Add link to paper and pipeline tag (#2)
Browse files- Add link to paper and pipeline tag (eaf1afaff8fdfa86b050cdb03b284c32694cc5ef)
Co-authored-by: Niels Rogge <[email protected]>
README.md
CHANGED
|
@@ -1,6 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# LLaDA-V
|
|
|
|
| 2 |
We introduce LLaDA-V, a competitive diffusion-based vision-language model, outperforming other diffusion MLLMs.
|
| 3 |
|
|
|
|
|
|
|
| 4 |
Project Page: https://ml-gsai.github.io/LLaDA-V-demo/
|
| 5 |
|
| 6 |
Code: https://github.com/ML-GSAI/LLaDA-V
|
|
|
|
| 1 |
+
---
|
| 2 |
+
pipeline_tag: image-text-to-text
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
# LLaDA-V
|
| 6 |
+
|
| 7 |
We introduce LLaDA-V, a competitive diffusion-based vision-language model, outperforming other diffusion MLLMs.
|
| 8 |
|
| 9 |
+
It was presented in the paper [LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning](https://huggingface.co/papers/2505.16933).
|
| 10 |
+
|
| 11 |
Project Page: https://ml-gsai.github.io/LLaDA-V-demo/
|
| 12 |
|
| 13 |
Code: https://github.com/ML-GSAI/LLaDA-V
|