https://github.com/baaivision/Emu

Emu Series: Generative Multimodal Models from BAAI
https://github.com/baaivision/Emu

foundation-models generative-pretraining-in-multimodality in-context-learning instruct-tuning multimodal-generalist multimodal-pretraining

Last synced: 25 days ago
JSON representation

Emu Series: Generative Multimodal Models from BAAI

• Host: GitHub
• URL: https://github.com/baaivision/Emu
• Owner: baaivision
• License: apache-2.0
• Created: 2023-07-11T00:10:19.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-09-27T03:24:23.000Z (3 months ago)
• Last Synced: 2024-11-11T17:11:57.259Z (about 1 month ago)
• Topics: foundation-models, generative-pretraining-in-multimodality, in-context-learning, instruct-tuning, multimodal-generalist, multimodal-pretraining
• Language: Python
• Homepage: https://baaivision.github.io/emu2/
• Size: 46.3 MB
• Stars: 1,659
• Watchers: 21
• Forks: 86
• Open Issues: 42
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• StarryDivineSky - baaivision/Emu
• AiTreasureBox - baaivision/Emu - 12-20_1674_0](https://img.shields.io/github/stars/baaivision/Emu.svg)|Emu Series: Generative Multimodal Models from BAAI| (Repos)
• Awesome-Segment-Anything - [code

README

        


Emu: Generative Multimodal Models from BAAI




---







- [**Emu1**](Emu1) (ICLR 2024, 2023/07) - Generative Pretraining in Multimodality

- [**Emu2**](Emu2) (CVPR 2024, 2023/12) - Generative Multimodal Models are In-Context Learners

- [**Emu3**](https://github.com/baaivision/Emu3) (arXiv 2024, 2024/09) - Next-Token Prediction is All You Need 🔥🔥🔥

## News

- 2024.9 We introduce **Emu3**, a new suite of state-of-the-art multimodal models trained solely with next-token prediction. 🔥🔥🔥

- 2024.2 **Emu1 and Emu2 are accepted by ICLR 2024 and CVPR 2024 respectively! 🎉**

- 2023.12 Inference code, model and demo of Emu2 are available. Enjoy the [demo](http://218.91.113.230:9002/).

- 2023.12 We have released Emu2, open and largest generative multimodal models that achieve new state of the art on multimodal understanding and generation tasks.

- 2023.7 Inference code and model of Emu are available.

- 2023.7 We have released Emu, a multimodal generalist that can seamlessly generate images and texts in multimodal context.

## Hightlights

- State-of-the-art performance

- Next-generation capabilities

- A base model for diverse tasks

We hope to foster the growth of our community through open-sourcing and promoting collaboration👬. Let's step towards multimodal intelligence together🍻.

## Contact

- **We are hiring** at all levels at BAAI Vision Team, including full-time researchers, engineers and interns. 

If you are interested in working with us on **foundation model, visual perception and multimodal learning**, please contact [Xinlong Wang](https://www.xloong.wang/) (`[email protected]`).

## Misc



[![Stargazers repo roster for @baaivision/Emu](https://bytecrank.com/nastyox/reporoster/php/stargazersSVG.php?user=baaivision&repo=Emu)](https://github.com/baaivision/Emu/stargazers)

[![Forkers repo roster for @baaivision/Emu](https://bytecrank.com/nastyox/reporoster/php/forkersSVG.php?user=baaivision&repo=Emu)](https://github.com/baaivision/Emu/network/members)

[![Star History Chart](https://api.star-history.com/svg?repos=baaivision/Emu&type=Date)](https://star-history.com/#baaivision/Emu&Date)