Dongcheng Zhao
I am now the Assistant Professor at BrainCog Lab. I currently focus on Brain inspired LLM, Brain inspired Super Safe Alignment, Spiking Neural Networks, Event Based Vision, etc. Before that, I did my PhD at Institute of Automation, Chinese Academy of Sciences, where I was advised by Prof. Yi Zeng. I did my bachelors at school of mathematics and statistics, Xidian University.
I currently serve as a reviewer for several leading conferences and journals, including IJCAI, NeurIPS, ICLR, Neural Networks, Neurocomputing, Pattern Recognition and IEEE TNNLS, TIP, TETCI.
Email  / 
Google Scholar  / 
Zhi Hu  / 
DBLP
News
12/2024, Two Papers have been accepted by AAAI 2025.
11/2024, Two Papers have been accepted by DATE 2025
11/2024, 2023 Cell Press China Paper of the Year Award (in interdisciplinary science category)
11/2024, Our paper has been accepted by TCAS-I Regular Papers.
10/2024, Our paper has been accepted by Pattern Recognition.
09/2024, Our paper has been accepted by NeurlPS.
07/2024, Our paper has been accepted by ACM MM.
06/2024, Our paper has been accepted by Neural Networks.
05/2024, Our paper has been accepted by FPL.
05/2024, Our paper has been accepted by Neural Networks.
04/2024, Our paper has been accepted by IJCAI.
03/2024, Our paper has been accepted by TCAD 2024.
02/2024, Our paper has been accepted by CVPR.
Recent Projects
Recently, I mainly focus on the development of BrainCog and Born.
BrainCog
Project Page | Paper
BrainCog is accepted by Patterns! Brain-inspired Cognitive Intelligence Engine (BrainCog) is a brain-inspired neural network based platform for realizing Brain-inspired Artificial Intelligence, and simulating the cognitive brains of different animal species at multiple scales. The ultimate goal and long term efforts of BrainCog is to provide a comprehensive theory and systems to decode the mechanisms and principles of human intelligence and its evolution, and develop artificial brains for brain-inspired conscious living becomings for the future human-AI symbiotic society.
BORN
Project Page
BORN is an Artificial Intelligence Engine based on Brain-inspired Spiking Neural Networks. The ultimate vision of BORN is to achieve living Artificial General Intelligence, as a new type of evolutionary becoming, and as a moral member of the future symbiotic society. The near term goal of BORN is a self enabled learning AI powered by spiking neural networks that can coordinate various cognitive functions in a self organized way to solve complex problems. BORN is powered by BrainCog, the Brain-inspired Cognitive Intelligence Engine.
Publications
I'm interested in devleoping biologically plausible Spiking Neural Networks with high performance for image recognition, tracking and robot control, etc.
Preprint
- Yiting Dong, Guobin Shen, Dongcheng Zhao, Xiang He, Yi Zeng. Harnessing Task Overload for Scalable Jailbreak Attacks on Large Language Models. arXiv:2410.04190, 2024.
- Guobin Shen, Dongcheng Zhao, Aorigele Bao, Xiang He, Yiting Dong, Yi Zeng. Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models. arXiv:2410.02298, 2024.
- Yonghao Yu, Dongcheng Zhao, Guobin Shen, Yiting Dong, Yi Zeng. Brain-Inspired Stepwise Patch Merging for Vision Transformers. arXiv:2409.06963, 2024.
- Linghao Feng, Dongcheng Zhao, Sicheng Shen, Yiting Dong, Guobin Shen, Yi Zeng. Time Cell Inspired Temporal Codebook in Spiking Neural Networks for Enhanced Image Generation. arXiv:2405.14474, 2024. Co-First Author
- Guobin Shen, Dongcheng Zhao, Yiting Dong, Yang Li, Jindong Li, Yi Zeng. Astrocyte-Enabled Advancements in Spiking Neural Networks for Large Language Modeling. arXiv:2312.07625, 2023. Co-First Author
- Guobin Shen, Dongcheng Zhao, Yiting Dong, Yang Li, Feifei Zhao, Yi Zeng. Metaplasticity: Unifying Learning and Homeostatic Plasticity in Spiking Neural Networks. arXiv:2308.12063, 2023. Co-First Author
- Guobin Shen, Dongcheng Zhao, Yiting Dong, Yang Li, Yi Zeng. Dive into the Power of Neuronal Heterogeneity. arXiv:2305.11484, 2023.
- Guobin Shen, Dongcheng Zhao, Yi Zeng. Exploiting High Performance Spiking Neural Networks with Efficient Spiking Patterns. arXiv:2301.12356, 2023. Co-First Author
- Jihang Wang, Dongcheng Zhao, Guobin Shen, Qian Zhang, Yi Zeng. DPSNN: A Differentially Private Spiking Neural Network with Temporal Enhanced Pooling. arXiv:2205.12718, 2022. Co-First Author
Publications
- Guobin Shen, Dongcheng Zhao, Aorigele Bao, Xiang He, Yiting Dong, Yi Zeng. StressPrompt: Does Stress Impact Large Language Models and Human Performance Similarly?. AAAI, 2025. Co-First Author
- Yiting Dong, Xiang He, Guobin Shen, Dongcheng Zhao, Yang Li, Yi Zeng. EventZoom: A Progressive Approach to Event-Based Data Augmentation for Enhanced Neuromorphic Vision. AAAI, 2025.
- Tenglong Li, Jindong Li, Guobin Shen, Dongcheng Zhao, Qian Zhang, Yi Zeng. 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.
- Dongcheng Zhao, Guobin Shen, Yiting Dong, Yang Li, Yi Zeng. Improving Stability and Performance of Spiking Neural Networks through Enhancing Temporal Consistency. Pattern Recognition, 2024.
- Guobin Shen, Dongcheng Zhao, Xiang He, Linghao Feng, Yiting Dong, Jihang Wang, Qian Zhang, Yi Zeng. Neuro-Vision to Language: Enhancing Visual Reconstruction and Language Interaction through Brain Recordings. NeurlPS, 2024
- Xiang He, Xiangxi Liu, Yang Li, Dongcheng Zhao, Guobin Shen, Qingqun Kong, Xin Yang, Yi Zeng. CACE-Net: Co-guidance Attention and Contrastive Enhancement for Effective Audio-Visual Event Localization. ACM MM, 2024
- Yang Li, Feifei Zhao, Dongcheng Zhao, Yi Zeng. Directly training temporal Spiking Neural Network with sparse surrogate gradient. Neural Networks 2024.
- Jindong Li, Tenglong Li, Guobin Shen, Dongcheng Zhao, Qian Zhang, Yi Zeng. Revealing Untapped DSP Optimization Potentials for FPGA-Based Systolic Matrix Engines. FPL, 2024
- Linghao Feng, Dongcheng Zhao, Yi Zeng. Spiking generative adversarial network with attention scoring decoding. Neural Networks 2024.
- Sicheng Shen, Dongcheng Zhao, Guobin Shen, Yi Zeng. TIM: An Efficient Temporal Interaction Module for Spiking Transformer. IJCAI, 2024. Co-First Author
- Yang Li, Yinqian Sun, Xiang He, Yiting Dong, Dongcheng Zhao, Yi Zeng. Efficient Training Spiking Neural Networks with Parallel Spiking Unit. IJCNN, 2024.
- Jindong Li, Guobin Shen, Dongcheng Zhao, Qian Zhang, Yi Zeng. 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
- Yiting Dong, Dongcheng Zhao, Yi Zeng. Temporal Knowledge Sharing enable Spiking Neural Network Learning from Past and Future. IEEE Transactions on Artificial Intelligence, 2024. Co-First Author
- Guobin Shen, Dongcheng Zhao, Tenglong Li, Jindong Li, Yi Zeng. Are Conventional SNNs Really Efficient? A Perspective from Network Quantization. CVPR, 2024.
- Xiang He, Yang Li, Dongcheng Zhao, Qingqun Kong, Yi Zeng. MSAT: biologically inspired multistage adaptive threshold for conversion of spiking neural networks. Neural Computing and Applications, 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, Oral, Co-First Author
- Guobin Shen, Dongcheng Zhao, Sicheng Shen, Yi Zeng. Enhancing Spiking Neural Networks with Binary Attention Mechanisms. ICLR Tiny Paper, 2024.
- Guobin Shen, Dongcheng Zhao, Yi Zeng. Exploiting nonlinear dendritic adaptive computation in training deep Spiking Neural Networks. Neural Networks, 2023. Co-First Author
- Yiting Dong, Yang Li, Dongcheng Zhao, Guobin Shen, Yi Zeng. Bullying10K: A Large-Scale Neuromorphic Dataset towards Privacy-Preserving Bullying Recognition. NeurlPS, 2023. Co-First Author
- Guobin Shen, Dongcheng Zhao, Yiting Dong, Yi Zeng Brain-inspired neural circuit evolution for spiking neural networks. PNAS, 2023 Co-First Author
- 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 Co-First Author
- Yiting Dong, Dongcheng Zhao, Yi Zeng. An unsupervised STDP-based spiking neural network inspired by biologically plausible learning rules and connections. Neural Networks, 2023. Co-First Author
- Jindong Li, Guobin Shen, Dongcheng Zhao, Qian Zhang, Yi Zeng. 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, 2023
- Guobin Shen, Dongcheng Zhao, Yi Zeng. EventMix: An efficient data augmentation strategy for event-based learning. Information Sciences, 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. Co-First Author
- Yang Li, Dongcheng Zhao, and Yi Zeng. BSNN: Towards Faster and Better Conversion of Artificial Neural Networks to Spiking Neural Networks with Bistable Neurons. Frontiers in Neuroscience, 2022.
- Dongcheng Zhao, Yi Zeng, Yang Li, Jihang Wang, Qian Zhang. Spiking CapsNet: A spiking neural network with a biologically plausible routing rule between capsules. Information Sciences, 2022.
- Dongcheng Zhao, Yi Zeng, Yang Li. BackEISNN: A Deep Spiking Neural Network with Adaptive Self-Feedback and Balanced Excitatory-Inhibitory Neurons. Neural Networks, 2022.
- Guobin Shen, Dongcheng Zhao, Yi Zeng. Backpropagation with biologically plausible spatiotemporal adjustment for training deep spiking neural networks. Patterns, Cell Press, 2022. Co-First Author
- Dongcheng Zhao, Yi Zeng, Tielin Zhang, Mengting Shi, Feifei Zhao. GLSNN: A Multi-Layer Spiking Neural Network Based on Global Feedback Alignment and Local STDP Plasticity. Frontiers in Computational Neuroscience, 2020.
- Yi Zeng, Yuxuan Zhao, Tielin Zhang, Dongcheng Zhao, Feifei Zhao, Enmeng Zhao. A Brain-Inspired Model of Theory of Mind. Frontiers in Neurorobotics, 2020.
Welcome to use this website's
source code, just add a link back to here.
✩.