Post

WebVoyager

  • Paper: WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models
  • GitHub Link
  • Publisher: Arxiv
  • Author Affiliation: Zhejiang University
  • Functional Division
    • Understanding
    • Generation
  • Design Division
    • Tool-using
    • End-to-end
  • Input Modalities $\rightarrow$ Output Modalities
    (I: Image, V: Video, A: Audio, 3D: Point Cloud, T: Text, ID: Document understanding, IB: Output bounding box, IM: Output segmentation mask, IR: Output retrieved images)
    • I+T $\rightarrow$ Action+T
This post is licensed under CC BY 4.0 by the author.