MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing
Paper
• 2509.22186 • Published
• 147
Yuefeng Sun
SunYuefeng
AI & ML interests
None yet
Recent Activity
upvoted a paper 5 days ago
DocDancer: Towards Agentic Document-Grounded Information Seeking upvoted a paper 6 days ago
The Trinity of Consistency as a Defining Principle for General World Models Organizations
None yet
authored a paper 5 months ago