mlsanityData to 14 Oct 2026

Zero-Shot Translation using Diffusion Models

arXiv 2111.01471 ↗First posted 2 Nov 2021cs.CL cs.LGcited by 9

On the map: Diffusion models → Discrete and text diffusion

Abstract (arXiv)

In this work, we show a novel method for neural machine translation (NMT), using a denoising diffusion probabilistic model (DDPM), adjusted for textual data, following recent advances in the field. We show that it's possible to translate sentences non-autoregressively using a diffusion model conditioned on the source sentence. We also show that our model is able to translate between pairs of languages unseen during training (zero-shot learning).

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Placed in Discrete and text diffusion, one of 14 directions in Diffusion models. Builds on 15 of its 19 references that are in the map. First posted on arXiv 2 Nov 2021.

Builds on

15 of 19 references.

References · 15

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  7. 2013Auto-Encoding Variational Bayescited by 4,053
  8. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  9. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,799
  10. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,719
  11. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,545
  12. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,387
3 more
  1. 2020NVAE: A Deep Hierarchical Variational Autoencodercited by 637
  2. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 622
  3. 2018Adversarial Audio Synthesiscited by 225

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 4; 2024: 1; 2025: 2.

9 papers.

  1. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  2. 2022All are Worth Words: A ViT Backbone for Diffusion Modelscited by 502
  3. 2023Gaussian Mixture Solvers for Diffusion Modelscited by 18
  4. 2023Diffusion Models in NLP: A Surveycited by 16
  5. 2023A Survey of Diffusion Models in Natural Language Processingcited by 16
  6. 2025Diffuse Thinking: Exploring Diffusion Language Models as Efficient Thought Proposers for Reasoningcited by 3
  7. 2024Let's Rectify Step by Step: Improving Aspect-based Sentiment Analysis with Diffusion Modelscited by 2
  8. 2025Diffusion Models for Reinforcement Learning: Foundations, Taxonomy, and Developmentcited by 2
  9. 2023Diffusion-EXR: Controllable Review Generation for Explainable Recommendation via Diffusion Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Discrete Diffusion Models for Language Generation
  2. 2025Simple Denoising Diffusion Language Models
  3. 2023Diffusion-NAT: Self-Prompting Discrete Diffusion for Non-Autoregressive Text Generation
  4. 2025Improving Text Style Transfer using Masked Diffusion Language Models with Inference-time Scaling
  5. 2026Towards Latent Diffusion Suitable For Text
  6. 2025A Survey on Diffusion Language Models
  7. 2022Text Generation with Diffusion Language Models: A Pre-training Approach with Continuous Paragraph Denoise
  8. 2024Simple and Effective Masked Diffusion Language Models