Guobin Shen

Guobin Shen

Institute of Automation, Chinese Academy of Sciences

👻 About Me

Guobin Shen is a fourth-year PhD student at the Institute of Automation, Chinese Academy of Sciences, under the guidance of Prof. Yi Zeng. His research focuses on biologically inspired neural networks, machine learning, and their applications in cognitive science and artificial intelligence. He is particularly interested in integrating brain-inspired models with advanced AI systems, as well as exploring the safety and interpretability of large-scale models to address complex real-world challenges.

You can find his CV here.

His research interests include:

  • Biologically Inspired Neural Networks
  • Cognitive Science and Neuroscience-Inspired AI
  • Mechanistic Interpretability of LLMs
  • Alignment Strategy for LLMs
  • AI Safety

📰 News

  1. Our paper on LLM jailbreak antidote has been accepted by ICLR 2025. See you in Singapore!
  2. Our two papers, StressPrompt on LLM stress analysis and DVS data augmentation, have been accepted by AAAI 2025. See you in Philadelphia!
  3. Our multimodal LLM framework on fMRI, vision, and language has been accepted by NeurIPS 2024. See you in Vancouver!
  4. Our paper on SNN efficiency analysis has been accepted by CVPR 2024 and selected as a highlight paper. See you in Seattle!
  5. Our work on neuro-evolution strategies has been accepted by PNAS. Read more.

📝 Publications

2025

  • Shen, Guobin, Zhao, Dongcheng, Dong, Yiting, He, Xiang, and Zeng, Yi. “Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models.” Proceedings of the 13th International Conference on Learning Representations (ICLR 2025), 2025. 🔗[OpenReview] 📃[PDF]

  • Shen, Guobin, Zhao, Dongcheng, Bao, Aorigele, He, Xiang, Dong, Yiting, and Zeng, Yi. “StressPrompt: Does Stress Impact Large Language Models and Human Performance Similarly?” Proceedings of the 39th AAAI Conference on Artificial Intelligence (AAAI 2025), 2025. 🔗[OpenReview] 📃[PDF]

  • Shen, Guobin, Zhao, Dongcheng, and Zeng, Yi. “Exploiting High-Performance Spiking Neural Networks with Efficient Spiking Patterns.” IEEE Transactions on Emerging Topics in Computational Intelligence (TETCI), 2025.

  • Zhao, Dongcheng, Shen, Guobin, Dong, Yiting, Li, Yang, and Zeng, Yi. “Improving Stability and Performance of Spiking Neural Networks through Enhancing Temporal Consistency.” Pattern Recognition, vol. 159, 2025, p. 111094. Pergamon. 🔗[Arxiv] 📃[PDF]

  • Dong, Yiting, He, Xiang, Shen, Guobin, Zhao, Dongcheng, Li, Yang, and Zeng, Yi. “EventZoom: A Progressive Approach to Event-Based Data Augmentation for Enhanced Neuromorphic Vision.” Proceedings of the 39th AAAI Conference on Artificial Intelligence (AAAI 2025), 2025. 🔗[OpenReview]

2024

  • Shen, Guobin, Zhao, Dongcheng, Li, Tenglong, Li, Jindong, and Zeng, Yi. “Are Conventional SNNs Really Efficient? A Perspective from Network Quantization.” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 27538-27547. 📃[PDF] 🔗[Poster]

  • Shen, Guobin, Zhao, Dongcheng, He, Xiang, Feng, Linghao, Dong, Yiting, Wang, Jihang, Zhang, Qian, and Zeng, Yi. “Neuro-Vision to Language: Image Reconstruction and Interaction via Non-invasive Brain Recordings.” Proceedings of the 38th Conference on Neural Information Processing Systems (NeurIPS 2024), 2024. 📃[PDF] 🔗[Poster]

  • Shen, Guobin, Zhao, Dongcheng, Shen, Sicheng, and Zeng, Yi. “Enhancing Spiking Transformers with Binary Attention Mechanisms.” The Second Tiny Papers Track at ICLR 2024. 📃[PDF]

  • Shen, Guobin, Zhao, Dongcheng, and Zeng, Yi. “Exploiting Nonlinear Dendritic Adaptive Computation in Training Deep Spiking Neural Networks.” Neural Networks, vol. 170, 2024, pp. 190-201. Pergamon. 📃[PDF]

  • Li, Jindong, Shen, Guobin, Zhao, Dongcheng, Zhang, Qian, and Zeng, Yi. “Firefly v2: Advancing Hardware Support for High-Performance Spiking Neural Network with a Spatiotemporal FPGA Accelerator.” IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2024. IEEE. 📃[PDF]

  • Han, Bing, Zhao, Feifei, Zeng, Yi, and Guobin Shen. “Developmental Plasticity-Inspired Adaptive Pruning for Deep Spiking and Artificial Neural Networks.” IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024. IEEE. 📃[PDF]

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

  • Li, Jindong, Li, Tenglong, Shen, Guobin, Zhao, Dongcheng, Zhang, Qian, and Zeng, Yi. “Revealing Untapped DSP Optimization Potentials for FPGA-Based Systolic Matrix Engines.” 2024 34th International Conference on Field-Programmable Logic and Applications (FPL), IEEE, 2024, pp. 197-203. 🔗[Arxiv] 📃[PDF]

  • Li, Tenglong, Li, Jindong, Shen, Guobin, Zhao, Dongcheng, Zhang, Qian, and 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, 2024. IEEE. 📃[PDF]

  • Dong, Yiting, Li, Yang, Zhao, Dongcheng, Shen, Guobin, and Zeng, Yi. “Bullying10K: A Large-Scale Neuromorphic Dataset Towards Privacy-Preserving Bullying Recognition.” Advances in Neural Information Processing Systems, vol. 36, 2024. 📃[PDF] 🔗[Poster]

  • He, Xiang, Liu, Xiangxi, Li, Yang, Zhao, Dongcheng, Shen, Guobin, Kong, Qingqun, Yang, Xin, and Zeng, Yi. “CACE-Net: Co-guidance Attention and Contrastive Enhancement for Effective Audio-Visual Event Localization.” Proceedings of the 32nd ACM International Conference on Multimedia, 2024, pp. 985-993. 🔗[OpenReview] 📃[PDF]

  • Shen, Sicheng, Zhao, Dongcheng, Shen, Guobin, and Zeng, Yi. “TIM: An Efficient Temporal Interaction Module for Spiking Transformer.” Proceedings of the 33rd International Joint Conference on Artificial Intelligence (IJCAI 2024), 2024. 📃[PDF]

  • He, Xiang, Zhao, Dongcheng, Li, Yang, Shen, Guobin, Kong, Qingqun, and Zeng, Yi. “An Efficient Knowledge Transfer Strategy for Spiking Neural Networks from Static to Event Domain.” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, no. 1, 2024, pp. 512-520. 🔗[Arxiv]

2023

  • Shen, Guobin, Zhao, Dongcheng, Dong, Yiting, and Zeng, Yi. “Brain-Inspired Neural Circuit Evolution for Spiking Neural Networks.” Proceedings of the National Academy of Sciences, vol. 120, no. 39, 2023, p. e2218173120. National Academy of Sciences. 📃[PDF]

  • Shen, Guobin, Zhao, Dongcheng, and Zeng, Yi. “EventMix: An Efficient Data Augmentation Strategy for Event-Based Learning.” Information Sciences, vol. 644, 2023, p. 119170. Elsevier. 📃[PDF]

  • Li, Jindong, Shen, Guobin, Zhao, Dongcheng, Zhang, Qian, and Zeng, Yi. “Firefly: A High-Throughput Hardware Accelerator for Spiking Neural Networks with Efficient DSP and Memory Optimization.” IEEE Transactions on Very Large Scale Integration (VLSI) Systems, vol. 31, no. 8, 2023, pp. 1178-1191. IEEE. 📃[PDF]

  • Han, Bing, Zhao, Feifei, Zeng, Yi, Pan, Wenxuan, and Shen, Guobin. “Enhancing Efficient Continual Learning with Dynamic Structure Development of Spiking Neural Networks.” Proceedings of the 32nd International Joint Conference on Artificial Intelligence (IJCAI 2023), 2023. 📃[PDF]

  • Zeng, Yi, Zhao, Dongcheng, Zhao, Feifei, Shen, Guobin, Dong, Yiting, Lu, Enmeng, Zhang, Qian, Sun, Yinqian, Liang, Qian, Zhao, Yuxuan, and others. “BrainCog: A Spiking Neural Network Based, Brain-Inspired Cognitive Intelligence Engine for Brain-Inspired AI and Brain Simulation.” Patterns, 2023, p. 100789. 📃[PDF]

2022

  • Shen, Guobin, Zhao, Dongcheng, and Zeng, Yi. “Backpropagation with Biologically Plausible Spatiotemporal Adjustment for Training Deep Spiking Neural Networks.” Patterns, vol. 3, no. 6, 2022. Elsevier. 📃[PDF]

Preprint

  • Shen, Guobin, Li, Jindong, Li, Tenglong, Zhao, Dongcheng, and Zeng, Yi. “$SpikePack$: Enhanced Information Flow in Spiking Neural Networks with High Hardware Compatibility.” arXiv preprint arXiv:2501.14484, 2025. 🔗[Arxiv]

  • Dong, Yiting, Shen, Guobin, Zhao, Dongcheng, He, Xiang, and Zeng, Yi. “Harnessing Task Overload for Scalable Jailbreak Attacks on Large Language Models.” arXiv preprint arXiv:2410.04190, 2024. 🔗[Arxiv]

  • Yu, Yonghao, Zhao, Dongcheng, Shen, Guobin, Dong, Yiting, and Zeng, Yi. “Brain-Inspired Stepwise Patch Merging for Vision Transformers.” arXiv preprint arXiv:2409.06963, 2024. 🔗[Arxiv]

  • Feng, Linghao, Zhao, Dongcheng, Shen, Sicheng, Dong, Yiting, Shen, Guobin, and Zeng, Yi. “Time Cell Inspired Temporal Codebook in Spiking Neural Networks for Enhanced Image Generation.” arXiv preprint arXiv:2405.14474, 2024. 🔗[Arxiv]

  • Shen, Guobin, Zhao, Dongcheng, Dong, Yiting, Li, Yang, and Zeng, Yi. “Dive into the Power of Neuronal Heterogeneity.” arXiv preprint arXiv:2305.11484, 2023. 🔗[Arxiv]

  • Shen, Guobin, Zhao, Dongcheng, Dong, Yiting, Li, Yang, Zhao, Feifei, and Zeng, Yi. “Learning the Plasticity: Plasticity-Driven Learning Framework in Spiking Neural Networks.” arXiv preprint arXiv:2308.12063, 2023. 🔗[Arxiv]

  • Shen, Guobin, Zhao, Dongcheng, Dong, Yiting, Li, Yang, Li, Jindong, Sun, Kang, and Zeng, Yi. “Astrocyte-Enabled Advancements in Spiking Neural Networks for Large Language Modeling.” arXiv preprint arXiv:2312.07625, 2023. 🔗[Arxiv]

  • He, Xiang, Zhao, Dongcheng, Li, Yang, Shen, Guobin, Kong, Qingqun, and Zeng, Yi. “Improving the Performance of Spiking Neural Networks on Event-Based Datasets with Knowledge Transfer.” arXiv preprint arXiv:2303.13077, 2023. 🔗[Arxiv]

  • Wang, Jihang, Zhao, Dongcheng, Shen, Guobin, Zhang, Qian, and Zeng, Yi. “DPSNN: A Differentially Private Spiking Neural Network with Temporal Enhanced Pooling.” arXiv preprint arXiv:2205.12718, 2022. 🔗[Arxiv]

🎓 Educations

🏅 Honors and Awards

  • 2024.11 National Scholarship (Doctoral Student) Top 1%
  • 2019.11 National Scholarship (Undergraduate) Top 1%
  • 2020.11 National Scholarship (Undergraduate) Top 1%
  • 2019.09 Runner-Up, International Aerial Robotics Competition (Asia-Pacific Region)
  • 2019.09 National Second Prize, National Undergraduate Electronic Design Competition Top 5%