Skip to content
AIMarketCap

PaddleOCR-VL

Model
BaiduPart of PaddlePaddleactive

Compact vision-language model for multilingual document parsing.

Released
Oct 16, 2025
Context window
—
Modality
textimage
Open source
Yes
API available
—
Releases
1

Releases

1
Oct 16, 2025PaddleOCR-VL releasedPaddleOCR-VL

Baidu released a compact multilingual vision-language model for document parsing.

Baidu Open weightsBaiduPaddleOCR-VL