AdaBrain-Bench evaluates four EEG foundation models and four traditional baselines on 13 datasets and finds pretrained models, especially LaBraM and CBraMod, generally win on cross-subject and few-shot transfer.
: A high-performance speech neuroprosthesis
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
AdaBrain-Bench: Benchmarking Brain Foundation Models for Brain-Computer Interface Applications
AdaBrain-Bench evaluates four EEG foundation models and four traditional baselines on 13 datasets and finds pretrained models, especially LaBraM and CBraMod, generally win on cross-subject and few-shot transfer.