arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2404.07922cs.CLcs.CVcs.LG
收藏

LaVy:越南语多模态大语言模型

LaVy: Vietnamese Multimodal Large Language Model

Hanoi University of Science and Technology(河内科技大学)

Chi Tran, Huong Le Thanh

AI总结:

本文提出越南语多模态大语言模型LaVy及其评估基准LaVy-Bench,旨在解决越南语多模态资源匮乏问题,推动该领域发展。

摘要:

大语言模型(LLMs)和多模态大语言模型(MLLMs)凭借在复杂推理和语言理解方面的出色能力席卷全球。与此同时,尽管已有大量关于越南语大语言模型的研究工作,但高质量多模态资源的缺乏限制了越南语多模态大语言模型的发展。在本文中,我们率先解决这一问题,推出了LaVy,一个最先进的越南语多模态大语言模型,并引入了LaVy-Bench基准,该基准专门用于评估多模态大语言模型在越南语视觉语言任务上的理解能力。我们的项目公开于https://github.com/baochi0212/LaVy。

英文摘要:

Large Language Models (LLMs) and Multimodal Large language models (MLLMs) have taken the world by storm with impressive abilities in complex reasoning and linguistic comprehension. Meanwhile there are plethora of works related to Vietnamese Large Language Models, the lack of high-quality resources in multimodality limits the progress of Vietnamese MLLMs. In this paper, we pioneer in address this by introducing LaVy, a state-of-the-art Vietnamese MLLM, and we also introduce LaVy-Bench benchmark designated for evaluating MLLMs's understanding on Vietnamese visual language tasks. Our project is public at https://github.com/baochi0212/LaVy

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑