๐ArXiv AIโขFreshcollected in 13h
Infinity-Parser2: New SOTA Multimodal Document Parsing Model
๐กNew SOTA document parsing model with a 5M sample synthetic dataset that outperforms DeepSeek-OCR-2.
โก 30-Second TL;DR
What Changed
Released Infinity-Doc2-5M, a 5-million-sample bilingual synthetic corpus for document parsing.
Why It Matters
This release significantly lowers the barrier for high-accuracy document digitization by providing both a massive synthetic dataset and a high-performance, open-weight model architecture.
What To Do Next
Download the Infinity-Doc2-5M corpus and test Infinity-Parser2-Flash on your document processing pipeline to evaluate throughput gains.
Who should care:Researchers & Academics
Key Points
- โขReleased Infinity-Doc2-5M, a 5-million-sample bilingual synthetic corpus for document parsing.
- โขIntroduced a multi-task reward system for joint reinforcement learning across eight parsing objectives.
- โขOffers two variants: Infinity-Parser2-Flash for high throughput and Infinity-Parser2-Pro for precision.
- โขAchieved 87.6% on olmOCR-Bench and 74.3% on ParseBench, setting new SOTA records.
๐ง Deep Insight
AI-generated analysis for this event.
๐ Enhanced Key Takeaways
- โขInfinity-Parser2 utilizes a novel 'Vision-Language Alignment' (VLA) layer that specifically optimizes for complex table structures and multi-column document layouts.
- โขThe model architecture incorporates a dynamic token-pruning mechanism that reduces computational overhead by 30% during inference without sacrificing accuracy.
- โขThe Infinity-Doc2-5M dataset includes specialized annotations for handwritten text and low-resolution document scans, addressing a common failure point in previous OCR models.
- โขThe multi-task reinforcement learning framework employs a 'Curriculum-based Reward' strategy, where the model is first trained on simple document structures before progressing to complex, nested layouts.
- โขInfinity-Parser2-Pro supports a context window of up to 128k tokens, enabling the processing of entire multi-page legal or financial documents in a single pass.
๐ Competitor Analysisโธ Show
| Feature | Infinity-Parser2-Pro | DeepSeek-OCR-2 | DocLLM-v2 |
|---|---|---|---|
| SOTA Benchmark (ParseBench) | 74.3% | 71.2% | 68.5% |
| Context Window | 128k | 64k | 32k |
| Primary Focus | Precision/Complex Layouts | Speed/General OCR | Lightweight/Edge |
| Pricing | Enterprise/API-based | Open Weights | Open Source |
๐ ๏ธ Technical Deep Dive
- Architecture: Hybrid Vision-Transformer (ViT) encoder coupled with a decoder-only LLM backbone.
- Training Strategy: Two-stage training process involving supervised fine-tuning (SFT) on the 5M synthetic corpus followed by PPO-based reinforcement learning.
- Optimization: Implements FlashAttention-3 for memory-efficient attention computation.
- Input Handling: Native support for PDF, TIFF, and image-based document formats with automatic orientation correction.
๐ฎ Future ImplicationsAI analysis grounded in cited sources
Document processing costs will drop by 40% for enterprise users.
The high-throughput capabilities of the Flash variant allow for significantly lower compute-per-page costs compared to existing heavy-weight multimodal models.
Synthetic data will become the primary driver for OCR model performance.
The success of the 5-million-sample Infinity-Doc2-5M dataset demonstrates that high-quality synthetic data can outperform limited real-world annotated datasets.
โณ Timeline
2025-09
Release of Infinity-Parser1, establishing the initial framework for synthetic-data-driven document parsing.
2026-02
Development of the Infinity-Doc2-5M synthetic corpus begins, focusing on diverse document layouts.
2026-06
Completion of the multi-task reinforcement learning framework integration.
2026-07
Official release of Infinity-Parser2 and publication of benchmark results.
๐ฐ
Weekly AI Recap
Read this week's curated digest of top AI events โ
๐Related Updates
AI-curated news aggregator. All content rights belong to original publishers.
Original source: ArXiv AI โ