On the Design Fundamentals of Pixel Text Representation Learning
This work investigates the fundamental design principles required for robust visual text representation learning and trains Pixel Linguist II, a native-resolution vision encoder trained with on-the-fly rendering, unified contrastive grounding, and a multilingual curriculum over 280M training examples.
Chaohao Yuan, Rui-Feng Yuan, Zhuoxu Huang et al.
· 0 citations