@inproceedings{liu-etal-2025-vift,
    title = "{V}i{FT}: Towards Visual Instruction-Free Fine-tuning for Large Vision-Language Models",
    author = "Liu, Zikang  and
      Zhou, Kun  and
      Zhao, Xin  and
      Gao, Dawei  and
      Li, Yaliang  and
      Wen, Ji-Rong",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.547/",
    doi = "10.18653/v1/2025.findings-emnlp.547",
    pages = "10341--10366",
    ISBN = "979-8-89176-335-7",
    abstract = "Visual instruction tuning has become the predominant technology in eliciting the multimodal task-solving capabilities of large vision-language models (LVLMs). Despite the success, as visual instructions require images as the input, it would leave the gap in inheriting the task-solving capabilities from the backbone LLMs, and make it costly to collect a large-scale high-quality dataset. To address it, we propose ViFT, a visual instruction-free fine-tuning framework for LVLMs. In ViFT, we only require the text-only instructions and image caption data during training, to separately learn the task-solving and visual perception abilities. During inference, we extract and combine the representations of the text and image inputs, for fusing the two abilities to fulfill multimodal tasks. Experimental results demonstrate that ViFT can achieve state-of-the-art performance on several downstream benchmarks, with rather less training data. Our code and data will be publicly released."
}