alphaXiv

Explore

State of the Art

Sign In

Labs

Feedback

Browser Extension

We're hiring
PaperBlogResources

Multimodal Language Models See Better When They Look Shallower

BibTex
Copy
@misc{chenFri Oct 10 2025 12:32:25 GMT+0000 (Coordinated Universal Time)multimodallanguagemodels,
      title={Multimodal Language Models See Better When They Look Shallower},
      author={Haoran Chen and Junyan Lin and Xinghao Chen and Yue Fan and Jianfeng Dong and Xin Jin and Hui Su and Jinlan Fu and Xiaoyu Shen},
      year={Fri Oct 10 2025 12:32:25 GMT+0000 (Coordinated Universal Time)},
      eprint={2504.21447},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2504.21447},
}
GitHub
VisualProbing-for-MLLM
2
HTTPS
https://github.com/EIT-NLP/VisualProbing-for-MLLM
SSH
git@github.com:EIT-NLP/VisualProbing-for-MLLM.git
CLI
gh repo clone EIT-NLP/VisualProbing-for-MLLM
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