# Bridging scalp and intracranial EEG in BCI via pretrained neural representations and geometric constraint embedding

arXiv: https://arxiv.org/abs/2604.14202 · HTML: https://mlsanity.com/paper/2604.14202/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 48 references that are in the map.
- First posted on arXiv 3 Apr 2026.

## Builds on (most cited first, 3 of 3)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCI](https://mlsanity.com/paper/2405.18765/) (2024)
- [Neuro-GPT: Towards A Foundation Model for EEG](https://mlsanity.com/paper/2311.03764/) (2023)

## Built on by (most cited first, 3 of 3)

- [Cross-Subject Intracranial EEG Reconstruction from Scalp Recordings Using Multi-Scale Cross-Attention Transformers](https://mlsanity.com/paper/2605.18897/) (2026)
- [Virtual iEEG from Scalp EEG: Charting the Landscape of Source Imaging, Intracranial Inference and Reconstruction](https://mlsanity.com/paper/2608.26998/) (2026)
- [iBrain: A Unified Foundation Model Reading the Brain from Surface to Spikes](https://mlsanity.com/paper/2609.06960/) (2026)

## Abstract (arXiv)

Electroencephalography (EEG) has become one of the key modalities underpinning brain-computer interfaces (BCIs) due to its high temporal resolution, rapid responsiveness, non-invasiveness, low cost, and portability. However, EEG signals are substantially inferior to intracranial EEG (iEEG) in signal-to-noise ratio and local spatial resolution, whereas iEEG suffers from extremely limited clinical accessibility owing to its invasive nature, hindering widespread application. To address this challenge, this study proposes a unified data-and prior knowledge-driven framework for EEG-iEEG representational enhancement. Guided by the principle that "geometric structure dictates function", the framework maps static cortical anatomy onto dynamic constraints governing neural signal propagation and integrates general-purpose neural representations extracted by a pre-trained large EEG model to explicitly model signal transmission through the brain. Enhanced EEG signals are then synthesized via a multidimensional representation diffusion process. Numerous experimental results demonstrate that the generated enhanced EEG signals effectively recover the neural activity patterns lost during propagation through the brain. This finding indicates that the performance ceiling of BCIs is constrained not only by acquisition hardware but also by the depth to which the generative model resolves the mechanisms of neural signal propagation. Collectively, the proposed framework provides a viable pathway toward acquiring high-fidelity neural signals at low cost.