Update README.md


README.md

@@ -1,9 +1,10 @@
 ---
 license: mit
 ---
+![sjepa](https://cdn-uploads.huggingface.co/production/uploads/646e0135174cc96d509582a6/DS-cXrFyxZ78hK48ft0iU.png)
 # Usage
 
-**Instantiate the base model**
+**Instantiate the Base Model**
 ```python
 from braindecode.models import SignalJEPA
 from huggingface_hub import hf_hub_download
@@ -27,10 +28,14 @@ assert unexpected_keys == []
 assert set(missing_keys) == {"pos_encoder.pos_encoder_spat.weight"}
 ```
 
-**Instantiate the downstream architectures**
+**Instantiate the Downstream Architectures**
+
+Contrary to the base model, the downstream architectures are equipped with a classification head which is not pre-trained. 
+Guetschel et al. (2024) [arXiv:2403.11772](https://arxiv.org/abs/2403.11772) introduce three downstream architectures:
+- a) Contextual downstream architecture
+- b) Post-local downstream architecture
+- c) Pre-local architecture
 
-The downstream architectures are equipped with a classification head. 
-See the article [arXiv:2403.11772](https://arxiv.org/abs/2403.11772) for more details.
 ```python
 from braindecode.models import (
     SignalJEPA_Contextual,