Update README.md

README.md

@@ -9,11 +9,11 @@ tags:
   - IBM
   - ESA
 ---
-[![Website](https://img.shields.io/badge/Website-TerraMind-0F62FE)](https://ibm.github.io/terramind/)
+[![Website](https://img.shields.io/badge/Website-TerraMind-0F62FE)](https://www.fast-eo.eu/terramind)
 [![arXiv](https://img.shields.io/badge/arXiv-2504.11171-b31b1b?logo=arxiv)](https://arxiv.org/abs/2504.11171)
-[![Docs](https://img.shields.io/badge/Docs-EE4B2B?logo=materialformkdocs&logoColor=fff)](https://ibm.github.io/terratorch/stable/guide/terramind/)
+[![Docs](https://img.shields.io/badge/Docs-EE4B2B?logo=materialformkdocs&logoColor=fff)](https://terrastackai.github.io/terratorch/stable/guide/terramind/)
 [![Examples](https://img.shields.io/badge/GitHub-Examples-0F62FE?logo=github)](https://github.com/IBM/terramind)
-[![Code](https://img.shields.io/badge/code-TerraTorch-EE4B2B?logo=github)](https://github.com/IBM/terratorch/tree/main/terratorch/models/backbones/terramind)
+[![Code](https://img.shields.io/badge/code-TerraTorch-EE4B2B?logo=github)](https://github.com/terrastackai/terratorch/tree/main/terratorch/models/backbones/terramind)
 [![ESAblog](https://img.shields.io/badge/Blog-ESA-113145)](https://www.esa.int/Applications/Observing_the_Earth/ESA_and_IBM_collaborate_on_TerraMind)
 [![IBMblog](https://img.shields.io/badge/Blog-IBM-0F62FE)](https://research.ibm.com/blog/terramind-esa-earth-observation-model)
 
@@ -40,12 +40,12 @@ During pre-training, TerraMind leverages masked token reconstruction, learning c
 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.
 The evaluation highlights its effectiveness in handling diverse Earth Observation scenarios.
-We present additional experiments in our [pre-print](https://arxiv.org/abs/2504.11171).
+We present additional experiments in our [paper](https://arxiv.org/abs/2504.11171).
 
 
 ## Usage
 
-TerraMind is fully integrated into the fine-tuning package [TerraTorch](https://ibm.github.io/terratorch/). 
+TerraMind is fully integrated into the fine-tuning package [TerraTorch](https://terrastackai.github.io/terratorch/). 
 This makes it easy to initialize the pre-trained model or fine-tune it via PyTorch Lightning. 
 The weights are automatically downloaded from Hugging Face. 
 
@@ -116,7 +116,7 @@ model = BACKBONE_REGISTRY.build(
 )
 ```
 
-If you use TiM models, we recommend using the [pre-training statistics](https://github.com/IBM/terratorch/blob/a4ca8df7c7f22ddf469f372e1099157d2d7beeb2/terratorch/models/backbones/terramind/model/terramind_register.py#L111) for standardization.
+If you use TiM models, we recommend using the [pre-training statistics](https://github.com/terrastackai/terratorch/blob/main/terratorch/models/backbones/terramind/model/terramind_register.py#L145) for standardization.
 
 ### Generations
 
@@ -156,13 +156,13 @@ Already working with TerraMind? Submit your use case to the [TerraMind Blue-Sky
 
 ## Citation
 
-If you use TerraMind in your research, please cite the [TerraMind](https://arxiv.org/abs/2504.11171) pre-print.
+If you use TerraMind in your research, please cite the [TerraMind](https://arxiv.org/abs/2504.11171) paper.
 
 ```text
 @article{jakubik2025terramind,
   title={TerraMind: Large-Scale Generative Multimodality for Earth Observation},
   author={Jakubik, Johannes and Yang, Felix and Blumenstiel, Benedikt and Scheurer, Erik and Sedona, Rocco and Maurogiovanni, Stefano and Bosmans, Jente and Dionelis, Nikolaos and Marsocci, Valerio and Kopp, Niklas and others},
-  journal={arXiv preprint arXiv:2504.11171},
+  journal={IEEE/CVF International Conference on Computer Vision (ICCV)},
   year={2025}
 }
 ```