Welcome to T-lab

T-Lab, led by Prof. Xiaoying Tang at The Chinese University of Hong Kong, Shenzhen, focuses on research in artificial intelligence, federated learning, large models (reasoning, MOE, multimodal), and intelligent electric vehicle charging optimization. The lab has published high-impact work at NeurIPS, ICML, ICLR, AISTATS, CVPR, ICCV, AAAI, EMNLP and other top conferences, as well as IEEE SmartGridComm, TMC, TII, TSG, TPWRS, TMLR, IOTJ and other leading journals. The lab continuously advances three core research directions: in federated learning, tackling critical algorithmic challenges including heterogeneous data client clustering, diverse client sampling, federated forgetting and conflict mitigation, and fairness optimization; in large models (reasoning, MOE, multimodal), advancing frontier research in video temporal localization, causal event modeling for temporal understanding, dynamic mixture of experts models, prompt learning, and model laziness mitigation; in intelligent electric vehicle charging optimization, exploring key technologies such as optimal charging station placement, highway charging decision game analysis, and electric vehicle participation in primary frequency regulation markets. T-Lab is dedicated to promoting theoretical innovation and technological breakthroughs in the above research directions, achieving deep integration and innovative applications in core scenarios such as smart grids, computer vision, and distributed learning.