Update README.md
Browse files
README.md
CHANGED
|
@@ -4,6 +4,6 @@ license: cc-by-nc-sa-4.0
|
|
| 4 |
# DIFFA: Large Language Diffusion Models Can Listen and Understand
|
| 5 |
[](https://arxiv.org/abs/2507.18452)
|
| 6 |
[](https://huggingface.co/zhoujiaming777/DIFFA)
|
| 7 |
-
[ to enhance **audio perception and reasoning**.
|
|
|
|
| 4 |
# DIFFA: Large Language Diffusion Models Can Listen and Understand
|
| 5 |
[](https://arxiv.org/abs/2507.18452)
|
| 6 |
[](https://huggingface.co/zhoujiaming777/DIFFA)
|
| 7 |
+
[](https://github.com/NKU-HLT/DIFFA)
|
| 8 |
**DIFFA** is the first **diffusion-based large audio-language model** for spoken language understanding.
|
| 9 |
It combines a frozen diffusion LLM with **dual adapters** (semantic + acoustic) to enhance **audio perception and reasoning**.
|