Improve model card: add `transformers` library_name, paper abstract, and update links

This PR enhances the model card by:
- Adding `library_name: transformers` to the metadata, enabling the automated "how to use" code snippet on the Hugging Face Hub.
- Updating the primary paper link to the Hugging Face Papers page ([GraspMolmo: Generalizable Task-Oriented Grasping via Large-Scale Synthetic Data Generation](https://huggingface.co/papers/2505.13441)) for better discoverability.
- Including a direct link to the project's GitHub repository: [[Code]](https://github.com/abhaybd/GraspMolmo).
- Adding the paper's abstract to provide a comprehensive overview of the model.
- Adding the BibTeX citation from the GitHub README for proper academic referencing.

README.md

@@ -1,25 +1,29 @@
 ---
-license: mit
+base_model:
+- allenai/Molmo-7B-D-0924
 datasets:
 - allenai/PRISM
 language:
 - en
-base_model:
-- allenai/Molmo-7B-D-0924
+license: mit
 pipeline_tag: robotics
 tags:
 - robotics
 - grasping
 - task-oriented-grasping
 - manipulation
+library_name: transformers
 ---
 
 # GraspMolmo
 
-[[Paper]](https://arxiv.org/pdf/2505.13441) [[arXiv]](https://arxiv.org/abs/2505.13441) [[Project Website]](https://abhaybd.github.io/GraspMolmo/) [[Data]](https://huggingface.co/datasets/allenai/PRISM)
+[[Paper]](https://huggingface.co/papers/2505.13441) [[arXiv]](https://arxiv.org/abs/2505.13441) [[Project Website]](https://abhaybd.github.io/GraspMolmo/) [[Data]](https://huggingface.co/datasets/allenai/PRISM) [[Code]](https://github.com/abhaybd/GraspMolmo)
 
 GraspMolmo is a generalizable open-vocabulary task-oriented grasping (TOG) model for robotic manipulation. Given an image and a task to complete (e.g. "Pour me some tea"), GraspMolmo will point to the most appropriate grasp location, which can then be matched to the closest stable grasp.
 
+## Paper Abstract
+We present GrasMolmo, a generalizable open-vocabulary task-oriented grasping (TOG) model. GraspMolmo predicts semantically appropriate, stable grasps conditioned on a natural language instruction and a single RGB-D frame. For instance, given "pour me some tea", GraspMolmo selects a grasp on a teapot handle rather than its body. Unlike prior TOG methods, which are limited by small datasets, simplistic language, and uncluttered scenes, GraspMolmo learns from PRISM, a novel large-scale synthetic dataset of 379k samples featuring cluttered environments and diverse, realistic task descriptions. We fine-tune the Molmo visual-language model on this data, enabling GraspMolmo to generalize to novel open-vocabulary instructions and objects. In challenging real-world evaluations, GraspMolmo achieves state-of-the-art results, with a 70% prediction success on complex tasks, compared to the 35% achieved by the next best alternative. GraspMolmo also successfully demonstrates the ability to predict semantically correct bimanual grasps zero-shot. We release our synthetic dataset, code, model, and benchmarks to accelerate research in task-semantic robotic manipulation, which, along with videos, are available at this https URL .
+
 ## Code Sample
 
 ```python
@@ -75,4 +79,18 @@ gm = GraspMolmo()
 idx = gm.pred_grasp(rgb, point_cloud, task, grasps)
 
 print(f"Predicted grasp: {grasps[idx]}")
+```
+
+## Citation
+
+```
+@misc{deshpande2025graspmolmo,
+      title={GraspMolmo: Generalizable Task-Oriented Grasping via Large-Scale Synthetic Data Generation}, 
+      author={Abhay Deshpande and Yuquan Deng and Arijit Ray and Jordi Salvador and Winson Han and Jiafei Duan and Kuo-Hao Zeng and Yuke Zhu and Ranjay Krishna and Rose Hendrix},
+      year={2025},
+      eprint={2505.13441},
+      archivePrefix={arXiv},
+      primaryClass={cs.RO},
+      url={https://arxiv.org/abs/2505.13441}, 
+}
 ```