alphaXiv

Explore

State of the Art

Sign In

Labs

Feedback

Browser Extension

We're hiring
PaperBlogResources

Adaptive Chain-of-Focus Reasoning via Dynamic Visual Search and Zooming for Efficient VLMs

BibTex
Copy
@misc{zhangFri Dec 05 2025 05:44:39 GMT+0000 (Coordinated Universal Time)adaptivechainoffocusreasoning,
      title={Adaptive Chain-of-Focus Reasoning via Dynamic Visual Search and Zooming for Efficient VLMs},
      author={Xintong Zhang and Zhi Gao and Bofei Zhang and Pengxiang Li and Xiaowen Zhang and Yang Liu and Tao Yuan and Yuwei Wu and Yunde Jia and Song-Chun Zhu and Qing Li},
      year={Fri Dec 05 2025 05:44:39 GMT+0000 (Coordinated Universal Time)},
      eprint={2505.15436},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2505.15436},
}
GitHub
Chain-of-Focus
33
HTTPS
https://github.com/xtong-zhang/Chain-of-Focus
SSH
git@github.com:xtong-zhang/Chain-of-Focus.git
CLI
gh repo clone xtong-zhang/Chain-of-Focus
Transform this paper into an audio lecture
Get an engaging lecture and Q&A format to quickly understand the paper in minutes, perfect for learning on the go.
Audio lecture
Q&A format