Arrow Research search

Author name cluster

Andrew Thwaites

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

2 papers
1 author row

Possible papers

2

NeurIPS Conference 2025 Conference Paper

BrainOmni: A Brain Foundation Model for Unified EEG and MEG Signals

  • Qinfan Xiao
  • Ziyun Cui
  • Chi Zhang
  • Siqi Chen
  • Wen Wu
  • Andrew Thwaites
  • Alexandra Woolgar
  • Bowen Zhou

Electroencephalography (EEG) and magnetoencephalography (MEG) measure neural activity non-invasively by capturing electromagnetic fields generated by dendritic currents. Although rooted in the same biophysics, EEG and MEG exhibit distinct signal patterns, further complicated by variations in sensor configurations across modalities and recording devices. Existing approaches typically rely on separate, modality- and dataset-specific models, which limits the performance and cross-domain scalability. This paper proposes BrainOmni, the first brain foundation model that generalises across heterogeneous EEG and MEG recordings. To unify diverse data sources, we introduce BrainTokenizer, the first tokeniser that quantises spatiotemporal brain activity into discrete representations. Central to BrainTokenizer is a novel Sensor Encoder that encodes sensor properties such as spatial layout, orientation, and type, enabling compatibility across devices and modalities. Building upon the discrete representations, BrainOmni learns unified semantic embeddings of brain signals by self-supervised pretraining. To the best of our knowledge, it is the first foundation model to support both EEG and MEG signals, as well as the first to incorporate large-scale MEG pretraining. A total of 1, 997 hours of EEG and 656 hours of MEG data are curated and standardised from publicly available sources for pretraining. Experiments show that BrainOmni outperforms both existing foundation models and state-of-the-art task-specific models on a range of downstream tasks. It also demonstrates strong generalisation to unseen EEG and MEG devices. Further analysis reveals that joint EEG-MEG (EMEG) training yields consistent improvements across both modalities. Code and checkpoints are publicly available at https: //github. com/OpenTSLab/BrainOmni

PDF Details

YNIMG Journal 2025 Journal Article

Information processing pathway maps — A scalable framework for mapping cortical processing

  • Andrew Thwaites
  • Chao Zhang
  • Alexandra Woolgar

Cortical processing in the human brain is highly complex, and researchers have long faced challenges in describing and sharing formal accounts of it in an intuitive yet rigorous manner. Traditional mathematical representations, while precise, often obscure the underlying concepts, whereas narrative descriptions lack the necessary detail. Information Processing Pathway Maps (IPPMs) bridge this gap by providing a clear and flexible way to represent neural processing that maintains mathematical accuracy. These maps can be generated directly from neuroimaging data such as electroencephalography (EEG) and magnetoencephalography (MEG), making them a scalable tool for mapping brain processes. They are also theory-agnostic, making them applicable across various mathematical frameworks of neuronal processing. Recent advances in neuroimaging techniques have significantly improved the efficiency of IPPM creation and expanded their coverage. This paper presents an introductory overview of the IPPM framework, its interpretability, methods for generation, breadth of coverage, and potential applications in both research and clinical settings. We conclude with a discussion on their limitations and suggest promising avenues for future research.

Details DOI