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

TL;DR

This survey reviews recent advancements in Brain Foundation Models (BFMs), highlighting their role in transforming neural signal processing through large-scale pre-training, and discusses future challenges and directions in the field.

Contribution

It provides the first comprehensive definition and framework for BFMs, reviewing methodological innovations, applications, and challenges in neural signal processing.

Findings

BFMs enable unified neural data analysis across multiple modalities.

Recent advancements improve model generalization and robustness.

Key challenges include data quality, model interpretability, and training efficiency.

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.