Login / Signup

ManipVQA: Injecting Robotic Affordance and Physically Grounded Information into Multi-Modal Large Language Models.

Siyuan HuangIaroslav PonomarenkoZhengkai JiangXiaoqi LiXiaobin HuPeng GaoHongsheng LiHao Dong
Published in: CoRR (2024)
Keyphrases
  • multi modal
  • language model
  • probabilistic model
  • multi modality
  • n gram
  • retrieval model
  • language modeling
  • language modelling
  • classification accuracy
  • test collection
  • statistical language models