3 papers
cs.CV2025
TextGuider: Training-Free Guidance for Text Rendering via Attention Alignment
Kanghyun Baek, Sangyub Lee, Jin Young Choi +6
Despite recent advances, diffusion-based text-to-image models still struggle with accurate text rendering. Several studies have proposed fine-tuning or training-free refinement met…
cs.CV2025
Emergence of Text Readability in Vision Language Models
Jaeyoo Park, Sanghyuk Chun, Wonjae Kim +2
We investigate how the ability to recognize textual content within images emerges during the training of Vision-Language Models (VLMs). Our analysis reveals a critical phenomenon:…
cs.CV2024
Hierarchical Visual Feature Aggregation for OCR-Free Document Understanding
Jaeyoo Park, Jin Young Choi, Jeonghyung Park +1
We present a novel OCR-free document understanding framework based on pretrained Multimodal Large Language Models (MLLMs). Our approach employs multi-scale visual features to effec…