I work in Computer Vision, Machine Learning, and AI Systems & Applications. I am broadly interested in basic research and interdisciplinary collaborations motivated by important applications, with current focuses on Creative, Efficient, and Responsible Multimodal AI to Understand, Emulate, and Interact with the visual world we live in.Β
I care about both the basic aspect (fundamental, curiosity, simplicity) and the application aspect (effective, useful/fun, impactful).Β I've recently worked on:
Computer Vision: accurate & efficient visual recognition, super-resolution & enhancement, inpainting & editing, vision-language, multimodal understanding & generation, etc.
Machine Learning: transformers, data & compute efficient deep learning, transfer learning, interpretability, generative models, etc.
Creative & Responsible AI: Systems & Applications for Art, Agriculture, Education, Engineering, Medicine, Finance, Science, Transportation, etc.
Β Β Β Β Β find our recent papers on Google Scholar ...
A note on the SHI Labs:
SHI stands for our core values: Service, Humanity, Innovation.Β
We are committed to developing leaders who advance technology and improve the human condition, and we embrace progress and service.
The SHI Labs is situated at CODA, a thriving hub for technology and innovations shared by both industry trailblazers and academic thinkers alike. And CODA sits at the heart of Atlanta, a vibrant city and a verdant forest with a dynamic blend of culture, nature, technology and commerce. We welcome future members, visitors and collaborators.