Model
MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing
Why Lacuna links this resource
Confirmed by the paper and resource
The paper explicitly provides the Hugging Face URL for its model in the header (P1). The resource's README shares the exact title of the paper (R1, R4) and links back to the paper's arXiv ID as its technical report (R2), confirming they are the same primary resource.