Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Contribute
Light
Dark
XLM-RoBERTa-base
Report a problem with this record
anchor
Findings
IC-1544
The latent spaces of pretrained foundational models across vision and text are not related by a single class of geometric transformations; the optimal alignment depends on the specific model pair, architecture, and dataset.