Siqi Cai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Siqi Cai has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Haizhou Li
The Chinese University of Hong Kong, Shenzhen, China
2 shared publications Haizhou Li
School of Artificial Intelligence School of Data Science SRIBD The Chinese University of Hong Kong Shenzhen China
1 shared publicationShaochen Zhang
School of Data Science, Chinese University of Hong Kong, Shenzhen, 518172, Shenzhen, China
1 shared publicationSirui Li
School of Data Science, Chinese University of Hong Kong, Shenzhen, 518172, Shenzhen, China
1 shared publicationSuli Wang
School of Artificial Intelligence School of Data Science SRIBD The Chinese University of Hong Kong Shenzhen China
1 shared publication- Xueyi Zhang
School of Data Science, Chinese University of Hong Kong, Shenzhen, 518172, Shenzhen, China
1 shared publication
Latest Publications
- 9 July 2026
- Published by Elsevier in Neural Networks
- Vol. 205 (Pt A) , 109370
MT-RevSNN: Memory and Time Efficient Reversible Framework for Hierarchical Spiking Transformer
- 9 July 2026
- Published by Elsevier in Neural Networks
- Vol. 205 (Pt A) , 109370
MT-RevSNN: Memory and Time Efficient Reversible Framework for Hierarchical Spiking Transformer
- Open Access
Decoding Listeners Identity: Person Identification from EEG Signals Using a Lightweight Spiking Transformer
EEG-based person identification enables applications in security, personalized brain-computer interfaces (BCIs), and cognitive monitoring. However, existing techniques often rely on deep learning architectures at high computational cost, limiting their scope of applications. In this study, we propose a novel EEG person identification approach using spiking neural networks (SNNs) with a lightweight spiking transformer for efficiency and effectiveness. The proposed SNN model is capable of handling the temporal complexities inherent in EEG signals. On the EEG-Music Emotion Recognition Challenge dataset, the proposed model achieves 100% classification accuracy with less than 10% energy consumption of traditional deep neural networks. This study offers a promising direction for energy-efficient and high-performance BCIs. The source code is available at https://github.com/PatrickZLin/Decode-ListenerIdentity.
Open AccessDecoding Listeners Identity: Person Identification from EEG Signals Using a Lightweight Spiking Transformer
EEG-based person identification enables applications in security, personalized brain-computer interfaces (BCIs), and cognitive monitoring. However, existing techniques often rely on deep learning architectures at high computational cost, limiting their scope of applications. In this study, we propose a novel EEG person identification approach using spiking neural networks (SNNs) with a lightweight spiking transformer for efficiency and effectiveness. The proposed SNN model is capable of handling the temporal complexities inherent in EEG signals. On the EEG-Music Emotion Recognition Challenge dataset, the proposed model achieves 100% classification accuracy with less than 10% energy consumption of traditional deep neural networks. This study offers a promising direction for energy-efficient and high-performance BCIs. The source code is available at https://github.com/PatrickZLin/Decode-ListenerIdentity.
- Open Access
A Robust Multi-Scale Framework with Test-Time Adaptation for sEEG-Based Speech Decoding
Decoding speech from stereo-electroencephalography (sEEG) signals has emerged as a promising direction for brain-computer interfaces (BCIs). Its clinical applicability, however, is limited by the inherent non-stationarity of neural signals, which causes domain shifts between training and testing, undermining decoding reliability. To address this challenge, a two-stage framework is proposed for enhanced robustness. First, a multi-scale decomposable mixing (MDM) module is introduced to model the hierarchical temporal dynamics of speech production, learning stable multi-timescale representations from sEEG signals. Second, a source-free online test-time adaptation (TTA) method performs entropy minimization to adapt the model to distribution shifts during inference. Evaluations on the public DU-IN spoken word decoding benchmark show that the approach outperforms state-of-the-art models, particularly in challenging cases. This study demonstrates that combining invariant feature learning with online adaptation is a principled strategy for developing reliable BCI systems. Our code is available at https://github.com/lyyi599/MDM-TENT.
Open AccessA Robust Multi-Scale Framework with Test-Time Adaptation for sEEG-Based Speech Decoding
Decoding speech from stereo-electroencephalography (sEEG) signals has emerged as a promising direction for brain-computer interfaces (BCIs). Its clinical applicability, however, is limited by the inherent non-stationarity of neural signals, which causes domain shifts between training and testing, undermining decoding reliability. To address this challenge, a two-stage framework is proposed for enhanced robustness. First, a multi-scale decomposable mixing (MDM) module is introduced to model the hierarchical temporal dynamics of speech production, learning stable multi-timescale representations from sEEG signals. Second, a source-free online test-time adaptation (TTA) method performs entropy minimization to adapt the model to distribution shifts during inference. Evaluations on the public DU-IN spoken word decoding benchmark show that the approach outperforms state-of-the-art models, particularly in challenging cases. This study demonstrates that combining invariant feature learning with online adaptation is a principled strategy for developing reliable BCI systems. Our code is available at https://github.com/lyyi599/MDM-TENT.