MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing
Paper • 2509.22186 • Published • 164
Junbo Niu
Niujunbo2002
AI & ML interests
Computer vision and pattern recognition
Recent Activity
upvoted a paper 11 days ago
WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation upvoted a paper 26 days ago
Turning the TIDE: Cross-Architecture Distillation for Diffusion Large Language ModelsOrganizations
authored a
paper 7 months ago
authored 2
papers over 1 year ago