Xu Mingkun
Ph.D., Postdoctoral Researcher
Email：xumingkun@gdiist.cn
Biography:
Dr. Xu Mingkun graduated with a bachelor's degree in Measurement and Control Technology from Xidian University in 2018. In 2023, he earned his Ph.D. in Engineering from Tsinghua University, specializing in Brain-Inspired Computing at the Center for Brain-inspired Computing Research.
Research Achievements:
Dr. Xu has primarily published his research findings in prestigious journals such as Nature Communications, Neural Networks, ACS Applied Materials & Interfaces.
Research Focus:
During his doctoral studies, Dr. Xu focused on the algorithm design and applications of spiking neural networks. After joining the Guangdong Institute of Intelligent Technology, his research shifted towards the study of spiking neural networks and neuromorphic graph computing models for cognitive reasoning. By incorporating neuroscience and cognition science-guided inductive biases, he enabled networks to learn structured knowledge and symbolic representations from data. This research delves into hierarchical spatiotemporal dynamics, distributed information integration, flexible compositional generalization, and aims to provide a technological foundation for advanced cognitive intelligence tasks such as causal reasoning, planning, and decision-making.
Representative Publications:
1. Zhong S *, Zhou J C, Yu F W, Xu M, Zhang Y S*, Yu B, Zhao R*. An Optical Neuromorphic Sensor with High Uniformity and High Linearity for Indoor Visible Light Localization. Advanced Sensor Research. (2024)
a2. Xu M, Liu F Q, Hu Y F, Li H Y, Wei Y Y, Zhong S, Pei J and Deng L. Adaptive Synaptic Scaling in Spiking Networks for Continual Learning and Enhanced Robustness[J]. IEEE Transactions on Neural Networks and Learning Systems. (Accepted in 2024.2.25)
3. Xu M*. Exploiting homeostatic synaptic modulation in spiking neural networks for semi-supervised graph learning[C]. Proceedings of the 32nd ACM International Conference on Information and Knowledge Management. 5193-5195. (2023)
4. Yu F, Wu Y, Ma S, Xu M, et al. Brain-inspired multimodal hybrid neural network for robot place recognition[J]. Science Robotics, 8(78): eabm6996. (2023)
5. Li H, Xu M, Pei J, et al. Efficient GCN Deployment with Spiking Property on Spatial-Temporal Neuromorphic Chips[C]. Proceedings of the 2023 International Conference on Neuromorphic Systems. 1-8. (2023)
6. Xu M, Zheng H, Pei J, et al. A Unified Structured Framework for AGI: Bridging Cognition and Neuromorphic Computing[C]. International Conference on Artificial General Intelligence. Cham: Springer Nature Switzerland, 345-356. (2023)
7. Ran X, Xu M (Co-first author), Mei L, et al. Detecting out-of-distribution samples via variational auto-encoder with reliable uncertainty estimation[J]. Neural Networks, 145: 199-208. (2022)
8. Xu M, Liu F, Pei J. Endowing spiking neural networks with homeostatic adaptivity for APS-DVS bimodal scenarios[C]. Companion Publication of the 2022 International Conference on Multimodal Interaction. 12-17. (2022)
9. Liu F, Xu M (Co-first author), Li G, et al. Adversarial symmetric GANs: Bridging adversarial samples and adversarial networks[J]. Neural Networks, 133: 148-156. (2021)
10. Xu M, Wu Y, Deng L, Liu F, Li G and Pei J. Exploiting spiking dynamics with spatial-temporal feature normalization in graph learning. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence (IJCAI-21), pages 3207-3213, 2021.
11. Yang Y, Xu M (Co-first author), Jia S, Wang B, et al. A new opportunity for the emerging tellurium semiconductor: making resistive switching devices[J]. Nature communications, 2021, 12(1): 1-12.
12. Wu Y, Zhao R, Zhu J, Chen F, Xu M (Co-first author), Li G, et al. Brain-inspired global-local learning incorporated with neuromorphic computing[J]. Nature Communications, 2022, 13(1): 1-14.
