作者位次 #2/9ACL 2026Poster· Natural Language Processing
VFA : Empowering Multilingual MLLM s via Vision-Free Adaptation
Yixia Li · Yaqing Shi · Zhiwen Ruan · Dongdong Zhang · Lingjie Jiang · Shaohan Huang · Yun Chen · Guanhua Chen · Furu Wei
摘要
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 fi...