Universal BCI Personalization: One API for Frozen EEG Trunks and Foundation Models
One standardized adapter for brain-computer interfaces across incompatible models
Brain-computer interfaces rely on machine learning models trained to decode brain signals, but each model type requires its own custom personalization approach — making it expensive and slow to support multiple architectures. This paper presents Nimbus Personalizer, a single standardized adapter that works across five different model types and four datasets without modification, recovering most of the accuracy gains of full retraining while using a fraction of the calibration time.
Brain-computer interface companies currently need to build separate personalization pipelines for each model they want to support. A universal adapter means they can integrate once and swap between models freely as technology improves, cutting engineering complexity and time-to-market. For users, faster calibration means less time in the setup chair before the system is ready to use.