Scholar

Wenhao Wu (吴文灏)

Google Scholar ID: Kn5d1ckAAAAJ

Scientist @ Amazon AGI

Computer VisionVideo UnderstandingMultimodal Model

Citations & Impact

All-time

Citations

2,260

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 in top-tier conferences, such as Mulberry (NeurIPS'25 Spotlight), R1-ShareVL (NeurIPS'25), MMReason (ICCV'25), Dense Connecter (NeurIPS'24), AMP (NeurIPS'24), DistinctAD (CVPR'25 Highlight), and more. Recipient of the Baidu PhD Fellowship (2023) and DAAD AInet Fellowship (2025).

Research Experience

Applied Scientist at Amazon AGI, working on the Nova Cross-modal Foundation Model. Previously spent nearly seven years at Baidu VIS, growing from a research intern to a Senior/Staff Researcher and contributing to multiple large-scale computer vision and multimodal projects. Since 2021, has collaborated closely with Chief Scientist Dr. Jingdong Wang (IEEE Fellow). Also worked at Snap Research, SenseTime Research, Samsung Research, iQIYI AI, and others.

Education

Ph.D. from MMLab, The University of Sydney, supervised by Prof. Wanli Ouyang; M.S.E. from University of Chinese Academy of Sciences (UCAS), supervised by Prof. Shifeng Chen and Prof. Yu Qiao.

Background

Research interests include Computer Vision and Deep Learning, particularly in Multi-modal/Cross-modal Models, Video-Language Learning, and Video Foundation Models. Extensive experience in both academia and industry.

Miscellany