{"ID":2859803,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.04670","arxiv_id":"2510.04670","title":"Improving Multimodal Brain Encoding Model with Dynamic Subject-awareness Routing","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.","short_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-pl...","url_abs":"https://arxiv.org/abs/2510.04670","url_pdf":"https://arxiv.org/pdf/2510.04670v3","authors":"[\"Xuanhua Yin\",\"Runkai Zhao\",\"Weidong Cai\"]","published":"2025-10-06T10:24:28Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[]","has_code":false}