PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing
Abstract
A compact vision-language model achieves state-of-the-art accuracy on document understanding tasks while maintaining efficiency through specialized benchmarking and extended functionality.
We introduce PaddleOCR-VL-1.5, an upgraded model achieving a new state-of-the-art (SOTA) accuracy of 94.5% on OmniDocBench v1.5. To rigorously evaluate robustness against real-world physical distortions, including scanning, skew, warping, screen-photography, and illumination, we propose the Real5-OmniDocBench benchmark. Experimental results demonstrate that this enhanced model attains SOTA performance on the newly curated benchmark. Furthermore, we extend the model's capabilities by incorporating seal recognition and text spotting tasks, while remaining a 0.9B ultra-compact VLM with high efficiency. Code: https://github.com/PaddlePaddle/PaddleOCR
Community
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR (2026)
- UniRec-0.1B: Unified Text and Formula Recognition with 0.1B Parameters (2025)
- STEP3-VL-10B Technical Report (2026)
- DOCR-Inspector: Fine-Grained and Automated Evaluation of Document Parsing with VLM (2025)
- Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking (2026)
- GutenOCR: A Grounded Vision-Language Front-End for Documents (2026)
- DeepSeek-OCR 2: Visual Causal Flow (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 2
Datasets citing this paper 0
No dataset linking this paper