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

arXiv:2609.37712 · cs.CV, cs.AI · Submitted 2026-09-29 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-09-29

Updated: 2026-09-29

Comments: Technical Report

Code: https://github.com/inclusionAI/PolyOCR-Venus

License: http://creativecommons.org/licenses/by/4.0/

The gist: 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

Terminology

Benchmark — 44× in this paper · explained in 2 episodes
Distillation — 28× in this paper · explained in 2 episodes
GRPO — 26× in this paper · explained in 6 episodes
Verifier — 26× in this paper · explained in 2 episodes
Calibration — 25× in this paper · explained in 7 episodes
Consistency — 23× in this paper · explained in 3 episodes
Foundation Model — 17× in this paper · explained in 3 episodes
Grounding — 17× in this paper · explained in 3 episodes
Text Perception — 14× in this paper
Key Information Extraction — 12× in this paper
Foundation Models — 11× in this paper · explained in 7 episodes
Competence-Guided Policy Optimization — 9× in this paper
Verification — 9× in this paper · explained in 2 episodes
F1 Score — 8× in this paper · explained in 3 episodes
On-Policy Distillation — 8× in this paper · explained in 3 episodes
Accuracy — 7× in this paper · explained in 1 episode
Alignment — 6× in this paper · explained in 1 episode
Fine-Tuning — 6× in this paper · explained in 5 episodes
International Conference on Document Analysis and Recognition — 6× in this paper
Reinforcement Learning — 6× in this paper · explained in 4 episodes
Optical Character Recognition — 5× in this paper
Ablation — 4× in this paper · explained in 1 episode
Aggregation — 3× in this paper · explained in 1 episode
CVF International Conference on Computer Vision — 3× in this paper
Document Structure Understanding — 3× in this paper
Generalization — 3× in this paper · explained in 13 episodes
Group Relative Policy Optimization — 3× in this paper
Semantic Understanding — 3× in this paper · explained in 2 episodes
Trace — 3× in this paper · explained in 2 episodes
Transformer — 3× in this paper · explained in 2 episodes
Ablation study — 2× in this paper · explained in 1 episode
Catastrophic Forgetting — 2× in this paper · explained in 5 episodes
General Multimodal Alignment — 2× in this paper
Knowledge Distillation — 2× in this paper · explained in 11 episodes
LLM judge — 2× in this paper · explained in 2 episodes
OCR Understanding and Reasoning — 2× in this paper
Reasoning Traces — 2× in this paper · explained in 3 episodes
Robustness — 2× in this paper · explained in 5 episodes
Two-stage training — 2× in this paper · explained in 2 episodes
alpha — 2× in this paper · explained in 1 episode
Adam — 1× in this paper · explained in 2 episodes
Adaptation — 1× in this paper · explained in 1 episode
Adaptive Weighting — 1× in this paper · explained in 1 episode
Annotation Errors — 1× in this paper · explained in 1 episode
Benchmarking — 1× in this paper · explained in 3 episodes
Clustering — 1× in this paper · explained in 2 episodes
Core — 1× in this paper · explained in 2 episodes
Degeneracy — 1× in this paper · explained in 3 episodes
Fidelity — 1× in this paper · explained in 2 episodes
GRPO Objective — 1× in this paper · explained in 2 episodes
Generative AI — 1× in this paper · explained in 2 episodes
Generative Modeling — 1× in this paper · explained in 3 episodes
Multimodal Reasoning — 1× in this paper · explained in 5 episodes
Perplexity — 1× in this paper · explained in 3 episodes
Representation Learning — 1× in this paper · explained in 2 episodes
Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes
Two-Stage Training Strategy — 1× in this paper · explained in 3 episodes
Unified Framework — 1× in this paper · explained in 5 episodes
Visual Grounding — 1× in this paper · explained in 2 episodes

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.

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

Terminology

Abstract

Sources

Related papers