Currently, I am a second-year PhD student in Computer Science at the Computer Vision Group in the School of Electronic Engineering and Computer Science at the Queen Mary University of London, under the supervision of Prof. Shaogang Gong.
My research aim is to answer the question: In what ways can large language models be optimally utilized to facilitate multimodal learning in fine-grained unsupervised domain adaptation and domain generalization? Consequently, I am deeply interested in generative models, multimodal, and domain generalization.
π₯ News
- 2025.03: Β ππ Two papers were accepted to CVPRβ25!
- 2024.10: Β ππ One paper was accepted to WACVβ25 (Oral)!
- 2024.07: Β ππ One paper was accepted to ECCVβ24!
π Publications

Temporal Score Analysis for Understanding and Correcting Diffusion Artifacts
CVPR 2025
Yu Cao, Zengqun Zhao, Ioannis Patras, Shaogang Gong

Zengqun Zhao, Ziquan Liu, Yu Cao, Shaogang Gong, Ioannis Patras

Enhancing Zero-Shot Facial Expression Recognition by LLM Knowledge Transfer
WACV 2025 (Oral)
Zengqun Zhao, Yu Cao, Shaogang Gong, Ioannis Patras

Few-Shot Image Generation by Conditional Relaxing Diffusion Inversion
ECCV 2024 (Poster)
Yu Cao, Shaogang Gong
π Honors and Awards
- 2021.12 Computer Science Deanβs list, University College London, UK.
π Educations
- *2023.09 - Now, PhD, Queen Mary University of London (QMUL), London, UK.
- 2020.09 - 2021.09, Master (Distinct GPA 4.0), University College London (UCL), London, UK.
- 2016.09 - 2020.09, Bachelor (First-Class Honours, GPA 4.0), University of Liverpool, Liverpool, UK.
π» Internships
- 2024.06 - Now, Research Assistant, Digital Environment Research Institute (QMUL), UK.
- 2023.12 - 2024.05, Research Asistant, Scalpel Limited, UK.