---
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.