Scholar
Bingyi Kang
Google Scholar ID: NmHgX-wAAAAJ
Research Scientist @ TikTok
Citations & Impact
Citations
9,276
H-index
28
i10-index
40
Publications
20
Co-authors
27
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Published papers include 'Trace Anything: Representing Any Video in 4D via Trajectory Fields' and others; Research integrated into Hugging Face's transformers codebase; Depth Anything V2 optimized and selected as official Core ML Models by Apple.
Research Experience
- Currently a research scientist at TikTok, Seattle; Formerly a research scientist at Sea AI Lab; Leading the development of the Depth Anything series.
Education
- PhD from National University of Singapore; Visiting researcher at UC Berkeley under the supervision of Prof. Trevor Darrell; Interned at Facebook AI Research, working with Saining Xie, Yannis Kalantidis, and Marcus Rohrbach during PhD.
Background
- Research Interests: Computer vision, multi-modal models, and decision making. Goal is to develop agents that can acquire knowledge from various observations and interact with the physical world.
Miscellany
- Email: bingykang [at] gmail [dot] com; Multiple intern and FTE positions (on 3D&4D foundation models) open for application.
