Update README.md

README.md

@@ -1,11 +1,12 @@
 ---
 license: apache-2.0
 ---
+
 # EWAM: Emergent Depth-Wise Specialization in a Unified Embodied Model
 
 **From Semantic Understanding through Visual Foresight to Action**
 
-[**Project Page**](https://wanghao00pro.github.io/EWAM-project/) | [**Technical Report**](https://wanghao00pro.github.io/EWAM-project/assets/EWAM_Technical_Report.pdf) | **Code** (coming soon)
+[**Project Page**](https://wanghao00pro.github.io/EWAM-project/) | [**Paper (arXiv)**](https://arxiv.org/abs/2609.39973) | [**Code**](https://github.com/Wanghao00pro/EWAM)
 
 EWAM is a unified embodied model that jointly processes vision-language, future-video, and action tokens in a single flow-matching Diffusion Transformer. Without any explicit stage design, the action stream learns a depth-wise division of labor: shallow layers retrieve instruction and current-scene semantics from the vision-language expert, intermediate layers shift toward predicted future-frame representations, and deep layers are dominated by action self-attention for motor refinement.
 
@@ -62,7 +63,7 @@ The backbone weights are not included. Download [Wan2.2-TI2V-5B](https://hugging
 
 ## Usage
 
-Training and evaluation pipelines for RoboTwin 2.0 and LIBERO are provided in the code repository (coming soon). Evaluation requires about 41 GB of GPU memory (A100-80G or H100 recommended); training requires more than 80 GB per GPU.
+Training and evaluation pipelines for RoboTwin 2.0 and LIBERO are provided in the [code repository](https://github.com/Wanghao00pro/EWAM). Evaluation requires about 41 GB of GPU memory (A100-80G or H100 recommended); training requires more than 80 GB per GPU.
 
 ## License
 
@@ -71,10 +72,10 @@ The EWAM weights and code are released under the Apache License 2.0. The Wan2.2
 ## Citation
 
 ```bibtex
-@techreport{wang2026ewam,
-  title       = {{EWAM}: Emergent Depth-Wise Specialization in a Unified Embodied Model --- From Semantic Understanding through Visual Foresight to Action},
-  author      = {Wang, Hao and Wen, Jiajun and Liu, Jingzhi and Xue, Shuoshuo and Chen, Zhiliang and others},
-  institution = {Yinwang Intelligent Technology Co. Ltd.},
-  year        = {2026}
+@article{wang2026ewam,
+  title   = {{EWAM}: Emergent Depth-Wise Specialization in a Unified Embodied Model -- From Semantic Understanding through Visual Foresight to Action},
+  author  = {Wang, Hao and Wen, Jiajun and Liu, Jingzhi and Xue, Shuoshuo and Chen, Zhiliang and Lin, Min and Chang, Yicheng and Guo, Xiaoyu and Zhuo, Yukang and Chong, Zheng and Nie, Yunshuang and Zhang, Jian and Liufu, Weijia and Wu, Qingman and Xu, Heming and Song, Bingchang and Wu, Dantong and Wang, Zhiyuan and Xu, Hang and Han, Jianhua and Chen, Bokui and Zhao, Shen and Li, Rui and Liang, Xiaodan},
+  journal = {arXiv preprint arXiv:2609.39973},
+  year    = {2026}
 }
 ```