From 420565779590b2cabd34d3f85f4bb20d1b7068af Mon Sep 17 00:00:00 2001
From: Zhang Zelun <33217105+BluebirdStory@users.noreply.github.com>
Date: Wed, 3 Jun 2026 14:43:14 +0800
Subject: [PATCH] add PaddleOCR-VL-1.6 docs (#18095)
---
README.md | 10 ++
.../PaddleOCR-VL/PaddleOCR-VL-1.6.en.md | 147 ++++++++++++++++++
.../PaddleOCR-VL/PaddleOCR-VL-1.6.md | 147 ++++++++++++++++++
mkdocs.yml | 3 +-
4 files changed, 306 insertions(+), 1 deletion(-)
create mode 100644 docs/version3.x/algorithm/PaddleOCR-VL/PaddleOCR-VL-1.6.en.md
create mode 100644 docs/version3.x/algorithm/PaddleOCR-VL/PaddleOCR-VL-1.6.md
diff --git a/README.md b/README.md
index 94f7820cf7..aeb7f7e9a3 100644
--- a/README.md
+++ b/README.md
@@ -289,4 +289,14 @@ This project is released under the [Apache 2.0 license](LICENSE).
primaryClass={cs.CV},
url={https://arxiv.org/abs/2601.21957},
}
+
+@misc{zhang2026paddleocrvl16expandingfrontierdocument,
+ title={PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training},
+ author={Zelun Zhang and Hongen Liu and Suyin Liang and Yubo Zhang and Yiqing Xiang and Jiaxuan Liu and Ting Sun and Manhui Lin and Yue Zhang and Changda Zhou and Tingquan Gao and Cheng Cui and Yi Liu and Dianhai Yu and Yanjun Ma},
+ year={2026},
+ eprint={2606.03264},
+ archivePrefix={arXiv},
+ primaryClass={cs.CV},
+ url={https://arxiv.org/abs/2606.03264},
+}
```
diff --git a/docs/version3.x/algorithm/PaddleOCR-VL/PaddleOCR-VL-1.6.en.md b/docs/version3.x/algorithm/PaddleOCR-VL/PaddleOCR-VL-1.6.en.md
new file mode 100644
index 0000000000..25229898e7
--- /dev/null
+++ b/docs/version3.x/algorithm/PaddleOCR-VL/PaddleOCR-VL-1.6.en.md
@@ -0,0 +1,147 @@
+## 1. Introduction to PaddleOCR-VL-1.6
+
+**PaddleOCR-VL-1.6** further optimizes PaddleOCR-VL-1.5 by systematically analyzing under-optimized areas in the current model, applying targeted data optimization, and adopting refined post-training strategies. It achieves a new state-of-the-art (SOTA) result of 96.33% on the OmniDocBench v1.6 document parsing benchmark. PaddleOCR-VL-1.6 also reaches SOTA performance across all scenarios on Real5-OmniDocBench, a benchmark designed to evaluate robustness against real-world physical distortions. In addition, PaddleOCR-VL-1.6 outperforms PaddleOCR-VL-1.5 on three subtasks: seal recognition, text detection and recognition, and chart recognition, while still maintaining an ultra-compact 0.9B-parameter VLM and high efficiency.
+
+### **Key Metrics:**
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+