Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
Contributed to the Grounded-Segment-Anything project, which combines Grounding DINO with Segment Anything, Stable Diffusion, and Recognize Anything for automatic detection, segmentation, and generation of anything.
Research Experience
Currently working at IDEA AI4Science; also a member of EmoCareAI and IDEA Research.
Education
Hong Kong University of Science and Technology (HKUST)
Background
Research interests include Large Language Models (LLMs), benchmarking, generative vision models, and more.
Miscellany
Enjoys quoting Japanese haiku, such as works by Matsuo Basho; still learning coding.