diff --git a/docs/source/_static/FL-framework.png b/docs/source/_static/FL-framework.png
index 1cb16f37d00e100aaeb5b62f558e7434f6007571..b2c228e1948c13508fc8433cbc48a6d4d62aa59f 100644
Binary files a/docs/source/_static/FL-framework.png and b/docs/source/_static/FL-framework.png differ
diff --git a/docs/source/examples/md/dpsgd-example.md b/docs/source/examples/md/dpsgd-example.md
index 5fc95639b8ac3c29d0772b7ed46daeda60a3f9d1..1397acf3968bf6a9c18933c77c22c3289fa095c3 100644
--- a/docs/source/examples/md/dpsgd-example.md
+++ b/docs/source/examples/md/dpsgd-example.md
@@ -213,4 +213,4 @@ while not trainer.stop():
To show the effectiveness of DPSGD-based federated learning with PaddleFL, a simulated experiment is conducted on an open source dataset MNIST. From the figure given below, model evaluation results are similar between DPSGD-based federated learning and traditional parameter server training when the overall privacy budget *epsilon* is 1.3 or 0.13.
-
+
diff --git a/docs/source/examples/md/gru4rec_examples.md b/docs/source/examples/md/gru4rec_examples.md
index 97178aed1c9aae6663c2ce9b1af54f9975994b05..4b49bc408a59870dc1fdd08860441e3088e96f7f 100644
--- a/docs/source/examples/md/gru4rec_examples.md
+++ b/docs/source/examples/md/gru4rec_examples.md
@@ -109,4 +109,4 @@ wget https://paddle-zwh.bj.bcebos.com/gru4rec_paddlefl_benchmark/gru4rec_benchma
| 1/4 of the whole dataset | private training | - | 0.269 |
| 1/4 of the whole dataset | private training | - | 0.282 |
-
+
diff --git a/docs/source/examples/md/uci_demo.md b/docs/source/examples/md/uci_demo.md
index 4fd5d3a7a9254ab1652fe558855d5b4480222388..ccd2b9b826213cab383b264eb700f516cc4d6f48 100644
--- a/docs/source/examples/md/uci_demo.md
+++ b/docs/source/examples/md/uci_demo.md
@@ -1,7 +1,5 @@
## Instructions for PaddleFL-MPC UCI Housing Demo
-([简体中文](./README_CN.md)|English)
-
This document introduces how to run UCI Housing demo based on Paddle-MPC, which has two ways of running, i.e., single machine and multi machines.
### 1. Running on Single Machine
diff --git a/docs/source/md/introduction.md b/docs/source/md/introduction.md
index e283ccd1465b447349ef2387d06586ccc31e3969..8822e48f0179b4b24da0776455778c8ac05a2b86 100644
--- a/docs/source/md/introduction.md
+++ b/docs/source/md/introduction.md
@@ -8,7 +8,8 @@ Data is becoming more and more expensive nowadays, and sharing of raw data is ve
## Overview of PaddleFL
-
+
+
In PaddleFL, horizontal and vertical federated learning strategies will be implemented according to the categorization given in [4]. Application demonstrations in natural language processing, computer vision and recommendation will be provided in PaddleFL.
@@ -36,7 +37,7 @@ Besides, PFM is implemented based on secure multi-party computation (MPC) to ena
### Data Parallel
-
+
In Data Parallel, components for defining a federated learning task and training a federated learning job are as follows:
@@ -60,7 +61,7 @@ In Data Parallel, components for defining a federated learning task and training
### Federated Learning with MPC
-
+
Paddle FL MPC implements secure training and inference tasks based on the underlying MPC protocol like ABY3[11], which is a high efficient three-party computing model.