Abstract
Optical character recognition (OCR) has evolved from line-level transcription to structured document parsing, requiring models to recover long-form sequences containing layout, tables, and formulas. Despite recent advances in vision-language models, most existing systems rely on autoregressive decoding, which introduces sequential latency and amplifies error propagation in long documents. In this work, we revisit document OCR from an inverse rendering perspective, arguing that left-to-right causal generation is an artifact of serialization rather than an intrinsic property of the task. Motivated by this insight, we propose MinerU-Diffusion, a unified diffusion-based framework that replaces autoregressive sequential decoding with parallel diffusion denoising under visual conditioning. MinerU-Diffusion employs a block-wise diffusion decoder and an uncertainty-driven curriculum learning strategy to enable stable training and efficient long-sequence inference. Extensive experiments demonstrate that MinerU-Diffusion consistently improves robustness while achieving up to 3.2x faster decoding compared to autoregressive baselines. Evaluations on the proposed Semantic Shuffle benchmark further confirm its reduced dependence on linguistic priors and stronger visual OCR capability.
Abstract (translated)
光学字符识别（OCR）已从逐行转录演进为结构化文档解析，需要模型重建包含版式、表格和公式的长序列内容。尽管视觉语言模型近期取得进展，但现有系统大多依赖自回归解码，该方法会引入顺序延迟并加剧长文档中的错误传播。本研究从逆向渲染视角重新审视文档OCR，认为从左至右的因果生成是序列化的产物而非任务的内在属性。受此启发，我们提出MinerU-Diffusion——一个基于扩散模型的统一框架，用视觉条件下的并行扩散去噪取代自回归序列解码。该方法采用分块扩散解码器与不确定性驱动的课程学习策略，实现稳定训练与高效长序列推理。大量实验表明，MinerU-Diffusion在保持鲁棒性的同时，解码速度较自回归基线提升最高达3.2倍。在提出的语义打乱基准测试中，该方法进一步验证了其对语言先验依赖的降低及更强的视觉OCR能力。
URL
https://arxiv.org/abs/2603.22458
