NeurIPS: Neuro-anatomical Inductive Priors for Sphere-based Brain Decoding
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910252482428928 |
|---|---|
| author | Yu, Sijin Chen, Zijiao Yang, Zhenyu Tan, Zihao Xu, Jiakun Liu, Zhongliang Chen, Shengxian Wu, Wenxuan Xu, Xiangmin Zhang, Xin |
| author_facet | Yu, Sijin Chen, Zijiao Yang, Zhenyu Tan, Zihao Xu, Jiakun Liu, Zhongliang Chen, Shengxian Wu, Wenxuan Xu, Xiangmin Zhang, Xin |
| contents | Current fMRI decoders face a performance-fidelity trade-off where efficient ID encoders outperform geometrically faithful surface-based models. We argue this is partly driven by inefficient surface tokenization and the failure to use anatomy as a predictive signal. We present NeurIPS, a framework that improves surface-based decoding by reframing anatomical variation from a nuisance to a powerful inductive prior. NeurIPS unites two innovations: a Selective ROI Spherical Tokenizer (SRST) for efficient geometric encoding, and a Structure-Guided Mixture of Experts (SG-MoE) that explicitly models individual anatomy using cortical features. On the Natural Scenes Dataset, NeurIPS establishes a new state-of-the-art for surface decoders and achieves performance comparable to strong 1D baselines. This is achieved with unprecedented efficiency, as the model converges dramatically faster (10 vs. 600 epochs). This efficiency enables rapid adaptation to new subjects using only 20% of data and ensures robust scalability as the training cohort is expanded. Ablations provide causal evidence that these gains are driven by the model's use of cortical features, not by memorizing subject IDs. By leveraging anatomical priors, NeurIPS provides a principled and scalable path toward robust, generalizable brain decoding. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_24993 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | NeurIPS: Neuro-anatomical Inductive Priors for Sphere-based Brain Decoding Yu, Sijin Chen, Zijiao Yang, Zhenyu Tan, Zihao Xu, Jiakun Liu, Zhongliang Chen, Shengxian Wu, Wenxuan Xu, Xiangmin Zhang, Xin Artificial Intelligence Computer Vision and Pattern Recognition Current fMRI decoders face a performance-fidelity trade-off where efficient ID encoders outperform geometrically faithful surface-based models. We argue this is partly driven by inefficient surface tokenization and the failure to use anatomy as a predictive signal. We present NeurIPS, a framework that improves surface-based decoding by reframing anatomical variation from a nuisance to a powerful inductive prior. NeurIPS unites two innovations: a Selective ROI Spherical Tokenizer (SRST) for efficient geometric encoding, and a Structure-Guided Mixture of Experts (SG-MoE) that explicitly models individual anatomy using cortical features. On the Natural Scenes Dataset, NeurIPS establishes a new state-of-the-art for surface decoders and achieves performance comparable to strong 1D baselines. This is achieved with unprecedented efficiency, as the model converges dramatically faster (10 vs. 600 epochs). This efficiency enables rapid adaptation to new subjects using only 20% of data and ensures robust scalability as the training cohort is expanded. Ablations provide causal evidence that these gains are driven by the model's use of cortical features, not by memorizing subject IDs. By leveraging anatomical priors, NeurIPS provides a principled and scalable path toward robust, generalizable brain decoding. |
| title | NeurIPS: Neuro-anatomical Inductive Priors for Sphere-based Brain Decoding |
| topic | Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.24993 |