Wei Xu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Wei Xu has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Jia-Hong Gao
Center for MRI Research, Academy for Advanced Interdisciplinary Studies, Peking University
3 shared publications Bingjiang Lyu
Changping Laboratory
2 shared publicationsCongcong Li
Changping Laboratory
2 shared publicationsFufu Zheng
Center for MRI Research, Academy for Advanced Interdisciplinary Studies, Peking University
2 shared publications- Hao Cheng
Center for MRI Research, Academy for Advanced Interdisciplinary Studies, Peking University, Beijing, China
2 shared publications - Pan Liao
Center for MRI Research, Academy for Advanced Interdisciplinary Studies, Peking University, Beijing, China
2 shared publications
Latest Publications
- Top Cited PapersOpen Access
- 13 January 2026
- Published by Springer Nature in Nature Communications
- Vol. 17 (1)
A unified time-frequency foundation model for sleep decoding
Sleep decoding is key to revealing sleep architecture and its links to health, yet prevailing deep-learning models rely on supervised, task-specific designs and dual encoders that isolate time-domain and frequency-domain information, limiting generalizability and scalability. We introduce SleepGPT for sleep decoding, a time-frequency foundation model based on generative pretrained transformer, developed using multi-pretext pretraining strategy on 86,335 hours of polysomnography (PSG) from 8,377 subjects. SleepGPT includes a channel-adaptive mechanism for variable channel configurations and a unified time-frequency fusion module that enables deep cross-domain interaction. Evaluations across diverse PSG datasets demonstrate that SleepGPT sets a new benchmark for sleep decoding tasks, achieving superior performance in sleep staging, sleep-related pathology classification, sleep data generation, and sleep spindle detection. Moreover, it reveals channel- and stage-specific physiological patterns underlying sleep decoding. In sum, SleepGPT is an all-in-one method with exceptional generalizability and scalability, offering transformative potential in addressing sleep decoding challenges.
- 13 January 2026
- Published by Springer Nature in Nature Communications
- Vol. 17 (1)
Top Cited PapersOpen AccessA unified time-frequency foundation model for sleep decoding
Sleep decoding is key to revealing sleep architecture and its links to health, yet prevailing deep-learning models rely on supervised, task-specific designs and dual encoders that isolate time-domain and frequency-domain information, limiting generalizability and scalability. We introduce SleepGPT for sleep decoding, a time-frequency foundation model based on generative pretrained transformer, developed using multi-pretext pretraining strategy on 86,335 hours of polysomnography (PSG) from 8,377 subjects. SleepGPT includes a channel-adaptive mechanism for variable channel configurations and a unified time-frequency fusion module that enables deep cross-domain interaction. Evaluations across diverse PSG datasets demonstrate that SleepGPT sets a new benchmark for sleep decoding tasks, achieving superior performance in sleep staging, sleep-related pathology classification, sleep data generation, and sleep spindle detection. Moreover, it reveals channel- and stage-specific physiological patterns underlying sleep decoding. In sum, SleepGPT is an all-in-one method with exceptional generalizability and scalability, offering transformative potential in addressing sleep decoding challenges.
- Open Access
- 15 July 2025
- Published by Elsevier in NeuroImage
- Vol. 318, 121367
Temporal dynamics of quantity processing: distinct time course and representational patterns revealed by multivariate pattern analysis
- 15 July 2025
- Published by Elsevier in NeuroImage
- Vol. 318, 121367
Open AccessTemporal dynamics of quantity processing: distinct time course and representational patterns revealed by multivariate pattern analysis
- Open Access
- 2 October 2024
- Published by Society for Neuroscience in The Journal of Neuroscience
- Vol. 44 (47)
Decoding the Temporal Structures and Interactions of Multiple Face Dimensions Using Optically Pumped Magnetometer Magnetoencephalography (OPM-MEG)
Humans possess a remarkable ability to rapidly access diverse information from others’ faces with just a brief glance, which is crucial for intricate social interactions. While previous studies using event-related potentials/fields have explored various face dimensions during this process, the interplay between these dimensions remains unclear. Here, by applying multivariate decoding analysis to neural signals recorded with optically pumped magnetometer magnetoencephalography, we systematically investigated the temporal interactions between invariant and variable aspects of face stimuli, including race, gender, age, and expression. First, our analysis revealed unique temporal structures for each face dimension with high test–retest reliability. Notably, expression and race exhibited a dominant and stably maintained temporal structure according to temporal generalization analysis. Further exploration into the mutual interactions among face dimensions uncovered age effects on gender and race, as well as expression effects on race, during the early stage (∼200–300 ms postface presentation). Additionally, we observed a relatively late effect of race on gender representation, peaking ∼350 ms after the stimulus onset. Taken together, our findings provide novel insights into the neural dynamics underlying the multidimensional aspects of face perception and illuminate the promising future of utilizing OPM-MEG for exploring higher-level human cognition.
- 2 October 2024
- Published by Society for Neuroscience in The Journal of Neuroscience
- Vol. 44 (47)
Open AccessDecoding the Temporal Structures and Interactions of Multiple Face Dimensions Using Optically Pumped Magnetometer Magnetoencephalography (OPM-MEG)
Humans possess a remarkable ability to rapidly access diverse information from others’ faces with just a brief glance, which is crucial for intricate social interactions. While previous studies using event-related potentials/fields have explored various face dimensions during this process, the interplay between these dimensions remains unclear. Here, by applying multivariate decoding analysis to neural signals recorded with optically pumped magnetometer magnetoencephalography, we systematically investigated the temporal interactions between invariant and variable aspects of face stimuli, including race, gender, age, and expression. First, our analysis revealed unique temporal structures for each face dimension with high test–retest reliability. Notably, expression and race exhibited a dominant and stably maintained temporal structure according to temporal generalization analysis. Further exploration into the mutual interactions among face dimensions uncovered age effects on gender and race, as well as expression effects on race, during the early stage (∼200–300 ms postface presentation). Additionally, we observed a relatively late effect of race on gender representation, peaking ∼350 ms after the stimulus onset. Taken together, our findings provide novel insights into the neural dynamics underlying the multidimensional aspects of face perception and illuminate the promising future of utilizing OPM-MEG for exploring higher-level human cognition.
- 8 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (18) , 28722-28732
A Compact Triaxial SERF Magnetometer With High Sensitivity and 1.1 kHz Bandwidth for Magnetoencephalography
Miniaturized spin-exchange relaxation-free (SERF) magnetometers are recognized for their exceptional sensitivity and ability to function without the need for cryogenic cooling. These devices are particularly valuable for detecting ultra-weak magnetic fields, such as those generated by the human brain. However, the use of miniaturized SERF magnetometers has been limited due to their narrow bandwidth. In this study, we developed a compact triaxial SERF magnetometer that incorporates closed-loop feedback, significantly broadening its bandwidth to 1.1 kHz. This magnetometer achieves high sensitivity, approximately 35 fT/√Hz across each axis and remains compact, with dimensions of 13.8 mm × 21.0 mm × 44.0 mm. It accurately measured the time course of pulsed sinusoidal magnetic fields, with each pulse containing a single cycle of a 1030 Hz sinusoidal signal at a 1 pT amplitude. Our magnetometer also successfully detected various magnetic fields generated by the human brain, including alpha rhythms, auditory evoked fields, and steady-state visual evoked fields. Looking forward, this high-bandwidth, high-sensitivity and compact triaxial SERF magnetometer showcases its great potential for advancing magnetoencephalography and opening new research avenues in neuroscience and clinical research.
- 8 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (18) , 28722-28732
A Compact Triaxial SERF Magnetometer With High Sensitivity and 1.1 kHz Bandwidth for Magnetoencephalography
Miniaturized spin-exchange relaxation-free (SERF) magnetometers are recognized for their exceptional sensitivity and ability to function without the need for cryogenic cooling. These devices are particularly valuable for detecting ultra-weak magnetic fields, such as those generated by the human brain. However, the use of miniaturized SERF magnetometers has been limited due to their narrow bandwidth. In this study, we developed a compact triaxial SERF magnetometer that incorporates closed-loop feedback, significantly broadening its bandwidth to 1.1 kHz. This magnetometer achieves high sensitivity, approximately 35 fT/√Hz across each axis and remains compact, with dimensions of 13.8 mm × 21.0 mm × 44.0 mm. It accurately measured the time course of pulsed sinusoidal magnetic fields, with each pulse containing a single cycle of a 1030 Hz sinusoidal signal at a 1 pT amplitude. Our magnetometer also successfully detected various magnetic fields generated by the human brain, including alpha rhythms, auditory evoked fields, and steady-state visual evoked fields. Looking forward, this high-bandwidth, high-sensitivity and compact triaxial SERF magnetometer showcases its great potential for advancing magnetoencephalography and opening new research avenues in neuroscience and clinical research.