Top AI Repos β open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
[TMLR 2025π₯] A survey for the autoregressive models in vision.
| Date | Stars |
|---|---|
| 2026-07-30 | 805 |
| 2026-08-10 | 805 |
| 2026-08-18 | 806 |
| 2026-08-26 | 807 |
| 2026-09-02 | 808 |
| 2026-09-14 | 808 |
| 2026-09-16 | 807 |
| 2026-09-23 | 808 |
| 2026-10-07 | 808 |
| 2026-10-10 | 807 |
| 2026-11-04 | 805 |
Today
-2 stars today
This week
-2 stars this week
This month
-3 stars this month
Momentum
0.0
growth rate 0.00%/day
<div align=center>
<img src="img/ARV_logo.png" width="160px">
</div>
<h2 align="center"> <a href="https://arxiv.org/abs/2411.05902">[TMLR 2025] Awesome Autoregressive Models in Vision <div align=center> </a></h2>
<h5 align="center"> If you like our project, please give us a star β on GitHub for the latest update.</h5>
<h5 align="center">
[](https://awesome.re)
[](https://arxiv.org/pdf/2411.05902.pdf)
[](https://mp.weixin.qq.com/s/_O8W1qgvMZu37IKwgtskMA)
</h5>
Autoregressive models have shown significant progress in generating high-quality content by modeling the dependencies sequentially. This repo is a curated list of papers about the latest advancements in autoregressive models in vision.
> **Paper**: [[TMLR 2025π₯]](https://openreview.net/forum?id=1BqXkjNEGP) [Autoregressive Models in Vision: A Survey](https://arxiv.org/abs/2411.05902) | [[δΈζ解读]](https://mp.weixin.qq.com/s/_O8W1qgvMZu37IKwgtskMA)
> **Authors**: *Jing Xiong<sup>1,β </sup>, Gongye Liu<sup>2,β </sup>, Lun Huang<sup>3</sup>, Chengyue Wu<sup>1</sup>, Taiqiang Wu<sup>1</sup>, Yao Mu<sup>1</sup>, Yuan Yao<sup>4</sup>, Hui Shen<sup>5</sup>, Zhongwei Wan<sup>5</sup>, Jinfa Huang<sup>4</sup>, Chaofan Tao<sup>1,β‘</sup>, Shen Yan<sup>6</sup>, Huaxiu Yao<sup>7</sup>, Lingpeng Kong<sup>1</sup>, Hongxia Yang<sup>9</sup>, Mi Zhang<sup>5</sup>, Guillermo Sapiro<sup>8,10</sup>, Jiebo Luo<sup>4</sup>, Ping Luo<sup>1</sup>, Ngai Wong<sup>1</sup>*
> *<sup>1</sup>The University of Hong Kong, <sup>2</sup>Tsinghua University, <sup>3</sup>Duke University, <sup>4</sup>University of Rochester, <sup>5</sup>The Ohio State University, <sup>6</sup>Bytedance, <sup>7</sup>The University of North Carolina at Chapel Hill, <sup>8</sup>Apple, <sup>9</sup>The Hong Kong Polytechnic University, <sup>10</sup>Princeton University*
> *<sup>β </sup> Core Contributors, <sup>β‘</sup> Corresponding Authors*
<br>
<details open><summary>π‘ We also have other generative projects that may interest you β¨. </summary><p>
<!-- may -->
> [**Personalized Video Generation: Progress, Applications, and Challenges**]() <br>
> Jinfa Huang, Shenghai Yuan, Kunyang Li, and Meng Cao etc. <br>
[](https://github.com/inFaaa/Awesome-Personalized-Video-Creation) [](https://github.com/inFaaa/Awesome-Personalized-Video-Creation) <br>
> </p></details>
## π Citation
Please consider citing π our papers if our repository is helpful to your work. Thanks sincerely!
```BibTeX
@misc{xiong2024autoregressive,
title={Autoregressive Models in Vision: A Survey},
author={Jing Xiong and Gongye Liu and Lun Huang and Chengyue Wu and Taiqiang Wu and Yao Mu and Yuan Yao and Hui Shen and Zhongwei Wan and Jinfa Huang and Chaofan Tao and Shen Yan and Huaxiu Yao and Lingpeng Kong and Hongxia Yang and Mi Zhang and Guillermo Sapiro and Jiebo Luo and Ping Luo and Ngai Wong},
year={2024},
eprint={2411.05902},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```
## π£ Update News
`[2025-11-01]` βΈοΈ After a year of rapid progress in autoregressive visual generation, two clear trends now define the field: **unified multimodal models** and **autoregressive diffusion-forcing video generation**. Our current repository categories no longer capture this evolving landscape, so weβre moving to maintenance mode and **pausing proactive updates as of today**. The repo remains available as a reference, and **targeted PRs are welcome** (additions, corrections, or reorganizations with new trends). Thanks for your support! π
`[2025-05-31]` π₯ Our survey has been revised in [arXiv](https://arxiv.oExcerpt of 93,747 characters
Read on GitHub
Jinfa Huang Β· UR & PKU & UESTC
244
11
9
4
3
1
Vinh H. Pham Β· Vietnam
1
1
1
1
Zhicheng Sun Β· Peking University
1
Yi Jiang Β· Bytedance Seed Β· United States
1
1
1
Would you bet a product on this? Bounded 0β100 and slow moving.
matched fp:6c5486d69d089224, topic:image-generation, topic:text-to-image
matched fp:6c5486d69d089224, topic:deep-learning
matched fp:6c5486d69d089224, topic:video-generation, readme:video generation
matched fp:6c5486d69d089224, topic:multimodal, readme:multimodal