My research focuses on digital agents and their environments 🕹️. I’m open to collaborations and discussions—feel free to drop me an email: siyuan.hu.sg [AT] gmail.com.
You can pronounce my name as "Who's Yuan". Who's Yuan? It’s me.
ShowUI-Ď€: Flow-based Generative Models as GUI Dexterous Hands.
Siyuan Hu*, Kevin Qinghong Lin*, Mike Zheng Shou.
CVPR 2026.
[Project Page]
Computer-Use Agents as Judges for Generative User Interface.
Kevin Qinghong Lin*, Siyuan Hu*, Linjie Li, Zhengyuan Yang, Lijuan Wang, Philip Torr, Mike Zheng Shou.
Preprint, 2025.
[Project Page]
[Paper]
[Code]
[Demo]
AssistGPT: Towards Multi-modal Agent for Human-Centric AI Assistant.
Difei Gao, Siyuan Hu, Zechen Bai, Kevin Qinghong Lin, Mike Zheng Shou. ACM MM Human-Centric Multimedia Analysis Workshop, Best Demo Paper, 2024.
Experience
Nanyang Technological University
Computer Science, 2020–2024.
Honors
NTU Science and Technology Undergraduate Full Scholarship, 2020–2024
NTU President Research Scholar, Academic Years 2021–2022, 2022–2023
Dean’s List, Top 5% of NTU students, Academic Years 2020–2021, 2023–2024
Best Demo Paper, ACM MM 2024 Human-Centric Multimedia Analysis Workshop
Tinker Research Grant, Thinking Machines Lab, 2025
Services
Conference Reviewer: ACL, ICLR, ICML, ACM MM
Misc
I am a beatmaker; I use Roland SP404 for beatmaking and live jamming, in Jazz and Lo-Fi vibes.