Video1_1.mp4 Apr 2026

This paper introduces , a multi-agent framework designed to automate the creation of presentation videos directly from scientific LaTeX documents . Key Features

If you tell me what you're looking for, I can find more info: A for the dataset or code. Specific technical details on the Slide or Talker builders. Other demo videos from the Paper2Video benchmark. Automatic Video Generation from Scientific Papers - arXiv

The filename video1_1.mp4 is a demonstration video from the academic paper . video1_1.mp4

: The system achieves quality levels approaching human-created content, specifically improving "PresentQuiz" accuracy—a metric measuring audience understanding—by 10% .

: The project is open-source, with code and datasets available on GitHub . This paper introduces , a multi-agent framework designed

: It synthesizes slides, generates narration subtitles, grounds on-screen cursor movements, and renders a talking-head video of the speaker .

💡 : The framework specifically solves the problem of "long-horizon agentic tasks," requiring the integration of text, figures, and spoken presentation into a cohesive video . Other demo videos from the Paper2Video benchmark

: The authors established a benchmark of 101 papers paired with author-recorded videos to evaluate how effectively AI can convey complex research .