PolyOCR-Venus: Unified OCR Foundation Models for Text-Centric Visual Intelligence

Hugging Face Daily Papers Papers
ocr foundation-models visual-intelligence multimodal reinforcement-learning document-parsing

Summary

PolyOCR-Venus 提出了一系列统一的 OCR 基础模型，结合共享指令框架、大规模数据引擎与Competence-Guided Policy Optimization，并发布修订版 OCRBench v2.1 基准，在多个文档理解基准上达到最先进的性能。

Optical Character Recognition (OCR) is evolving from plain-text transcription toward general visual intelligence, requiring models to recognize, localize, and reason over textual information in complex visual environments. However, existing OCR systems often excel at only some tasks and struggle to balance recognition, parsing, and reasoning across scenarios. In this report, we present PolyOCR, a family of unified OCR foundation models of varying scales. PolyOCR combines a shared instruction-following framework with a large-scale data engine that converts heterogeneous visual resources into quality-verified OCR supervision. We introduce Competence-Guided Policy Optimization, which combines verifier-based Group Relative Policy Optimization with on-policy distillation through sample-wise routing based on teacher reliability and the teacher--student competence gap. We also introduce OCRBench v2.1, our revision of OCRBench v2 with manually verified annotation corrections and task-aligned scoring metrics. Extensive experiments across OCRBench v2.1, CC-OCR, in-house KIE Benchmark, OmniDocBench v1.6 and MDPBench demonstrate that PolyOCR achieves state-of-the-art or highly competitive performance.
Original Article
View Cached Full Text

Cached at: 10/12/26, 02:37 AM

Paper page - PolyOCR-Venus: Unified OCR Foundation Models for Text-Centric Visual Intelligence

Source: https://huggingface.co/papers/2609.37712 Published on Sep 29

#3 Paper of the day Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

OpticalCharacterRecognition(OCR)isevolvingfromplain-texttranscriptiontowardgeneralvisualintelligence,requiringmodelstorecognize,localize,andreasonovertextualinformationincomplexvisualenvironments.However,existingOCRsystemsoftenexcelatonlysometasksandstruggletobalancerecognition,parsing,andreasoningacrossscenarios.Inthisreport,wepresentPolyOCR,afamilyofunifiedOCRfoundationmodelsofvaryingscales.PolyOCRcombinesasharedinstruction-followingframeworkwithalarge-scaledataenginethatconvertsheterogeneousvisualresourcesintoquality-verifiedOCRsupervision.WeintroduceCompetence-GuidedPolicyOptimization,whichcombinesverifier-basedGroupRelativePolicyOptimizationwithon-policydistillationthroughsample-wiseroutingbasedonteacherreliabilityandtheteacher--studentcompetencegap.WealsointroduceOCRBenchv2.1,ourrevisionofOCRBenchv2withmanuallyverifiedannotationcorrectionsandtask-alignedscoringmetrics.ExtensiveexperimentsacrossOCRBenchv2.1,CC-OCR,in-houseKIEBenchmark,OmniDocBenchv1.6andMDPBenchdemonstratethatPolyOCRachievesstate-of-the-artorhighlycompetitiveperformance.

View arXiv pageView PDFGitHub46Add to collection

Get this paper in your agent:

hf papers read 2609\.37712

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2609.37712 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2609.37712 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2609.37712 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

MonkeyOCRv2: A Visual-Text Foundation Model for Document AI

Hugging Face Daily Papers

MonkeyOCRv2 is a visual-text foundation model for document AI, pretrained on a large corpus of 113 million images across 17 languages using joint image-to-text generation and pixel-level document reconstruction. It achieves state-of-the-art results on document parsing and understanding tasks, outperforming previous models with a smaller vision encoder.

@geekbb: Baidu's open-source visual language model OCR project, upgraded from DeepSeek-OCR, focuses on one-shot parsing of extremely long documents. The model has two inference modes: 'gundam' mode for dense text in a single image, and 'base' mode for multi-page or PDF processing. https://github…

X AI KOLs Timeline

Baidu has open-sourced the visual language model Unlimited-OCR, upgraded from DeepSeek-OCR, supporting one-shot parsing of extremely long documents, offering two inference modes: gundam (dense text in a single image) and base (multi-page/PDF).

OvisOCR3 Technical Report

Hugging Face Daily Papers

OvisOCR3 is a compact 0.8B vision-language model that unifies document parsing, general OCR, key information extraction, figure captioning, and cross-page table reconstruction via multi-teacher on-policy distillation and mixed-task reinforcement learning, achieving state-of-the-art results on benchmarks like OmniDocBench v1.6, OCRBench v2, and PureDocBench.

@berryxia: https://x.com/berryxia/status/2067078380017828205

X AI KOLs Timeline

The author tested the three tiers of PP-OCRv6 models and provided open-source tools for local deployment. They demonstrated performance comparisons of each model on OmniDocBench and real-world scenarios, emphasizing the advantages of lightweight specialized models for OCR tasks.