Update README.md
Browse files
README.md
CHANGED
@@ -2,13 +2,13 @@
|
|
2 |
|
3 |
<div align='center'>
|
4 |
<h1>Emu: An Open Multimodal Generalist</h1h1>
|
5 |
-
<h3><a href="">Generative Pretraining in Multimodality</a></h3>
|
6 |
|
7 |
[Quan Sun](https://github.com/Quan-Sun)<sup>1*</sup>, [Qiying Yu](https://yqy2001.github.io)<sup>2,1*</sup>, [Yufeng Cui]()<sup>1*</sup>, [Fan Zhang]()<sup>1*</sup>, [Xiaosong Zhang](https://github.com/zhangxiaosong18)<sup>1*</sup>, [Yueze Wang]()<sup>1</sup>, [Hongcheng Gao]()<sup>1</sup>, [Jingjing Liu](https://air.tsinghua.edu.cn/en/info/1046/1194.htm)<sup>2</sup>, [Tiejun Huang](https://scholar.google.com/citations?user=knvEK4AAAAAJ&hl=en)<sup>1,3</sup>, [Xinlong Wang](https://www.xloong.wang/)<sup>1</sup>
|
8 |
|
9 |
<sup>1</sup> [BAAI](https://www.baai.ac.cn/english.html), <sup>2</sup> [THU](https://air.tsinghua.edu.cn), <sup>3</sup> [PKU](https://english.pku.edu.cn/) <br><sup>*</sup> Equal Contribution
|
10 |
|
11 |
-
| [Paper]() | [Demo(
|
12 |
</div>
|
13 |
|
14 |
**Emu** is a Large Multimodal Model (LMM) trained with a unified autoregressive objective, *i.e.*, predict-the-next-element, including both visual embeddings and textual tokens. Trained under this objective, **Emu** can serve as a generalist interface for diverse multimodal tasks, such as image captioning, image/video question answering, and text-to-image generation, together with new abilities like in-context text and image generation, and image blending.
|
@@ -49,7 +49,7 @@ If you find Emu useful for your your research and applications, please consider
|
|
49 |
@article{Emu,
|
50 |
title={Generative Pretraining in Multimodality},
|
51 |
author={Sun, Quan and Yu, Qiying and Cui, Yufeng and Zhang, Fan and Zhang, Xiaosong and Wang, Yueze and Gao, Hongcheng and Liu, Jingjing and Huang, Tiejun and Wang, Xinlong},
|
52 |
-
publisher={arXiv:},
|
53 |
year={2023},
|
54 |
}
|
55 |
|
|
|
2 |
|
3 |
<div align='center'>
|
4 |
<h1>Emu: An Open Multimodal Generalist</h1h1>
|
5 |
+
<h3><a href="https://arxiv.org/abs/2307.05222">Generative Pretraining in Multimodality</a></h3>
|
6 |
|
7 |
[Quan Sun](https://github.com/Quan-Sun)<sup>1*</sup>, [Qiying Yu](https://yqy2001.github.io)<sup>2,1*</sup>, [Yufeng Cui]()<sup>1*</sup>, [Fan Zhang]()<sup>1*</sup>, [Xiaosong Zhang](https://github.com/zhangxiaosong18)<sup>1*</sup>, [Yueze Wang]()<sup>1</sup>, [Hongcheng Gao]()<sup>1</sup>, [Jingjing Liu](https://air.tsinghua.edu.cn/en/info/1046/1194.htm)<sup>2</sup>, [Tiejun Huang](https://scholar.google.com/citations?user=knvEK4AAAAAJ&hl=en)<sup>1,3</sup>, [Xinlong Wang](https://www.xloong.wang/)<sup>1</sup>
|
8 |
|
9 |
<sup>1</sup> [BAAI](https://www.baai.ac.cn/english.html), <sup>2</sup> [THU](https://air.tsinghua.edu.cn), <sup>3</sup> [PKU](https://english.pku.edu.cn/) <br><sup>*</sup> Equal Contribution
|
10 |
|
11 |
+
| [Paper](https://arxiv.org/abs/2307.05222) | [Demo(tmp)](http://218.91.113.230:9002/) |
|
12 |
</div>
|
13 |
|
14 |
**Emu** is a Large Multimodal Model (LMM) trained with a unified autoregressive objective, *i.e.*, predict-the-next-element, including both visual embeddings and textual tokens. Trained under this objective, **Emu** can serve as a generalist interface for diverse multimodal tasks, such as image captioning, image/video question answering, and text-to-image generation, together with new abilities like in-context text and image generation, and image blending.
|
|
|
49 |
@article{Emu,
|
50 |
title={Generative Pretraining in Multimodality},
|
51 |
author={Sun, Quan and Yu, Qiying and Cui, Yufeng and Zhang, Fan and Zhang, Xiaosong and Wang, Yueze and Gao, Hongcheng and Liu, Jingjing and Huang, Tiejun and Wang, Xinlong},
|
52 |
+
publisher={arXiv:2307.05222},
|
53 |
year={2023},
|
54 |
}
|
55 |
|