nkkbr
/

ViCA2-stage1-align

Video-Text-to-Text

text-generation

vision-language

video understanding

visuospatial cognition

spatial reasoning

Model card Files Files and versions

ViCA2-stage1-align

16.2 GB

1 contributor

History: 3 commits

nkkbr's picture

Create README.md

653b4ae verified 7 months ago