mlsanityData to 7 Oct 2026

FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow

arXiv 1909.02480 ↗First posted 5 Sep 2019cs.CL cs.LGcited by 89

Not on the map. Why?

Abstract (arXiv)

Most sequence-to-sequence (seq2seq) models are autoregressive; they generate each token by conditioning on previously generated tokens. In contrast, non-autoregressive seq2seq models generate all tokens in one pass, which leads to increased efficiency through parallel processing on hardware such as GPUs. However, directly modeling the joint distribution of all tokens simultaneously is challenging, and even with increasingly complex model structures accuracy lags significantly behind autoregressive models. In this paper, we propose a simple, efficient, and effective model for non-autoregressive sequence generation using latent variable models. Specifically, we turn to generative flow, an elegant technique to model complex distributions using neural networks, and design several layers of flow tailored for modeling the conditional density of sequential latent variables. We evaluate this model on three neural machine translation (NMT) benchmark datasets, achieving comparable performance with state-of-the-art non-autoregressive NMT models and almost constant decoding time w.r.t the sequence length.

Key facts. Cited by 89 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 27; 2022: 26; 2023: 16; 2024: 9; 2025: 6; 2026: 5.

89 papers.

Sort:

By area:

  1. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,006
  2. 2022SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Controlcited by 191
  3. 2023Geometric Latent Diffusion Models for 3D Molecule Generationcited by 185
  4. 2021Step-unrolled Denoising Autoencoders for Text Generationcited by 102
  5. 2021Intermediate Loss Regularization for CTC-based Speech Recognitioncited by 95
  6. 2023Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipelinecited by 86
  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. 2021Transformer-based Conditional Variational Autoencoder for Controllable Story Generationcited by 44
  10. 2022Directed Acyclic Transformer for Non-Autoregressive Machine Translationcited by 44
  11. 2021FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognitioncited by 43
  12. 2021Non-Autoregressive Text Generation with Pre-trained Language Modelscited by 36
38 more
  1. 2021Civil Rephrases Of Toxic Texts With Self-Supervised Transformerscited by 32
  2. 2021Fast End-to-End Speech Recognition via Non-Autoregressive Models and Cross-Modal Knowledge Transferring from BERTcited by 31
  3. 2021A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generationcited by 27
  4. 2022On the Learning of Non-Autoregressive Transformerscited by 27
  5. 2022Controllable Text Generation via Probability Density Estimation in the Latent Spacecited by 27
  6. 2025A Survey on Parallel Text Generation: From Parallel Decoding to Diffusion Language Modelscited by 27
  7. 2021Non-Autoregressive Translation by Learning Target Categorical Codescited by 25
  8. 2021AligNART: Non-autoregressive Neural Machine Translation by Jointly Learning to Estimate Alignment and Translatecited by 24
  9. 2022textitlatent-GLAT: Glancing at Latent Variables for Parallel Text Generationcited by 20
  10. 2022One Reference Is Not Enough: Diverse Distillation with Reference Selection for Non-Autoregressive Translationcited by 20
  11. 2021Sequence-Level Training for Non-Autoregressive Neural Machine Translationcited by 18
  12. 2021Non-Autoregressive Semantic Parsing for Compositional Task-Oriented Dialogcited by 17
  13. 2021Thinking Clearly, Talking Fast: Concept-Guided Non-Autoregressive Generation for Open-Domain Dialogue Systemscited by 17
  14. 2022Non-Monotonic Latent Alignments for CTC-Based Non-Autoregressive Machine Translationcited by 16
  15. 2021Discovering Non-monotonic Autoregressive Orderings with Variational Inferencecited by 15
  16. 2022Recent Advances in Neural Text Generation: A Task-Agnostic Surveycited by 14
  17. 2023Universal Multimodal Representation for Language Understandingcited by 14
  18. 2021Enriching Non-Autoregressive Transformer with Syntactic and SemanticStructures for Neural Machine Translationcited by 13
  19. 2021Memory-Efficient Differentiable Transformer Architecture Searchcited by 13
  20. 2022Viterbi Decoding of Directed Acyclic Transformer for Non-Autoregressive Machine Translationcited by 13
  21. 2023Candidate Soups: Fusing Candidate Results Improves Translation Quality for Non-Autoregressive Translationcited by 13
  22. 2023Diffusion-Model-Assisted Supervised Learning of Generative Models for Density Estimationcited by 13
  23. 2022Semi-Discrete Normalizing Flows through Differentiable Tessellationcited by 11
  24. 2022ELMER: A Non-Autoregressive Pre-trained Language Model for Efficient and Effective Text Generationcited by 10
  25. 2021Duplex Sequence-to-Sequence Learning for Reversible Machine Translationcited by 9
  26. 2021Non-autoregressive End-to-end Speech Translation with Parallel Autoregressive Rescoringcited by 9
  27. 2021NAST: Non-Autoregressive Spatial-Temporal Transformer for Time Series Forecastingcited by 8
  28. 2022ngram-OAXE: Phrase-Based Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translationcited by 8
  29. 2021Parallel and High-Fidelity Text-to-Lip Generationcited by 7
  30. 2024Beyond Next Token Prediction: Patch-Level Training for Large Language Modelscited by 7
  31. 2025Bifidelity Parameter Estimation Using Conditional Diffusion Modelscited by 7
  32. 2022Multi-Granularity Optimization for Non-Autoregressive Translationcited by 6
  33. 2024Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical Guidelinescited by 6
  34. 2025Parallel Token Prediction for Language Modelscited by 6
  35. 2021MvSR-NAT: Multi-view Subset Regularization for Non-Autoregressive Machine Translationcited by 5
  36. 2022Non-Autoregressive Neural Machine Translation: A Call for Claritycited by 5
  37. 2024A Comprehensive Survey of Accelerated Generation Techniques in Large Language Modelscited by 5
  38. 2021Modeling Coverage for Non-Autoregressive Neural Machine Translationcited by 4

50 most cited of 89 All 89 (JSON)