Audio description (AD) makes video content accessible to blind and low-vision (BLV) audiences, but producing high-quality descriptions is resource-intensive. Automated AD offers scalability, and prior studies show human-in-the-loop editing and user queries effectively improve narration. We introduce ADx3, a novel framework integrating these three modules: GenAD, upgrading baseline description generation with modern vision-language models (VLMs) guided by accessibility-informed prompting; RefineAD, supporting BLV and sighted users to view and edit drafts through an inclusive interface; and AdaptAD, enabling on-demand user queries. We evaluated GenAD in a study where seven accessibility specialists reviewed VLM-generated descriptions using professional guidelines. Findings show that with tailored prompting, VLMs produce good descriptions meeting basic standards, but excellent descriptions require human edits (RefineAD) and interaction (AdaptAD). ADx3 demonstrates collaborative workflows for accessible content creation, where components reinforce one another and enable continuous improvement: edits guide future baselines and user queries reveal gaps in AI-generated and human-authored descriptions.
CATVis: A Collaborative Multi-Agent Workflow for Turbomachinery Simulation Data Visualization
Beijing China 2 Computer Network Information Center Chinese Academy of Sciences(中国科学院计算机网络信息中心);Hangzhou Institute for Advanced Study UCAS Hangzhou China(杭州高等研究院(UCAS));Michigan Technological University Houghton MI USA(密歇根理工大学)
Can GenAI Move from Individual Use to Collaborative Work? Experiences, Challenges, and Opportunities of Coordinating GenAI into Collaborative Newswork
Human-Computer Interaction Institute, Carnegie Mellon University(卡内基梅隆大学人机交互研究所);Department of Sociology, University of California San Diego(加州大学圣地亚哥分校社会学系);Goizueta Business School, Emory University(埃默里大学戈伊泽塔商学院)
A Collective Knowledge workflow for collaborative research into multi-objective autotuning and machine learning techniques
开发高效的软件和硬件从未如此困难,无论是小型物联网设备还是Exascale超级计算机。除了不断增长的设计和优化复杂性,还存在更根本的问题,如缺乏有效的软件/硬件协同设计所需的跨学科知识,以及学术界和工业界之间日益扩大的技术转让差距。我们介绍我们的新的教育举措,以解决这些问题,通过开发集体知识(CK),一个统一的实验框架计算机系统的研究和开发。我们使用CK来教社区如何使他们的研究工件和实验工作流程便携,可复制,可定制和可重复使用,同时实现可持续的研发和促进技术转让。我们还演示了如何重新设计多目标自动调整和机器学习作为一个便携式和可扩展的CK工作流程。这样的工作流程使研究人员能够使用不同的应用程序,数据集和工具进行实验;跨不同平台进行众包实验;共享实验结果,模型,可视化;使用简单的JSON API逐渐暴露更多的设计和优化选择;并最终建立在彼此的发现之上。作为第一个实际步骤,我们已经实现了可定制的编译器自动调优,在Raspberry Pi 3设备上对各种工作负载进行众包优化,将执行时间和代码大小减少了40%,并应用机器学习来预测优化。我们希望这种方法将有助于教学生如何建立在彼此的工作,使有效的和自我优化的软件/硬件/模型堆栈的新兴工作负载。
A Human-AI Collaborative Workflow for Mathematical Discovery: A Case Study in Grover-Compatible Riemannian Optimization
Beijing International Center for Mathematical Research, Peking University(北京大学北京国际数学研究中心);Yau Mathematical Sciences Center, Tsinghua University(清华大学尤伊数学科学中心)
MR-DAW: Towards Collaborative Digital Audio Workstations in Mixed Reality
SolJAMM Research(SolJAMM研究);University of Colorado Boulder(科罗拉多大学博尔德分校);ATLAS Insitute(ATLAS研究所);Hsinchu County Liou-Jia Senior High School(新竹县柳家高中);National Taiwan Normal University(台湾师范大学);University of Trento(特伦托大学)
From Data to Decision: Data-Centric Infrastructure for Reproducible ML in Collaborative eScience
Dept. of Industrial and Systems Engineering(工业与系统工程系);University of Southern California(南加州大学);Information Sciences Institute(信息科学研究所);Dept. of Computer Science(计算机科学系);Dept. of Ophthalmology(眼科学系)