T2M

• Paper: NExT-GPT: Any-to-Any Multimodal LLM
• GitHub Link
• Publisher: ICLR 2024
• Author Affiliation: National University of Singapore
• 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)
  • T $\rightarrow$ I/V/A+T
• Source
  • WebVid, CC3M, AudioCap
• Method
  • Auto.
• I/V/A Scale
  • I
    • 4.9K
  • V
    • 4.9K
  • A
    • 4.9K
• Dialog Turn
  • 1
• Instance Scale
  • 14.7K