--- license: apache-2.0 datasets: - Senqiao/VisionThink-Smart-Train - Senqiao/VisionThink-Smart-Val base_model: - Qwen/Qwen2.5-VL-7B-Instruct ---

Stanford-Alpaca

# VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning [![Paper](https://img.shields.io/badge/Paper-Arxiv%20Link-light)](https://arxiv.org/abs/2507.13348) [![HF](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Discussion-orange)](https://huggingface.co/papers/2507.13348) [![Code License](https://img.shields.io/badge/Code%20License-Apache_2.0-yellow.svg)](https://github.com/dvlab-research/VisionThink/blob/main/LICENSE) ## Senqiao/VisionThink-Efficient This model is trained via reinforcement learning using [`Senqiao/VisionThink-Smart-Train`](https://huggingface.co/datasets/Senqiao/VisionThink-Smart-Train), demonstrating enhanced performance and efficiency on general VQA tasks. **VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning [[Paper](https://arxiv.org/abs/2507.13348)]**
[Senqiao Yang](https://scholar.google.com/citations?user=NcJc-RwAAAAJ), [Junyi Li](https://scholar.google.com/citations?hl=zh-CN&user=zQ0P3JAAAAAJ), [Xin Lai](https://scholar.google.com/citations?user=tqNDPA4AAAAJ), [Bei Yu](https://scholar.google.com/citations?user=tGneTm4AAAAJ), [Hengshuang Zhao](https://scholar.google.com/citations?user=4uE10I0AAAAJ), [Jiaya Jia](https://scholar.google.com/citations?user=XPAkzTEAAAAJ)
## Highlights

Stanford-Alpaca

1. Our VisionThink leverages reinforcement learning to **autonomously** learn whether to reduce visual tokens. Compared to traditional efficient VLM approaches, our method achieves significant improvements on **fine-grained** benchmarks, such as those involving OCR-related tasks. 2. VisionThink improves performance on **General VQA** tasks while reducing visual tokens by **50%**, achieving **102%** of the original model’s performance across nine benchmarks. 3. VisionThink achieves strong performance and efficiency by simply resizing input images to reduce visual tokens. We hope this inspires further research into **Efficient Reasoning Vision Language Models**. ## Video

Stanford-Alpaca

## Citation If you find this project useful in your research, please consider citing: > This work is highly motivated by our previous effort on efficient VLMs, [**VisionZip**](https://github.com/dvlab-research/VisionZip), which explores token compression for faster inference. ``` @article{yang2025visionthink, title={VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning}, author={Yang, Senqiao and Li, Junyi and Lai, Xin and Yu, Bei and Zhao, Hengshuang and Jia, Jiaya}, journal={arXiv preprint arXiv:2507.13348}, year={2025} } @article{yang2024visionzip, title={VisionZip: Longer is Better but Not Necessary in Vision Language Models}, author={Yang, Senqiao and Chen, Yukang and Tian, Zhuotao and Wang, Chengyao and Li, Jingyao and Yu, Bei and Jia, Jiaya}, journal={arXiv preprint arXiv:2412.04467}, year={2024} } ```