DeepSeek-VL2

• Paper: DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
• Project Link
• Publisher: Arxiv
• Author Affiliation: DeepSeek-AI
• 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 $\rightarrow$ I_B+T