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, large models (reasoning, MOE, multimodal), intelligent electric vehicle charging optimization, and federated learning. 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 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; in federated learning, tackling critical algorithmic challenges including heterogeneous data client clustering, diverse client sampling, federated forgetting and conflict mitigation, and fairness optimization. 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.
Lab News
- 09/2025 2 papers accepted by NeurIPS 2025 (CCF A)
- 07/2025 Prof. Xiaoying Tang was invited to attend WAIC 2025 World Artificial Intelligence Conference and participated in the AI Women Elite Forum
- 07/2025 1 paper accepted by ICCV 2025 (CCF A)
- 04/2025 1 paper accepted by TII 2025 (CAS Q1)
- 04/2025 1 paper accepted by EMBC 2025
- 03/2025 2 papers accepted by TVT 2025 (JCR Q1) and IOTJ 2025 (JCR Q1)
- 03/2025 2 papers accepted by VTC 2025 and ICLR 2025 Workshop
- 02/2025 2 papers accepted by TNSE 2025 (JCR Q1) and CAIE 2025 (JCR Q1)
- 01/2025 1 paper accepted by IOTJ 2025 (JCR Q1)
- 01/2025 3 papers accepted by ICLR 2025
- 11/2024 Prof. Xiaoying Tang received the Shenzhen Natural Science Foundation (General Program) funding
Lab Related Reports
Proposed by Tencent AI Lab with CUHK-Shenzhen, AutoDeco equips Transformers with lightweight heads to dynamically predict temperature and top-p per token, and introduces a differentiable soft top-p to enable end-to-end training. It achieves SOTA-level results across models/tasks with ~1.7% latency overhead, and shows early signs of natural-language controllable decoding. See coverage for details.
T-lab's research advances vehicle-to-grid synergy, enabling smart interactions between electric vehicles and the power grid. See the China News story for details.
T-lab's research achievements in battery swap station pricing strategy and charging optimization have garnered industry attention. The related paper was published in IEEE Transactions on Mobile Computing (TMC) journal, providing new insights for theoretical research and practical applications in the battery swap station market.
Shenzhen TV interviewed Prof. Xiaoying Tang, who discussed how Shenzhen's electricity consumption growth is closely related to the development of new quality productive forces. The construction of industrial computing centers, data centers, and R&D activities all require substantial power support, reflecting Shenzhen's rapid development in digital transformation.
The university's official WeChat account featured Prof. Xiaoying Tang's contributions in fundamental algorithm innovation. As the thirteenth scholar in the AI Rising Star series, the report showcases her exploration and practice in multi-domain applications.
V2G system algorithms developed by the T-lab team have been applied in this landmark project, providing key technical support for large-scale vehicle-to-grid interaction in China. See full coverage at CCTV News.
Machine Heart reported on T-lab's latest research published at The Thirteenth International Conference on Learning Representations (ICLR 2025). The TRACE model, through causal event modeling, provides a new technical approach for temporal localization tasks in video understanding.
Prof. Xiaoying Tang was invited by Shenzhen Municipal Talent Work Bureau to participate in the production of "Come to Shenzhen, Be a Shenzhener" as one of the young talent representatives from Shenzhen universities.