Update ReadMe

README.md

@@ -7,10 +7,17 @@ tags:
   - IBM
   - ESA
 ---
+[**Paper**](https://arxiv.org/abs/2504.11171) 
+| [**Examples**](https://github.com/IBM/terramind) 
+| [**Model Code**](https://github.com/IBM/terratorch/tree/terramind/terratorch/models/backbones/terramind) 
+| [**ESA Blog**](todo)
+| [**IBM Blog**](todo)
+
 # TerraMind 1.0 base
 
 TerraMind is the first multimodal any-to-any generative foundation model for Earth Observation jointly developed by IBM, ESA, and Forschungszentrum Jülich.
 
+
 ![terramind_architecture.png](assets%2Fterramind_architecture.png)
 
 ## Architecture
@@ -24,7 +31,7 @@ During pre-training, TerraMind leverages masked token reconstruction, learning c
 
 ## Evaluation
 
-![terramind_generations.png](assets%2Fterramind_generations.png)
+![terramind_evaluation.png](assets%2Fterramind_evaluation.png)
 
 We benchmarked TerraMind against other geospatial foundation models using the PANGAEA benchmark. 
 TerraMind consistently achieved state-of-the-art performance, surpassing existing models in various downstream tasks such as land use segmentation, water body mapping, and vegetation assessments.