FAME, a frequency-balanced masked autoencoder that standardizes and equally weights per-band reconstruction targets, reduces the low-frequency bias of EEG representations and beats prior models on 24 of 41 downstream tasks.
International Journal of Neuroscience , volume=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Understanding and Correcting Low-Frequency Bias in EEG Foundation Model
FAME, a frequency-balanced masked autoencoder that standardizes and equally weights per-band reconstruction targets, reduces the low-frequency bias of EEG representations and beats prior models on 24 of 41 downstream tasks.