Yu-Chiang Frank Wang
Also known as Frank Wang
Yu-Chiang Frank Wang is a computer-vision researcher who leads NVIDIA Research Taiwan. He earned electrical-engineering degrees at National Taiwan University and Carnegie Mellon, then joined Academia Sinica and became a professor at NTU. His research includes domain adaptation in the 2018 paper Detach and Adapt and VideoMage, a 2025 framework for customizing generated videos around multiple subjects and their motions. As of October 2026, he is NVIDIA's Research Director for Deep Learning and Computer Vision. His Taiwan group works on generative AI, multimodal learning, and 3D vision.
Timeline
-
2001–2009
Degrees at NTU and CMU
He earns a bachelor's degree in electrical engineering at National Taiwan University in 2001, then master's and doctoral degrees in electrical and computer engineering at Carnegie Mellon in 2004 and 2009.
-
2009–2017
Research at Academia Sinica
He joins the Research Center for Information Technology Innovation at Academia Sinica as an assistant research fellow in 2009. He serves as deputy director from 2015 to 2017.
-
2017–2019
Professor at NTU
He joins the Department of Electrical Engineering at NTU in 2017 and becomes a professor in 2019.
-
2018
Detach and Adapt
With five collaborators, he coauthors Detach and Adapt, a CVPR 2018 paper that introduces a Cross-Domain Representation Disentangler. The model transfers attribute information between fully annotated source-domain data and unlabeled target-domain data.
-
2025
CIEE Outstanding EE Award
He receives the CIEE Outstanding EE Professor Award in 2025.
-
2025
VideoMage for text-to-video
With five collaborators, he coauthors VideoMage, a CVPR 2025 framework for customizing generated videos around multiple subjects and their interactive motions.
-
Since August 2022
Research director at NVIDIA
Since August 2022, he leads NVIDIA Research Taiwan as Research Director for Deep Learning and Computer Vision. As of October 2026, he is a professor of electrical engineering at National Taiwan University. The Taiwan group focuses on generative AI, multimodal learning, and 3D vision.
Career
- Since 2022NVIDIAResearch Director for Deep Learning and Computer Vision
- Since 2017National Taiwan UniversityProfessor
- 2019–2021Asus
- 2009–2017Academia SinicaAssistant Research Fellow, Deputy Director
Education
- 2009Carnegie Mellon UniversityPhD in electrical and computer engineering
- 2004Carnegie Mellon UniversityMaster's degree in electrical and computer engineering
- 2001National Taiwan UniversityBachelor's degree in electrical engineering
Most-cited works
- A Closer Look at Few-shot Classification
- No More Discrimination: Cross City Adaptation of Road Scene Segmenters
- Multi-label Zero-Shot Learning with Structured Knowledge Graphs
- Towards Scene Understanding: Unsupervised Monocular Depth Estimation With Semantic-Aware RepresentationWith Alexander H. Liu
- Convolution in the Cloud: Learning Deformable Kernels in 3D Graph Convolution Networks for Point Cloud Analysis
Colleagues
Sources and credits
Photo: vllab.ee.ntu.edu.tw; Director - VISION & LEARNING LAB; creator not stated. License: Not stated by source. Source: vllab.ee.ntu.edu.tw. Cropped to a square and resized. Ask us to remove or replace this photo.