| 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. |