Cite
Notes
Only stored in your browser.
Attribution
MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing
arXiv 2025
Benchmarking and Boosting Multilingual Capabilities of LVLMs via OCR-Centric Reinforcement Learning
from 2 papers
Bin Wang
Conghui He
Dahua Lin
Jiang Wu
Lijun Wu
Shasha Wang
Weijia Li
Bo Zhang
Bowen Zhou
professor
Boyu Niu