Neuroprobe: Evaluating Intracranial Brain Responses to Naturalistic Stimuli

ICLR 2026 Conference Submission14833 Authors

Keywords: neuroscience, intracranial EEG, brain foundation models, benchmark, language processing, naturalistic stimuli, brain-computer interfaces

TL;DR: Neuroprobe: the first standardized benchmark for intracranial EEG that enables rigorous evaluation of brain foundation models.

Abstract:

High-resolution neural datasets enable foundation models for the next generation of brain-computer interfaces and neurological treatments. The community requires rigorous benchmarks to discriminate between competing modeling approaches, yet no standardized evaluation frameworks exist for intracranial EEG (iEEG) recordings. To address this gap, we present Neuroprobe: a suite of decoding tasks for studying multi-modal language processing in the brain. Unlike scalp EEG, intracranial EEG requires invasive surgery to implant electrodes that record neural activity directly from the brain with minimal signal distortion. Neuroprobe is built on the BrainTreebank dataset, which consists of 40 hours of iEEG recordings from 10 human subjects performing a naturalistic movie viewing task. Neuroprobe serves two critical functions. First, it is a mine from which neuroscience insights can be drawn. The high temporal and spatial resolution of the labeled iEEG allows researchers to systematically determine when and where computations for each aspect of language processing occur in the brain by measuring the decodability of each feature across time and all electrode locations. Using Neuroprobe, we visualize how information flows from key language and audio processing sites in the superior temporal gyrus to sites in the prefrontal cortex. We also demonstrate the progression from processing simple auditory features (e.g., pitch and volume) to more complex language features (part of speech and word position in the sentence tree) in a purely data-driven manner. Second, as the field moves toward neural foundation models trained on large-scale datasets, Neuroprobe provides a rigorous framework for comparing competing architectures and training protocols. We found that the linear baseline on spectrogram inputs is surprisingly strong, beating frontier foundation models on many tasks. Neuroprobe is designed with computational efficiency and ease of use in mind.
We make the code for Neuroprobe openly available and will maintain a public leaderboard of evaluation submissions, aiming to enable measurable progress in the field of iEEG foundation models.

Primary Area: datasets and benchmarks

Submission Number: 14833