Pulse
0
Velocity
Stars
0
A framework for multimodal foundation models. Supports vision, language, and vision-language tasks.
A multimodal foundation model framework supporting vision, language, and VL tasks.
Unify vision, language, and vision-language tasks with one multimodal framework.
Why Trending
Tencent's latest multimodal foundation model research.
Target Audience
Researchers and developers in multimodal AI.
Similar Projects