Develop Gemini-powered document parsing pipeline for understanding unstructured data, to empower AI applications such as RAG and Gemini Enterprise.

Develop deep learning models for traffic light recognition system.

Part-time Research Assistant advised by Professor Feng Jiashi

Ÿ Designed a speed-efficient algorithm to simulate optical flow features from motion vectors in compressed videos

Ÿ Improved compressed video action recognition pipeline with the designed algorithm

Ÿ Summarized our work in my undergraduate thesis paper