MOSS-VL
Open-source visual understanding model for images and long video
Community-submitted · content unverified. This organization has not verified ownership or the information in this profile.
About
MOSS-VL is OpenMOSS's open-source visual understanding model. It separates visual encoding from cognitive reasoning through a cross-attention architecture and natively supports interleaved text, image and video input, including long video understanding and temporal reasoning.
- Website
- mosi.cn/en/models/moss-vl
- Added via
- web
- Ownership
- unclaimed
Where to go
Product details
- Product kind
- Open Source