NeuroSTORM logo NeuroSTORM
Contact Us

Supported Models

All 12 models share the supervised training, fine-tuning, validation, testing, and checkpoint workflow through the common runner.

Choose the model's input representation and use its --model value with the shared experiment runner.

ModelInputEntry point
NeuroSTORMVoxel sequences--model neurostorm
SwiFTVoxel sequences--model swift
BAnDVoxel sequences--model band
Brain-JEPAOrdered 450-ROI time series--model brainjepa
BrainGNNFC-derived graphs--model braingnn
LG-GNNFC-derived graphs--model lggnn
IBGNNFC-derived graphs--model ibgnn
BNTFC matrices--model bnt
Com-BrainTFFC matrices--model combraintf
BrainNetCNNFC matrices--model brainnetcnn
BrainLMOrdered ROI time series--model brainlm
TFFVoxel sequences--model tff

Brain-JEPA requires ROI signals in the same 450-region order as its gradient table. NeuroSTORM MAE and SwiFT contrastive learning have model-specific pretraining configurations. The dedicated Task4 evaluator covers NeuroSTORM, SwiFT, BrainLM, TFF, BNT, Com-BrainTF, LG-GNN, and BrainGNN. See the model configuration reference and dataset support table to select inputs and tasks.