R.I.P.
๐ป
Ghosted
Modulating Cross-Modal Convergence with Single-Stimulus, Intra-Modal Dispersion
April 23, 2026 ยท Grace Period ยท ๐ ICLR 2026 Workshop on Representational Alignment (Re-Align)
Authors
Eghbal A. Hosseini, Brian Cheung, Evelina Fedorenko, Alex H. Williams
arXiv ID
2604.21836
Category
q-bio.NC
Cross-listed
cs.AI
Citations
0
Venue
ICLR 2026 Workshop on Representational Alignment (Re-Align)
Abstract
Neural networks exhibit a remarkable degree of representational convergence across diverse architectures, training objectives, and even data modalities. This convergence is predictive of alignment with brain representation. A recent hypothesis suggests this arises from learning the underlying structure in the environment in similar ways. However, it is unclear how individual stimuli elicit convergent representations across networks. An image can be perceived in multiple ways and expressed differently using words. Here, we introduce a methodology based on the Generalized Procrustes Algorithm to measure intra-modal representational convergence at the single-stimulus level. We applied this to vision models with distinct training objectives, selecting stimuli based on their degree of alignment (intra-modal dispersion). Crucially, we found that this intra-modal dispersion strongly modulates alignment between vision and language models (cross-modal convergence). Specifically, stimuli with low intra-modal dispersion (high agreement among vision models) elicited significantly higher cross-modal alignment than those with high dispersion, by up to a factor of two (e.g., in pairings of DINOv2 with language models). This effect was robust to stimulus selection criteria and generalized across different pairings of vision and language models. Measuring convergence at the single-stimulus level provides a path toward understanding the sources of convergence and divergence across modalities, and between neural networks and human neural representations.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ q-bio.NC
R.I.P.
๐ป
Ghosted
SuperSpike: Supervised learning in multi-layer spiking neural networks
R.I.P.
๐ป
Ghosted
Generic decoding of seen and imagined objects using hierarchical visual features
R.I.P.
๐ป
Ghosted
Convolutional Neural Networks as a Model of the Visual System: Past, Present, and Future
R.I.P.
๐ป
Ghosted
A probabilistic atlas of the human thalamic nuclei combining ex vivo MRI and histology
R.I.P.
๐ป
Ghosted