Lead story
Models & availability
Latest
← Feed
Copy✕ Close copy menu
PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model
Baidu releases PaddleOCR-VL, a compact vision-language model for document parsing with SOTA performance, multilingual support for 109 languages, and Apache 2.0 license.
From the source
We are excited to release PaddleOCR-VL, a SOTA and resource-efficient model tailored for document parsing.
ernie.baidu.com
Visit source ↗ernie.baidu.com
- Announced
- 16 Oct 2025 00:00 UTC
- Detected
- 28 Aug 2026 19:42 UTC (+316d after)
- License
- Apache License 2.0
