arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2304.04083cs.HCcs.GR
收藏

VOICE:交互、对话和解释的视觉 oracle

VOICE: Visual Oracle for Interaction, Conversation, and Explanation

King Abdullah University of Science and Technology (KAUST)(阿卜杜拉国王科技大学);TU Wien(维也纳工业大学);Linköping University(林雪平大学);Umeå University(于默奥大学)

Donggang Jia, Alexandra Irger, Lonni Besancon, Ondrej Strnad, Deng Luo, Johanna Bjorklund, Anders Ynnerman, Ivan Viola

AI总结:

本文提出VOICE,一种将大语言模型的对话能力与交互式探索可视化相结合的科学传播新方法,通过多机器人系统实现任务分配、指令提取和内容生成,结合文本到可视化方法和自然语言交互,实现实时3D模型导航和操控,并在分子可视化领域验证其有效性。

摘要:

我们提出了VOICE,一种将大语言模型(LLM)的对话能力与交互式探索可视化相结合的科学传播新方法。VOICE引入了若干创新性的技术贡献,推动了我们的对话可视化框架。我们的基础是一个机器人集合,可以执行特定任务,如任务分配、指令提取和生成连贯内容。我们采用微调和提示工程技术来定制机器人性能以适应其特定角色,并准确响应用户查询。我们的交互式文本到可视化方法生成与内容解释匹配的飞行序列。此外,自然语言交互提供了实时导航和操控3D模型的能力。VOICE框架可以接收任意语音命令并以语音回应,与相应的视觉表示紧密耦合,具有低延迟和高准确性。我们通过将其应用于分子可视化领域,分析三个具有多尺度和多实例属性的3D分子模型来证明我们的方法的有效性。最后,我们通过与识别出的教育专家评估VOICE,以展示我们方法的潜力。所有补充材料均可在https://osf.io/g7fbr获取。

英文摘要:

We present VOICE, a novel approach to science communication that connects large language models' (LLM) conversational capabilities with interactive exploratory visualization. VOICE introduces several innovative technical contributions that drive our conversational visualization framework. Our foundation is a pack-of-bots that can perform specific tasks, such as assigning tasks, extracting instructions, and generating coherent content. We employ fine-tuning and prompt engineering techniques to tailor bots' performance to their specific roles and accurately respond to user queries. Our interactive text-to-visualization method generates a flythrough sequence matching the content explanation. Besides, natural language interaction provides capabilities to navigate and manipulate the 3D models in real-time. The VOICE framework can receive arbitrary voice commands from the user and respond verbally, tightly coupled with corresponding visual representation with low latency and high accuracy. We demonstrate the effectiveness of our approach by applying it to the molecular visualization domain: analyzing three 3D molecular models with multi-scale and multi-instance attributes. We finally evaluate VOICE with the identified educational experts to show the potential of our approach. All supplemental materials are available at https://osf.io/g7fbr.

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。

↑