Update docs

README.md

@@ -13,7 +13,7 @@ EmbodiChain is an end-to-end, GPU-accelerated framework for Embodied AI. It stre
 
 > [!NOTE]
 > EmbodiChain is in Alpha and under active development:
-> * More features will be continually added in the coming months.
+> * More features will be continually added in the coming months. You can find more details in the [roadmap](https://dexforce.github.io/EmbodiChain/resources/roadmap.html).
 > * Since this is an early release, we welcome feedback (bug reports, feature requests, etc.) via GitHub Issues.
 
 
@@ -25,6 +25,13 @@ EmbodiChain is an end-to-end, GPU-accelerated framework for Embodied AI. It stre
 - ⚡ **Efficient Training & Evaluation**: Online data streaming, parallel environment rollouts, and modern training paradigms.
 - 🧩 **Modular & Extensible**: Easily integrate new robots, environments, and learning algorithms.
 
+The figure below illustrates the overall architecture of EmbodiChain:
+
+<p align="center">
+  <img src="assets/imgs/frameworks.jpg" alt="architecture" width="90%"/>
+</p>
+
+
 
 ## Getting Started
 
@@ -37,7 +44,7 @@ To get started with EmbodiChain, follow these steps:
 
 ## Citation
 
-If you use EmbodiChain in your research, please cite:
+If you find EmbodiChain helpful for your research, please consider citing our work:
 
 ```bibtex
 @misc{EmbodiChain,
@@ -47,4 +54,15 @@ If you use EmbodiChain in your research, please cite:
   year = {2025},
   url = {https://github.com/DexForce/EmbodiChain}
 }
+```
+
+```bibtex
+@misc{GS-World,
+  author = {Liu, G., Deng, Y., Liu, Z., and Jia, K},
+  title = {GS-World: An Efficient, Engine-driven Learning Paradigm for Pursuing Embodied Intelligence using World
+   Models of Generative Simulation},
+  month = {October},
+  year = {2025},
+  journal = {TechRxiv}
+}
 ```

docs/source/introduction.rst

@@ -18,7 +18,7 @@ EmbodiChain is an end-to-end, GPU-accelerated framework for Embodied AI. It stre
 .. NOTE::
    EmbodiChain is in Alpha and under active development:
 
-   * More features will be continually added in the coming months.
+   * More features will be continually added in the coming months. You can find more details in the `roadmap <https://dexforce.github.io/EmbodiChain/resources/roadmap.html>`_.
    * Since this is an early release, we welcome feedback (bug reports, feature requests, etc.) via GitHub Issues.
 
 
@@ -31,6 +31,11 @@ Key Features
 * ⚡ **Efficient Training & Evaluation**: Online data streaming, parallel environment rollouts, and modern training paradigms.
 * 🧩 **Modular & Extensible**: Easily integrate new robots, environments, and learning algorithms.
 
+The figure below illustrates the overall architecture of EmbodiChain:
+
+.. image:: ../../assets/imgs/frameworks.jpg
+   :alt: frameworks
+
 Getting Started
 ---------------
 
@@ -44,7 +49,7 @@ To get started with EmbodiChain, follow these steps:
 Citation
 --------
 
-If you use EmbodiChain in your research, please cite:
+If you find EmbodiChain helpful for your research, please consider citing our work:
 
 .. code-block:: bibtex
 
@@ -55,3 +60,15 @@ If you use EmbodiChain in your research, please cite:
      year = {2025},
      url = {https://github.com/DexForce/EmbodiChain}
    }
+
+.. code-block:: bibtex
+
+   @misc{GS-World,
+   author = {Liu, G., Deng, Y., Liu, Z., and Jia, K},
+   title = {GS-World: An Efficient, Engine-driven Learning Paradigm for Pursuing Embodied Intelligence using World
+      Models of Generative Simulation},
+   month = {October},
+   year = {2025},
+   journal = {TechRxiv}
+   }
+