mlsanityData to 14 Oct 2026

DIMT25@ICDAR2025: HW-TSC's End-to-End Document Image Machine Translation System Leveraging Large Vision-Language Model

arXiv 2504.17315 ↗First posted 24 Apr 2025cs.CV cs.AIcited by 0

On the map: Multimodal LLMs / vision-language models → Document understanding and multimodal RAG

Abstract (arXiv)

This paper presents the technical solution proposed by Huawei Translation Service Center (HW-TSC) for the "End-to-End Document Image Machine Translation for Complex Layouts" competition at the 19th International Conference on Document Analysis and Recognition (DIMT25@ICDAR2025). Leveraging state-of-the-art open-source large vision-language model (LVLM), we introduce a training framework that combines multi-task learning with perceptual chain-of-thought to develop a comprehensive end-to-end document translation system. During the inference phase, we apply minimum Bayesian decoding and post-processing strategies to further enhance the system's translation capabilities. Our solution uniquely addresses both OCR-based and OCR-free document image translation tasks within a unified framework. This paper systematically details the training methods, inference strategies, LVLM base models, training data, experimental setups, and results, demonstrating an effective approach to document image machine translation.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Document understanding and multimodal RAG, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 15 of its 27 references that are in the map. First posted on arXiv 24 Apr 2025.

Builds on

15 of 27 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Evaluating Menu OCR and Translation: A Benchmark for Aligning Human and Automated Evaluations in Large Vision-Language Models16 Apr

Other references · 14

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2025Qwen2.5-VL Technical Reportcited by 5,587
  3. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  4. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scalingcited by 1,599
  5. 2023A Survey on Evaluation of Large Language Modelscited by 1,242
  6. 2020COMET: A Neural Framework for MT Evaluationcited by 1,033
  7. 2017A Survey on Multi-Task Learningcited by 840
  8. 2024Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimizationcited by 239
  9. 2023How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Compositioncited by 223
  10. 2023Continual Pre-Training of Large Language Models: How to (re)warm your model?cited by 137
  11. 2023An Empirical Study of Translation Hypothesis Ensembling with Large Language Modelscited by 16
  12. 2021Perspectives and Prospects on Transformer Architecture for Cross-Modal Tasks with Language and Visioncited by 14
2 more
  1. 2024Choose the Final Translation from NMT and LLM hypotheses Using MBR Decoding: HW-TSC's Submission to the WMT24 General MT Shared Taskcited by 4
  2. 2024HW-TSC's Submission to the CCMT 2024 Machine Translation Taskscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Comparative Evaluation of Machine Translation Systems on Images with Text
  2. 2025Single-to-mix Modality Alignment with Multimodal Large Language Model for Document Image Machine Translation
  3. 2025Improving MLLM's Document Image Machine Translation via Synchronously Self-reviewing Its OCR Proficiency
  4. 2025Rethinking Multilingual Vision-Language Translation: Dataset, Evaluation, and Adaptation
  5. 2025MT3: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning
  6. 2026MMTIT-Bench: A Multilingual and Multi-Scenario Benchmark with Cognition-Perception-Reasoning Guided Text-Image Machine Translation
  7. 2025Evaluating Multimodal Large Language Models on Vertically Written Japanese Text
  8. 2025VARCO-VISION-2.0 Technical Report