Guardado en:
Detalles Bibliográficos
Autores principales: Li, Lei, Zhao, Ze, Li, Meng, Lun, Zhongwang, Yuan, Yi, Lu, Xingjing, Wei, Zheng, Bian, Jiang, Li, Zang
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2603.15206
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918391316480000
author Li, Lei
Zhao, Ze
Li, Meng
Lun, Zhongwang
Yuan, Yi
Lu, Xingjing
Wei, Zheng
Bian, Jiang
Li, Zang
author_facet Li, Lei
Zhao, Ze
Li, Meng
Lun, Zhongwang
Yuan, Yi
Lu, Xingjing
Wei, Zheng
Bian, Jiang
Li, Zang
contents Document parsing, as a fundamental yet crucial vision task, is being revolutionized by vision-language models (VLMs). However, the autoregressive (AR) decoding inherent to VLMs creates a significant bottleneck, severely limiting parsing speed. In this paper, we propose Parallel-Token Prediction (PTP), a plugable, model-agnostic and simple-yet-effective method that enables VLMs to generate multiple future tokens in parallel with improved sample efficiency. Specifically, we insert some learnable tokens into the input sequence and design corresponding training objectives to equip the model with parallel decoding capabilities for document parsing. Furthermore, to support effective training, we develop a comprehensive data generation pipeline that efficiently produces large-scale, high-quality document parsing training data for VLMs. Extensive experiments on OmniDocBench and olmOCR-bench demonstrate that our method not only significantly improves decoding speed (1.6x-2.2x) but also reduces model hallucinations and exhibits strong generalization abilities.
format Preprint
id arxiv_https___arxiv_org_abs_2603_15206
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Efficient Document Parsing via Parallel Token Prediction
Li, Lei
Zhao, Ze
Li, Meng
Lun, Zhongwang
Yuan, Yi
Lu, Xingjing
Wei, Zheng
Bian, Jiang
Li, Zang
Computation and Language
Computer Vision and Pattern Recognition
Document parsing, as a fundamental yet crucial vision task, is being revolutionized by vision-language models (VLMs). However, the autoregressive (AR) decoding inherent to VLMs creates a significant bottleneck, severely limiting parsing speed. In this paper, we propose Parallel-Token Prediction (PTP), a plugable, model-agnostic and simple-yet-effective method that enables VLMs to generate multiple future tokens in parallel with improved sample efficiency. Specifically, we insert some learnable tokens into the input sequence and design corresponding training objectives to equip the model with parallel decoding capabilities for document parsing. Furthermore, to support effective training, we develop a comprehensive data generation pipeline that efficiently produces large-scale, high-quality document parsing training data for VLMs. Extensive experiments on OmniDocBench and olmOCR-bench demonstrate that our method not only significantly improves decoding speed (1.6x-2.2x) but also reduces model hallucinations and exhibits strong generalization abilities.
title Efficient Document Parsing via Parallel Token Prediction
topic Computation and Language
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.15206