Login / Signup

MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?

Renrui ZhangDongzhi JiangYichi ZhangHaokun LinZiyu GuoPengshuo QiuAojun ZhouPan LuKai-Wei ChangPeng GaoHongsheng Li
Published in: CoRR (2024)
Keyphrases
  • multi modal
  • cross modal
  • video search
  • multi modality
  • audio visual
  • auto annotation
  • high dimensional
  • low level
  • mutual information
  • semantic concepts