README.md

---

license: mit
---


# LCL-ViT-B/16_Laion



[\[📜 Paper\]](https://arxiv.org/abs/2406.07543)

[\[📂 GitHub\]](https://github.com/OpenGVLab/LCL)



This is the model of the paper [Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning](https://arxiv.org/abs/2406.07543).



Please refer to https://github.com/OpenGVLab/LCL for details.