Tongkun Guan
3
Papers
20
Total Citations
Papers (3)
PosFormer: Recognizing Complex Handwritten Mathematical Expression with Position Forest Transformer
ECCV 2024arXiv
16
citations
A Token-level Text Image Foundation Model for Document Understanding
ICCV 2025arXiv
4
citations
Marten: Visual Question Answering with Mask Generation for Multi-modal Document Understanding
CVPR 2025
0
citations