Subject-specific fMRI embeddings learned unsupervised from the Natural Scenes Dataset can be aligned across individuals via orthogonal rotations, supporting a shared neural geometry in visual cortex.
mini-vec2vec: Scaling universal geometry alignment with linear transformations
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
other 1
citation-polarity summary
years
2026 2roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
Platonic Representations in the Human Brain: Unsupervised Recovery of Universal Geometry
Subject-specific fMRI embeddings learned unsupervised from the Natural Scenes Dataset can be aligned across individuals via orthogonal rotations, supporting a shared neural geometry in visual cortex.
- Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale