Tag
This paper presents a large-scale study comparing Bayesian complete-pooling models to frequentist baselines for cross-subject motor imagery EEG classification, finding that Bayesian methods improve reliability modestly but at a higher computational cost, with limited practical benefit.
Proposes Stacked LoRA, a framework that decouples subject-invariant and subject-specific knowledge for adapting EEG foundation models to motor imagery decoding, achieving improved accuracy across multiple benchmarks.