Discrete Flow Matching for Automated Video Dubbing via Cross-Modal Alignment and Synchronization

Ngoc-Son Nguyen¹     Thanh V. T. Tran¹     Jeongsoo Choi²     Hieu-Nghia Huynh-Nguyen¹     Truong-Son Hy³     Van Nguyen^1†

¹ FPT Software AI Center, Vietnam    ² KAIST, South Korea    ³ University of Alabama at Birmingham, USA

^† Corresponding author

🎬 Framework

📦 Code Release

The official code will be released soon. Stay tuned!

📝 Citation

If you find this work useful, please cite:

@InProceedings{nguyen2026diflowdubber,
    author    = {Nguyen, Ngoc-Son and Tran, Thanh V. T. and Choi, Jeongsoo and Huynh-Nguyen, Hieu-Nghia and Hy, Truong-Son and Nguyen, Van},
    title     = {DiFlowDubber: Discrete Flow Matching for Automated Video Dubbing via Cross-Modal Alignment and Synchronization},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Findings},
    month     = {June},
    year      = {2026},
    pages     = {5838-5848}
}