Hello👋! I am Zijian Zhou (周仔谏), a Ph.D. student in the School of Computer Science and Engineering at the University of Electronic Science and Technology of China (UESTC), Chengdu, China, starting from Spring 2026. I am advised by Prof. Malu Zhang (张马路). Currently, I am also participating in a joint Ph.D. program at the Shenzhen Loop Area Institute.

My research interests broadly encompass Multimodal Large Language Models, Brain-inspired Computing, Spiking Neural Networks, Model Compression, etc. I have published papers in leading AI conferences and journals, including ICML, ICLR, NeurIPS, AAAI, and IJCAI. My Google Scholar citation record is available here .

Telegram/Wechat: (+86) 13032875612. Please feel free to reach out to me.

📖 Educations

• 2020.09 - 2024.06, B.Eng. in Artificial Intelligence (School of Computer Science and Engineering, University of Electronic Science and Technology of China)
• 2024.09 - 2026.03, M.Eng. in Computer Technology (School of Computer Science and Engineering, University of Electronic Science and Technology of China)
• 2026.03 - 2029.06 (Expected), Ph.D. Student in Computer Science and Technology (School of Computer Science and Engineering, University of Electronic Science and Technology of China)

🎖 Honors and Awards

• 2021.12 National Scholarship (国家奖学金)
• 2022.12 National Scholarship (国家奖学金)
• 2023.12 National Scholarship (国家奖学金)
• 2025.12 National Scholarship (国家奖学金)
• 2024.3 Outstanding Graduate of Sichuan Province (四川省优秀大学毕业生)
• 2023.5 Outstanding Winner and Leonhard Euler Award in the Interdisciplinary Contest in Modeling (美国大学生数学建模竞赛O奖)

💻 Internships

• 2025.12 - Current, ModelBest. Multimodal Group, Basic Modeling Department. Research aims to improve the grounding and counting capabilities of Multimodal Large Language Models.

💬 Academic Services

• Conference Reviewer: NeurIPS 2025, AAAI 2026, ICLR 2026, ICML 2026 (Gold Reviewer Award), NeurIPS 2026, etc.
• Journal Reviewer: Transactions on Machine Learning Research, IEEE Transactions on Cognitive and Developmental Systems, etc.

📝 Publications

First Author

ICML 2026

SmoothSpike: Spiking Transformer with Learnable Hadamard Transformation

Zijian Zhou, Wenjie Wei, Yu Liang, Jialin Li, Ammar Belatreche, Honglin Cao, Shuai Wang, Malu Zhang, Yang Yang, Haizhou Li

• SmoothSpike enhances the representational capacity of spiking transformers by suppressing spike saturation with a learnable Hadamard transformation.

• 

ICML 2026

Positional Encoding for Spiking Transformers

Zijian Zhou, Yu Liang, Honglin Cao, Ammar Belatreche, Jieyuan Zhang, Wenjie Wei, Shuai Wang, Malu Zhang, Yang Yang, Haizhou Li

• This work introduces Spiking Positional Encoding with a PE-LIF neuron layer, embedding positional information into neuron thresholds while preserving spike-driven computation.

• 

ICML 2026

AdaS: Adaptive Gradient Descent for Spiking Transformers

Zijian Zhou, Honglin Cao, Ammar Belatreche, Wenjie Wei, Yimeng Shan, Yu Liang, Yu Yang, Shuai Wang, Yalan Ye, Malu Zhang, Yang Yang, Haizhou Li

• AdaS analyzes noisy surrogate-gradient updates in spiking transformers and adaptively controls update-direction noise to improve training stability and performance.

• 

IJCAI 2025

Binary Event-Driven Spiking Transformer

Honglin Cao*, Zijian Zhou*, Wenjie Wei, Ammar Belatreche, Yu Liang, Dehao Zhang, Malu Zhang, Yang Yang, Haizhou Li

• BESTformer integrates binarization into event-driven spiking transformers for compact and efficient neuromorphic vision models.

• |

Co-Author

• Spike-based Neuromorphic Model for Sound Source Localization.
  Dehao Zhang, Shuai Wang, Ammar Belatreche, Wenjie Wei, Yichen Xiao, Haorui Zheng, Zijian Zhou, Malu Zhang, Yang Yang

• Towards Accurate Binary Spiking Neural Networks: Learning with Adaptive Gradient Modulation Mechanism.
  Yu Liang, Wenjie Wei, Ammar Belatreche, Honglin Cao, Zijian Zhou, Shuai Wang, Malu Zhang, Yang Yang

• QP-SNN: Quantized and Pruned Spiking Neural Networks.
  Wenjie Wei, Malu Zhang, Zijian Zhou, Ammar Belatreche, Yimeng Shan, Yu Liang, Honglin Cao, Jieyuan Zhang, Yang Yang

• Toward Energy-Efficient Spike-Based Deep Reinforcement Learning With Temporal Coding.
  Malu Zhang, Shuai Wang, Jibin Wu, Wenjie Wei, Dehao Zhang, Zijian Zhou, Siying Wang, Fan Zhang, Yang Yang

• Spike-Driven Lightweight Large Language Model With Evolutionary Computation.
  Malu Zhang, Wenjie Wei, Zijian Zhou, Wanlong Liu, Jie Zhang, Ammar Belatreche, Yang Yang

• Towards Training-Free and Accurate ANN-to-SNN Conversion via Activation-Aware Redistribution.
  Honglin Cao, Shuai Wang, Zijian Zhou, Ammar Belatreche, Wenjie Wei, Yu Liang, Yu Yang, Rui Xi, Malu Zhang, Haizhou Li

• TP-Spikformer: Token Pruned Spiking Transformer.
  Wenjie Wei, Xiaolong Zhou, Malu Zhang, Ammar Belatreche, Qian Sun, Yimeng Shan, Dehao Zhang, Zijian Zhou, Zeyu Ma, Yang Yang, Haizhou Li

• Robust Spiking Neural Networks Against Adversarial Attacks.
  Shuai Wang, Malu Zhang, Yulin Jiang, Dehao Zhang, Ammar Belatreche, Yu Liang, Yimeng Shan, Zijian Zhou, Yang Yang, Haizhou Li

• Towards Efficient Spiking Neural Networks: A Reliable Structured Pruning Criterion.
  Hanwen Liu, Zijian Zhou, Kexin Shi, Wenjie Wei, Wenyu Chen, Jibin Wu, Malu Zhang, Yang Yang

• SpikingLM: Towards Fully Spiking Language Model.
  Yu Liang, Zijian Zhou, Wenjie Wei, Shuai Wang, Honglin Cao, Ammar Belatreche, Yu Yang, Malu Zhang, Yang Yang, Haizhou Li