Siyang Li (李思扬)

Siyang Li (李思扬)

Siyang Li

Biography

My research spans machine learning theory, algorithms, and models. Technically, I study transfer learning, ensemble learning, and multimodal learning. I am also familiar with signal processing techniques, modern large language models and vision-language models (LLMs/VLMs).

For applications, I am particularly interested in brain decoding for brain-computer interfaces (BCIs). For the long-term goal, I aim at multimodal human-computer interaction systems for future generations.

News

  • Position
    I am looking for postdoc positions in AI / Agents / BCI / BME / Neuroscience. Feel free to contact me for related positions.
  • Publication
    Our paper Backpropagation-Free Test-Time Adaptation for Lightweight EEG-Based Brain-Computer Interfaces is now published (Early Access) in IEEE Journal of Biomedical and Health Informatics! Many thanks to my co-first authors Jiayi Ouyang and Zhenyao Cui!Backpropagation-Free Test-Time Adaptation in IEEE Journal of Biomedical and Health Informatics
  • Publication
    Our paper StackingNet: Collective Inference Across Independent AI Foundation Models is now published (Open Access) in Advanced Science! Many thanks to my co-first author Chenhao Liu!StackingNet published in Advanced Science
  • Open Source
    I built and will manage HUST-BCIML, a repository collecting the published code and related resources of Prof. Dongrui Wu's lab.

Education

  • Ph.D. in Artificial Intelligence2026
    School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, China
    Supervisor: Prof. Dongrui Wu
  • Master in Artificial Intelligence2021
    College of Arts and Science, Boston University, USA
  • Bachelor in Mathematics and Computer Science2018
    Courant Institute, College of Arts and Science, New York University, USA

Selected Publications

StackingNet: Collective Inference Across Independent AI Foundation Models
Siyang Li†, Chenhao Liu†, Dongrui Wu📩, Zhigang Zeng📩, Lieyun Ding📩
Advanced Science 2026 Code
Backpropagation-Free Test-Time Adaptation for Lightweight EEG-Based Brain-Computer Interfaces
Siyang Li†, Jiayi Ouyang†, Zhenyao Cui†, Ziwei Wang, Tianwang Jia, Feng Wan, Dongrui Wu📩
IEEE Journal of Biomedical and Health Informatics 2026 Code
Black-Box Test-Time Ensemble
Siyang Li, Ziwei Wang, Chenhao Liu, Dongrui Wu📩
IEEE Computational Intelligence Magazine 2026 Code
Poster, the 2nd Chinese Conference on Brain-Machine Intelligence (ChinaBMI), CAAI, 2025China Patent
Canine EEG Helps Human: Cross-Species and Cross-Modality Epileptic Seizure Detection via Multi-Space Alignment
Ziwei Wang, Siyang Li, Dongrui Wu📩
National Science Review 2025
EurekAlert!
T-TIME: Test-Time Information Maximization Ensemble for Plug-and-Play BCIs
Siyang Li, Ziwei Wang, Hanbin Luo, Lieyun Ding📩, Dongrui Wu📩
IEEE Transactions on Biomedical Engineering 2024 Code
Youth Paper Defense Competition Award, World Robot Contest (WRC) - BCI Track, 2023Poster, Spotlight, the 1st Chinese Conference on Brain-Machine Intelligence (ChinaBMI), CAAI, 2024China Patent
Meta-Learning for Fast and Privacy-Preserving Source Knowledge Transfer of EEG-Based BCIs
Siyang Li, Huanyu Wu, Lieyun Ding, Dongrui Wu📩
IEEE Computational Intelligence Magazine 2022 Code
China Patent

Code

HUST-BCIML
Unified EEG-decoding benchmark and a searchable paper-to-code gallery for the Brain-Computer Interface and Machine Learning Lab (BCIML), HUST.
DeepTransferEEG
Deep transfer learning for EEG-based brain-computer interfaces (code of T-TIME and BFT).
TestEnsemble
Test-time combination of black-box model predictions (code of StackingNet and SML-OVR).