Songmiao obtained a master’s degree in Computer Science and Technology from Tianjin University in 2025, with a research focus on video understanding, human action recognition, and vision-language models. During postgraduate studies, Songmiao explored multimodal learning techniques, aiming to interpret complex visual and temporal patterns and ground language in visual contexts for more robust understanding. Songmiao’s work involved developing deep learning models for spatiotemporal reasoning and cross-modal alignment. In September 2025, Songmiao will join the Department of Industrial and Systems Engineering at The Hong Kong Polytechnic University as a research student. Songmiao’s current research interests revolve around artificial intelligence agents, particularly in the area of Retrieval-Augmented Generation (RAG), with the goal of building intelligent systems that combine perception, memory, and reasoning. Songmiao aims to enable AI agents to interact more effectively with the world by integrating external knowledge retrieval with deep neural understanding.