Yonghao Song

Biography

I am a post-doc in the Department of Computer Science and Technology at Tsinghua University, working with Prof. Guoliang Li. I received my Ph.D. in Biomedical Engineering from Tsinghua University, advised by Prof. Xiaorong Gao. Before that, I received my M.Phil. in Control Science and Engineering and B.Eng. in Information Engineering from South China University of Technology.

My research focuses on neural modeling and brain-computer interfaces (BCIs). I'm particularly interested in using multi-scale neural data to build foundation models that connect perception, state, and behavior, and translating these models into practical BCI systems.

Research Interests

Database

Data management, BCI benchmarks, cross-scale neural recordings, and data-centric infrastructure for scalable brain-AI modeling.

Foundation Model

Brain-AI alignment, representation learning, neural foundation models, and generalizable models across perception, state, and behavior.

BCI Systems

Visual coding, mental-state modeling, motor decoding, and embodied BCIs for real-world assistive systems and clinical applications.

News

Preparing for several exciting projects!

[Jun. 2026] I graduated from DBME and joined the DCST as a postdoctoral researcher at Tsinghua University.

[May, 2026] Our work on resolving visual representations from 1,024-channel brain recordings appeared in IEEE TFS.

[May, 2025] Our language-guided M/EEG visual decoding framework appeared in IEEE TNNLS.

[May, 2024] Our work on EEG-based natural image decoding was presented at the ICLR.

Selected Publications

Representative papers are listed below. Please see my Google Scholar for the full publication list.

Fuzzy Alignment Resolves Visual Systems from 1024-Channel Brain Recordings

Yonghao Song, Chengjian Xu, Qingqing Zheng, Nanlin Shi, Xiaogang Chen, Yijun Wang, and Xiaorong Gao

IEEE Transactions on Fuzzy Systems, 2026 [code]

Recognizing Natural Images from M/EEG with Language-Guided Contrastive Learning

Yonghao Song, Yijun Wang, Huiguang He, and Xiaorong Gao

IEEE Transactions on Neural Networks and Learning Systems, 2025 [code]

Decoding Natural Images from EEG for Object Recognition

Yonghao Song, Bingchuan Liu, Xiang Li, Nanlin Shi, Yijun Wang, and Xiaorong Gao

International Conference on Learning Representations, 2024 [code] [openreview]

EEG Conformer: Convolutional Transformer for EEG Decoding and Visualization

Yonghao Song, Qingqing Zheng, Bingchuan Liu, and Xiaorong Gao

IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2023 [code] [braindecode]

Global Adaptive Transformer for Cross-Subject Enhanced EEG Classification

Yonghao Song, Qingqing Zheng, Qiong Wang, Xiaorong Gao, and Pheng-Ann Heng

IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2023 [code]

A Practical EEG-Based Human-Machine Interface to Online Control an Upper-Limb Assist Robot

Yonghao Song, Siqi Cai, Lie Yang, Guofeng Li, Weifeng Wu, and Longhan Xie

Frontiers in Neurorobotics, 2020

Impact

30+ publications in neural engineering and brain-computer interfaces.

2.6k+ Google Scholar citations; H-index 19.

1.4k+ GitHub stars across public repositories, including 750+ stars for EEG-Conformer and 200+ stars for NICE-EEG.

EEG-Conformer has been adopted as a backbone model and widely used in EEG decoding studies.

Selected Honors & Awards

Tsinghua Outstanding PhD Dissertation and Outstanding Graduate, 2026.

CAST Young Talent Support Program for Doctoral Students, 2025.

National Scholarship, Ministry of Education, 2025.

First Prize, Paper Competition, Chinese Society of Biomedical Engineering, 2025.

First Prize, Paper Competition, World Robot Conference & BCI competition, 2024.