research
Seven Thousand Hours Joined Brain-Surface Signals to Spikes
iBrain jointly pretrained on intracranial EEG and intracortical spiking with signal-specific encoders and one shared temporal backbone.
Summary
iBrain jointly pretrained on intracranial EEG and intracortical spiking with signal-specific encoders and one shared temporal backbone.
Most neural foundation models specialize in one recording type. iBrain instead uses separate encoders for intracranial EEG and intracortical spike trains, followed by a shared spatiotemporal transformer trained with masked reconstruction and channel-view alignment. The pretraining corpus contains more than 7,000 hours of heterogeneous invasive recordings. Across the reported benchmarks, the joint model outperformed single-signal pretraining baselines and transferred with improved data efficiency across recording settings. These are research benchmarks on invasive recordings, not evidence that the model can read thoughts or support unsupervised clinical decisions.
Why it matters
iBrain jointly pretrained on intracranial EEG and intracortical spiking with signal-specific encoders and one shared temporal backbone.
Limits and context
- These are research benchmarks on invasive recordings, not evidence that the model can read thoughts or support unsupervised clinical decisions.
Key claims
iBrain jointly pretrained on intracranial EEG and intracortical spiking with signal-specific encoders and one shared temporal backbone.
Qualification: These are research benchmarks on invasive recordings, not evidence that the model can read thoughts or support unsupervised clinical decisions.
Evidence: source-2026-09-09-011
Sources
- arXiv preprint 2609.06960arXiv · primary research
Corrections
No corrections have been recorded for this story.