NeurIPS 2025 Workshop BrainBodyFM (Spotlight Talk). [paper] [openreview]

We propose TABLeT (Two-dimensionally Autoencoded Brain Latent Transformer), a novel approach that tokenizes fMRI volumes using a pre-trained 2D natural image autoencoder. Each 3D fMRI volume is compressed into a compact set of continuous tokens, enabling efficient long-sequence modeling with a simple transformer encoder. Our findings highlight a new paradigm for scalable spatiotemporal modeling of brain activity.