Efficient One-to-Many Translation with Joint Multi-Stream Diffusion

2026-09-14

AI Summary

研究通过联合多流扩散方法解决自回归系统在多语言翻译中的计算效率问题，实现并行处理多种目标语言，提高速度和灵活性。

Abstract

One-to-many machine translation (MT) is computationally expensive for autoregressive (AR) systems, which suffer from linear latency scaling with both sequence length and the number of target languages. We explore how diffusion can enable multilingual translation with a discrete diffusion framework that refines all target languages in parallel, achieving sublinear latency scaling with the number of targets, and supports deployment as a single unified model to replace multiple independent systems. Conditioned on a continuous semantic anchor rather than source tokens, our framework supports zero-shot transfer to unseen source languages without retraining, maintaining approximately $75\%$ of its supervised translation quality on zero-shot sources. We investigate the quality-latency frontier and find that with accelerated sampling, it achieves comparable supervised quality to AR baselines with a $2 \times$ speedup and $11.9\%$ better zero-shot BLEU. These results highlight the potential of joint multi-stream diffusion as a practical and flexible alternative for efficient one-to-many translation.

Problem

• one-to-many machine translation
• autoregressive systems
• latency scaling
• multilingual translation
• zero-shot transfer

Innovation

• discrete diffusion framework
• parallel refinement
• sublinear latency scaling
• zero-shot transfer
• accelerated sampling