RABBiT: Rapidly adaptive BOLD foundation model via brain-tuning for accurate zero-shot and few-shot prediction of speech-elicited responses in the brain
2026-07-06 • Computation and Language
Computation and Language
AI summaryⓘ
The authors created RABBiT, a computer model that predicts brain activity related to understanding language from sound input. It works well even without data from a new person and improves quickly with only a small amount of their brain data. This is possible because RABBiT looks at specific brain regions separately and splits brain responses into parts shared by everyone and parts unique to each person. The model helps researchers study how language works in the brain without needing lots of data from each individual.
fMRIbrain activitylanguage processingfoundation modelzero-shot predictionfew-shot learningregion-specific attentionaudio-to-fMRI encoderbrain tuning
Authors
Omer Moussa, Mariya Toneva
Abstract
Language understanding in the brain is context-dependent, varying across experimental stimuli and individuals, which makes it difficult to build computational models that generalize across both. This calls for a foundation model of language-evoked brain activity that can capture shared structure while adapting efficiently to new participants and inputs. We introduce RABBiT (Rapidly Adaptive BOLD foundation model via BraIn-Tuning), a compact audio-to-fMRI encoder designed for accurate zero- and few-shot prediction. A comprehensive evaluation on 324 participants across multiple unseen fMRI datasets shows that RABBiT enables accurate zero-shot prediction of fMRI responses to natural speech across auditory and language-selective regions, surpassing the SOTA foundation model for fMRI and predictions based on group averages. With as little as 10 minutes of participant-specific data, RABBiT further improves performance via parameter-efficient tuning, substantially outperforming per-participant linear models. RABBiT's performance is driven by two key innovations: (1) learned region-specific attention, and (2) a decomposition of brain responses into shared and subject-specific components, combined with a brain-tuned speech backbone. In addition to supporting strong predictive accuracy, the structured, region-specific representations that RABBiT learns enable interpretability. By eliminating the need for extensive per-participant data and model fitting, RABBiT enables scalable population-level analyses of language in the human brain. We make the code available at https://github.com/bridge-ai-neuro/rabbit.