Compositional Neuro-Symbolic Concepts in Neural Activities
Yanchen Wang, Joy Hsu, Ehsan Adeli, Jiajun Wu
Abstract
We propose NEURONA, a modular neuro-symbolic framework for fMRI decoding and concept grounding in neural activity. Leveraging image- and video-based fMRI question-answering datasets, NEURONA learns to decode interacting concepts from visual stimuli from patterns of fMRI signals, integrating symbolic reasoning and compositional execution with fMRI grounding across brain regions. We demonstrate that incorporating structure into the decoding pipeline improves both decoding accuracy and generalization performance. NEURONA shows that modeling the compositional structure of concepts through hierarchical predicate-argument dependencies enables more precise decoding from fMRI, highlighting neuro-symbolic frameworks as promising tools for neural decoding.
BibTeX
@inproceedings{
wang2026compositional,
title={Compositional Neuro-Symbolic Concepts in Neural Activities},
author={Yanchen Wang and Joy Hsu and Ehsan Adeli and Jiajun Wu},
booktitle={The Fourteenth International Conference on Learning Representations},
year={2026},
url={https://openreview.net/forum?id=alEx0sm74l}
}