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
If you are looking for the video itself, it is likely part of the mentioned in the dataset or a specific case study used to demonstrate the "cursor grounding" or "talking-head" features of their AI. The authors created PaperTalker , which automates the
Turning a complex research paper into a compelling presentation video is time-consuming for researchers. The authors created PaperTalker
A new benchmark called Paper2Video that includes metadata and metrics (like "PresentArena" and "IP Memory") to evaluate how effectively a video conveys a paper's information.