diff --git a/.github/workflows/test_release.yml b/.github/workflows/test_release.yml
deleted file mode 100644
index 67ca365..0000000
--- a/.github/workflows/test_release.yml
+++ /dev/null
@@ -1,56 +0,0 @@
-name: Publish to TestPyPI
-
-on:
-  # Trigger this workflow when a new tag is pushed
-  push:
-    tags:
-      - 'test*'
-
-jobs:
-  build:
-    name: Build distribution 📦
-    runs-on: ubuntu-latest
-
-    steps:
-    - uses: actions/checkout@v4
-    - name: Set up Python
-      uses: actions/setup-python@v5
-      with:
-        python-version: "3.x"
-    - name: Install pypa/build
-      run: >-
-        python3 -m
-        pip install
-        build
-        --user
-    - name: Build a binary wheel and a source tarball
-      run: python3 -m build
-    - name: Store the distribution packages
-      uses: actions/upload-artifact@v4
-      with:
-        name: python-package-distributions
-        path: dist/
-
-  publish-to-testpypi:
-    name: Publish Python 🐍 distribution 📦 to TestPyPI
-    needs:
-    - build
-    runs-on: ubuntu-latest
-
-    environment:
-      name: testpypi
-      url: https://test.pypi.org/p/GenerativeRL
-
-    permissions:
-      id-token: write  # IMPORTANT: mandatory for trusted publishing
-
-    steps:
-    - name: Download all the dists
-      uses: actions/download-artifact@v4
-      with:
-        name: python-package-distributions
-        path: dist/
-    - name: Publish distribution 📦 to TestPyPI
-      uses: pypa/gh-action-pypi-publish@release/v1
-      with:
-        repository-url: https://test.pypi.org/legacy/
diff --git a/README.md b/README.md
index 1feb2e5..544a611 100644
--- a/README.md
+++ b/README.md
@@ -1,4 +1,4 @@
-# Generative Reinforcement Learning (GRL)
+# Generative Reinforcement Learning
 
 [![Twitter](https://img.shields.io/twitter/url?style=social&url=https%3A%2F%2Ftwitter.com%2Fopendilab)](https://twitter.com/opendilab)    
 [![GitHub stars](https://img.shields.io/github/stars/opendilab/GenerativeRL)](https://github.com/opendilab/GenerativeRL/stargazers)
@@ -57,6 +57,7 @@ English | [简体中文(Simplified Chinese)](https://github.com/opendilab/Genera
 
 | Algo./Models                                        | Diffusion Model                                                                                                                                             |  Flow Model            |
 |---------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------- |
+| [IDQL](https://arxiv.org/abs/2304.10573)            | ✔                                                                                                                                                           |  🚫                   |
 | [QGPO](https://arxiv.org/abs/2304.12824)            | ✔                                                                                                                                                           |  🚫                   |
 | [SRPO](https://arxiv.org/abs/2310.07297)            | ✔                                                                                                                                                           |  🚫                   |
 | GMPO                                                | ✔  [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1A79ueOdLvTfrytjOPyfxb6zSKXi1aePv)  | ✔                     |
@@ -66,7 +67,7 @@ English | [简体中文(Simplified Chinese)](https://github.com/opendilab/Genera
 ## Installation
 
 ```bash
-pip install grl
+pip install GenerativeRL
 ```
 
 Or, if you want to install from source:
@@ -142,6 +143,18 @@ We offer some baseline experiments to evaluate the performance of generative rei
 
 We welcome contributions to GenerativeRL! If you are interested in contributing, please refer to the [Contributing Guide](CONTRIBUTING.md).
 
+## Citation
+
+```latex
+@misc{generative_rl,
+    title={GenerativeRL: A Python Library for Solving Reinforcement Learning Problems Using Generative Models},
+    author={Zhang, Jinouwen and Xue, Rongkun and Niu, Yazhe and Chen, Yun and Chen, Xinyan and Wang, Ruiheng and Liu, Yu},
+    publisher={GitHub},
+    howpublished={\url{https://github.com/opendilab/GenerativeRL}},
+    year={2024},
+}
+```
+
 ## License
 
 GenerativeRL is licensed under the Apache License 2.0. See [LICENSE](LICENSE) for more details.
diff --git a/README.zh.md b/README.zh.md
index 00d7263..f413088 100644
--- a/README.zh.md
+++ b/README.zh.md
@@ -55,6 +55,7 @@
 
 | 算法/模型                                           | 扩散模型                                                                                                                                                               | 流模型                  |
 |---------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------- |
+| [IDQL](https://arxiv.org/abs/2304.10573)            | ✔                                                                                                                                                                    |  🚫                   |
 | [QGPO](https://arxiv.org/abs/2304.12824)            | ✔                                                                                                                                                                    |  🚫                   |
 | [SRPO](https://arxiv.org/abs/2310.07297)            | ✔                                                                                                                                                                    |  🚫                   |
 | GMPO                                                | ✔  [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1A79ueOdLvTfrytjOPyfxb6zSKXi1aePv)           | ✔                     |
@@ -63,7 +64,7 @@
 ## 安装
 
 ```bash
-pip install grl
+pip install GenerativeRL
 ```
 
 或者，如果你想从源码安装：
@@ -139,6 +140,18 @@ if __name__ == '__main__':
 
 我们欢迎所有对 GenerativeRL 的贡献和支持！请参考 [开源贡献指南](CONTRIBUTING.md)。
 
+## 引用
+
+```latex
+@misc{generative_rl,
+    title={GenerativeRL: A Python Library for Solving Reinforcement Learning Problems Using Generative Models},
+    author={Zhang, Jinouwen and Xue, Rongkun and Niu, Yazhe and Chen, Yun and Chen, Xinyan and Wang, Ruiheng and Liu, Yu},
+    publisher={GitHub},
+    howpublished={\url{https://github.com/opendilab/GenerativeRL}},
+    year={2024},
+}
+```
+
 ## 开源协议
 
 GenerativeRL 开源协议为 Apache License 2.0。更多信息和文档，请参考 [开源协议](LICENSE)。
diff --git a/docs/source/tutorials/installation/index.rst b/docs/source/tutorials/installation/index.rst
index 000f97a..633d77c 100644
--- a/docs/source/tutorials/installation/index.rst
+++ b/docs/source/tutorials/installation/index.rst
@@ -5,7 +5,7 @@ GenerativeRL can be installed using pip:
 
 .. code-block:: console
 
-   $ pip install grl
+   $ pip install GenerativeRL
 
 You can also install the latest development version from GitHub:
 
diff --git a/grl_pipelines/tutorials/README.md b/grl_pipelines/tutorials/README.md
index 174408e..af6086b 100644
--- a/grl_pipelines/tutorials/README.md
+++ b/grl_pipelines/tutorials/README.md
@@ -2,22 +2,52 @@
 
 English | [简体中文(Simplified Chinese)](https://github.com/opendilab/GenerativeRL/tree/main/grl_pipelines/tutorials/README.zh.md)
 
-## Train a Generative Model
+## Train a generative model
 
-### Diffusion Model
+### Diffusion model
 
-We provide a simple colab notebook to demonstrate how to build a diffusion model using the `grl` library. You can access the notebook [here](https://colab.research.google.com/drive/18yHUAmcMh_7xq2U6TBCtcLKX2y4YvNyk#scrollTo=aqtDAvG6cQ1V).
+We provide a simple colab notebook to demonstrate how to build a diffusion model using the `GenerativeRL` library. You can access the notebook [here](https://colab.research.google.com/drive/18yHUAmcMh_7xq2U6TBCtcLKX2y4YvNyk#scrollTo=aqtDAvG6cQ1V).
 
-### Flow Model
+### Flow model
 
-We provide a simple colab notebook to demonstrate how to build a flow model using the `grl` library. You can access the notebook [here](https://colab.research.google.com/drive/1vrxREVXKsSbnsv9G2CnKPVvrbFZleElI?usp=drive_link).
+We provide a simple colab notebook to demonstrate how to build a flow model using the `GenerativeRL` library. You can access the notebook [here](https://colab.research.google.com/drive/1vrxREVXKsSbnsv9G2CnKPVvrbFZleElI?usp=drive_link).
 
-## Evaluate a Generative Model
+## Evaluate a generative model
 
-### Sample Generation
+### Sample generation
 
-We provide a simple colab notebook to demonstrate how to generate samples from a trained generative model using the `grl` library. You can access the notebook [here](https://colab.research.google.com/drive/16jQhf1BDjtToxMZ4lDxB4IwGdRmr074j?usp=sharing).
+We provide a simple colab notebook to demonstrate how to generate samples from a trained generative model using the `GenerativeRL` library. You can access the notebook [here](https://colab.research.google.com/drive/16jQhf1BDjtToxMZ4lDxB4IwGdRmr074j?usp=sharing).
 
-### Density Estimation
+### Density estimation
 
-We provide a simple colab notebook to demonstrate how to estimate the density of samples using a trained generative model using the `grl` library. You can access the notebook [here](https://colab.research.google.com/drive/1zHsW13n338YqX87AIWG26KLC4uKQL1ZP?usp=sharing).
+We provide a simple colab notebook to demonstrate how to estimate the density of samples using a trained generative model using the `GenerativeRL` library. You can access the notebook [here](https://colab.research.google.com/drive/1zHsW13n338YqX87AIWG26KLC4uKQL1ZP?usp=sharing).
+
+## Tutorials via toy examples
+
+We provide several toy examples to demonstrate the features of the `GenerativeRL` library. You can access the examples [here](https://github.com/opendilab/GenerativeRL/tree/main/grl_pipelines/tutorials/).
+
+### Diverse generative models
+
+- [Diffusion Model](https://github.com/opendilab/GenerativeRL/tree/main/grl_pipelines/tutorials/generative_models/swiss_roll_diffusion.py)
+- [Energy condition Diffusion Model](https://github.com/opendilab/GenerativeRL/tree/main/grl_pipelines/tutorials/generative_models/swiss_roll_energy_condition.py)
+- [Independent Conditional Flow Matching Model](https://github.com/opendilab/GenerativeRL/tree/main/grl_pipelines/tutorials/generative_models/swiss_roll_icfm.py)
+- [Optimal Transport Conditional Flow Matching Model](https://github.com/opendilab/GenerativeRL/tree/main/grl_pipelines/tutorials/generative_models/swiss_roll_otcfm.py)
+- [SF2M](https://github.com/opendilab/GenerativeRL/tree/main/grl_pipelines/tutorials/generative_models/swiss_roll_otcfm.py)
+
+### Generative model applications
+
+- [World Model](https://github.com/opendilab/GenerativeRL/tree/main/grl_pipelines/tutorials/applications/swiss_roll_world_model.py)
+
+### Generative model evaluation
+
+- [Likelihood Evaluation](https://github.com/opendilab/GenerativeRL/tree/main/grl_pipelines/tutorials/metrics/swiss_roll_likelihood.py)
+
+### ODE/SDE solvers usages
+
+- [DPM Solver](https://github.com/opendilab/GenerativeRL/tree/main/grl_pipelines/tutorials/solvers/swiss_roll_dpmsolver.py)
+- [SDE Solver](https://github.com/opendilab/GenerativeRL/tree/main/grl_pipelines/tutorials/solvers/swiss_roll_sdesolver.py)
+
+### Special usages in GenerativeRL
+
+- [Customized Neural Network Modules](https://github.com/opendilab/GenerativeRL/tree/main/grl_pipelines/tutorials/special_usages/customized_modules.py)
+- [Dict-like Structure Data Generation](https://github.com/opendilab/GenerativeRL/tree/main/grl_pipelines/tutorials/special_usages/dict_tensor_ode.py)
diff --git a/grl_pipelines/tutorials/README.zh.md b/grl_pipelines/tutorials/README.zh.md
index 4991c1d..72e5252 100644
--- a/grl_pipelines/tutorials/README.zh.md
+++ b/grl_pipelines/tutorials/README.zh.md
@@ -6,18 +6,48 @@
 
 ### 扩散模型
 
-我们提供了一个简单的 colab 笔记本，演示如何使用 `grl` 库构建扩散模型。您可以在[这里](https://colab.research.google.com/drive/18yHUAmcMh_7xq2U6TBCtcLKX2y4YvNyk#scrollTo=aqtDAvG6cQ1V)访问笔记本。
+我们提供了一个简单的 colab 笔记本，演示如何使用 `GenerativeRL` 库构建扩散模型。您可以在[这里](https://colab.research.google.com/drive/18yHUAmcMh_7xq2U6TBCtcLKX2y4YvNyk#scrollTo=aqtDAvG6cQ1V)访问笔记本。
 
 ### 流模型
 
-我们提供了一个简单的 colab 笔记本，演示如何使用 `grl` 库构建流模型。您可以在[这里](https://colab.research.google.com/drive/1vrxREVXKsSbnsv9G2CnKPVvrbFZleElI?usp=drive_link)访问笔记本。
+我们提供了一个简单的 colab 笔记本，演示如何使用 `GenerativeRL` 库构建流模型。您可以在[这里](https://colab.research.google.com/drive/1vrxREVXKsSbnsv9G2CnKPVvrbFZleElI?usp=drive_link)访问笔记本。
 
 ## 评估生成模型
 
 ### 采样生成
 
-我们提供了一个简单的 colab 笔记本，演示如何使用 `grl` 库从训练有素的生成模型生成样本。您可以在[这里](https://colab.research.google.com/drive/16jQhf1BDjtToxMZ4lDxB4IwGdRmr074j?usp=sharing)访问笔记本。
+我们提供了一个简单的 colab 笔记本，演示如何使用 `GenerativeRL` 库从训练有素的生成模型生成样本。您可以在[这里](https://colab.research.google.com/drive/16jQhf1BDjtToxMZ4lDxB4IwGdRmr074j?usp=sharing)访问笔记本。
 
 ### 概率密度估计
 
-我们提供了一个简单的 colab 笔记本，演示如何使用 `grl` 库从训练有素的生成模型估计样本的概率密度。您可以在[这里](https://colab.research.google.com/drive/1zHsW13n338YqX87AIWG26KLC4uKQL1ZP?usp=sharing)访问笔记本。
+我们提供了一个简单的 colab 笔记本，演示如何使用 `GenerativeRL` 库从训练有素的生成模型估计样本的概率密度。您可以在[这里](https://colab.research.google.com/drive/1zHsW13n338YqX87AIWG26KLC4uKQL1ZP?usp=sharing)访问笔记本。
+
+## 玩具示例教程
+
+我们提供了几个玩具示例，演示了 `GenerativeRL` 库的特性。您可以在[这里](https://github.com/opendilab/GenerativeRL/tree/main/grl_pipelines/tutorials/)访问示例。
+
+### 多种生成模型
+
+- [扩散模型](https://github.com/opendilab/GenerativeRL/tree/main/grl_pipelines/tutorials/generative_models/swiss_roll_diffusion.py)
+- [能量条件扩散模型](https://github.com/opendilab/GenerativeRL/tree/main/grl_pipelines/tutorials/generative_models/swiss_roll_energy_condition.py)
+- [独立条件流匹配模型](https://github.com/opendilab/GenerativeRL/tree/main/grl_pipelines/tutorials/generative_models/swiss_roll_icfm.py)
+- [最优输运条件流匹配模型](https://github.com/opendilab/GenerativeRL/tree/main/grl_pipelines/tutorials/generative_models/swiss_roll_otcfm.py)
+- [SF2M](https://github.com/opendilab/GenerativeRL/tree/main/grl_pipelines/tutorials/generative_models/swiss_roll_otcfm.py)
+
+### 生成模型应用
+
+- [世界模型](https://github.com/opendilab/GenerativeRL/tree/main/grl_pipelines/tutorials/applications/swiss_roll_world_model.py)
+
+### 生成模型评估
+
+- [似然性评估](https://github.com/opendilab/GenerativeRL/tree/main/grl_pipelines/tutorials/metrics/swiss_roll_likelihood.py)
+
+### ODE/SDE 求解器用法
+
+- [DPM 求解器](https://github.com/opendilab/GenerativeRL/tree/main/grl_pipelines/tutorials/solvers/swiss_roll_dpmsolver.py)
+- [SDE 求解器](https://github.com/opendilab/GenerativeRL/tree/main/grl_pipelines/tutorials/solvers/swiss_roll_sdesolver.py)
+
+### GenerativeRL 的特殊用法
+
+- [自定义神经网络模块](https://github.com/opendilab/GenerativeRL/tree/main/grl_pipelines/tutorials/special_usages/customized_modules.py)
+- [类似字典结构的数据生成](https://github.com/opendilab/GenerativeRL/tree/main/grl_pipelines/tutorials/special_usages/dict_tensor_ode.py)
diff --git a/grl_pipelines/tutorials/rl_examples/swiss_roll_world_model.py b/grl_pipelines/tutorials/applications/swiss_roll_world_model.py
similarity index 100%
rename from grl_pipelines/tutorials/rl_examples/swiss_roll_world_model.py
rename to grl_pipelines/tutorials/applications/swiss_roll_world_model.py
diff --git a/grl_pipelines/tutorials/toy_examples/swiss_roll/swiss_roll_diffusion.py b/grl_pipelines/tutorials/generative_models/swiss_roll_diffusion.py
similarity index 100%
rename from grl_pipelines/tutorials/toy_examples/swiss_roll/swiss_roll_diffusion.py
rename to grl_pipelines/tutorials/generative_models/swiss_roll_diffusion.py
diff --git a/grl_pipelines/tutorials/toy_examples/swiss_roll_discrete/swiss_roll_discrete_flow_model.py b/grl_pipelines/tutorials/generative_models/swiss_roll_discrete_flow_model.py
similarity index 100%
rename from grl_pipelines/tutorials/toy_examples/swiss_roll_discrete/swiss_roll_discrete_flow_model.py
rename to grl_pipelines/tutorials/generative_models/swiss_roll_discrete_flow_model.py
diff --git a/grl_pipelines/tutorials/toy_examples/swiss_roll/swiss_roll_energy_condition.py b/grl_pipelines/tutorials/generative_models/swiss_roll_energy_condition.py
similarity index 100%
rename from grl_pipelines/tutorials/toy_examples/swiss_roll/swiss_roll_energy_condition.py
rename to grl_pipelines/tutorials/generative_models/swiss_roll_energy_condition.py
diff --git a/grl_pipelines/tutorials/toy_examples/swiss_roll/swiss_roll_icfm.py b/grl_pipelines/tutorials/generative_models/swiss_roll_icfm.py
similarity index 100%
rename from grl_pipelines/tutorials/toy_examples/swiss_roll/swiss_roll_icfm.py
rename to grl_pipelines/tutorials/generative_models/swiss_roll_icfm.py
diff --git a/grl_pipelines/tutorials/toy_examples/swiss_roll/swiss_roll_icfm_with_mask.py b/grl_pipelines/tutorials/generative_models/swiss_roll_icfm_with_mask.py
similarity index 100%
rename from grl_pipelines/tutorials/toy_examples/swiss_roll/swiss_roll_icfm_with_mask.py
rename to grl_pipelines/tutorials/generative_models/swiss_roll_icfm_with_mask.py
diff --git a/grl_pipelines/tutorials/toy_examples/swiss_roll/swiss_roll_otcfm.py b/grl_pipelines/tutorials/generative_models/swiss_roll_otcfm.py
similarity index 100%
rename from grl_pipelines/tutorials/toy_examples/swiss_roll/swiss_roll_otcfm.py
rename to grl_pipelines/tutorials/generative_models/swiss_roll_otcfm.py
diff --git a/grl_pipelines/tutorials/toy_examples/swiss_roll/swiss_roll_sf2m.py b/grl_pipelines/tutorials/generative_models/swiss_roll_sf2m.py
similarity index 100%
rename from grl_pipelines/tutorials/toy_examples/swiss_roll/swiss_roll_sf2m.py
rename to grl_pipelines/tutorials/generative_models/swiss_roll_sf2m.py
diff --git a/grl_pipelines/tutorials/toy_examples/swiss_roll/swiss_roll_likelihood.py b/grl_pipelines/tutorials/metrics/swiss_roll_likelihood.py
similarity index 100%
rename from grl_pipelines/tutorials/toy_examples/swiss_roll/swiss_roll_likelihood.py
rename to grl_pipelines/tutorials/metrics/swiss_roll_likelihood.py
diff --git a/grl_pipelines/tutorials/toy_examples/swiss_roll/swiss_roll_dpmsolver.py b/grl_pipelines/tutorials/solvers/swiss_roll_dpmsolver.py
similarity index 100%
rename from grl_pipelines/tutorials/toy_examples/swiss_roll/swiss_roll_dpmsolver.py
rename to grl_pipelines/tutorials/solvers/swiss_roll_dpmsolver.py
diff --git a/grl_pipelines/tutorials/toy_examples/swiss_roll/swiss_roll_sdesolver.py b/grl_pipelines/tutorials/solvers/swiss_roll_sdesolver.py
similarity index 100%
rename from grl_pipelines/tutorials/toy_examples/swiss_roll/swiss_roll_sdesolver.py
rename to grl_pipelines/tutorials/solvers/swiss_roll_sdesolver.py
diff --git a/grl_pipelines/tutorials/customized_modules.py b/grl_pipelines/tutorials/special_usages/customized_modules.py
similarity index 99%
rename from grl_pipelines/tutorials/customized_modules.py
rename to grl_pipelines/tutorials/special_usages/customized_modules.py
index 3840d3f..e5db821 100644
--- a/grl_pipelines/tutorials/customized_modules.py
+++ b/grl_pipelines/tutorials/special_usages/customized_modules.py
@@ -100,7 +100,7 @@
             lr=5e-3,
             data_num=10000,
             iterations=1000,
-            batch_size=2048,
+            batch_size=4096,
             clip_grad_norm=1.0,
             eval_freq=500,
             checkpoint_freq=100,
diff --git a/grl_pipelines/tutorials/dict_tensor_ode.py b/grl_pipelines/tutorials/special_usages/dict_tensor_ode.py
similarity index 99%
rename from grl_pipelines/tutorials/dict_tensor_ode.py
rename to grl_pipelines/tutorials/special_usages/dict_tensor_ode.py
index 1d0eae4..6a951c9 100644
--- a/grl_pipelines/tutorials/dict_tensor_ode.py
+++ b/grl_pipelines/tutorials/special_usages/dict_tensor_ode.py
@@ -124,7 +124,7 @@ def forward(
             lr=5e-4,
             data_num=10000,
             iterations=3000,
-            batch_size=2048,
+            batch_size=4096,
             clip_grad_norm=1.0,
             eval_freq=2999,
             checkpoint_freq=100,