Weizmann researchers used AI to reconstruct images from brain scans
proceedings.iclr.cc
Weizmann researchers introduced Brain-IT, a brain-inspired model that reconstructs images from fMRI recordings by predicting localized image features from brain-voxel clusters. The method produces results comparable to models trained on 40-hour recordings using only 1 hour of fMRI data from a new subject. This lets new subjects require much less scan time while improving how faithfully reconstructed images match what participants saw, outperforming prior approaches on visual quality and standard metrics.
Why it matters
Weizmann researchers used AI to turn brain scans into reconstructions of pictures people were looking at. The newsletter frames it as AI applied to interpreting visual cognition.