vix.ing · top · new · best · stats · spec

Ryu, Sunghyun

  1. How Do Large Vision-Language Models See Text in Image? Unveiling the Distinctive Role of OCR Heads
    2025/05/21 by Baek, Ingeol, Chang, Hwan, Ryu, Sunghyun +2 · 2 citations
    Computer Science · #Multimodal Machine Learning Applications #Topic Modeling #Handwritten Text Recognition Techniques