arXiv:2607.04438cs.CVcs.AI2026-07被引 1

一键生成可编辑的论文海报、视频和博客,三者集成在交互式界面中。

ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog

论文配图:ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog
图 1 · 摘自论文原文
  • 用五个可执行技能整合论文到多格式输出,共享资源包支持统一编辑。
  • 在100篇论文上,美学评分3.56优于作者原始海报的3.03,质量胜出74~95篇。
  • 成果以可交互视图打包,所有源文件保持原生可编辑,适合科研人员复用。

尽管自动化技术不断进步,将论文转化为连贯的海报、演讲视频和博客内容仍常是耗时的最后一步。现有系统逐步支持多格式生成,但实际工作流还需确保输出在原生工具中可编辑,并整合为一个可导航的交付物以便修订与复用。我们提出ResearchStudio-Reel,一个原生可编辑的传播工作空间,通过五项可在Claude Code和Codex中执行的技能实现:一个共享提取器、三个可编辑的产物生成器和一个交互式融合层。共享资产包同时供给PowerPoint海报、视频幻灯片及双语Word博客;无需再渲染成第四种格式,Paper2Reel在体验层面融合已生成的海报区域、视频片段和博客段落,形成一个交互式查看器。特定产物的发布校验使交付契约可测试,Paper2Poster还引入测量填充循环。在Paper2Poster基准上,我们的Claude Code配置在所有三项美学子指标中表现最佳,在两项信息子指标中达到最优或并列最优。经两名VLM裁判评估,其平均美学分达3.56(高于作者海报的3.03),并在100篇论文中分别以74和95篇的高分胜出整体质量。完整流程额外打包了原生可编辑的源文件及其对齐的交互视图。项目地址:https://aka.ms/ResearchStudio

原文摘要 · Abstract (English)

Despite growing automation, turning a paper into a coherent poster, talk video, and blog piece often remains a labor-intensive last mile. Recent systems increasingly generate multiple dissemination formats, but a practical workflow must also keep the outputs editable in native tools and bound into one navigable deliverable for revision and reuse. We present ResearchStudio-Reel, a native-editable dissemination workspace that binds its three artifacts into one interactive deliverable at the experience level, implemented as five skills executable in Claude Code and Codex: one shared extractor, three editable artifact generators, and one interactive convergence layer. A shared asset bundle feeds a PowerPoint poster and video deck, plus a bilingual Word blog; rather than re-rendering the paper into a fourth format, Paper2Reel converges these already-produced artifacts at the experience level, binding poster regions, video segments, and blog passages into one interactive viewer. Artifact-specific release checks make this delivery contract testable, and Paper2Poster additionally uses a measured-fill loop. On the Paper2Poster benchmark, our Claude Code configuration achieves the best scores among automated systems on all three aesthetic sub-criteria and the best or tied-best scores on two of three information sub-criteria. Under two VLMjudges, it exceeds the authors' posters in average aesthetics (3.56 vs. 3.03) and wins on overall quality on 74 and 95 of the 100 papers under the two judges. The full pipeline additionally packages the native-editable source artifacts and their aligned viewer. Project is available at https://aka.ms/ResearchStudio

论文自动化多模态生成科研工作流可编辑输出

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。