arXiv Artificial Intelligence

VFA: Empowering Multilingual MLLMs via Vision-Free Adaptation

12 days ago 29.08.2026 07:00 👁 1 views
VFA: Empowering Multilingual MLLMs via Vision-Free Adaptation

Quick summary

arXiv:2608.26155v1 Announce Type: cross Abstract: Multimodal large language models have advanced rapidly, yet most remain English-centric, as scaling multilingual multimodal instruction tuning is limited by the scarcity and high cost of high-quality non-English image-text supervision. Although multilingual text data is abundant, naive textual fine-tuning can disrupt vision-language alignment and induce catastrophic forgetting. We propose Vision-Free Adaptation (VFA), a framework that decouples multilingual language enhancement from visual alignment by composing complementary task vectors over

Key takeaways

  • arXiv:2608.26155v1 Announce Type: cross Abstract: Multimodal large language models have advanced rapidly, yet most remain English-centric, as scaling multilingual multimodal instruction tuning is limited by the scarcity and high cost of high-quality non-English image-text supervision.
  • Although multilingual text data is abundant, naive textual fine-tuning can disrupt vision-language alignment and induce catastrophic forgetting.
  • We propose Vision-Free Adaptation (VFA), a framework that decouples multilingual language enhancement from visual alignment by composing complementary task vectors over

Why it matters

“VFA: Empowering Multilingual MLLMs via Vision-Free Adaptation” should be evaluated beyond branding and benchmark scores. Its practical importance will emerge in task accuracy, latency, unit cost, safety and integration with real workflows.

Kaynak sitede devamını oku: arXiv Artificial Intelligence ↗