BriefGPT.xyz
Oct, 2023
Ziya-VL: 多任务指导微调的双语大型视觉语言模型
Ziya-VL: Bilingual Large Vision-Language Model via Multi-Task Instruction Tuning
HTML
PDF
Junyu Lu, Dixiang Zhang, Xiaojun Wu, Xinyu Gao, Ruyi Gan...
TL;DR
通过引入视觉语义,将大规模的视觉-语言模型 (LVLMs) 融合到多模态对话中,Ziya-VL 在英语和汉语多模态场景中展现出了具有竞争力的图片-文本生成和理解能力。
Abstract
Recent advancements enlarge the capabilities of
large language models
(LLMs) in
zero-shot image-to-text generation
and understanding by integrating multi-modal inputs. However, such success is typically limited t
→