Brief

Researchers have developed a new framework called NeurIPS to improve brain decoding using fMRI data. This approach reframes anatomical variation as a predictive signal, moving beyond the typical performance-fidelity trade-off seen in current decoders. NeurIPS incorporates a novel spherical tokenizer for efficient geometric encoding and a structure-guided mixture of experts that models individual anatomy. The framework achieves state-of-the-art performance for surface-based decoders, matching efficient 1D baselines with significantly faster convergence and requiring less data for subject adaptation. AI

Researchers have demonstrated that human brain representations of visual stimuli exhibit a shared underlying geometry. Using fMRI data and a self-supervised encoder, they learned subject-specific embeddings and showed these could be translated across individuals through unsupervised geometric transformations. This suggests that neural representations in the visual cortex are approximately isometric and compatible with a common coordinate system, potentially extending the concept of Platonic representations beyond artificial neural networks. AI