Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

VideoDetailCaption

Benchmarks

Task NameDataset NameSOTA ResultTrend
Video DescriptionVideoDetailCaption (VideoDC) (test)
Test Score3.35
17
Speculative DecodingVideoDetailCaption ~17k visual tokens
Tau (τ)3.91
8
Video-Language UnderstandingVideoDetailCaption
RG-L0.254
7
Showing 3 of 3 rows