Reading, Not Thinking: Understanding and Bridging the Modality Gap When Text Becomes Pixels in Multimodal LLMs 文章

ArXiv CS.CV2026-06-02NEWSen作者: Kaiser Sun, Xiaochuang Yuan, Hongjun Liu, Chen Zhao, Cheng Zhang, Mark Dredze, Fan Bai
查看原文 →
关系图谱

Reading, Not Thinking: Understanding and Bridging the Modality Gap When Text Becomes Pixels in Multimodal LLMs · 相关技术

相关技术

Multimodal Large Language Models (MLLMs)