diff --git a/README.md b/README.md
index 8f1531f..c7e06e6 100644
--- a/README.md
+++ b/README.md
@@ -3,12 +3,12 @@
 ## Introduction
 
 This is an implementation repository for our work in EMNLP 2021.
-**Relation-aware Video Reading Comprehension for Temporal Language Grounding**. 
+**Relation-aware Video Reading Comprehension for Temporal Language Grounding**. [arxiv paper](https://arxiv.org/abs/2110.05717)
 
 ![](https://github.com/Huntersxsx/RaNet/blob/master/img/framework.png)
 
 ## Note:
-Our pre-trained models are available at [SJTU jbox](https://jbox.sjtu.edu.cn/l/215Z2T) or [baiduyun, passcode:xmc0](https://pan.baidu.com/s/1CRojAlDURJ57tUprdNbfFg) or [Google Drive](https://drive.google.com/drive/folders/1AFdgfxFCA9ji36HaveL2dQ7wr7OjlHjb?usp=sharing). We will release our code upon the release of our paper.
+Our pre-trained models are available at [SJTU jbox](https://jbox.sjtu.edu.cn/l/215Z2T) or [baiduyun, passcode:xmc0](https://pan.baidu.com/s/1CRojAlDURJ57tUprdNbfFg) or [Google Drive](https://drive.google.com/drive/folders/1AFdgfxFCA9ji36HaveL2dQ7wr7OjlHjb?usp=sharing). We will release our code soon.
 <!-- The repository contains the development code. This preview is intended for the reviewers of our AAAI2022 submission.
 The code provided allows for evaluating our pretrained models. We will release the final version of the code on our official GitHub repo soon.
 We discourage the reviewers from distributing this repository to third party users. Please follow the instructions below for the installation and download of necessary data.  -->
@@ -124,6 +124,8 @@ Use the following commands for testing:
 We greatly appreciate the [2D-Tan repository](https://github.com/microsoft/2D-TAN), [gtad repository](https://github.com/frostinassiky/gtad) and [CCNet repository](https://github.com/speedinghzl/CCNet). Please remember to cite the papers:
 
 ```
+
+
 @InProceedings{2DTAN_2020_AAAI,
 author = {Zhang, Songyang and Peng, Houwen and Fu, Jianlong and Luo, Jiebo},
 title = {Learning 2D Temporal Adjacent Networks forMoment Localization with Natural Language},