aiqbench analysis
This research advances brain-computer interfaces by introducing a zero-shot neural prior framework using Transformer foundation models to overcome the variability inherent in EEG signals across different subjects and tasks. The proposed progressive unfreezing strategy effectively mitigates catastrophic forgetting, achieving superior decoding accuracy without requiring calibration for new users. This development is significant for enabling scalable, objective biomarkers in computational psychiatry and behavioral prediction through generalizable machine learning architectures.
Zero-Shot Neural Priors for Generalizable Cross-Subject and Cross-Task EEG Decoding
arXiv:2606.23706v2 Announce Type: replace-cross Abstract: The development of generalizable electroencephalography (EEG) decoding models is essential for robust brain-computer interfaces (BCI) and objective neural biomarkers in mental health. Conventional approaches have been hindered by poor cross-subject and cross-task generalization, owing to high inter-subject variability and non-stationary neural signals. We address this challenge with a zero-shot cross-subject decoding framework on the large-scale Healthy Brain Network dataset, benchmarking a convolutional neural network baseline, a hybrid LSTM, and a Transformer-based foundation model. To adapt the Transformer for regression while averting catastrophic forgetting, we propose a novel progressive unfreezing strategy. The baseline yielded an nRMSE of 0.9991, whereas our fine-tuned Transformer achieved 0.9799 on unseen subjects. This work advances scalable, calibration-free EEG decoding for computational psychiatry and behavioral prediction.
Abstract:The development of generalizable electroencephalography (EEG) decoding models is essential for robust brain-computer interfaces (BCI) and objective neural biomarkers in mental health. Conventional approaches have been hindered by poor cross-subject and cross-task generalization, owing to high inter-subject variability and non-stationary neural signals. We address this challenge with a zero-shot cross-subject decoding framework on the large-scale Healthy Brain Network dataset, benchmarking a convolutional neural network baseline, a hybrid LSTM, and a Transformer-based foundation model. To adapt the Transformer for regression while averting catastrophic forgetting, we propose a novel progressive unfreezing strategy. The baseline yielded an nRMSE of 0.9991, whereas our fine-tuned Transformer achieved 0.9799 on unseen subjects. This work advances scalable, calibration-free EEG decoding for computational psychiatry and behavioral prediction.
Signal Processing (eess.SP); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)
arXiv:2606.23706 [eess.SP]
(or arXiv:2606.23706v2 [eess.SP] for this version)
https://doi.org/10.48550/arXiv.2606.23706 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 217 words
Related coverage
[AINews] not much happened today
Latent Space · Oct 3, 2026
Learning Generalizable Reconstruction of High-Dimensional Neural Dynamics
arXiv · Aug 19, 2026
Neural Visual Decoding via Cognitive guided Adaptive Blurring and Information Constrained Alignment
arXiv · Oct 17, 2026
Generalist Graph Anomaly Detection via Prototype-Based Distillation
arXiv · Sep 1, 2026