Visual-Interactive Text-Image Universal Embedder (ICLR-26)
AI & ML interests
None defined yet.
Recent Activity
Papers
SoundReactor: Frame-level Online Video-to-Audio Generation
VIRTUE: Visual-Interactive Text-Image Universal Embedder
models
8
Sony/VIRTUE-2B-SCaR
Image-Text-to-Text
•
Updated
•
49
•
1
Sony/VIRTUE-7B-SCaR
Image-Text-to-Text
•
Updated
•
1
Sony/AKI-4B-phi-3.5-mini
Image-Text-to-Text
•
Updated
•
65
•
27
Sony/humangif
Updated
•
1
Sony/genwarp
Image-to-Image
•
Updated
•
12
Sony/MoLA
Updated
•
1
Sony/SilentCipher
Updated
•
801
•
6
Sony/soundctm
Text-to-Audio
•
Updated
•
18
datasets
6
Sony/SCaR-Train
Viewer
•
Updated
•
958k
•
1
Sony/SCaR-Eval
Viewer
•
Updated
•
47.1k
•
2
Sony/Hokkaido_Agriculture_Image_Dataset
Viewer
•
Updated
•
250
•
56
•
2
Sony/DeepResonance_data_models
Viewer
•
Updated
•
77.5k
•
110
•
1
Sony/OpenMU-Bench
Preview
•
Updated
•
17
Sony/ComperDial
Updated
•
26
•
1