Search papers, labs, and topics across Lattice.
3
0
3
3
By explicitly accounting for EEG's noisy nature, IRENE learns compact and reliable connectivity patterns that boost seizure detection performance beyond SOTA methods.
By dynamically integrating graph-derived functional connectivity with Riemannian manifold learning, RepSPD unlocks more robust and generalizable EEG representations.
By modeling EEG dynamics in continuous time with Neural ODEs, ODEBrain avoids error accumulation and captures instantaneous, nonlinear brain activity better than recurrent architectures.
