刘晟材，工学博士，南方科技大学计算机科学与工程系助理教授。刘博士长期从事人工智能领域的研究，以第一/通讯作者在人工智能领域顶级会议和期刊发表论文10余篇。个人主页：https://senshinel.github.io

研究方向

(1) 算法自动设计的基础理论、方法及应用

(2) 自动机器学习、演化大模型

教育经历

2014年9月-2020年7月，中国科学技术大学，计算机科学与工程系，博士

2010年9月-2014年7月，中国科学技术大学，计算机科学与工程系，学士

工作经历

2024年8月至今，南方科技大学，计算机科学与工程系，助理教授

2023年5月-2024年5月，新加坡科技研究局，人工智能前沿研究中心，高级研究科学家
2023年1月-2023年5月，新加坡科技研究局，人工智能前沿研究中心，访问教授

2021年1月-2023年1月，南方科技大学，计算机科学与工程系，研究助理教授

Journal Publications（*表示通讯作者）

[12] X. Li, S. Liu*, and K. Tang. Novel Genetic Algorithm for Solving Chance-Constrained Multiple-Choice Knapsack Problems. Journal of Computer Applications, 2024, 44(5): 1378-1385.

[11] X. Li, S. Liu*, J. Wang, X. Chen, Y.-S. Ong, and K. Tang. Chance-Constrained Multiple-Choice Knapsack Problem: Model, Algorithms, and Applications. IEEE Transactions on Cybernetics, 2024, DOI: 10.1109/TCYB.2024.3402395

[10] N. Lu, S. Liu*, Rui He, Qi Wang, Yew-Soon Ong, and Ke Tang. Large Language Models can be Guided to Evade AI-Generated Text Detection. Transactions on Machine Learning Research, 2024.

[9] S. Liu, N. Lu, W. Hong, C. Qian, and K. Tang. Effective and Imperceptible Adversarial Textual Attack via Multi-objectivization. ACM Transactions on Evolutionary Learning and Optimization, 2024, 4(3), pp.1-23.

[8] S. Liu, Y. Zhang, K. Tang, and X. Yao. How Good is Neural Combinatorial Optimization? A Systematic Evaluation on the Traveling Salesman Problem. IEEE Computational Intelligence Magazine, 2023, 18(3): 14-28.

[7] Z. Dai, S. Liu*, Q. Li, and K. Tang. Saliency Attack: Towards Imperceptible Black-box Adversarial Attack. ACM Transactions on Intelligent Systems and Technology, 2023, 14(3): 1-20.

[6] R. He, S. Liu*, S. He, and K. Tang. Multi-Domain Active Learning: Literature Review and Comparative Study. IEEE Transactions on Emerging Topics in Computational Intelligence, 2023, 7(3): 791-804.

[5] 刘晟材 , 杨鹏, 唐珂. 近似最优并行算法组智能汇聚构造. 中国科学: 技术科学, 2023, 280-290.

[4] S. Liu, N. Lu, C. Chen, and K. Tang. Efficient Combinatorial Optimization for Word-level Adversarial Textual Attack. IEEE/ACM Transactions on Audio, Speech and Language Processing, 2022, 30: 98-111.

[3] S. Liu, K. Tang, and X. Yao. Generative Adversarial Construction of Parallel Portfolios. IEEE Transactions on Cybernetics, 2022, 52(2): 784-795.

[2] S. Liu, K. Tang, and X. Yao. Memetic Search for Vehicle Routing with Simultaneous PickupDelivery and Time Windows. Swarm and Evolutionary Computation, 66: 100927, 2021.

[1] K. Tang, S. Liu, P. Yang, and X. Yao. Few-shots Parallel Algorithm Portfolio Construction via Co-evolution. IEEE Transactions on Evolutionary Computation, 2021, 25(3): 595-607.

Conference Publications （*表示通讯作者）

[6] S. Liu, C. Chen, X. Qu, K. Tang, and Y.-S. Ong. Large Language Models as Evolutionary Optimizers. In: Proceedings of The 2024 IEEE Congress on Evolutionary Computation (CEC’2024), Yokohama, Japan, 2024, To Appear

[5] N. Lu, S. Liu*, Z. Zhang, Q. Wang, H. Liu, and K. Tang. Less is More: Understanding Word-level Textual Adversarial Attack via n-gram Frequency Descend. In: Proceedings of The 2024 IEEE Conference on Artificial Intelligence (CAI’2024), Singapore, Singapore, 2024, 823-830.

[4] R. He, S. Liu*, J. Wu, S. He, and K. Tang. Multi-Domain Learning From Insufficient Annotations. In: Proceedings of The 26th European Conference on Artificial Intelligence (ECAI’2023), Kraków, Poland, 2023, 1028-1035.

[3] S. Liu, F. Peng, and K. Tang. Reliable Robustness Evaluation via Automatically Constructed Attack Ensembles. In: Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI’2023), Washington, DC, 2023, 8852-8860.

[2] S. Liu, K. Tang, Y. Lei, and X. Yao. On Performance Estimation in Automatic Algorithm Configuration. In: Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI’2020), New York, NY, 2020, 2384-2391.

[1] S. Liu, K. Tang, and X. Yao. Automatic Construction of Parallel Portfolios via Explicit Instance Grouping. In: Proceedings of the 33rd AAAI Conference on Artificial Intelligence (AAAI’2019), Honolulu, HI, 2019, 1560-1567.

Fundings

[1] 项目负责人，“高可靠组合优化求解器的自动构建关键方法”， 华为-南方科技大学计算机系人工智能 RAMS 技术创新实验室长期合作框架协议项目, 05/2021 - 05/2022, CNY 400,000.

Patents

[2] 刘晟材，杨鹏，唐珂，姚新，“一种仓储网络的库存调拨方法、装置及存储介质”，授权专利号ZL201811598496.1，2023年5月.

[1]  刘晟材，杨鹏，唐珂，姚新，“一种车辆调度方法、装置、设备及存储介质”，授权专利号ZL201811404905.X，2021年10月.

Dissertation

[1] 刘晟材，“面向并行启发式算法组的自动构建技术研究“，博士论文，中国科学技术大学，2020年7月.

Professional Services

• Professional Membership
  ○ IEEE, IEEE CIS, AAAI
• Journal Reviewer
  ○ TPAMI, TEVC, TCYB, TNNLS, CIM, AIJ, JAIR 
• Conference Reviewer
  ○ NeurIPS, ICML, AAAI, IJCAI, ECAI, GECCO, CEC