I am currently a Ph.D. student in the School of Biomedical Engineering at Tsinghua University, under the supervision of Prof. Sen Song.

I received my bachelor’s degree in Computer Science and Technology from the College of Computer Science and Technology, Zhejiang University, under the supervision of Prof. Qian Zheng and Prof. Zhengxing Huang.

My research interests include AI for neuroscience, EEG decoding, and deep learning.

🔥 News

• 2026.04:  🎉 Our paper “Training-Driven Representational Geometry Modularization Predicts Brain Alignment in Language Models” is accepted by CogSci 2026 (Oral)!
• 2025.07:  🎉 Our paper “Reward-optimizing learning using stochastic release plasticity” is accepted by Frontiers in Neural Circuits!

📝 Publications

Preprint 2026

Rethinking EEG-Based Disease Diagnosis: Decoupling Instance Representation Learning from Subject-Level Supervision

Zhiyuan Ma^#, Zeyuan Li^#, Zhiyi Lu^#, Jiacheng Hao, Youlang Du, Zhen Jiang, Xinche Zhang, Yuhao Sun, Xinke Shen^†, Sen Song^†

• We identify a two-sided supervision problem in subject-level EEG disease diagnosis.
• We propose BridgeMIL, which decouples instance representation learning from subject-level supervision.
• Across three datasets and five backbones, BridgeMIL ranks first in 14 of 15 settings and improves mean accuracy by 4.28 percentage points.

Preprint 2026

DSAINet: An Efficient Dual-Scale Attentive Interaction Network for General EEG Decoding

Zhiyuan Ma^#, Zeyuan Li^#, Zihao Qiu^#, Jinhao Li, Lingqin Meng, Xinche Zhang, Yixuan Liu, Xinke Shen^†, Sen Song^†

• We propose DSAINet, an efficient dual-scale attentive interaction network for general EEG decoding.
• Comprehensive experiments across five EEG decoding tasks and ten public datasets show that DSAINet consistently outperforms 13 representative baselines under subject-independent evaluation, while maintaining the same architecture and architecture-related hyperparameters across datasets.

• arXiv 2026 EEG-JEPA: Structured Latent Prediction for EEG Foundation Models, Jinhao Li^#, Zhiyuan Ma^#, Xueqiao Han^#, Zhongye Xia, Xinche Zhang, Shanghong Xie, Yixuan Liu, Yongjian Li, Runmin Gan, Tianlin Huo^†, Sen Song^†
• arXiv 2026 LI-DSN: A Layer-wise Interactive Dual-Stream Network for EEG Decoding, Chenghao Yue^#, Zhiyuan Ma^#, Zhongye Xia, Xinche Zhang, Yisi Zhang^†, Xinke Shen^†, Sen Song^†
• arXiv 2026 Signal-Adaptive Trust Regions for Gradient-Free Optimization of Recurrent Spiking Neural Networks, Jinhao Li^#, Yuhao Sun^#, Zhiyuan Ma, Hao He, Xinche Zhang, Xing Chen, Jin Li^†, Sen Song^†
• CogSci 2026 Training-Driven Representational Geometry Modularization Predicts Brain Alignment in Language Models, Yixuan Liu^#, Zhiyuan Ma^#, Likai Tang, Runmin Gan, Xinche Zhang, Jinhao Li, Chao Xie^†, Sen Song^†
• Frontiers in Neural Circuits 2025 Reward-optimizing learning using stochastic release plasticity, Yuhao Sun^#, Wantong Liao^#, Jinhao Li^#, Xinche Zhang^#, Guan Wang, Zhiyuan Ma, Sen Song^†

^† denotes corresponding author and ^# denotes equal contribution.

🏆 Awards

• 2025.5, Outstanding Undergraduate Thesis, Zhejiang University.

📖 Educations

• 2025.08 - now, Ph.D. Student, Biomedical Engineering, Tsinghua University, Beijing, China.
• 2021.08 - 2025.06, Undergraduate, Computer Science and Technology, Zhejiang University, Hangzhou, China.

👨‍🏫 Teaching

• 2026 Fall, Teaching Assistant, Technology Innovation and Challenge 2C, Tsinghua University.
• 2026 Spring, Teaching Assistant, Technology Innovation and Challenge 2C, Tsinghua University.
• 2025 Fall, Teaching Assistant, Technology Innovation and Challenge 2C, Tsinghua University.
• 2024 Fall, Teaching Assistant, Computer Organization, Zhejiang University.
• 2024 Spring, Teaching Assistant, Computer Organization, Zhejiang University.

🌏 Activities

Reviewer

• IEEE Journal of Biomedical and Health Informatics
• IEEE Transactions on Neural Systems and Rehabilitation Engineering
• CogSci