AI ethics
Research on ethical considerations in AI development and deployment, focusing on ensuring AI systems align with human values and societal norms.
Recent Publications
- Huang, C., Zhang, Z., Mao, B., & Yao, X. (2022). An overview of artificial intelligence ethics. IEEE Transactions on Artificial Intelligence, 4(4), 799-819.
Fairness in AI systems
Developing methods to detect and mitigate bias in AI algorithms to ensure fair treatment across different demographic groups.
Recent Publications
- Zhang, Q., Liu, J., Zhang, Z., Wen, J., Mao, B., & Yao, X. (2022). Mitigating unfairness via evolutionary multiobjective ensemble learning. IEEE transactions on evolutionary computation, 27(4), 848-862.
- Zhang, Q., Liu, J., & Yao, X. (2024). Fairness-aware multiobjective evolutionary learning. IEEE Transactions on Evolutionary Computation.
- Wang, Z., Huang, C., & Yao, X. (2024). Procedural fairness in machine learning. arXiv preprint arXiv:2404.01877.
Interpretable AI
Creating transparent AI models that provide understandable explanations for their decisions, enhancing trust and accountability.
Recent Publications
- Wang, Z., Huang, C., Li, Y., & Yao, X. (2024). Multi-objective feature attribution explanation for explainable machine learning. ACM Transactions on Evolutionary Learning and Optimization, 4(1), 1-32.
- Shi, X., Wang, Z., Minku, L. L., & Yao, X. (2023, July). Explaining Memristive Reservoir Computing Through Evolving Feature Attribution. In Proceedings of the Companion Conference on Genetic and Evolutionary Computation (pp. 683-686).
- Wang, Z., Huang, C., & Yao, X. (2023, June). Feature attribution explanation to detect harmful dataset shift. In 2023 International Joint Conference on Neural Networks (IJCNN) (pp. 1-8). IEEE.
Safe AI
Ensuring AI systems operate safely and reliably, with mechanisms to prevent harmful behaviors and unintended consequences.
Recent Publications
- Huang, C., Zhang, Z., Mao, B., & Yao, X. (2022, July). Preventing undesirable behaviors of neural networks via evolutionary constrained learning. In 2022 International Joint Conference on Neural Networks (IJCNN) (pp. 1-7). IEEE.
- Hu, C., Wang, Z., Liu, J., Wen, J., Mao, B., & Yao, X. (2023, June). Constrained Reinforcement Learning for Dynamic Material Handling. In 2023 International Joint Conference on Neural Networks (IJCNN) (pp. 1-9). IEEE.
- Su, Z., Zhang, G., Yue, F., Zhan, D., Li, M., Li, B., & Yao, X. (2021). Enhanced constraint handling for reliability-constrained multiobjective testing resource allocation. IEEE Transactions on Evolutionary Computation, 25(3), 537-551.
Robust AI
Developing AI systems that maintain performance under varying conditions and are resilient to adversarial attacks.
Recent Publications
- Hu, C., Wang, Z., Yuan, B., Liu, J., Zhang, C., & Yao, X. (2025). Robust dynamic material handling via adaptive constrained evolutionary reinforcement learning. IEEE Transactions on Neural Networks and Learning Systems, 36(10), 19327–19341.
- Zhao, Y., Gao, D., Yao, Y., Zhang, Z., Mao, B., & Yao, X. (2023, June). Robust deep learning models against semantic-preserving adversarial attack. In 2023 International Joint Conference on Neural Networks (IJCNN) (pp. 1-8). IEEE.
- Pan, C., Tang, K., Li, Q., & Yao, X. (2025, October). Rethinking RobustBench: Is High Synthetic-Test Data Similarity an Implicit Information Advantage Inflating Robustness Scores?. In 2025 IEEE 12th International Conference on Data Science and Advanced Analytics (DSAA) (pp. 1-10). IEEE.
AI in games
Applying AI techniques to game development, including procedural content generation, NPC behavior, and player modeling.
Recent Publications
- Hu, C., Zhao, Y., Wang, Z., Du, H., & Liu, J. (2024). Games for artificial intelligence research: A review and perspectives. IEEE Transactions on Artificial Intelligence, 5(12), 5949-5968.
- Volz, V., Schrum, J., Liu, J., Lucas, S. M., Smith, A., & Risi, S. (2018, July). Evolving mario levels in the latent space of a deep convolutional generative adversarial network. In Proceedings of the genetic and evolutionary computation conference (pp. 221-228).
- Liu, J., Snodgrass, S., Khalifa, A., Risi, S., Yannakakis, G. N., & Togelius, J. (2021). Deep learning for procedural content generation. Neural Computing and Applications, 33(1), 19-37.
Self-aware and self-expressive systems
Creating AI systems that can monitor their own performance, adapt to changing environments, and explain their internal states.
Recent Publications
- Torresen, J., Plessl, C., & Yao, X. (2015). Self-aware and self-expressive systems. Computer, 48(7), 18-20.
- Lewis, P. R., Chandra, A., Faniyi, F., Glette, K., Chen, T., Bahsoon, R., ... & Yao, X. (2015). Architectural aspects of self-aware and self-expressive computing systems: From psychology to engineering. Computer, 48(8), 62-70.
Evolvable hardware
Developing hardware systems that can adapt and reconfigure themselves in response to changing requirements or environmental conditions.
Recent Publications
- Shi, X., & Yao, X. (2025, November). Evolutionary Harnessing of Sneak Currents of 1R Memristive Crossbar. In International Conference on Innovative Techniques and Applications of Artificial Intelligence (pp. 270-282). Cham: Springer Nature Switzerland.
- Shi, X., Minku, L. L., & Yao, X. (2023). Evolving memristive reservoir. IEEE Transactions on Neural Networks and Learning Systems, 35(10), 13574-13588.
- Wang, Z., Shi, X., & Yao, X. (2023). A brain-inspired hardware architecture for evolutionary algorithms based on memristive arrays. ACM Transactions on Design Automation of Electronic Systems, 28(5), 1-32.