Scholar
Humphrey Shi
Google Scholar ID: WBvt5A8AAAAJ
Georgia Tech | UIUC || ...
Citations & Impact
Citations
20,175
Β
H-index
57
Β
i10-index
104
Β
Publications
20
Β
Co-authors
94
list available
Publications
Resume (English only)
Academic Achievements
- Published papers across CVPR, NeurIPS, ICLR, ICCV, ECCV, TPAMI (including highly cited works); won a dozen international AI competitions (ImageNet, NVIDIA AI City Challenge, NIST TRECVID, DAC-System Design Contest, etc.); open-source impact: NATTEN, StreamingT2V, Text2Video-Zero, Versatile Diffusion, OneFormerβwidely adopted across academia and industry; frequently GitHub trending; models downloaded millions of times; Hugging Face: #1 most-liked US university lab (Nov 2023); received National Science Foundation CAREER Award; selected among 100 outstanding early-career engineers in the US by the National Academy of Engineering Frontiers of Engineering; industry recognition: Apple App Store βTrend of the Year: Generative AIβ (2023); TIPA Best Consumer AI App (2023); IBM Research Accomplishment Award (2018).
Research Experience
- Served as Chief Scientist at Picsart (2021-2025), where he built a global AI team from the ground up across research, engineering, and product, and delivered AI tools used by 150M+ monthly users; also worked as Research Staff Member at IBM T. J. Watson Research Center, and professor at Oregon & UIUC.
Education
- No detailed educational background information provided.
Background
- A professor at Georgia Tech, and an engineer-researcher working across high-performance AI, multimodal AI, and computer vision. His mission is to build the next generation high-performance, multimodal, and creative AI systems that empower intelligence, creativity, and humanity.
Miscellany
- Leadership & mentoring: program chair, CVPR 2027; teaches Computer Vision (UG/Grad); advised students now at NVIDIA, Google, OpenAI, Meta, Apple, Amazon, Tesla, etc.; for future collaborators & investors: building high-performance multimodal & agentic AIβfrom kernels and algorithms to deployed systems and products; email/DM welcome.
