Foundation model

LaBraM: results on public EEG datasets

LaBraM (Large Brain Model) is an EEG foundation model from Jiang, Zhao and Lu (Shanghai Jiao Tong University; ICLR 2024), described in Base, Large and Huge sizes. A vector-quantized tokenizer turns per-channel EEG patches into discrete codes, and a Transformer is pretrained to predict the codes of masked patches, using about 2,500 hours of EEG from around 20 datasets.

Also known as LaBraM · Large Brain Model · LaBraM-Base · Labram · Jiang et al. 2024

Reference Jiang W-B, Zhao L-M, Lu B-L. Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCI. International Conference on Learning Representations (ICLR), 2024. ↗

Directory status: Evaluated · Official code ↗ · Description sources arxiv.org · github.com · github.com

Published results

Grouped by dataset. Compare figures within a group only: across groups the task, cohort, chance level and electrode layout all change.

ds003810 · Core matrix · motor imagery & rest

Read with its protocol: Core matrix (home page) · Chance level 50.0% · experiments.json

Method	Condition	Metric	Value	People
LaBraM	Rest versus right-hand imagery	Balanced accuracy	53.5%51.4%–55.4%	10

ds003810 · Pretraining · fixed readout

Read with its protocol: Does pretraining help? · deployment-topics.json

Method	Condition	Metric	Value	People
LaBraM	MI / rest · pretrained	Balanced accuracy	53.5%	10
LaBraM	MI / rest · random initialization (mean)	Balanced accuracy	55.9%	10

ds003810 · Pretraining · train-selected readout

Read with its protocol: Does pretraining help? · deployment-topics.json

Method	Condition	Metric	Value	People
LaBraM	MI / rest · pretrained	Balanced accuracy	52.9%	10
LaBraM	MI / rest · random initialization (mean)	Balanced accuracy	56.5%	10

EEGMAT · Core matrix · arithmetic & rest

Read with its protocol: Core matrix (home page) · Chance level 50.0% · experiments.json

Method	Condition	Metric	Value	People
LaBraM	Serial subtraction versus resting EEG	Balanced accuracy	64.6%60.5%–68.6%	36

EEGMAT · Pretraining · fixed readout

Read with its protocol: Does pretraining help? · deployment-topics.json

Method	Condition	Metric	Value	People
LaBraM	Mental workload · pretrained	Balanced accuracy	64.6%	36
LaBraM	Mental workload · random initialization (mean)	Balanced accuracy	56.5%	36

EEGMAT · Pretraining · train-selected readout

Read with its protocol: Does pretraining help? · deployment-topics.json

Method	Condition	Metric	Value	People
LaBraM	Mental workload · pretrained	Balanced accuracy	64.4%	36
LaBraM	Mental workload · random initialization (mean)	Balanced accuracy	56.5%	36

BETA · Core matrix · SSVEP, 8 channels

Read with its protocol: Core matrix (home page) · Chance level 2.5% · experiments.json

Method	Condition	Metric	Value	People
LaBraM	40 visual targets · 8 posterior electrodes	Balanced accuracy	10.8%9.5%–12.2%	70

BETA · Core matrix · SSVEP, 4 channels

Read with its protocol: Core matrix (home page) · Chance level 2.5% · experiments.json

Method	Condition	Metric	Value	People
LaBraM	40 visual targets · 4 posterior electrodes	Balanced accuracy	12.9%11.2%–14.6%	70

ds006593 · Core matrix · P300 target ERP

Read with its protocol: Core matrix (home page) · Chance level 50.0% · experiments.json

Method	Condition	Metric	Value	People
LaBraM	Visual target versus nontarget events	Balanced accuracy	49.4%47.7%–51.2%	21

TMNRED / ds005383 · Core matrix · semantic target ERP

Read with its protocol: Core matrix (home page) · Chance level 50.0% · experiments.json

Method	Condition	Metric	Value	People
LaBraM	Reading · target versus nontarget events	Balanced accuracy	53.2%51.3%–54.9%	30

EESM19 scalp subset · Core matrix · sleep staging

Read with its protocol: Core matrix (home page) · Chance level 20.0% · experiments.json

Method	Condition	Metric	Value	People
LaBraM	Five stages · balanced scalp-EEG sample	Balanced accuracy	71.1%69.0%–73.2%	20

ds005342 · Core matrix · idle & command

Read with its protocol: Core matrix (home page) · experiments.json

Method	Condition	Metric	Value	People
LaBraM	Seated motor imagery · cue-gated replay	Command detection ≤3 s	18.3%	4
LaBraM	Seated motor imagery · cue-gated replay	Idle false activation	3.3%	4

Mobile BCI dataset (SSVEP and ERP paradigms) · Movement · SSVEP, 2-second windows

Read with its protocol: On the move · deployment-topics.json

LaBraM · Standing · scalp · 8 ch

59.5% (53.6%–65.5%)

LaBraM · Slow walk · 0.8 m/s · scalp · 8 ch

54.7% (49.5%–60.1%)

LaBraM · Fast walk · 1.6 m/s · scalp · 8 ch

47.8% (43.3%–52.3%)

Balanced accuracy, 3 configurations. Dot: the estimate; line: 95% interval; dashed line: chance level where the payload records one.

Method	Condition	Metric	Value	People
LaBraM	Standing · scalp · 8 ch	Balanced accuracy	59.5%53.6%–65.5%	23
LaBraM	Slow walk · 0.8 m/s · scalp · 8 ch	Balanced accuracy	54.7%49.5%–60.1%	23
LaBraM	Fast walk · 1.6 m/s · scalp · 8 ch	Balanced accuracy	47.8%43.3%–52.3%	23

All methods → · All datasets →