Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
Gramian Multimodal Representation Learning and Alignment
2025-01-22
· ICLR 2025 Poster ·
anchor
Findings
IC-390
The parallelotope volume of modality embeddings from LanguageBind, VAST, and Valor on MSR-VTT is strongly correlated with their downstream R@1 retrieval performance