UniRec-0.1B: Unified Text and Formula Recognition with 0.1B Parameters

TL;DR

UniRec-0.1B is a lightweight, unified model for text and formula recognition that outperforms larger models in accuracy and speed, trained on a large-scale dataset with innovative hierarchical and semantic decoupling techniques.

Contribution

The paper introduces UniRec-0.1B, a novel 0.1-billion-parameter model for unified text and formula recognition, with new hierarchical supervision and semantic-decoupled tokenization methods.

Findings

Outperforms larger vision-language models and expert systems.

Achieves 2-9 times faster processing speed.

Demonstrates effectiveness across multiple languages and domains.

Abstract

Text and formulas constitute the core informational components of many documents. Accurately and efficiently recognizing both is crucial for developing robust and generalizable document parsing systems. Recently, vision-language models (VLMs) have achieved impressive unified recognition of text and formulas. However, they are large-sized and computationally demanding, restricting their usage in many applications. In this paper, we propose UniRec-0.1B, a unified recognition model with only 0.1B parameters. It is capable of performing text and formula recognition at multiple levels, including characters, words, lines, paragraphs, and documents. To implement this task, we first establish UniRec40M, a large-scale dataset comprises 40 million text, formula and their mix samples, enabling the training of a powerful yet lightweight model. Secondly, we identify two challenges when building such a lightweight but unified expert model. They are: structural variability across hierarchies and semantic entanglement between textual and formulaic content. To tackle these, we introduce a hierarchical supervision training that explicitly guides structural comprehension, and a semantic-decoupled tokenizer that separates text and formula representations. Finally, we develop a comprehensive evaluation benchmark covering Chinese and English documents from multiple domains and with multiple levels. Experimental results on this and public benchmarks demonstrate that UniRec-0.1B outperforms both general-purpose VLMs and leading document parsing expert models, while achieving a 2-9$\times$ speedup, validating its effectiveness and efficiency. Codebase and Dataset: https://github.com/Topdu/OpenOCR.