Junfeng Luo

3
Papers
4
Total Citations

Papers (3)

InstructOCR: Instruction Boosting Scene Text Spotting

AAAI 2025
4
citations

Marten: Visual Question Answering with Mask Generation for Multi-modal Document Understanding

CVPR 2025
0
citations

A Token-level Text Image Foundation Model for Document Understanding

ICCV 2025
0
citations