Multimodal Machine Translation (MMT) typically enhances text-only translation by incorporating aligned visual features. Despite the remarkable progress, state-of-the-art MMT approaches often rely on paired image-text inputs at inference and are sensitive to irrelevant visual noise, which limits their robustness and practical applicability. To address these issues, we propose D2P-MMT, a diffusion-based dual-branch prompting framework for robust vision-guided translation. Specifically, D2P-MMT requires only the source text and a reconstructed image generated by a pre-trained diffusion model, which naturally filters out distracting visual details while preserving semantic cues. During training, the model jointly learns from both authentic and reconstructed images using a dual-branch prompting strategy, encouraging rich cross-modal interactions. To bridge the modality gap and mitigate training-inference discrepancies, we introduce a distributional alignment loss that enforces consistency between the output distributions of the two branches. Extensive experiments on the Multi30K dataset demonstrate that D2P-MMT achieves superior translation performance compared to existing state-of-the-art approaches.
@article{arxiv.2507.17588,
title = {Dual-branch Prompting for Multimodal Machine Translation},
author = {Jie Wang and Zhendong Yang and Liansong Zong and Xiaobo Zhang and Dexian Wang and Ji Zhang},
journal= {arXiv preprint arXiv:2507.17588},
year = {2025}
}
Comments
This manuscript is currently under review at the ACM Transactions on Multimedia Computing, Communications, and Applications