chengyewang's picture

chengyewang

chengyewang

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 1 day ago

VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding

submitted a paper about 1 month ago

TexOCR: Advancing Document OCR Models for Compilable Page-to-LaTeX Reconstruction

authored a paper about 1 month ago

TexOCR: Advancing Document OCR Models for Compilable Page-to-LaTeX Reconstruction

View all activity

Organizations

Collections 1

Papers 1

arxiv:2604.22880

models 7

chengyewang/TexOCR-RL

2B • Updated Apr 24 • 3

chengyewang/TexOCR-SFT

2B • Updated Apr 24 • 6

chengyewang/Open-o3

Updated Dec 29, 2025

chengyewang/IR_Qwen2vl-2B_originloss

2B • Updated Sep 1, 2025 • 2

chengyewang/IR_Qwen2vl-2B_newlossk32

2B • Updated Sep 1, 2025 • 1

chengyewang/qwen_ft

8B • Updated Jul 25, 2025 • 1

chengyewang/llava_smu_ft

7B • Updated Mar 26, 2025 • 9

datasets 16

chengyewang/TexOCR-RL-figures

Viewer • Updated Apr 22 • 3k • 68

chengyewang/TexOCR-RL-json

Viewer • Updated Apr 22 • 3k • 17

chengyewang/TexOCR-eval

Viewer • Updated Apr 22 • 1.14k • 1.07k

chengyewang/TexOCR-SFT-json

Viewer • Updated Apr 22 • 405k • 19

chengyewang/TexOCR-SFT-figures

Preview • Updated Apr 22 • 889

chengyewang/all_train

Preview • Updated Mar 29 • 46

chengyewang/Tex_enlarge_figures

Viewer • Updated Mar 22 • 1.34k • 14

chengyewang/minitrain_figures

Updated Feb 22 • 62

chengyewang/IR_eval_figures

Preview • Updated Feb 2 • 21

chengyewang/QA_test_h264

Viewer • Updated Dec 27, 2025 • 1 • 14

View 16 datasets