Update README.md
Browse files
README.md
CHANGED
|
@@ -20,6 +20,8 @@ library_name: pytorch
|
|
| 20 |
arxiv: 2512.04847
|
| 21 |
---
|
| 22 |
|
|
|
|
|
|
|
| 23 |
# AcuLa
|
| 24 |
|
| 25 |
AcuLa (**Audio–Clinical Understanding via Language Alignment**) is a post-training alignment framework for medical audio understanding. It improves pretrained audio encoders by aligning their representations with clinical-language representations from a language model, allowing the audio encoder to capture richer clinical semantics while preserving fine-grained acoustic information.
|
|
@@ -30,7 +32,6 @@ This repository provides the checkpoint for AcuLa. The accompanying code is avai
|
|
| 30 |
|
| 31 |
This work is described in the paper **“Language Models as Semantic Teachers: Post-Training Alignment for Medical Audio Understanding.”**
|
| 32 |
|
| 33 |
-
|
| 34 |
|
| 35 |
---
|
| 36 |
|
|
|
|
| 20 |
arxiv: 2512.04847
|
| 21 |
---
|
| 22 |
|
| 23 |
+
|
| 24 |
+
|
| 25 |
# AcuLa
|
| 26 |
|
| 27 |
AcuLa (**Audio–Clinical Understanding via Language Alignment**) is a post-training alignment framework for medical audio understanding. It improves pretrained audio encoders by aligning their representations with clinical-language representations from a language model, allowing the audio encoder to capture richer clinical semantics while preserving fine-grained acoustic information.
|
|
|
|
| 32 |
|
| 33 |
This work is described in the paper **“Language Models as Semantic Teachers: Post-Training Alignment for Medical Audio Understanding.”**
|
| 34 |
|
|
|
|
| 35 |
|
| 36 |
---
|
| 37 |
|