Skip Tuning: Pre-trained Vision-Language Models are Effective and Efficient Adapters Themselves

@misc{zhang2025skiptuningpretrained,
      title={Skip Tuning: Pre-trained Vision-Language Models are Effective and Efficient Adapters Themselves}, 
      author={Ji Zhang and Lianli Gao and Jingkuan Song and Heng Tao Shen and Pengpeng Zeng and Shihan Wu},
      year={2025},
      eprint={2412.11509},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2412.11509}, 
}