My name is Xingcheng Xu, and I am a research scientist at Shanghai AI Laboratory. Previously, I worked as a data scientist at Ant Group and Alibaba Group. I earned my Ph.D. from the School of Mathematical Sciences at Peking University, where I was also a joint Ph.D. student at the Mathematical Institute, University of Oxford.
My research interests are focused on the intersection of probability theory, artificial intelligence and their applications. I am dedicated to exploring this interdisciplinary space and uncovering novel insights and practical applications.
Ph.D. in Mathematics
Education
-
School of Mathematical Science, Peking University (Beijing, China)
Ph.D. in Mathematics, 09/2014 – 07/2019.
Advisor: Prof. Yong Liu -
Mathematical Institute, University of Oxford (Oxford, UK)
Joint Ph.D. in Mathematics, 09/2017 – 10/2018.
Advisor: Prof. Zhongmin Qian -
BICMR, Peking University (Beijing, China)
(Beijing International Center for Mathematical Research)
Joint B.S. in Mathematics/Enhanced Program for Graduate Study, 02/2014 – 06/2014. -
School of Mathematical Science, Ocean University of China (Qingdao, Shandong, China)
B.S. in Mathematics, 09/2010 – 07/2014.
Research Interests
Probability Theory, Stochastic Analysis, Machine Learning, Artificial Intelligence, and their Applications.
Selected Publications
* as first/cofirst author, 📧 corresponding author
-
Xingcheng Xu*, Zibo Zhao, Haipeng Zhang, and Yanqing Yang. “Relating the Seemingly Unrelated: Principled Understanding of Generalization for Generative Models in Arithmetic Reasoning Tasks.” arXiv preprint arXiv:2407.17963, 2024.
[ArXiv Version] [PDF] [GitHub Code] -
Xingcheng Xu*, Zihao Pan, Haipeng Zhang, and Yanqing Yang. “It Ain’t That Bad: Understanding the Mysterious Performance Drop in OOD Generalization for Generative Transformer Models.” The 33rd International Joint Conference on Artificial Intelligence (IJCAI), 6578-6586, 2024. (CCF A)
[Published Version] [PDF] [GitHub Code] [Slides] [Poster] -
Zi Wang, Xingcheng Xu*, Yanqing Yang, Xiaodong Zhu. “Optimal Trade and Industrial Policies in the Global Economy: A Deep Learning Framework.” arXiv preprint arXiv:2407.17731, 2024.
[ArXiv Version] [PDF] -
Yanqing Yang, Xingcheng Xu, Jinfeng Ge, Yan Xu. “Machine Learning for Economic Forecasting: An Application to China’s GDP Growth.” arXiv preprint arXiv:2407.03595, 2024.
[ArXiv Version] [PDF] -
Qin Chen, Jinfeng Ge, Huaqing Xie, Xingcheng Xu*, Yanqing Yang. “Large Language Models at Work in China’s Labor Market.” arXiv preprint arXiv:2308.08776, 2023.
[ArXiv Version] [PDF] -
Thomas Cass, Terry Lyons, and Xingcheng Xu*. “Weighted Signature Kernels.” Annals of Applied Probability (AAP), Vol. 34, No. 1A, (2024), 585-626. (Early named as “General Signature Kernels”)
[Journal Version] [PDF] [GitHub Code] -
Zhongmin Qian, and Xingcheng Xu*📧. “Lévy Area Analysis and Parameter Estimation for fOU Processes via Non-Geometric Rough Path Theory.” Acta Mathematica Sci (ActaMS), Vol. 44, (2024), 1609-1638.
[Journal Version] [PDF] -
Zhongmin Qian, and Xingcheng Xu*📧. “Probability Bounds for Reflecting Diffusion Processes.” Statistics and Probability Letters (SPL), Vol 199, (2023), 109855.
[Journal Version] [PDF] -
Zengjing Chen, Shuhui Liu, Zhongmin Qian, and Xingcheng Xu*. “Explicit solutions for a class of nonlinear backward stochastic differential equations and their nodal sets.” Probability, Uncertainty and Quantitative Risk (PUQR), Vol. 7, No. 4, (2022), 283-300.
[Journal Version] [PDF] -
Renjie Feng, Xingcheng Xu📧, and Robert J. Adler. “Critical radius and supremum of random spherical harmonics (II).” Electronic Communications in Probability (ECP), 23 (2018): 1-11. DOI: 10.1214/18-ECP156.
[Journal Version] [PDF]
Reports
-
Xiaohui Cui, Di Guo, Zhao Jin, Chunjie Lin, Rong Xiao, Xingcheng Xu, Chenggang Xu, Yanqing Yang. “China Artificial Intelligence Index Report 2022“, (2022). (English Version: ~200 Pages, Report)
崔晓晖、郭迪、金钊、林纯洁、肖蓉、徐兴成、许成钢 、杨燕青：中国人工智能指数报告2022，2022。 (中文版：~200页)
[English Version] [Chinese Version] -
Jian An, Daixi Chen, Long Chen, Yuanfang Li, Wei Liu, Jiamin Meng, Michael Spence, Qidi Wang, Xingcheng Xu, and Kaiwen Zheng. “Measuring and Tracking the Global Pandemic Economy.” Luohan Academy Report (2020).
[LHA Report] [PDF]
Academic Activities
-
Conference Participation: 2024/8/3-9, IJCAI 2024 - The 33rd International Joint Conference on Artificial Intelligences (Main Track), Jeju, South Korea.
Talk Title: “It Ain’t That Bad: Understanding the Mysterious Performance Drop in OOD Generalization for Generative Transformer Models”. -
Invited Talk: 2023/12/7, Seminar on rough paths, stochastic partial differential equations and related topics, Technische Universität (TU) Berlin.
Talk Title: “Weighted Signature Kernels and Applications” (online). -
Conference Tutorial: 2023/12/4, WINE 2023 - The 19th Conference on Web and Internet Economics, Shanghaitech University, China.
Tutorial Title: “The Macroeconomics of Foundation Model / AI Economics”, joint with Yanqing Yang, Jinfeng Ge. -
Conference Participation: 2023/10/20-22, AI and Economics Workshop, Hangzhou, China.
Talk Title: “理解大语言模型”. -
Conference Participation: 2023/9/22-23, 第三届数据科学与现代经济统计论坛, 厦门大学.
Talk Title: “机器学习和中国宏观经济预测–模型应用、比较和可解释性分析”.
Slides
-
Deep Generative Modeling with Backward Stochastic Differential Equations, 2023-04
-
Generative Ambiguity Modeling Using Multiple Transformers, 2022-11
Grants and Awards
-
Shanghai Sailing Program (Shanghai scientific and technological innovation action plans), STCSM / 上海市“科技创新行动计划”启明星项目(扬帆专项), 2022
-
Hangzhou High-level Talents Category E / 杭州市高层次人才E类, 2021
-
Excellent Graduate of Peking University / 北京大学优秀毕业生, 2019
-
National Scholarship, PKU / 国家奖学金, 2017
Contact Information
-
Name: Xingcheng Xu
-
Email: xingcheng.xu18@gmail.com
-
Affiliation: Shanghai AI Laboratory
-
Address: Xuhui District, Shanghai, China
Useful Links
American Mathematical Society
Association for the Advancement of Artificial Intelligence
Lens.org
AMiner
Knowledge Lab
Swarma Club