Tongkun Guan
- Papers
- 5
Cite
Notes
Only stored in your browser.
5papers
Authored papers
5CodePercept: Code-Grounded Visual STEM Perception for MLLMs
arXiv 2026
From Narrow to Panoramic Vision: Attention-Guided Cold-Start Reshapes Multimodal Reasoning
arXiv 2026
A Token-level Text Image Foundation Model for Document Understanding
ICCV 2025
Marten: Visual Question Answering with Mask Generation for Multi-modal Document Understanding
CVPR 2025 1
PosFormer: Recognizing Complex Handwritten Mathematical Expression with Position Forest Transformer
arXiv 2024
Affiliations
No known affiliations.
Frequent co-authors
10from 5 papers