TongkunGuan's picture

TongkunGuan

TongkunGuan

·

https://tongkunguan.github.io/

TongkunGuan

AI & ML interests

MLLM, CV

Recent Activity

authored a paper 6 days ago

CodePercept: Code-Grounded Visual STEM Perception for MLLMs

upvoted a paper 6 days ago

CodePercept: Code-Grounded Visual STEM Perception for MLLMs

submitted a paper 6 days ago

CodePercept: Code-Grounded Visual STEM Perception for MLLMs

View all activity

Organizations

None yet

Papers 4

arxiv:2603.10757

arxiv:2503.02304

arxiv:2407.07764

arxiv:2211.00288

spaces 1

Token-level Text Image Foundation Model

Visualize texts in images using BPE tokens

models 6

TongkunGuan/TokenFD

Image-to-Text • Updated Aug 27, 2025 • 4

TongkunGuan/Marten

8B • Updated Aug 9, 2025 • 1

TongkunGuan/TokenFD_qw_add_dis

Updated May 3, 2025

TongkunGuan/R50

Updated Apr 28, 2025

TongkunGuan/TokenFD_4096_English_seg

Image Feature Extraction • 0.7B • Updated Mar 8, 2025 • 4

TongkunGuan/TokenFD_2048_Bilingual_seg

0.5B • Updated Mar 4, 2025 • 1

datasets 4

TongkunGuan/TokenIT_demo

Viewer • Updated May 3, 2025 • 33.8k • 42

TongkunGuan/CHESE

Updated Dec 14, 2024 • 38

TongkunGuan/RCTW

Updated Dec 13, 2024 • 9

TongkunGuan/IAM_full_image

Updated Nov 12, 2024 • 7