👋 About Me

I’m Yuxuan Cheng, a Ph.D. student in Computer and Information Engineering at the Chinese University of Hong Kong, Shenzhen. Prior to this, I got my Bachelor of Engineering in Automation from the College of Engineering at Huazhong Agricultural University (HZAU) in 2025.

Building on my past work in Open-World Vision and Multimodal Learning, I now turn to World Models for Physics & Space; let’s connect if you’re interested.

Feel free to reach out via email or WeChat (Yuxuan_CHENG02) if you’re interested in collaboration or would like to discuss research!

🗞 News

2026

📄 [Mar 2026] Our paper “PhysNote: Self-Knowledge Notes for Evolvable Physical Reasoning in Vision-Language Models” was accepted at the ICLR 2026 Workshop on Efficient Spatial Reasoning.

2025

📌 [Jun] Graduated with a B.E. in Automation from HZAU.
Grateful to all my mentors, professors, and collaborators for their invaluable guidance and support throughout this journey.
📄 [May] Our paper “Rethinking Graph Domain Adaptation: A Spectral Contrastive Perspective” was accepted at ECML-PKDD 2025 (CCF-B).
📄 [Apr] Our paper “CLIP-AdaM: Adapting Multi-view CLIP for Open-set 3D Object Retrieval” was accepted at SIGIR 2025 (CCF-A).

2024

🌐 [Nov] My homepage is online!
📄 [Jul] Our paper “Robust Detection of Cracked Eggs Using a Multi-Domain Training Method for Practical Egg Production” was accepted at Foods (JCR Q1).
📄 [Jun] Our paper “SimpleFusion: A Simple Fusion Framework for Infrared and Visible Images” was accepted at PRCV 2024 (CCF-C).

🎓 Education

Ph.D. student in Computer and Information Engineering
The Chinese University of Hong Kong, Shenzhen (2025 – )
B.E. in Automation
Huazhong Agricultural University (2021 – 2025)

📝 Reviewer Service

ICME’25 ‘26, IJCNN’25, AAAI’26, IEEE TMC, Food Control, IEEE RAL

📫 Contact

Email: hanxuanwxss at gmail dot com
WeChat: Yuxuan_CHENG02