Scholar

Ying Tai (邰颖)

Google Scholar ID: NKaiUasAAAAJ

Asso. Prof., Nanjing University; Tencent Youtu Lab (2017-2023)

Computer VisionPattern RecognitionFace AnalysisVisual GenerationImage Restoration

Citations & Impact

All-time

Citations

13,753

H-index

i10-index

Publications

Co-authors

list available

Contact

Publications

20 items

Browse publications on Google Scholar (top-right) ↗

Resume (English only)

Academic Achievements

Published numerous papers covering areas like human-centric text-to-image editing and generation, multi-modal image/video generation, high-fidelity image/video restoration, and virtual digital humans. Some notable works include DescribeEdit (ICCV'25), HybridBooth (ECCV'24), FaceX (arXiv'24), PortraitBooth (CVPR'24), RAG-Diffusion (ICCV'25), and more. Also involved in recent research projects like MotionSight, CoDi, TextCrafter, etc.

Research Experience

Was a Principal Researcher and Team Lead at Tencent Youtu Lab for over 6 years (2017.04~2023.07), leading two teams that developed novel vision algorithms applied in several products such as Virtual Background feature in Tencent Meeting and High-fidelity face generation APIs in Tencent Cloud. The team also conducted cutting-edge research works published in top-tier AI conferences.

Education

Received a Ph.D. degree from the Department of Computer Science and Engineering, Nanjing University of Science & Technology (NUST) in 2017, under the supervision of Prof. Jian Yang. Spent 6 months as a visiting student at Prof. Xiaoming Liu's lab at Michigan State University in 2016.

Background

Currently an Associate Professor at the School of Intelligence Science and Technology, Nanjing University (Suzhou Campus). Research interests include frontier Generative AI research and applications based on advanced large vision and language models, specifically in human-centric text-to-image editing and generation, multi-modal image/video generation, high-fidelity image/video restoration, and virtual digital humans.

Miscellany