Text or Pixels? It Takes Half: On the Token Efficiency of Visual Text Inputs in Multimodal LLMs
Paper • 2510.18279 • Published • 6
design PRO
helvetiphant
AI & ML interests
None yet
Recent Activity
liked a model 12 days ago
fishaudio/s2-pro liked a Space 12 days ago
prithivMLmods/FireRed-Image-Edit-1.0-Fast liked a Space 12 days ago
FrameAI4687/Omni-Video-FactoryOrganizations
None yet
upvoted a paper about 1 month ago