Hu TianYu
2011.09-2015.06 山东大学 工学学士
2015.09-2020.06 清华大学 工学博士
2018.07-2019.08 加州大学伯克利分校 联合培养
2020.08 至今 北京科技大学计算机与通信工程学院 副教授
Hu T, Guo Q, Shen X, et al. Utilizing unlabeled data to detect electricity fraud in AMI: A semisupervised deep learning approach[J]. IEEE Transactions on Neural Networks and Learning Systems, 2019, 30(11): 3287-3299.
Hu T, Guo Q, Li Z, et al. Distribution-free probability density forecast through deep neural networks[J]. IEEE Transactions on Neural Networks and Learning Systems, 2019, 31(2): 612-625.
Hu T, Guo Q, Sun H, et al. Nontechnical losses detection through coordinated BiWGAN and SVDD[J]. IEEE Transactions on Neural Networks and Learning Systems, 2020, 32(5): 1866-1880.
Hu T, Ma H, Liu H, et al. Self-attention-based machine theory of mind for electric vehicle charging demand forecast[J]. IEEE Transactions on Industrial Informatics, 2022, 18(11): 8191-8202.
Liu K, Peng Q, Hu T*, et al. A transferred recurrent neural network for battery calendar health prognostics of energy-transportation systems[J]. IEEE Transactions on Industrial Informatics, 2022, 18(11): 8172-8181.
Hu T, Ma H, Liu K, et al. Lithium-ion battery calendar health prognostics based on knowledge-data-driven attention[J]. IEEE Transactions on Industrial Electronics, 2022, 70(1): 407-417.
H. Liu, J. Liu, T. Hu* and H. Ma, "Spatio-Temporal Probabilistic Forecasting of Wind Speed Using Transformer-Based Diffusion Models," in IEEE Transactions on Sustainable Energy, doi: 10.1109/TSTE.2025.3591920.
Hu T, Ma H, Sun H, et al. Electrochemical-theory-guided modeling of the conditional generative adversarial network for battery calendar aging forecast[J]. IEEE Journal of emerging and selected topics in power electronics, 2022, 11(1): 67-77.
Hu T, Wu W, Guo Q, et al. Very short-term spatial and temporal wind power forecasting: A deep learning approach[J]. CSEE Journal of Power and Energy Systems, 2020, 6(2): 434-443.
Hu T, Li K, Ma H, et al. Quantile forecast of renewable energy generation based on indicator gradient descent and deep residual BiLSTM[J]. Control Engineering Practice, 2021, 114: 104863.
Liu H, Liang F, Hu T*, et al. Multi-scale fusion model based on gated recurrent unit for enhancing prediction accuracy of state-of-charge in battery energy storage systems[J]. Journal of Modern Power Systems and Clean Energy, 2024, 12(2): 405-414.
H. Liu, T. Hu* and H. Ma, "Short-Term Wind Speed Forecasting using Graph Attention and Frequency Domain Attention," in CSEE Journal of Power and Energy Systems (accepted).
Zhang X, Wang K, Hu T*, et al. Efficient Knowledge Transfer in Multi-Task Learning through Task-Adaptive Low-Rank Representation[C]. ICME 2025.
Wang K, Zhang X, Hu T*, et al. Csce: Boosting llm reasoning by simultaneous enhancing of causal significance and consistency[C]. ICME, 2025.
Zhang X, Wang K, Hu T*, et al. Enhancing autonomous driving through dual-process learning with behavior and reflection integration[C]//ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2025: 1-5
纵向项目:
基于深度学习的完备分布预测模型构建及应用,国家自然科学基金面上项目,2021-2025
基于大语言模型的直升机-蜂群****方法,基础加强项目,450,2025-2026
面向自动驾驶场景的高真实感数据合成,科技部新一代人工智能重大项目子课题,100,2022-2025
基于逻辑推理和****的大模型*****决策方法研究,JKW军事智能领域交叉主题项目,170,2024-2025
智能空中群体的符号-数值耦合认知和导航,启元实验室创新基金,100, 2023-2024
基于生成式对抗网络和微分同胚的完备分布预测模型,博士后科学基金面上资助,8,2021-2022
知识与数据双向驱动的小样本目标识别方法,中国科学院光电信息处理重点实验室创新基金,10,2020-2022
基于双向Wasserstein生成式对抗网络和支持向量数据描述的单标签分类方法,北京科技大学基本科研业务,30,2020至今
横向项目:
无源干扰对抗仿真系统设计,清华大学,36,2021-2024
每年可招收硕士生1-2名,欢迎对大模型感兴趣的同学报考。
(1)北京市科学技术协会青年人才托举工程,北京市科学技术协会,2021年
(2)面向视觉任务的鲁棒特征表示与学习,中国图象图形学学会自然科学二等奖,中国图象图形学学会,2023年,5/5。
(3)《中国电机工程学会电力与能源系统学报》优秀论文奖,2020年,1/1。
基于多尺度融合GRU网络的汽车电池SOC多步预测方法与系统,第一发明人
一种基于知识与数据联合的路径规划方法,应用及装置,第一发明人
一种基于OD数据的多目标旅行商控制方法、系统及介质,第一发明人
基于注意力的锂离子电池日历老化预测模型和方法,第一发明人
基于机器心智模型和自注意力的风力发电分位数预测方法,第一发明人
基于图卷积神经网络和Transformer的时空短期风速预测方法及系统,第一发明人
一种基于大语言模型先验知识的推理状态控制方法及装置,第一发明人
一种基于3DGS 的单图车辆重建方法及系统,第一发明人