Brain Foundation Models: A Survey on Advancements in Neural Signal Processing and Brain Discovery

2025-03-01

AI Summary

This study addresses critical bottlenecks in computational neuroscience—namely, low-quality brain data, poor model generalizability, and limited interpretability—by proposing Brain Foundation Models (BFMs), a novel paradigm. Methodologically, we introduce the first unified cross-modal pretraining framework that integrates large-scale self-supervised learning, representation alignment across heterogeneous neural signals (e.g., fMRI, EEG, ECoG), and robustness optimization, while embedding intrinsic interpretability mechanisms. Our approach transcends the limitations of conventional single-task models. We formally define BFMs for the first time and establish a principled methodological pathway. Empirically, BFMs significantly enhance generalizability and reliability in brain–computer interface decoding, auxiliary diagnosis of neurological disorders, and cognitive mechanism analysis. This work provides both theoretical foundations and practical benchmarks for advancing foundational modeling in computational neuroscience.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Humans and AI: Other Foundations of Human Computation & AI

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

Brain foundation models (BFMs) have emerged as a transformative paradigm in computational neuroscience, offering a revolutionary framework for processing diverse neural signals across different brain-related tasks. These models leverage large-scale pre-training techniques, allowing them to generalize effectively across multiple scenarios, tasks, and modalities, thus overcoming the traditional limitations faced by conventional artificial intelligence (AI) approaches in understanding complex brain data. By tapping into the power of pretrained models, BFMs provide a means to process neural data in a more unified manner, enabling advanced analysis and discovery in the field of neuroscience. In this survey, we define BFMs for the first time, providing a clear and concise framework for constructing and utilizing these models in various applications. We also examine the key principles and methodologies for developing these models, shedding light on how they transform the landscape of neural signal processing. This survey presents a comprehensive review of the latest advancements in BFMs, covering the most recent methodological innovations, novel views of application areas, and challenges in the field. Notably, we highlight the future directions and key challenges that need to be addressed to fully realize the potential of BFMs. These challenges include improving the quality of brain data, optimizing model architecture for better generalization, increasing training efficiency, and enhancing the interpretability and robustness of BFMs in real-world applications.

Problem

• Developing Brain Foundation Models (BFMs) for unified neural signal processing.
• Overcoming traditional AI limitations in understanding complex brain data.
• Addressing challenges in data quality, model generalization, and interpretability.

Innovation

• Leverages large-scale pre-training techniques
• Unifies neural data processing methods
• Defines Brain Foundation Models framework