Reconstruction-based EEG foundation models preferentially encode aperiodic and low-frequency components over oscillatory structure, with embeddings capturing subject identity more than task-relevant information.
M., and Narayanan, S
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4roles
background 1polarities
background 1representative citing papers
Retrieval from out-of-domain foundation models enables personalization of a lightweight transformer for stress detection, yielding +3.92% accuracy and +4.76% F1 gains on WESAD without user labels.
A compact 0.09B model using hierarchical discrete tokenization and prompted latent translation outperforms larger baselines in cross-modal PPG-to-ECG synthesis and cross-frequency super-resolution.
Pre-training on long-context MEG data enables data-efficient word decoding from brain signals that matches supervised baselines with roughly 50 times less data.
citing papers explorer
-
Aperiodic and Low-Frequency Spectral Bias in Reconstruction based EEG Foundation Models
Reconstruction-based EEG foundation models preferentially encode aperiodic and low-frequency components over oscillatory structure, with embeddings capturing subject identity more than task-relevant information.
-
Retrieval-Augmented Personalization with Foundation Models for Wearable Stress Detection
Retrieval from out-of-domain foundation models enables personalization of a lightweight transformer for stress detection, yielding +3.92% accuracy and +4.76% F1 gains on WESAD without user labels.
-
Compact Latent Manifold Translation: A Parameter-Efficient Foundation Model for Cross-Modal and Cross-Frequency Physiological Signal Synthesis
A compact 0.09B model using hierarchical discrete tokenization and prompted latent translation outperforms larger baselines in cross-modal PPG-to-ECG synthesis and cross-frequency super-resolution.
-
MEG-XL: Data-Efficient Brain-to-Text via Long-Context Pre-Training
Pre-training on long-context MEG data enables data-efficient word decoding from brain signals that matches supervised baselines with roughly 50 times less data.