LLaDA-V
We introduce LLaDA-V, a competitive diffusion-based vision-language model, outperforming other diffusion MLLMs.
It was presented in the paper LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning.
Project Page: https://ml-gsai.github.io/LLaDA-V-demo/
- Downloads last month
- 1,421
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
๐
Ask for provider support