Spatio-temporal data can abstractly represent many things in reality. I focus on designing neural networks for representation learning on spatio-temporal data and using the learned representations to empower various scenarios. My research interests include (large) language models, graph neural networks, recommender systems, etc. I am strongly self-motivated and aim to pursue cutting-edge AI research. I have published several peer-reviewed papers in top venues like ICML, NeurIPS, KDD, WWW, IEEE TKDE, ACM TOIS, EMNLP, AAAI, and IJCAI. I have also served as a PC member/reviewer for conferences/journals like AAAI, LOG, ACM TOIS, ACM TKDD, IEEE TKDE, IEEE TNNLS, and Neural Networks.