-
Emu1 (Arxiv 2023) - Generative Pretraining in Multimodality
-
Emu2 (Arxiv 2023) - Generative Multimodal Models are In-Context Learners
- 2023.7 Inference code and model of Emu1 are available.
- 2023.12 Inference code, model and Demo of Emu2 are available. Enjoy the Demo.
- State-of-the-art performance
- Next-generation capabilities
- A base model for diverse tasks
- 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 (
wangxinlong@baai.ac.cn).