个人信息

丁立中，北京理工大学教授，博士生导师，国家级青年人才。研究课题包括深度统计学习理论和方法；大模型涌现机理与推理机制；多智能体环境建模与协同推理；图推理增强与可信图学习；统计假设检验与深度生成模型；因果学习与可解释人工智能；神经符号学习理论和方法。在ICML、NeurIPS、ICLR、AAAI、TPAMI、TNNLS等人工智能领域国内外顶级会议和期刊发表论文50余篇，长期担任ICML、NeurIPS、ICLR、AAAI、TKDE、TCYB、TNNLS等顶会顶刊审稿人。常年担任国家级青年人才评审专家，包括QC、YQ等。承担国家自然科学基金海外优青项目、面上项目、重点联合基金项目课题以及国家重点研发计划课题。围绕国产大模型全球竞争力与产业化路径撰写报告，被中央广播电视总台内参产品采纳并呈报中央主要领导，在决策咨询中发挥了重要作用。担任国际会议AIAAS 2026的程序委员会主席。担任中国自动化学会模式识别与机器智能专业委员会委员、国际模式识别协会委员、中国图学学会数字媒体专业委员会委员、中国计算机学会数字医学分会执行委员，窦店人工智能应用专家委员会委员等。

News: 每年计划招收博士生1~2人、硕士研究生3~5人，同时也欢迎优秀本科生加入实验室，表现优秀者将推荐至香港、新加坡、沙特、阿联酋继续深造。有意加入本课题组的学生请将个人简历发送至： 6120220231@bit.edu.cn

科研方向

深度统计学习理论和方法，大模型涌现机理与推理机制，多智能体环境建模与协同推理，统计假设检验与深度生成模型，核方法与深度核方法，图推理增强（大模型、多智能体）与可信图学习，因果学习与可解释人工智能，神经符号学习理论和方法

代表性学术成果

1. Jiarun Fu, Lizhong Ding*, Ye Yuan, Qiuning Wei, Zhaohuan Linghu, Yurong Cheng, Changsheng Li, Tianlong Gu, Liang Chang, Guoren Wang. FlowMAP: Flow Matching for Generalizable Agent Planning, Forty-third International Conference on Machine Learning (ICML), 2026. (*通讯作者)

2. Chunhui Zhang, Pengqi Li, Lizhong Ding*, Peng Yang, Ye Yuan, and Guoren Wang, Uncertainty-Constrained Trustworthinessfor Graph Learning, International Conference on Machine Learning (ICML), 2026. ( *通讯作者)

3. Yuhan Guo, Lizhong Ding*, Shihao Jia, Yanyu Ren, Pengqi Li, Jiarun Fu, Changsheng Li, Ye Yuan and Guoren Wang. Learning for Highly Faithful Explainability, The Fourteenth International Conference on Learning Representations (ICLR), 2026. (*通讯作者)

4. Jiarun Fu, Lizhong Ding*, Qiuning Wei, Yuhan Guo, Yurong Cheng and Junyu Zhang. Counterfactual planning for generalizable agents' actions, Proceedings of the 40th AAAI Conference on Artificial Intelligence (AAAI oral), pp. 29432-29440, 2026. (* 通讯作者)

5. Pengqi Li, Lizhong Ding*, Zhehao Zhou, Chunhui Zhang, Jiarun Fu, Hao Li, Ye Yuan, and Guoren Wang. Demystifying Uncertainty in LLMs: Active Calibration between Concepts and Human Evaluations, Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL), 2026. (* 通讯作者)

6. Huiwen Bai, Lizhong Ding*, Junyu Zhang, Chunhui Zhang, Jiarun Fu, Liang Chang, Tianlong Gu, Changsheng Li, Ye Yuan, Guoren Wang. VPF: Topology-preserving Virtual Path Fusion to tackle over-squashing, Pattern Recognition (PR), 2026, 179: 113770. (* 通讯作者)

7. Pengqi Li, Lizhong Ding*, Jiarun Fu, Chunhui Zhang, Guoren Wang, and Ye Yuan. Generalization Bounds for Kolmogorov-Arnold Networks (KANs) and Enhanced KANs with Lower Lipschitz Complexity, Advances in Neural Information Processing Systems 38 (NeurIPS), 2025. (* 通讯作者)

8. Junyu Zhang, Lizhong Ding†*, Minghong Zhang, Ye Yuan, Xingcan Li, Pengqi Li, Tihang Xi, Guoren Wang, Changsheng Li. Towards multi-table learning: Novel paradigm for complementarity quantification and integration, Advances in Neural Information Processing Systems 38 (NeurIPS), 2025. († 共同一作, * 通讯作者)

9. Chunhui Zhang, Rui Miao, Lizhong Ding*, Pengqi Li, Yuhan Guo, Xincan Li, Ye Yuan, and Guoren Wang, GCL-GroW: Graph Contrastive Learning via Group Whitening, Pattern Recognition(PR), 2025. (SCI一区, * 通讯作者)

10. Huiwen Bai, Lizhong Ding*, Guoren Wang, Ye Yuan, Junyu Zhang, Yuwan Yang, Lianpeng Qiao. Hierarchy-induced dual-channel tokenized graph learning, Knowledge-Based Systems (KBS), 2025, 330: 114505. (* 通讯作者)

11. Yanrui Yu, Tianfei Zhou, Jiaxin Sun, Lianpeng Qiao, Lizhong Ding, Ye Yuan, Guoren Wang. LAVA: Language Driven Scalable and Versatile Traffic Video Analytics, Proceedings of the 33rd ACM International Conference on Multimedia (ACM MM), pp. 7558-7567, 2025.

12. Zhenyu Yang, Gensheng Pei, Yazhou Yao, Tianfei Zhou, Lizhong Ding, and Fumin Shen. ChangeTitans: Toward Remote Sensing Change Detection With Neural Memory, IEEE Transactions on Geoscience and Remote Sensing (TGRS), 2025, 63: 1-14.

13. 李鹏奇, 丁立中*, 张春晖, 傅稼润. 深度泛化机制的再思考：过参数化与高维噪声扰动下的一致收敛界重构, 计算机科学, 2025. (* 通讯作者)

14. 李昊, 丁立中*, 傅稼润, 令狐赵桓. 大模型指令微调的数据压缩：一种基于推理贡献度的精化, 计算机科学, 2025. (* 通讯作者)

15. 李星灿, 丁立中*, 张君宇, 张春晖. ContraStacker: 一种极度不平衡欺诈检测的集成方法, 计算机应用, 2025. (* 通讯作者)

16. 果宇涵, 丁立中*, 韦秋宁, Polixplain: 基于策略梯度的黑盒模型显著性解释, 数据采集与处理, 2025. (* 通讯作者)

17. Lu Yu, Shichao Pei, Lizhong Ding, Jun Zhou, Longfei Li, Chuxu Zhang, and Xiangliang Zhang. SAIL: Self-Augmented Graph Contrastive Learning, Proceedings of the 36th AAAI Conference on Artificial Intelligence (AAAI), pp. 8927-8935, 2022.

18. Lizhong Ding, Shizhong Liao, Yong Liu, Li Liu, Fan Zhu, Yazhou Yao, Ling Shao, Xin Gao. Approximate Kernel Selection via Matrix Approximation, IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2020, 31(11): 4881-4891.

19. Lizhong Ding, Mengyang Yu, Li Liu, Fan Zhu, Yong Liu, Yu Li, Ling Shao. Two Generator Game: Learning to Sample via Linear Goodness-of-Fit Test, Proceedings of the 33rd Annual Conference on Neural Information Processing Systems (NeurIPS), 2019.

20 Yong Liu, Shizhong Liao, Shali Jiang, Lizhong Ding, Hailun Lin, and Weiping Wang. Fast Cross-Validation for Kernel-Based Algorithms, IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2019, 42(5):1083-1096.

21. Lizhong Ding, Zhi Liu, Yu Li, Shizhong Liao, Yong Liu, Peng Yang, Ge Yu, Ling Shao, Xin Gao. Linear Kernel Tests via Empirical Likelihood for High-Dimensional Data, Proceedings of the 33rd AAAI Conference on Artificial Intelligence (AAAI), pp. 3454-3461, 2019.

22. Lizhong Ding, Yong Liu, Shizhong Liao, Yu Li, Peng Yang, Yijie Pan, Chao Huang, Ling Shao, and Xin Gao. Approximate Kernel Selection with Strong Approximate Consistency, Proceedings of the 33rd AAAI Conference on Artificial Intelligence (AAAI), pp. 3462-3469, 2019.

23. Yazhou Yao, Zeren Sun, Fumin Shen, Li Liu, Limin Wang, Fan Zhu, Lizhong Ding, Gangshan Wu, and Ling Shao. Dynamically Visual Disambiguation of Keyword-based Image Search, Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI), pp. 996-1002, 2019.

24. Yu Li, Chao Huang, Lizhong Ding, Zhongxiao Li, Yijie Pan, and Xin Gao. Deep Learning in Bioinformatics: Introduction, Application, and Perspective in Big Data Era, Methods, 2019, 166: 4-21.

25. Lizhong Ding, Shizhong Liao, Yong Liu, Peng Yang, Xin Gao. Randomized Kernel Selection with Spectra of Multilevel Circulant Matrices, Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI), 2018.

26. Jian Li, Yong Liu, Rong Yin, Hua Zhang, Lizhong Ding, and Weiping Wang. Multi-Class Learning: From Theory to Algorithm, Advances in Neural Information Processing Systems (NeurIPS), pp. 1591-1600, 2018.

27. Yong Liu, Hailun Lin, Lizhong Ding, Weiping Wang, Shizhong Liao. Fast Cross-Validation, Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI), pp. 2497-2503, 2018.

28. Lizhong Ding, Shizhong Liao. An Approximate Approach to Automatic Kernel Selection, IEEE Transactions on Cybernetics (TCYB), 2017, 47(3): 554-565.

29. Lizhong Ding, Shizhong Liao. Approximate Consistency: Towards Foundations of Approximate Kernel Selection, Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Database (ECML PKDD), pp. 354-369, 2014.

30. Lizhong Ding, Shizhong Liao. Model Selection with the Covering Number of the Ball of RKHS, Proceedings of the 23rd ACM International Conference on Information and Knowledge Management (CIKM), pp. 1159-1168, 2014.

承担科研情况

深度统计学习，国家自然科学基金委员会，海外优青项目，2022年09月 - 2028年08月，项目负责人

骑行/驾驶就业群体安全与健康防护技术装备研究，工业和信息化部，国家重点研发计划，2026年06月 - 2029年05月，课题负责人

基于区块链的社会治理与风险防控技术及应用，工业和信息化部，国家重点研发计划，2022年11月 - 2025年10月，课题负责人

机器学习的公平性度量、分析及设计技术研究，国家自然科学基金委员会，联合基金项目-重点支持项目-区域创新发展联合基金，2023年01月 - 2026年12月，课题负责人

深度统计学习：理论基础与模型设计，国家自然科学基金委员会，面上项目，2024年01月 - 2027年12月，项目负责人

所获奖励

北京理工大学优秀人才奖

指导学生获得第十五届蓝桥杯软件赛个人赛 A 组 C++省赛一等奖

指导学生获得第二十一届世纪杯大学生创意竞赛一等奖

指导学生获得北京理工大学优秀毕业生

2025全国高校人工智能赋能教育大会三等奖

指导学生获得电信杯智能体创新创意大赛二等奖

指导学生获得多次研究生特等、一等学业奖学金

社会兼职

顶级会议审稿人：NeurIPS、ICML、ICLR、KDD、AAAI、ACL、IJCAI、ACMMM等

顶级期刊审稿人：IEEE TKDE、IEEE TCYB、IEEE TNNLS、IEEE TMM、IEEE TII、Pattern Recognition等

学术组织任职：担任国际会议AIAAS 2026的程序委员会主席，中国图学学会数字媒体专业委员会委员，中国自动化学会模式识别与机器智能专业委员会委员，国际模式识别协会会员，中国计算机学会数字医学分会执行委员，窦店人工智能应用专家委员会委员，中电联标准化技术委员会委员等

科研与人才评审专家：担任国家级人才项目评审专家及国家自然科学基金青年、面上项目评委；多次担任科研机构、高校项目和人才评审专家

备注

为中央广播电视总台提供决策咨询，《国产大模型在全球竞争中脱颖而出，建议“乘胜追击”推动产业升级多元应用》被采纳并呈报中央主要领导，在决策咨询中发挥了重要作用，并获得感谢信