Login / Signup

Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models.

Yushi HuWeijia ShiXingyu FuDan RothMari OstendorfLuke ZettlemoyerNoah A. SmithRanjay Krishna
Published in: CoRR (2024)
Keyphrases
  • language model
  • speech recognition
  • visual information
  • visual features
  • language modeling
  • retrieval model
  • probabilistic model
  • n gram
  • document retrieval
  • information retrieval
  • search engine
  • query expansion