Ke Xue @ NJU

Gosau, Austria. Photoed by Yushun

Ke Xue (薛轲)

Ph.D. student,
LAMDA Group,
School of Artificial Intelligence,
Nanjing University

E-mail: xuek [AT] lamda.nju.edu.cn

About me

I am a Ph.D. student of School of Artificial Intelligence in Nanjing University advised by Prof. Chao Qian and a member of LAMDA Group, led by Prof. Zhi-Hua Zhou. My research interests include black-box optimization algorithms, such as evolutionary algorithms (especially quality-diversity algorithms), Bayesian optimization, and learning to optimize, as well as their applications, such as electronic design automation and AI for science.

Biography:

2019/09 - Present Ph.D. candidate in Computer Science, School of Artificial Intelligence, Nanjing University

2015/09 - 2019/06 B.Sc. in Mathematics and Applied Mathematics, School of Mathematics, Sun Yat-Sen University.

2012/09 - 2015/06 Jiyuan No.1 Middle School of Henan

News

Selected Works (Full Publication)

^# Equal Contribution ^† Corresponding author

Evolutionary Algorithms

IEEE TEvC Heterogeneous Multi-Agent Zero-Shot Coordination by Coevolution.
Ke Xue, Yutong Wang, Cong Guan, Lei Yuan, Haobo Fu, Qiang Fu, Chao Qian, and Yang Yu.
IEEE Transactions on Evolutionary Computation.
PDF / Code
TL;DR: We provide an effective framework to solve heterogeneous human-AI coordination.

ICLR Spotlight Sample-Efficient Quality-Diversity by Cooperative Coevolution.
Ke Xue^# , Ren-Jian Wang^#, Pengyi Li, Dong Li, Jianye Hao, and Chao Qian.
In: Proceedings of the 12th International Conference on Learning Representations (ICLR'24), Vienna, Austria, 2024.
PDF / Code
TL;DR: We decompose and coevolve solutions to improve the sample efficieny of QD algorithms.

IJCAI Quality-Diversity Algorithms Can Provably Be Helpful for Optimization.
Chao Qian, Ke Xue, and Ren-Jian Wang.
In: Proceedings of the 33rd International Joint Conference on Artificial Intelligence (IJCAI'24), Jeju Island, Korea, 2024, pp.6994-7002.
PDF
TL;DR: We give the first theoretical explanation of the superior optimization ability of quality-diversity algorithms.

IJCAI Evolutionary Gradient Descent for Non-convex Optimization.
Ke Xue, Chao Qian, Ling Xu, and Xu-Dong Fei.
In: Proceedings of the 30th International Joint Conference on Artificial Intelligence (IJCAI'21), Virtual, 2021.
PDF / Code
TL;DR: We provide an evolutionary gradient algorithm with theoretical guarentee.

Learning to Optimize

NeurIPS Sequential Multi-Agent Dynamic Algorithm Configuration.
Chen Lu, Ke Xue^†, Lei Yuan, Yao Wang, Yaoyuan Wang, Fu Sheng, and Chao Qian.
In: Advances in Neural Information Processing Systems 38 (NeurIPS'25), San Diego, CA, 2025.
PDF / Code
TL;DR: We extend multi-agent dynamic algorithm configuration to sequential setting.

ICML Towards Universal Offline Black-Box Optimization via Learning Large Language Model Embeddings.
Rong-Xi Tan, Ming Chen, Ke Xue^†, Yao Wang, Yaoyuan Wang, Fu Sheng, and Chao Qian.
In: Proceedings of the 42nd International Conference on Machine Learning (ICML'25), Vancouver, Canada, 2025.
(A preliminary version has appeared at the 2nd Workshop on Foundation Models in the Wild at ICLR’25, Oral presentation)
PDF / Code
TL;DR: We leverage the embeddings of large language model to achieve universal offline optimization.

NeurIPS Spotlight Monte Carlo Tree Search based Space Transfer for Black Box Optimization.
Shukuan Wang^#, Ke Xue^#, Lei Song, Xiaobin Huang, and Chao Qian.
In: Advances in Neural Information Processing Systems 37 (NeurIPS'24), Vancouver, Canada, 2024.
PDF / Code
TL;DR: We can transfer information from diverse source tasks to help the optimization of target task.

ICML Offline Multi-Objective Optimization.
Ke Xue^#, Rong-Xi Tan^#, Xiaobin Huang, and Chao Qian.
In: Proceedings of the 41st International Conference on Machine Learning (ICML'24), Vienna, Austria, 2024.
PDF / Code
TL;DR: We formulate and provide the first benchmark for offline multi-objective optimization.

NeurIPS Spotlight Multi-Agent Dynamic Algorithm Configuration.
Ke Xue^#, Jiacheng Xu^#, Lei Yuan, Miqing Li, Chao Qian, Zongzhang Zhang, and Yang Yu.
In: Advances in Neural Information Processing Systems 35 (NeurIPS'22), New Orleans, LA, 2022.
PDF / Code
TL;DR: We can effectively adjust all the hyperparameters of the optimization algorithm online.

NeurIPS Spotlight Monte Carlo Tree Search based Variable Selection for High Dimensional Bayesian Optimization.
Lei Song^#, Ke Xue^#, Xiaobin Huang, and Chao Qian.
In: Advances in Neural Information Processing Systems 35 (NeurIPS'22), New Orleans, LA, 2022.
PDF / Code
TL;DR: We can adaptively select effective variables for high-dimensional optimization.

Electronic Design Automation

DATE Dynamic Algorithm Configuration for Global Placement.
Chen Lu, Ke Xue^†, Ruo-Tong Chen, Yunqi Shi, Siyuan Xu, Mingxuan Yuan, Chao Qian, and Zhi-Hua Zhou.
In: Proceedings of 2026 Design, Automation & Test in Europe Conference & Exhibition (DATE'26), Verona, Italy, 2026.
TL;DR: We apply dynamic algorithm configuration to global placement for EDA.

DATE Best Paper Award Timing-Driven Global Placement by Efficient Critical Path Extraction.
Yunqi Shi, Siyuan Xu, Shixiong Kai, Xi Lin, Ke Xue, Mingxuan Yuan, and Chao Qian.
In: Proceedings of 2025 Design, Automation & Test in Europe Conference & Exhibition (DATE'25), Lyon, France, 2025.
TL;DR: We provide an effective timing-driven global placement algorithm.

NeurIPS Reinforcement Learning Policy as Macro Regulator Rather than Macro Placer.
Ke Xue, Ruo-Tong Chen, Xi Lin, Yunqi Shi, Shixiong Kai, Siyuan Xu, and Chao Qian.
In: Advances in Neural Information Processing Systems 37 (NeurIPS'24), Vancouver, Canada, 2024.
PDF / Code
TL;DR: We provide a new paradigm of reinforcement learning for macro placement.

NeurIPS The 21st ACM SIGEVO Humies Bronze Award Macro Placement by Wire-Mask-Guided Black-Box Optimization.
Yunqi Shi, Ke Xue, Lei Song, and Chao Qian.
In: Advances in Neural Information Processing Systems 36 (NeurIPS'23), New Orleans, LA, 2023.
PDF / Code
TL;DR: We provide a new paradigm of black-box optimization for chip placement.

AI for Science

PNAS Reducing the Uncertainty in Estimating Soil Microbial Derived Carbon Storage.
Han Hu^#, Chao Qian^#, Ke Xue^#, Rainer Georg Jörgensen, Marco Keiluweit, Chao Liang, Xuefeng Zhu, Ji Chen, Yishen Sun, Haowei Ni, Jixian Ding, Weigen Huang, Jingdong Mao, Rong-Xi Tan, Jizhong Zhou, Thomas W. Crowther, Zhi-Hua Zhou, Jiabao Zhang, and Yuting Liang.
Proceedings of the National Academy of Sciences, 2024, 121(35): e2401916121.
PDF / Code
TL;DR: We use AI techniques for estimating soil microbial derived carbon storage.

Awards

2025	DATE 2025 Best Paper Award (with Yunqi Shi, Siyuan Xu, Shixiong Kai, Xi Lin, Mingxuan Yuan, and Chao Qian)
2025	Top-20 Nomination for the Baidu Scholarship (awarded to 20 candidates among Chinese students worldwide).
2024	Young Elite Scientists Sponsorship Program by CAST for PhD Students (中国科协青年人才托举工程博士生专项计划).
2024	National Science Foundation of China for PhD Students (国家自然科学基金博士生项目).
2024	National Scholarship, Ministry of Education of China.
2024	21st ACM SIGEVO Humies BRONZE Awards (with Yunqi Shi, Lei Song, and Chao Qian)
2023	Huawei Spark Award (华为“揭榜挂帅”火花奖), "Multi-objective Black-box Optimization Technology for Ultra-High-Dimensional Spaces", Huawei Technologies Co., Ltd.
2022	Huawei Spark Award (华为“揭榜挂帅”火花奖), "Fast Multi-objective Optimization Strategies for Large-Scale Network Optimization with Complex Network Parameter Correlations", Huawei Technologies Co., Ltd.
2021	National Scholarship, Ministry of Education of China.

Services

Reviewer

Conferences:

International Conference on Machine Learning (ICML)
Neural Information Processing Systems (NeurIPS)
International Conference on Learning Representations (ICLR)
AAAI Conference on Artificial Intelligence (AAAI)
European Conference on Artificial Intelligence (ECAI)
International Conference on Automated Machine Learning (AutoML)

Journals:

SCIENCE CHINA Information Sciences
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Evolutionary Computation
IEEE Transactions on Emerging Topics in Computational Intelligence
Swarm and Evolutionary Computation
Frontiers of Computer Science