Skip to content

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

Sep 2026 · 0 citations · 106 references
Computer Science

TL;DR

This report presents PolyOCR, a family of unified OCR foundation models of varying scales that combines a shared instruction-following framework with a large-scale data engine that converts heterogeneous visual resources into quality-verified OCR supervision.

Abstract

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.

View source

Similar papers

Preprint Sep 2026

Xiaomi-OCR-0 Technical Report

An approximately 170M-sample OCR-centric corpus is built using an automated data engine that combines expert consensus, render-based verification, and targeted synthesis and shows that, with sufficient parsing training, OCR-centric understanding supervision provides additional gains for document parsing.

Xin Chen, An-An Du, Feng-Juan Feng et al. · 0 citations
#natural language process... Preprint Aug 2026

OCR-MetaReasoning Benchmark: Evaluating the Meta-Reasoning Ability of MLLMs in Text-Rich Image Understanding

Experiments with representative closed-source and open-source MLLMs show that OCR-grounded meta-reasoning remains far from saturated: models struggle with visible-rule application and layout-sensitive inference, while process-compliant rationales can accompany incorrect final answers under exact-match evaluation.

Geng-Xu Li, Yuan Wu, Yi Chang · 0 citations
Preprint Sep 2026

From Retrieval to Recognition:How Vision--Language Models Become OCR Specialists

Comparisons show that OCR specialization largely preserves head identity, retaining 17-20 of the top 20 heads per task with all-head rank correlations of 0.874-0.942, while redistributing their functional and causal strengths.

Yuan-Xiang Huangfu, Han-Meng Zhong, Linqing Chen et al. · 0 citations
Aug 2026

OPUS: A Simple yet Effective Unified Framework for Open-Vocabulary Detection

The finding is that unified OVD can be made substantially simpler with semantic-rich visual representations and scalable grounding supervision, and turns mixed prompting from interference into complementarity, improving over text or visual prompt alone.

Xiao-Yan Wei, Zhi-Min Yao, Rui-Lin Yang et al. · 0 citations
#artificial intelligence Open access Oct 2026

From Pixels to Structure: Lightweight Vision-Language Models for Document OCR and Structured JSON Extraction

While massive, closed-source Vision-Language Models (VLMs) set strong benchmarks for document understanding, their dependence on commercial APIs limits adoption in institutional archives due to data autonomy concerns, recurring costs, and the environmental footprint of hyperscale computing. This is especially acute in...

Uddipan Basu Bir, Vincent Christlein, A. Maier et al. · 0 citations
Preprint Aug 2026

SEER: Long-Context Reasoning via Selective Visual-Text Compression

SEER is presented, a framework that learns to select query-relevant images through visual scanning and retrieve textual content only where needed, combining the efficiency of visual compression with the precision of text-based reasoning.

Jiawei Xu, Zhilin Zhai, Jinrui Fang et al. · 3 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.