---
title: LCL-ViT-B-16-Laion
canonical_url: "https://www.modelscope.ai/models/Shanghai_AI_Laboratory/LCL-ViT-B-16-Laion"
md_url: "https://www.modelscope.ai/models/Shanghai_AI_Laboratory/LCL-ViT-B-16-Laion.md"
repository: Shanghai_AI_Laboratory/LCL-ViT-B-16-Laion
last_updated: 2026-11-09
license: mit
library_name:
  - pytorch
frameworks:
  - pytorch
downloads: 252
stars: 0
---

# LCL-ViT-B-16-Laion

> LCL-ViT-B-16-Laion - An open-source model by Shanghai_AI_Laboratory on ModelScope. [\[📜 Paper\]](https://arxiv.org/abs/2406.07543) [\[📂 GitHub\]](https://github.com/OpenGVLab/LCL)

Shanghai_AI_Laboratory/LCL-ViT-B-16-Laion is a machine learning model on ModelScope. licensed under mit.

- **Repository**: Shanghai_AI_Laboratory/LCL-ViT-B-16-Laion
- **License**: mit
- **Downloads**: 252
- **Stars**: 0
- **Last updated**: 2026-11-09

Source: https://www.modelscope.ai/models/Shanghai_AI_Laboratory/LCL-ViT-B-16-Laion

---

# 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.