate degree at Nanjing University of Aeronautics and Astronautics (NUAA) in 2022.
- Currently I am actively seeking for Phd position in 2026 fall. Here is the newly updated CV.
Recent Updates
- 🎞️ Update 2023.8 Glad to join in SHOWLAB @NUS, where impressive and innovative works are been made!
- News: July 2024 Start an internship at Tencent WXG.
Research Interests
- Vision and Language
- LL(V)M based GUI Understanding
- Fine-grained Understanding and Generation
Reseach Works
- AssitGUI (CVPR 2024) Gao D, Ji L, Bai Z, Ouyang M, Li P, Mao D, Wu Q, Zhang W, Wang P, Guo X, Wang H.,Mike Z.
- Pioneer AI Assistant for Graphical User Interface (GUI) which can assist users in completing complex tasks, boosting human productivity.
- Pioneer AI Assistant for Graphical User Interface (GUI) which can assist users in completing complex tasks, boosting human productivity.
- Harmonizing Unets (Computers in Biology and Medicine) Zhuoyu Wu, Qinchen Wu, Wenqi Fang, Wenhui Ou, Quanjun Wang, Linde Zhang, ChaoChen, Zheng Wang
- Toward better fluid segmentation of noisy OCT images.
- Toward better fluid segmentation of noisy OCT images.
- VideoGUI (Neurips 2024 DB) Lin Kevin Qinghong, Linjie Li, Difei Gao, Qinchen Wu, Mingyi Yan, Zhengyuan Yang,Lijuan Wang, and Mike Zheng Shou.
- Evaluating Ai agent on Computer Use Tasks comprehensively.
- Evaluating Ai agent on Computer Use Tasks comprehensively.
- GUI Action Narrator (ACMMM 2025) Qinchen Wu, Difei Gao, Lin Qinghong, Zhuoyu Wu, Mike Zheng Shou.
- How Visual language model narrate the learn from human demonstrations in GUI through pure vision?
Internships
Tencent WXG Guangzhou From July 2024 to Oct 2024
Academic Services
- Served as reviewer in NeurIPS 2025