mlsanityData to 7 Oct 2026

Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement

arXiv 1802.06901 ↗First posted 19 Feb 2018cs.LG cs.CL stat.MLcited by 194

Not on the map. Why?

Cited by 27 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We propose a conditional non-autoregressive neural sequence model based on iterative refinement. The proposed model is designed based on the principles of latent variable models and denoising autoencoders, and is generally applicable to any sequence generation task. We extensively evaluate the proposed model on machine translation (En-De and En-Ro) and image caption generation, and observe that it significantly speeds up decoding while maintaining the generation quality comparable to the autoregressive counterpart.

Key facts. Cited by 194 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 60; 2022: 49; 2023: 36; 2024: 20; 2025: 12; 2026: 17.

194 papers.

Sort:

By area:

  1. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,006
  2. 2021Going deeper with Image Transformerscited by 759
  3. 2022Continuous diffusion for categorical datacited by 202
  4. 2022SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Controlcited by 191
  5. 2023Text Embeddings Reveal (Almost) As Much As Textcited by 189
  6. 2022Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generationcited by 169
  7. 2023Speculative Decoding with Big Little Decodercited by 163
  8. 2023A Reparameterized Discrete Diffusion Model for Text Generationcited by 152
  9. 2024LLM Inference Unveiled: Survey and Roofline Model Insightscited by 147
  10. 2022Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognitioncited by 139
  11. 2024Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planningcited by 135
  12. 2021Learning to Efficiently Sample from Diffusion Probabilistic Modelscited by 129
38 more
  1. 2023AR-Diffusion: Auto-Regressive Diffusion Model for Text Generationcited by 113
  2. 2021Step-unrolled Denoising Autoencoders for Text Generationcited by 102
  3. 2023Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systemscited by 101
  4. 2022Accelerating Bayesian Optimization for Biological Sequence Design with Denoising Autoencoderscited by 99
  5. 2023Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipelinecited by 86
  6. 2022Text Generation with Diffusion Language Models: A Pre-training Approach with Continuous Paragraph Denoisecited by 79
  7. 2022A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyondcited by 64
  8. 2021Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translationcited by 57
  9. 2025Edit Flows: Flow Matching with Edit Operationscited by 53
  10. 2023DINOISER: Diffused Conditional Sequence Learning by Manipulating Noisescited by 50
  11. 2022Directed Acyclic Transformer for Non-Autoregressive Machine Translationcited by 44
  12. 2021Subformer: Exploring Weight Sharing for Parameter Efficiency in Generative Transformerscited by 42
  13. 2022DiffusER: Discrete Diffusion via Edit-based Reconstructioncited by 41
  14. 2021Non-Autoregressive Translation with Layer-Wise Prediction and Deep Supervisioncited by 40
  15. 2022Empowering Diffusion Models on the Embedding Space for Text Generationcited by 40
  16. 2022Semantic-Conditional Diffusion Networks for Image Captioningcited by 38
  17. 2021M6-UFC: Unifying Multi-Modal Controls for Conditional Image Synthesis via Non-Autoregressive Generative Transformerscited by 36
  18. 2022EdiT5: Semi-Autoregressive Text-Editing with T5 Warm-Startcited by 35
  19. 2021Rejuvenating Low-Frequency Words: Making the Most of Parallel Data in Non-Autoregressive Translationcited by 34
  20. 2021Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Featurescited by 34
  21. 2021Universal Simultaneous Machine Translation with Mixture-of-Experts Wait-k Policycited by 32
  22. 2021Fast End-to-End Speech Recognition via Non-Autoregressive Models and Cross-Modal Knowledge Transferring from BERTcited by 31
  23. 2025FlowTok: Flowing Seamlessly Across Text and Image Tokenscited by 31
  24. 2022Learning to Model Editing Processescited by 30
  25. 2023A Review of Deep Learning for Video Captioningcited by 28
  26. 2021FastCorrect 2: Fast Error Correction on Multiple Candidates for Automatic Speech Recognitioncited by 27
  27. 2021A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generationcited by 27
  28. 2022On the Learning of Non-Autoregressive Transformerscited by 27
  29. 2023Iterative Translation Refinement with Large Language Modelscited by 27
  30. 2025A Survey on Parallel Text Generation: From Parallel Decoding to Diffusion Language Modelscited by 27
  31. 2024Flowing from Words to Pixels: A Noise-Free Framework for Cross-Modality Evolutioncited by 26
  32. 2021Non-Autoregressive Translation by Learning Target Categorical Codescited by 25
  33. 2021Towards Accurate Text-based Image Captioning with Content Diversity Explorationcited by 25
  34. 2021Progressive Multi-Granularity Training for Non-Autoregressive Translationcited by 25
  35. 2021AligNART: Non-autoregressive Neural Machine Translation by Jointly Learning to Estimate Alignment and Translatecited by 24
  36. 2021Parallel Refinements for Lexically Constrained Text Generation with BARTcited by 24
  37. 2021Investigating the Reordering Capability in CTC-based Non-Autoregressive End-to-End Speech Translationcited by 23
  38. 2021Learning to Complete Code with Sketchescited by 23

50 most cited of 194 All 194 (JSON)