Post

LLaVA-RLHF

Posted
By 1 min read
  • Paper: Aligning Large Multimodal Models with Factually Augmented RLHF
  • GitHub Link
  • Publisher: Arxiv
  • Author Affiliation: UC Berkeley
  • Type
    • SFT
    • RLHF
  • Multi-turn
    • ✔
    • ✖
  • Input Modalities $\rightarrow$ Output Modalities
    (I: Image, V: Video, A: Audio, 3D: Point Cloud, T: Text, B: Bounding box, Tab: Table, Web: Web page)
    • I+T $\rightarrow$ T
  • Source
    • Collected human preference
  • Method
    • Manu.
  • I/V/A Scale
    • I
      • Not report
    • V
      • Not report
    • A
      • Not report
  • Dialog Turn
    • Not report
  • Instance Scale
    • 10K
Arxiv
IT Dataset
This post is licensed under CC BY 4.0 by the author.