Add robotics pipeline tag and improve model card

Hi! I'm Niels from the community science team at Hugging Face. I'm opening this PR to add the `robotics` pipeline tag to your model metadata, which will help users discover it when filtering the Hub. I've also improved the model card's formatting by adding links to the paper and project page, providing a summary of the work, and adding a citation section.

README.md

@@ -1,14 +1,30 @@
 ---
 license: cc-by-4.0
+pipeline_tag: robotics
 ---
-SoMA: A Real-to-Sim Neural Simulator for Robotic Soft-body Manipulation
 
-TL;DR: SoMA is a Gaussian splat neural simulator that models deformable object dynamics from real-world robot manipulation, enabling action-conditioned, stable long-horizon simulation with high-fidelity, multi-view–consistent rendering.
+# SoMA: A Real-to-Sim Neural Simulator for Robotic Soft-body Manipulation
 
-cite arxiv.org/abs/2602.02402 
+SoMA is a 3D Gaussian Splat simulator for soft-body manipulation. It couples deformable dynamics, environmental forces, and robot joint actions in a unified latent neural space for end-to-end real-to-sim simulation. 
 
----
-arxiv: https://arxiv.org/pdf/2602.02402
----
-project page: https://city-super.github.io/SoMA/
----
+Modeling interactions over learned Gaussian splats enables controllable, stable long-horizon manipulation and generalization beyond observed trajectories without predefined physical models.
+
+- **Paper:** [https://arxiv.org/abs/2602.02402](https://arxiv.org/abs/2602.02402)
+- **Project Page:** [https://city-super.github.io/SoMA/](https://city-super.github.io/SoMA/)
+
+## Description
+
+SoMA is a Gaussian splat neural simulator that models deformable object dynamics from real-world robot manipulation, enabling action-conditioned, stable long-horizon simulation with high-fidelity, multi-view–consistent rendering. By coupling deformable dynamics, environmental forces, and robot joint actions in a unified latent neural space, SoMA improves resimulation accuracy and generalization on real-world robot manipulation by 20%, enabling stable simulation of complex tasks such as long-horizon cloth folding.
+
+## Citation
+
+If you find this work useful, please cite:
+
+```bibtex
+@article{huang2026soma,
+  title={SoMA: A Real-to-Sim Neural Simulator for Robotic Soft-body Manipulation},
+  author={Huang, Mu and Wang, Hui and Kerui Ren and Linning Xu and Yunsong Zhou and Mulin Yu and Bo Dai and Jiangmiao Pang},
+  journal={arXiv preprint arXiv:2602.02402},
+  year={2026}
+}
+```