# Brain Diffusion for Visual Exploration: Cortical Discovery using Large Scale Generative Models

Source: [Brain Diffusion for Visual Exploration: Cortical Discovery using Large Scale Generative Models](<https://www.sota2.com/research/paper/68fa71451e209131cea50436>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T04:29:53.966Z

Authors: Andrew F. Luo, Margaret M. Henderson, Leila Wehbe, Michael J. Tarr

Published: 2023-06-05T17:59:05.000Z

## Abstract

A long standing goal in neuroscience has been to elucidate the functional organization of the brain. Within higher visual cortex, functional accounts have remained relatively coarse, focusing on regions of interest (ROIs) and taking the form of selectivity for broad categories such as faces, places, bodies, food, or words. Because the identification of such ROIs has typically relied on manually assembled stimulus sets consisting of isolated objects in non-ecological contexts, exploring functional organization without robust a priori hypotheses has been challenging. To overcome these limitations, we introduce a data-driven approach in which we synthesize images predicted to activate a given brain region using paired natural images and fMRI recordings, bypassing the need for category-specific stimuli. Our approach -- Brain Diffusion for Visual Exploration ("BrainDiVE") -- builds on recent generative methods by combining large-scale diffusion models with brain-guided image synthesis. Validating our method, we demonstrate the ability to synthesize preferred images with appropriate semantic specificity for well-characterized category-selective ROIs. We then show that BrainDiVE can characterize differences between ROIs selective for the same high-level category. Finally we identify novel functional subdivisions within these ROIs, validated with behavioral data. These results advance our understanding of the fine-grained functional organization of human visual cortex, and provide well-specified constraints for further examination of cortical organization using hypothesis-driven methods.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Semantic Specificity Classification on Natural Scenes Dataset (NSD) 1.0 (Subject 1 (S1))](<https://www.sota2.com/research/sota/semantic-specificity-classification-on-natural-scenes-dataset-nsd-1-0-subject-1-s1.md>): Semantic Specificity Classification; Natural Scenes Dataset (NSD) 1.0 (Subject 1 (S1)); Faces: 69.5.

- [Semantic Specificity Classification on Natural Scenes Dataset (NSD) 1.0 (Subject 2 (S2))](<https://www.sota2.com/research/sota/semantic-specificity-classification-on-natural-scenes-dataset-nsd-1-0-subject-2-s2.md>): Semantic Specificity Classification; Natural Scenes Dataset (NSD) 1.0 (Subject 2 (S2)); Faces Acc: 70.

- [fMRI Encoding on Natural Scenes Dataset (NSD) subjects 1, 2, 5, 7 (avg) (test)](<https://www.sota2.com/research/sota/fmri-encoding-on-natural-scenes-dataset-nsd-subjects-1-2-5-7-avg-test.md>): fMRI encoding; Natural Scenes Dataset (NSD) subjects 1, 2, 5, 7 (avg) 7T (test); Pearson Correlation: 0.323.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2306.03089>)

[PDF](<https://arxiv.org/pdf/2306.03089.pdf>)

[Implementation](<https://www.cs.cmu.edu/~afluo/BrainDiVE>)