Update README.md

README.md

@@ -16,7 +16,7 @@ With its advanced reasoning capabilities and superior performance on geospatial
 
 ## Model Details
 
-- **Model architecture**: Inspired by LISA (![Lai et al., 2024](https://arxiv.org/pdf/2308.00692)), LISAT integrates a multimodal large language model (LLM) with a segmentation model. Its architechture is shown below.
+- **Model architecture**: Inspired by LISA ![Lai et al., 2024](https://arxiv.org/pdf/2308.00692), LISAT integrates a multimodal large language model (LLM) with a segmentation model. Its architechture is shown below.
 
 ![LISAT Model Architecture](https://huggingface.co/jquenum/LISAt-7b/resolve/main/model_architecture.png)
 
@@ -70,6 +70,9 @@ pip install --upgrade transformers
 
 Once your installation is updated, you can use LISAT-7B for inference as follows:
 
+
+This will render as a properly formatted Python code snippet in Markdown. When you view it in a Markdown-rendering environment, it will look like this:
+
 ```python
 from transformers import AutoModelForImageSegmentation, AutoTokenizer
 
@@ -85,7 +88,6 @@ inputs = tokenizer(input_image, return_tensors="pt")
 outputs = model.generate(**inputs)
 
 
-
 ## Intended Use
 
 ### Intended Use Cases
@@ -140,6 +142,22 @@ However, like any technology, **LISAT-7B** comes with inherent risks. Testing co
 
 Please, use **LISAT-7B** responsibly.
 
+## Citation
+
+If you use LISAt in your research or applications, please cite our paper:
+
+## Citation
+
+If you use LISAt in your research or applications, please cite our paper:
+
+```bibtex
+@article{TBD,
+  title={LISAt: Language-Instructed Segmentation Assistant for Satellite Imagery},
+  author={Quenum, Jerome and Hsieh, Wen-Han and Wu, Tsung-Han and Gupta, Ritwik and Darrell, Trevor and Chan, David M},
+  journal={TBD},
+  year={2025},
+  url={TBD}
+}