Research map / Architectures and efficiency / RNNs and normalization
Learning Sparse Semantic-Cortical Atoms for Multisubject Naturalistic fMRI Encoding
Alicia Zeng
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a sparse semantic-cortical atom model for multisubject naturalistic fMRI language encoding to make LLM-feature-based encoding representations more interpretable.
Problem
LLM-feature-based naturalistic language encoding models predict cortical responses well but their learned representations are hard to interpret; semantic selectivity is non-identifiable in correlated feature spaces, cortical organization is implicit in voxelwise weights, and cross-subject structure
Approach
Learns sparse semantic-cortical atoms shared across subjects so that semantic selectivity and cortical organization become explicit rather than implicit in voxelwise weight maps. Details beyond the abstract are not available.
Closest papers by meaning
- BrainSCUBA: Fine-Grained Natural Language Captions of Visual Cortex Selectivity (ICLR 2024 · similarity 0.89)
- MIRAGE: Adaptive Multimodal Gating for Whole-Brain fMRI Encoding (NeurIPS 2026 · similarity 0.88)
- Neuro-Vision to Language: Enhancing Brain Recording-based Visual Reconstruction and Language Interaction (NeurIPS 2024 · similarity 0.88)
- Brain-OF: An Omnifunctional Foundation Model for fMRI, EEG and MEG (NeurIPS 2026 · similarity 0.88)
- Finding Shared Decodable Concepts and their Negations in the Brain (ICLR 2025 · similarity 0.88)
- fMRI predictors based on language models of increasing complexity recover brain left lateralization (NeurIPS 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
