Vid_20230119_175021_814.mp4 Direct

The authors created PaperTalker , which automates the entire pipeline—from generating slides and layout refinement to speech synthesis and "talking-head" rendering.

The code and models are available on GitHub , requiring high-end hardware (like an NVIDIA A6000) to run the full automated pipeline. VID_20230119_175021_814.mp4

This research, published in 2025, focuses on automatically generating academic presentation videos from scientific papers using a multi-agent framework called . The project includes a benchmark dataset of 101 papers paired with author-created videos and slides. Key Aspects of the Paper2Video Project: The authors created PaperTalker , which automates the