zhiyuan zhao's picture

zhiyuan zhao

juliozhao

·

https://scholar.google.com/citations?user=K0BNv0YAAAAJ&hl=en

JulioZhao97

AI & ML interests

Document Understanding; Large Multimodal Models

Recent Activity

liked a model 7 days ago

opendatalab/MinerU2.5-Pro-2604-1.2B

upvoted a paper 7 days ago

MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale

upvoted a paper 6 months ago

OmniLayout: Enabling Coarse-to-Fine Learning with LLMs for Universal Document Layout Generation

View all activity

Organizations

liked a model 7 days ago

opendatalab/MinerU2.5-Pro-2604-1.2B

Image-Text-to-Text • 1B • Updated 3 days ago • 13.2k • 62

liked a model 7 months ago

opendatalab/MinerU2.5-2509-1.2B

Image-Text-to-Text • 1B • Updated 8 days ago • 1.18M • 352

liked a model 10 months ago

opendatalab/MinerU2.0-2505-0.9B

1B • Updated Jun 12, 2025 • 84 • 41

liked 4 Spaces over 1 year ago

MinerU OCR

A data extraction tool to convert PDF to Markdown and JSON

UniMERNet

Recognize math equations from images

DocLayout YOLO

Demo for DocLayout-YOLO

CDM

Evaluate formula recognition accuracy