| # Infinity-Parser2-Pro |
|
|
| <p align="center"> |
| <img src="assets/logo.png" width="400"/> |
| <p> |
| |
| <p align="center"> |
| 💻 <a href="https://github.com/infly-ai/INF-MLLM">Github</a> | |
| 📊 <a>Dataset (coming soon...)</a> | |
| 📄 <a>Paper (coming soon...)</a> | |
| 🚀 <a>Demo (coming soon...)</a> |
| </p> |
|
|
| # News |
| - [2026-04-09] We released our latest flagship document parsing model, Infinity-Parser2-Pro. Note that this is still a preview version. Model weights are being uploaded. |
|
|
| # Introduction |
|
|
| We are excited to release Infinity-Parser2-Pro, our latest flagship document understanding model that achieves a new state-of-the-art on olmOCR-Bench with a score of 86.7%, surpassing frontier models such as DeepSeek-OCR-2, PaddleOCR-VL-1.5, and dots.mocr. Building on our previous model Infinity-Parser-7B, we have significantly enhanced our data engine and multi-task reinforcement learning approach. This enables the model to consolidate robust multi-modal parsing capabilities into a unified architecture, delivering brand-new zero-shot capabilities for diverse real-world business scenarios. |
|
|
| ## Key Features |
|
|
| - Upgraded Data Engine: We have comprehensively enhanced our synthetic data engine to support both fixed-layout and flexible-layout document formats. By generating over 1 million diverse full-text samples covering a wide range of document layouts, combined with a dynamic adaptive sampling strategy, we ensure highly balanced and robust multi-task learning across various document types. |
|
|
| - Multi-Task Reinforcement Learning: We designed a novel verifiable reward system to support Joint Reinforcement Learning (RL), enabling seamless and simultaneous co-optimization of multiple complex tasks, including doc2json and doc2markdown. |
|
|
| - Breakthrough Parsing Performance: It substantially outperforms our previous 7B model, achieving 86.7% on olmOCR-Bench, surpassing frontier models such as DeepSeek-OCR-2, PaddleOCR-VL-1.5, and dots.mocr. |
|
|
| - Inference Acceleration: By adopting the highly efficient MoE architecture, our inference throughput has increased by 21% (from 441 to 534 tokens/sec), reducing deployment latency and costs. |
|
|
| # Performance |
|
|
| Coming soon... |
|
|
| # Citation |
|
|
| Coming soon... |
|
|
| # License |
|
|
| This model is licensed under apache-2.0. |
