AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Learning Sparse Semantic-Cortical Atoms for Multisubject Naturalistic fMRI Encoding

Alicia Zeng

NeurIPS 2026 · Architectures and efficiency › RNNs and normalization · approach: Layer-wise analysis of language models

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy