Short Bio

Dr. Yujie Wu is an Assistant Professor at The Hong Kong Polytechnic University (PolyU). Prior to this, he was a postdoctoral researcher collaborating with Prof. Wolfgang Maass, a pioneer in brain-inspired computing, at Graz University of Technology (2021–2024). He received his Ph.D. from Tsinghua University under the supervision of Prof. Luping Shi and Prof. Jun Zhu (2016-2021). His recent works have been published in prestigious journals and top AI conferences, including Nature, Science Robotics, Nature Computational Science, Nature Communications, TNNLs and AAAI. Three of his publications have been selected as ESI Top 1% Highly Cited Papers. The Tianjic chip project he participated in was recognized as one of the Top 10 Sci-tech Achievements in China in 2019.

Opening

I am looking for highly self-motivated PhD students, PostDocs, and Research Assistants. If you are interested, please send me your CV. Thanks! (All CVs are carefully evaluated. Only matched candidates will be responded within one week.)

Research Interests

I aim to uncover the computational principles of the brain and bridge the gap between neuroscience and AI to develop Brain-inspired General Intelligence (BGI). My recent research interests include:
  • Brain-inspired learning algorithms and foundation models;
  • Neuromorphic computing and spiking neural networks;
  • Computational neuroscience models for memory and synaptic plasticity;
  • Bioinspired robot applications;

Selected Ten Publications (updated as of December 2024)

  1. Y. Wu, W. Maass. “A simple model for Behavioral Time Scale Synaptic Plasticity (BTSP) provides content addressable memory with binary synapses and one-shot learning.” Nature Communications, 2025. (Featured paper)

  2. Y. Wu, L. Deng, et al. “Adaptive spatiotemporal neural networks through complementary hybridization.” Nature Communications, 2024, 15(1): 7355. (Featured paper)

  3. F. Yu# Y. Wu# (#Equal Contribution), M. Song#, et al. “Brain-inspired multimodal hybrid neural network for robot place recognition”, Science Robotics, May 2023. (Cover paper)

  4. Y. Wu, R. Zhao, J. Zhu, et al. “Brain-inspired global-local learning incorporated with neuromorphic computing.” Nature Communications, 2022, 13(1): 1-14.

  5. R. Zhao#, Y. Zhe#, H. Zheng#, Y. Wu#, et al. “A framework for the general design and computation of hybrid neural networks.” Nature Communications, 2022.

  6. Y. Wu, L. Deng, G. Li, et al. “Direct training for spiking neural networks: faster, larger, better.” In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2019, 33: 1311-1318. (Spotlight)

  7. Y. Wu, L. Deng, G. Li, et al. “Spatio-temporal backpropagation for training high-performance spiking neural networks.” Frontiers in Neuroscience, 2018, 12: 331. (ESI Top 1% Highly Cited Paper)

  8. Z. Zhang#, T. Li#, Y. Wu#, et al. “Truly concomitant and independently expressed short- and long-term plasticity in a Bi₂O₂Se-based three-terminal memristor.” Advanced Materials, 2019, 31(3): 1805769. (Impact Factor: 30.2)

  9. J. Pei, …, Y. Wu, et al. “Towards artificial general intelligence with hybrid Tianjic chip architecture.” Nature, 2019, 572(7767): 106-111. (Cover paper)

  10. L. He, Y. Xu, W. He, Y. Lin, Y. Tian, Y. Wu, et al. “Network model with internal complexity bridges artificial intelligence and neuroscience.” Nature Computational Science, 2024, 4: 8 (Cover runner-up).

Service Activities

  • Guest Editor for Nature Computational Science
  • Guest Editor for IEEE Transactions on Cognitive and Developmental Systems
  • Associate Editor for CIS-RAM 2024
  • Technical Chair for PRSC 2024
  • Program Committee Member for AAAI 2025
  • Technical Program Committee Member for IEEE GlobCon series

Selected Talks

  • December 2024, Hangzhou, China. Plasticity Models for Hippocampal One-shot online learning, China Brain-Machine Intelligence Conference
  • November 2024, Yunnan, China. Brain-Inspired Hybrid Intelligence, International Youth Forum on Brain and Intelligence
  • October 2024, Xiamen, China. Brain-Inspired Hybrid Intelligence, Nanqiang Forum, Xiamen University
  • July 2024, Salzburg, Austria. One-Shot Learning and Robust Recall with BTSP, Graz University of Technology
  • January 2024, Hong Kong, China. Brain-Inspired Hybrid Global-Local Learning Methods, The Hong Kong Polytechnic University
  • May 2023, Beijing, China. Exploring brain-inspired local and local-global learning with neuromorphic computing, Institute of Automation, Chinese Academy of Sciences