Xiaomi-OCR-0 Technical Report
Xiaomi has released Xiaomi-OCR-0, a compact 0.8B parameter vision-language model designed for document parsing and optical character recognition. By shifting focus away from resource-intensive supervision, the model aims to improve efficiency in extracting text and structural data from documents.
Covered by 1 source
- AarXiv CS.AI↗Xin Chen, Anan Du, Feng Feng, Pei Fu, Jian Luan, Longwei Xu, Shaojie Zhang, Hang Li, Heng Qu, Cheng Tan1d ago