Update README.md
Browse files
README.md
CHANGED
|
@@ -19,6 +19,10 @@
|
|
| 19 |
|
| 20 |
We are excited to release Infinity-Parser2, our latest flagship document understanding model. We offer two distinct variants to address diverse deployment constraints: Infinity-Parser2-Pro, optimized for maximum accuracy in precision-critical tasks, achieves state-of-the-art results on olmOCR-Bench (87.6%) and ParseBench (74.3%), surpassing frontier models including DeepSeek-OCR-2, PaddleOCR-VL-1.5, and MinerU-2.5. Infinity-Parser2-Flash, engineered for low-latency inference, delivers a 3.68x speedup over our previous Infinity-Parser-7B model. With significant upgrades to both our data engine and multi-task reinforcement learning approach, the model consolidates robust multi-modal parsing capabilities into a unified architecture, unlocking brand-new zero-shot capabilities across a wide range of real-world business scenarios.
|
| 21 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
### Key Features
|
| 23 |
|
| 24 |
- **Upgraded Data Engine**: We have comprehensively enhanced our synthetic data engine to support both fixed-layout and flexible-layout document formats. By curating nearly 5 million diverse document parsing samples across a wide range of layouts, combined with a dynamic adaptive sampling strategy, we ensure highly balanced and robust multi-task learning across various document types.
|
|
|
|
| 19 |
|
| 20 |
We are excited to release Infinity-Parser2, our latest flagship document understanding model. We offer two distinct variants to address diverse deployment constraints: Infinity-Parser2-Pro, optimized for maximum accuracy in precision-critical tasks, achieves state-of-the-art results on olmOCR-Bench (87.6%) and ParseBench (74.3%), surpassing frontier models including DeepSeek-OCR-2, PaddleOCR-VL-1.5, and MinerU-2.5. Infinity-Parser2-Flash, engineered for low-latency inference, delivers a 3.68x speedup over our previous Infinity-Parser-7B model. With significant upgrades to both our data engine and multi-task reinforcement learning approach, the model consolidates robust multi-modal parsing capabilities into a unified architecture, unlocking brand-new zero-shot capabilities across a wide range of real-world business scenarios.
|
| 21 |
|
| 22 |
+
<p align="center">
|
| 23 |
+
<img src="assets/example_1.png" width="1000"/>
|
| 24 |
+
<p>
|
| 25 |
+
|
| 26 |
### Key Features
|
| 27 |
|
| 28 |
- **Upgraded Data Engine**: We have comprehensively enhanced our synthetic data engine to support both fixed-layout and flexible-layout document formats. By curating nearly 5 million diverse document parsing samples across a wide range of layouts, combined with a dynamic adaptive sampling strategy, we ensure highly balanced and robust multi-task learning across various document types.
|