mlsanityData to 14 Oct 2026

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

arXiv 2609.16312 ↗First posted 14 Sep 2026cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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 × 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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 40 references that are in the map. First posted on arXiv 14 Sep 2026.

Builds on

25 of 40 references.

References · 25

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
  4. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,799
  5. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,719
  6. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,312
  7. 2020COMET: A Neural Framework for MT Evaluationcited by 1,033
  8. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,027
  9. 2020Beyond English-Centric Multilingual Machine Translationcited by 561
  10. 2016Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translationcited by 469
  11. 2017Non-Autoregressive Neural Machine Translationcited by 463
  12. 2022DiffuSeq: Sequence to Sequence Text Generation with Diffusion Modelscited by 450
13 more
  1. 2025Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decodingcited by 420
  2. 2016Multi30K: Multilingual English-German Image Descriptionscited by 250
  3. 2022DiffusionBERT: Improving Generative Masked Language Models with Diffusion Modelscited by 214
  4. 2025dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Cachingcited by 169
  5. 2025LLaDA2.0: Scaling Up Diffusion Language Models to 100Bcited by 166
  6. 2020Deep Encoder, Shallow Decoder: Reevaluating Non-autoregressive Machine Translationcited by 105
  7. 2020Glancing Transformer for Non-Autoregressive Neural Machine Translationcited by 103
  8. 2022A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyondcited by 64
  9. 2018Non-Autoregressive Neural Machine Translation with Enhanced Decoder Inputcited by 39
  10. 2023Fast Sampling via Discrete Non-Markov Diffusion Models with Predetermined Transition Timecited by 20
  11. 2020A Framework for Hierarchical Multilingual Machine Translationcited by 3
  12. 2023XDLM: Cross-lingual Diffusion Language Model for Machine Translationcited by 3
  13. 2026Forward-Learned Discrete Diffusion: Learning how to noise to denoise fastercited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Dream 7B: Diffusion Large Language Models
  2. 2026Unlocking Lossless Speedups in LLMs via Discrete Diffusion
  3. 2026Accelerating Masked Diffusion Large Language Models: A Survey of Efficient Inference Techniques
  4. 2025FS-DFM: Fast and Accurate Long Text Generation with Few-Step Diffusion Language Models
  5. 2024Transfer Learning for Text Diffusion Models
  6. 2025Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speed
  7. 2025Breaking AR's Sampling Bottleneck: Provable Acceleration via Diffusion Language Models
  8. 2025FlashDLM: Accelerating Diffusion Language Model Inference via Efficient KV Caching and Guided Diffusion