AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Disentangling the Factors of Convergence between Brains and Computer Vision Models

Joséphine Raugel, Marc Szafraniec, Huy V. Vo, Camille Couprie, Jérémy Rapin, Stéphane d'Ascoli, Patrick Labatut, Piotr Bojanowski, Valentin Wyart, Jean-Remi King

ICLR 2026 · Vision-language and multimodal › Human and embodied modeling · approach: fMRI visual decoding

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
increase model size from Small to Giant (trained from scratch) (ablation)DINOv3 (human-centric 1.7B images) · NSD fMRI/THINGS-MEG, end of trainingencoding score (Pearson R): 0.096 -> 0.107Improved
train DINOv3 on human-centric images instead of satellite or cellular images (10M images each) (ablation)DINOv3 Large · NSD fMRI and THINGS-MEGencoding, spatial and temporal scoresImproved
train DINOv3 longer, from untrained to trained (ablation)DINOv3 7B · fMRI average encoding scoreencoding score (Pearson R): .03 -> .09Improved
train on non-human-centric data (satellite, cellular) (ablation)DINOv3 Large · brain similarity across image typesencoding scoreImproved
increase model size (ablation)DINOv3 · higher-level cortices (BA44, IFS) vs early visual (V1, V2)encoding scoreMixed
compare half time to anatomical distance from V1DINOv3 7B training · fMRI ROIscorrelation: R=0.91Improved

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