Scholar
Lei Ke
Google Scholar ID: WseeNrUAAAAJ
Researcher, Tencent AI (Seattle)
Citations & Impact
Citations
2,891
H-index
22
i10-index
24
Publications
20
Co-authors
17
list available
Publications
Resume (English only)
Academic Achievements
- Published multiple papers including 'Segment Anything in High Quality' (NeurIPS 2023), 'Gaussian Grouping: Segment and Edit Anything in 3D Scenes' (ECCV 2024), and 'Matching Anything By Segmenting Anything' (CVPR 2024); involved in projects such as Gaussian Grouping, HQ-SAM, and SAM-PT; presented research at international conferences like ICCV, CVPR, and ECCV; served as an Area Chair for ICLR 2026 and NeurIPS 2025; organized a workshop at ICCV 2025.
Research Experience
- Currently a Senior Researcher at Tencent AI Seattle; was a Postdoctoral Research Associate at Carnegie Mellon University, working with Prof. Katerina Fragkiadaki; served as a visiting PhD student at the Computer Vision Lab, ETH Zurich, supervised by Prof. Fisher Yu and Dr. Martin Danelljan.
Education
- Obtained his Ph.D. degree from the CSE Department at HKUST in mid-2023, supervised by Chi-Keung Tang and Yu-Wing Tai. During his PhD, he also spent two years as a visiting scholar at ETH Zurich. He received his B.E. degree from the School of Computer Science at Wuhan University.
Background
- Senior Research Scientist at Tencent AI, Seattle Lab. His primary research interest lies in building multimodal foundation systems, especially visual understanding, reasoning, and generation. Previously, he worked as a Postdoctoral Research Associate at Carnegie Mellon University's Computer Science and in the Computer Vision Lab of ETH Zurich.
Miscellany
- His open-source projects have over 10K+ GitHub stars; gave a guest lecture on Vision Foundation Model at Texas A&M University; delivered talks on Scene Understanding with Vision Foundation Models at Stanford SVL and MARVL.
