Cite
Notes
Only stored in your browser.
Attribution
Multimodal OCR: Parse Anything from Documents
arXiv 2026
dots.ocr: Multilingual Document Layout Parsing in a Single Vision-Language Model
arXiv 2025
David and Goliath: Small One-step Model Beats Large Diffusion with Score Post-training
arXiv 2024
from 3 papers
Guang Yang
Hao liu
Weijian Luo
Yumeng Li
Bowen Wang
Debing Zhang
Guangwei Zhao
Handong Zheng
Jiayu Chen
Jie Lou