English | 简体中文
I am a Ph.D. student at South China University of Technology, advised by Prof. Lianwen Jin at the Deep Learning and Vision Computing Lab.
My research spans document intelligence, computer vision, and multimodal learning, with a current focus on:
- Multimodal OCR — large models for reading and understanding complex visual documents.
- AIGC — visual text generation, editing, and document content creation.
- Document restoration — recovering historical text and its visual appearance.
I play piano and guitar, enjoy playing in a band and improvising accompaniment, and spend time on football and badminton.
I welcome research discussions and open-source collaboration in document intelligence, multimodal OCR, AIGC, and historical document restoration.