A More Word-like Image Tokenization for MLLMs

📰 ArXiv cs.AI

arXiv:2605.17954v1 Announce Type: cross Abstract: Modern multimodal large language models (MLLMs) typically keep the language model fixed and train a visual projector that maps the pixels into a sequence of tokens in its embedding space, so that images can be presented in essentially the same form as text. However, the language model has been optimized to operate on discrete, semantically meaningful tokens, while prevailing visual projectors transform an image into a long stream of continuous an

Published 19 May 2026

Full Article

Title: A More Word-like Image Tokenization for MLLMs

Abstract:
arXiv:2605.17954v1 Announce Type: cross Abstract: Modern multimodal large language models (MLLMs) typically keep the language model fixed and train a visual projector that maps the pixels into a sequence of tokens in its embedding space, so that images can be presented in essentially the same form as text. However, the language model has been optimized to operate on discrete, semantically meaningful tokens, while prevailing visual projectors transform an image into a long stream of continuous an
Read full paper → ← Back to Reads