Text or Pixels? It Takes Half: On the Token Efficiency of Visual Text Inputs in Multimodal LLMs
Paper
•
2510.18279
•
Published
•
3
Yanhong Li
yanhong-l
·
AI & ML interests
None yet
Recent Activity
commented on
a paper
4 days ago
Text or Pixels? It Takes Half: On the Token Efficiency of Visual Text
Inputs in Multimodal LLMs
authored
a paper
4 days ago
Text or Pixels? It Takes Half: On the Token Efficiency of Visual Text
Inputs in Multimodal LLMs
Organizations
upvoted
a
paper
5 days ago