English

Improving Multimodal Brain Encoding Model with Dynamic Subject-awareness Routing

Artificial Intelligence 2026-02-05 v3

Abstract

Naturalistic fMRI encoding must handle multimodal inputs, shifting fusion styles, and pronounced inter-subject variability. We introduce AFIRE (Agnostic Framework for Multimodal fMRI Response Encoding), an agnostic interface that standardizes time-aligned post-fusion tokens from varied encoders, and MIND, a plug-and-play Mixture-of-Experts decoder with a subject-aware dynamic gating. Trained end-to-end for whole-brain prediction, AFIRE decouples the decoder from upstream fusion, while MIND combines token-dependent Top-K sparse routing with a subject prior to personalize expert usage without sacrificing generality. Experiments across multiple multimodal backbones and subjects show consistent improvements over strong baselines, enhanced cross-subject generalization, and interpretable expert patterns that correlate with content type. The framework offers a simple attachment point for new encoders and datasets, enabling robust, plug-and-improve performance for naturalistic neuroimaging studies.

Keywords

Cite

@article{arxiv.2510.04670,
  title  = {Improving Multimodal Brain Encoding Model with Dynamic Subject-awareness Routing},
  author = {Xuanhua Yin and Runkai Zhao and Weidong Cai},
  journal= {arXiv preprint arXiv:2510.04670},
  year   = {2026}
}

Comments

7 pages, 4 figures, accepted by ICASSP 2026

R2 v1 2026-07-01T06:18:50.535Z