The Platonic brain bridge hypothesis: human brain networks as an architectural prior for multimodal large language models
Abstract
Multimodal large language models predict brain activity, but brain alignment has been a measurement, not a design tool. We propose the Platonic brain bridge hypothesis: omni models, multimodal large language models that process video, audio and text jointly, converge on brain-like representations usable in both directions. From model to brain, brain-likeness of seven omni models is stable across participants, rises with every input channel in three bases, and our encoders lead the Algonauts 2025 out-of-distribution leaderboard. From brain to model, Brain-MoE fixes the expert partition of a frozen base to the seven networks of human cortex, trains experts on network-labelled Brain-AVQA questions, raises held-out accuracy in all 15 model-benchmark pairs by 6.42 percentage points on average and exceeds capacity-matched random experts in 14. Brain-Scope localizes the correspondence to sparse features whose removal weakens brain prediction. Human brain organization is therefore a usable architectural prior for multimodal large language models.
Related
- Simultaneous multi-task assessment of five neurological language disorders via cross-corpus multimodal learning
- MEMOIR-VLM—a multimodal vision-language model for Alzheimer's disease classification and question answering
- Algorithmic bottlenecks in evolution: Genetic code, symbolic language, and the Great Filter hypothesis
- Hippocampal Neuronal Overflow and Cortical Reconstruction: A Hypothesis on the Formation of Neural Networks Unique to the Human Brain
- Discovery of microbial intergenic features with genomic language modeling and multimodal search
BibTeX
@misc{zhang2026platonic,
title = {{The Platonic brain bridge hypothesis: human brain networks as an architectural prior for multimodal large language models}},
author = {Pengfei Zhang and Biao Tian and Xiangang Li and Li Liu},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.10947},
eprint = {2609.10947},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.10947},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - The Platonic brain bridge hypothesis: human brain networks as an architectural prior for multimodal large language models
AU - Pengfei Zhang
AU - Biao Tian
AU - Xiangang Li
AU - Li Liu
PY - 2026
DA - 2026/09/14
PB - arXiv
DO - 10.48550/arxiv.2609.10947
UR - https://arxiv.org/abs/2609.10947
AB - Multimodal large language models predict brain activity, but brain alignment has been a measurement, not a design tool. We propose the Platonic brain bridge hypothesis: omni models, multimodal large language models that process video, audio and text jointly, converge on brain-like representations usable in both directions. From model to brain, brain-likeness of seven omni models is stable across participants, rises with every input channel in three bases, and our encoders lead the Algonauts 2025 out-of-distribution leaderboard. From brain to model, Brain-MoE fixes the expert partition of a frozen base to the seven networks of human cortex, trains experts on network-labelled Brain-AVQA questions, raises held-out accuracy in all 15 model-benchmark pairs by 6.42 percentage points on average and exceeds capacity-matched random experts in 14. Brain-Scope localizes the correspondence to sparse features whose removal weakens brain prediction. Human brain organization is therefore a usable architectural prior for multimodal large language models.
ER -