Update README.md

Former-commit-id: 83bd1145fdd2f20f02446944fbd36633fe982e6d

README.md

@@ -1,10 +1,10 @@
 # LISA: Reasoning Segmentation via Large Language Model
 
-<font size=50><div align='center'><b><font size=100>LISA</font></b>: Large <b>L</b>anguage <b>I</b>nstructed <b>S</b>egmentation <b>A</b>ssistant</div></font>
+<div align='center'><b>LISA</b>: Large <b>L</b>anguage <b>I</b>nstructed <b>S</b>egmentation <b>A</b>ssistant</div>
 
-<font size=50><div align='center' >| <a href=https://arxiv.org/abs/2308.00692>[LISA Paper]</a> | <a href=https://huggingface.co/xinlai/LISA-13B-llama2-v0>[LISA Model]</a> | <a>Demo (Comming Soon)</a> |</div></font>
+<font size=50><div align='center' > <a href=https://arxiv.org/abs/2308.00692>Paper</a> | <a href=https://huggingface.co/xinlai/LISA-13B-llama2-v0>Model</a> | <a>Demo (Comming Soon)</a> </div></font>
 
-<!-- This is the official implementation of **LISA(large Language Instructed Segmentation Assistant)**.  -->
+<p align="center"> <img src="imgs/fig_overview.png" width="100%"> </p>
 
 <p align="center"> <img src="imgs/teaser.png" width="100%"> </p>
 
@@ -17,10 +17,6 @@
 - [ ] ReasonSeg Dataset Release
 - [ ] Training Code Release
 
-## Abstract
-In this work, we propose a new segmentation task --- ***reasoning segmentation***. The task is designed to output a segmentation mask given a complex and implicit query text. We establish a benchmark comprising over one thousand image-instruction pairs, incorporating intricate reasoning and world knowledge for evaluation purposes. Finally, we present LISA: Large-language Instructed Segmentation Assistant, which inherits the language generation capabilities of the multi-modal Large Language Model (LLM) while also possessing the ability to produce segmentation masks.
-For more details, please refer to:
-
 **LISA: Reasoning Segmentation Via Large Language Model [[Paper](https://arxiv.org/pdf/2308.00692.pdf)]** <br />
 [Xin Lai](https://scholar.google.com/citations?user=tqNDPA4AAAAJ&hl=zh-CN),
 [Zhuotao Tian](https://scholar.google.com/citations?user=mEjhz-IAAAAJ&hl=en),
@@ -30,7 +26,9 @@ For more details, please refer to:
 [Shu Liu](https://scholar.google.com.hk/citations?user=BUEDUFkAAAAJ&hl=zh-CN),
 [Jiaya Jia](https://scholar.google.com/citations?user=XPAkzTEAAAAJ&hl=en)<br />
 
-<p align="center"> <img src="imgs/fig_overview.png" width="100%"> </p>
+## Abstract
+In this work, we propose a new segmentation task --- ***reasoning segmentation***. The task is designed to output a segmentation mask given a complex and implicit query text. We establish a benchmark comprising over one thousand image-instruction pairs, incorporating intricate reasoning and world knowledge for evaluation purposes. Finally, we present LISA: Large-language Instructed Segmentation Assistant, which inherits the language generation capabilities of the multi-modal Large Language Model (LLM) while also possessing the ability to produce segmentation masks.
+For more details, please refer to:
 
 ## Highlights
 **LISA** unlocks the new segmentation capabilities of multi-modal LLMs, and can handle cases involving: