Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
From Bricks to Bridges: Product of Invariances to Enhance Latent Space Communication
2024-01-16
· ICLR 2024 spotlight ·
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.