Cite
Notes
Only stored in your browser.
Attribution
MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing
arXiv 2025
MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs
arXiv 2024
from 2 papers
Dahua Lin
Jiaqi Wang
Xiaoyi Dong
Yu Qiao
Yuhang Zang
Bin Wang
Bo Zhang
Bowen Zhou
professor
Boyu Niu
Chao Xu