Post

ChatSpot

  • Paper: ChatSpot: Bootstrapping Multimodal LLMs via Precise Referring Instruction Tuning
  • GitHub Link
  • Publisher: Arxiv
  • Author Affiliation: MEGVII
  • 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 $\rightarrow$ T
  • Model Architecture
    (Input $\rightarrow$ Modality Encoder $\rightarrow$ Input Projector $\rightarrow$ LLM Backbone $\rightarrow$ Output Projector $\rightarrow$ Modality Generator $\rightarrow$ Output)
    • Modality Encoder
      • I: CLIP ViT-L/14
    • Input Projector
      • Linear Projector
    • LLM Backbone
      • Vicuna-7B/LLaMA
    • Output Projector
      • None
    • Modality Generator
      • None
  • Datasets Scale
    • Pre-training Stage
      • Not report
    • Instruction-tuning Stage
      • Not report
This post is licensed under CC BY 4.0 by the author.