diff --git a/doc/imgs/esmm.png b/doc/imgs/esmm.png
new file mode 100644
index 0000000000000000000000000000000000000000..73db53d999503832e893016c41917d962a9e3860
Binary files /dev/null and b/doc/imgs/esmm.png differ
diff --git a/doc/imgs/mmoe.png b/doc/imgs/mmoe.png
new file mode 100644
index 0000000000000000000000000000000000000000..5a64982d84c0897f051d2f5329a71e958d6cc16d
Binary files /dev/null and b/doc/imgs/mmoe.png differ
diff --git a/doc/imgs/share-bottom.png b/doc/imgs/share-bottom.png
new file mode 100644
index 0000000000000000000000000000000000000000..f33872ffaf8d4ff815ba30e4918c091eb89fd812
Binary files /dev/null and b/doc/imgs/share-bottom.png differ
diff --git a/models/multitask/readme.md b/models/multitask/readme.md
index 9c58b33d56581d8c57837e67735164a675761b0d..dc58033819879b6c480b91450ffe6d40c7b4b15e 100755
--- a/models/multitask/readme.md
+++ b/models/multitask/readme.md
@@ -1,7 +1,7 @@
 # 多任务学习模型库
 
 ## 简介
-我们提供了常见的多任务学习中使用的模型算法的PaddleRec实现, 单机训练&预测效果指标以及分布式训练&预测性能指标等。实现的多任务模型包括 [MMoE](http://gitlab.baidu.com/tangwei12/paddlerec/tree/develop/models/multitask/mmoe)、[Share-Bottom](http://gitlab.baidu.com/tangwei12/paddlerec/tree/develop/models/multitask/share-bottom)、[ESMM](http://gitlab.baidu.com/tangwei12/paddlerec/tree/develop/models/multitask/esmm)。
+我们提供了常见的多任务学习中使用的模型算法的PaddleRec实现, 单机训练&预测效果指标以及分布式训练&预测性能指标等。实现的多任务模型包括 [MMoE](mmoe)、[Share-Bottom](share-bottom)、[ESMM](esmm)。
 
 模型算法库在持续添加中，欢迎关注。
 
@@ -19,10 +19,30 @@
 
 |       模型        |       简介        |       论文        |
 | :------------------: | :--------------------: | :---------: |
-| share-bottom | share-bottom | [Multitask learning](http://reports-archive.adm.cs.cmu.edu/anon/1997/CMU-CS-97-203.pdf)(1998) |
+| Share-bottom | share-bottom | [Multitask learning](http://reports-archive.adm.cs.cmu.edu/anon/1997/CMU-CS-97-203.pdf)(1998) |
 | ESMM | Entire Space Multi-Task Model | [Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion Rate](https://arxiv.org/abs/1804.07931)(2018) |
 | MMoE | Multi-gate Mixture-of-Experts | [Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts](https://dl.acm.org/doi/abs/10.1145/3219819.3220007)(2018) |
 
+下面是每个模型的简介（注：图片引用自链接中的论文）
+
+
+[share-bottom](http://reports-archive.adm.cs.cmu.edu/anon/1997/CMU-CS-97-203.pdf):
+<p align="center">
+<img align="center" src="../../doc/imgs/share-bottom.png">
+<p>
+
+
+[esmm](https://arxiv.org/abs/1804.07931):
+<p align="center">
+<img align="center" src="../../doc/imgs/esmm.png">
+<p>
+
+
+[mmoe](https://dl.acm.org/doi/abs/10.1145/3219819.3220007):
+<p align="center">
+<img align="center" src="../../doc/imgs/mmoe.png">
+<p>
+
 ## 使用教程
 ### 训练
 ```shell