Ideas & society2025 · shared on Hacker News
Text or pixels? On the token efficiency of visual text inputs in multimodal LLMs
Explore Text or pixels? On the token efficiency of visual text inputs in multimodal LLMs, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.
GO BEYOND THE ABSTRACT
The conversation around the idea.
Original Hacker News threads. Different perspectives, questions, and things worth thinking about.
Showing up to 100 related threads. A paper may appear in a comment rather than the original submission.
Yhhs ·
Text or pixels? On the token efficiency of visual text inputs in multimodal LLMs
2 points0 comments