InternLM-XComposer2

• Paper: InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Models
• GitHub Link
• Publisher: Arxiv
• Author Affiliation: Shanghai Artificial Intelligence Laboratory
• 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, I_D: Document understanding, I_B: Output bounding box, I_M: Output segmentation mask, I_R: Output retrieved images)
  • I+T $\rightarrow$ T