主要研究领域涉及人工智能伦理安全与治理、类脑人工智能、人工智能与可持续发展。

(1) 人工智能伦理安全与治理：研究人工智能的伦理道德模型、价值对齐、伦理评估、人工智能与智能体的近期与长远伦理、安全及其治理，并研究低风险、高度安全、具有道德的与人类和谐共生的人工智能。

(2) 类脑人工智能: 主要围绕面向通用人工智能和超级智能的类脑认知智能开展研究，类脑脉冲神经网络、类脑人工神经网络、类脑自主学习、发育与演化理论、算法、模型与应用。

(3) 人工智能与可持续发展：研究人工智能与青少年发展、人工智能促进文化传承与互鉴、人工智能赋能全球可持续发展目标的实现，人工智能对可持续发展的影响。

· 北京前瞻人工智能安全与治理研究院院长

· 人工智能安全与超级对齐北京市重点实验室主任

· 中国人工智能学会（CAAI）心智计算专委会主任

· 世界互联网大会(WIC)人工智能专委会主任委员

· 联合国人工智能高层顾问机构专家 (UN Advisory Body on AI)

· 联合国教科文组织人工智能伦理特设专家组专家(UNESCO Adhoc Expert Group on AI Ethics)

· 国家新一代人工智能治理专委会委员

· 国家科技伦理委员会人工智能分委会委员

· 国家人工智能标准化总体组人工智能治理专题组联合组长

· 北京市人工智能战略咨询专家委员会委员

AI伦理安全治理:

· Feifei Zhao, Hui Feng, Haibo Tong, Zhengqiang Han, Erliang Lin, Enmeng Lu, Yinqian Sun, Yi Zeng: Building Altruistic and Moral AI Agent With Brain-Inspired Emotional Empathy Mechanisms. IEEE Transactions on Affective Computing. 17(1): 559-574, 2026.

· Guobin Shen, Dongcheng Zhao, Haibo Tong, Jindong Li, Feifei Zhao, Yi Zeng. Safety Instincts: LLMs Learn to Trust Their Internal Compass for Self-Defense. Proceedings of the 14th International Conference on Learning Representations (ICLR), 2026.

· Guobin Shen, Dongcheng Zhao, Yiting Dong, Xiang He, Yi Zeng. Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models. International Conference on Learning Representations (ICLR), 2025.

· Guobin Shen, Dongcheng Zhao, Aorigele Bao, Xiang He, Yiting Dong, Yi Zeng. StressPrompt: Does Stress Impact Large Language Models and Human Performance Similarly?. AAAI Conference on Artificial Intelligence (AAAI), 2025.

· Haibo Tong, Zeyang Yue, Feifei Zhao, Erliang Lin, Lu Jia, Ruolin Chen, Yinqian Sun, Qian Zhang, Yi Zeng. CogToM: A Comprehensive Theory of Mind Benchmark inspired by Human Cognition for Large Language Models, ACL, 2026.

· Yuwei Wang, Enmeng Lu, Zizhe Ruan, Yao Liang, Yi Zeng. Stream: Social data and knowledge collective intelligence platform for TRaining Ethical AI Models. AI & SOCIETY, 2024: 1-9.

· Aorigele Bao, Yi Zeng. Understanding the dilemma of explainable artificial intelligence: a proposal for a ritual dialog framework. Humanities and Social Sciences Communications, Nature Press, 11.1 (2024): 1-9.

· Aorigele Bao, Yi Zeng. Embracing grief in the age of deathbots: a temporary tool, not a permanent solution. Ethics and Information Technology, 2024, 26(1): 7.

· Yi Zeng, Enmeng Lu, Kang Sun. Principles on symbiosis for natural life and living artificial intelligence. AI and Ethics, 2023.

· Aorigele Bao, Yi Zeng, Enmeng Lu. Mitigating emotional risks in human-social robot interactions through virtual interactive environment indication. Humanities and Social Sciences Communications, Nature Press, 2023.

· Yi Zeng, Kang Sun, Enmeng Lu. Declaration on the Ethics of Brain-Computer Interfaces and Augment Intelligence. AI and Ethics, Springer, 2021.

类脑人工智能：

· Xiang He, Dongcheng Zhao, Yang Li, Qingqun Kong, Xin Yang, Yi Zeng. Incorporating brain-inspired mechanisms for multimodal learning in artificial intelligence, Science Advances, accepted, 2026.

· Yinqian Sun, Feifei Zhao, Mingyang Lv, Yi Zeng. Spiking World Model with Multi-Compartment Neurons for Model-based Reinforcement Learning, . Proceedings of the National Academy of Sciences (PNAS), 122 (50) e2513319122, 2025.

· Guobin Shen, Dongcheng Zhao, Yiting Dong, Yi Zeng. Brain-inspired neural circuit evolution for spiking neural networks. Proceedings of the National Academy of Sciences (PNAS), 120 (39) e2218173120, 2023.

· Bing Han, Feifei Zhao, Yi Zeng, Guobin Shen. Developmental Plasticity-inspired Adaptive Pruning for Deep Spiking and Artificial Neural Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2024.

· Tenglong Li, Jindong Li, Guobin Shen, Dongcheng Zhao, Qian Zhang, Yi Zeng. FireFly-T: High-Throughput Sparsity Exploitation for Spiking Transformer Acceleration with Dual-Engine Overlay Architecture, IEEE Transactions on Computers, 2026.

· Shen Guobin, Li Jindong, Li Tenglong, Zhao Dongcheng, Zeng Yi. SpikePack: Enhanced Information Flow in Spiking Neural Networks with High Hardware Compatibility. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2025.

· Jihang Wang, Dongcheng Zhao, Chengcheng Du, Xiang He, Qian Zhang, Yi Zeng. Random heterogeneous spiking neural network for adversarial defense. iScience, Cell Press, 2025.

· Yonghao Yu, Dongcheng Zhao, Guobin Shen, Yiting Dong, Yi Zeng. Brain-Inspired Stepwise Patch Merging for Vision Transformers. IJCAI, 2025.

· Wenxuan Pan, Feifei Zhao, Guobin Shen, Bing Han, Yi Zeng. Brain-Inspired Multi-Scale Evolutionary Neural Architecture Search for Deep Spiking Neural Networks. IEEE Transactions on Evolutionary Computation, 2024.

· Ilana Witten, Daniel L.K. Yamins, Claudia Clopath, Matthias Bethge, Yi Zeng, Ann Kennedy, Abeba Birhane, Doris Tsao, Been Kim, Ila Fiete. Future views on neuroscience and AI. Cell, 2024.

· Li Tenglong, Li Jindong, Shen Guobin, Zhao Dongcheng, Zhang Qian, Zeng Yi. FireFly-S: Exploiting Dual-Side Sparsity for Spiking Neural Networks Acceleration with Reconfigurable Spatial Architecture. IEEE Transactions on Circuits and Systems I: Regular Papers (TCAS-I), 2024.

· Xiang He, Dongcheng Zhao, Yang Li, Guobin Shen, Qingqun Kong, Yi Zeng. An Efficient Knowledge Transfer Strategy for Spiking Neural Networks from Static to Event Domain. AAAI, 2024.

· Guobin Shen, Dongcheng Zhao, Tenglong Li, Jindong Li, Yi Zeng. Are Conventional SNNs Really Efficient? A Perspective from Network Quantization. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.

· Jindong Li, Tenglong Li, Guobin Shen, Dongcheng Zhao, Qian Zhang, Yi Zeng. Revealing Untapped DSP Optimization Potentials for FPGA-Based Systolic Matrix Engines. 34th International Conference on Field-Programmable Logic and Applications, 2024.

· Sicheng Shen, Dongcheng Zhao, Guobin Shen, Yi Zeng. TIM: An Efficient Temporal Interaction Module for Spiking Transformer. IJCAI, 2024.

· Yiting Dong, Yang Li, Dongcheng Zhao, Guobin Shen, Yi Zeng. Bullying10K: A Large-Scale Neuromorphic Dataset towards Privacy-Preserving Bullying Recognition. Advances in Neural Information Processing Systems (NeuRIPS), 2024, 36.

· Wenxuan Pan, Feifei Zhao, Bing Han, Yiting Dong, Yi Zeng. Emergence of brain-inspired small-world spiking neural network through neuroevolution. iScience, Cell Press, 2024.

· Yi Zeng, Dongcheng Zhao, Feifei Zhao, Guobin Shen, Yiting Dong, Enmeng Lu, Qian Zhang, Yinqian Sun, Qian Liang, Yuxuan Zhao, Zhuoya Zhao, Hongjian Fang, Yuwei Wang, Yang Li, Xin Liu, Chengcheng Du, Qingqun Kong, Zizhe Ruan, Weida Bi. BrainCog: A Spiking Neural Network based Brain-inspired Cognitive Intelligence Engine for Brain-inspired AI and Brain Simulation. Patterns, Cell Press, 2023.

· Yang Li, Yiting Dong, Dongcheng Zhao, Yi Zeng. N-Omniglot: a Large-scale Neuromorphic Dataset for Spatio-temporal Sparse Few-shot Learning. Scientific Data, 9(746), Nature Publishing Group, 2022.

邮箱：yi.zeng (@)ruc.edu.cn