Add model card linking the OpenWAM paper (arXiv 2609.07398)

README.md

@@ -0,0 +1,30 @@
+---
+license: apache-2.0
+library_name: openwam
+pipeline_tag: robotics
+tags:
+  - robotics
+  - world-action-model
+  - openwam
+---
+
+# sft_from_scratch_robotwin_clean
+
+An **OpenWAM-Study** checkpoint: downstream supervised finetuning on RoboTwin 2.0, applied identically across every Q5 pretraining variant so the recipes can be compared end to end.
+
+Finetuned on RoboTwin 2.0 Clean **from scratch**, the no-pretraining baseline.
+
+- Paper: https://arxiv.org/abs/2609.07398
+- Code: https://github.com/OpenWAM-Official/OpenWAM
+- Project page: https://openwam-official.github.io/
+
+## Citation
+
+```bibtex
+@article{wang2026openwam,
+  title   = {OpenWAM: An Open, Modular Exploration Towards Systematic World-Action Model Pretraining},
+  author  = {Yuran Wang and Siqiao Huang and Mingleyang Li and Chenhao Zhang and Jiaqi Liang and Weiyang Jin and Yue Chen and Xuemin Chi and Donghao Zhou and Qize Yu and Yu-Kai Wang and Yuhan Rui and Shenzhe Yao and Zhen Yuan and Zhenhao Shen and Kefei Zhu and Zijie Zhu and Ning Gao and Xiaowei Chi and Guanqi He and Shanghang Zhang and Hao Dong and Lin Shao and Hang Zhao},
+  year    = {2026},
+  journal = {arXiv preprint arXiv: 2609.07398}
+}
+```