mlsanityData to 14 Oct 2026

Generating Sentences from a Continuous Space

arXiv 1511.06349 ↗First posted 19 Nov 2015cs.LG cs.CLcited by 612

Not on the map. Why?

Cited by 28 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

The standard recurrent neural network language model (RNNLM) generates sentences one word at a time and does not work from an explicit global sentence representation. In this work, we introduce and study an RNN-based variational autoencoder generative model that incorporates distributed latent representations of entire sentences. This factorization allows it to explicitly model holistic properties of sentences such as style, topic, and high-level syntactic features. Samples from the prior over these sentence representations remarkably produce diverse and well-formed sentences through simple deterministic decoding. By examining paths through this latent space, we are able to generate coherent novel sentences that interpolate between known sentences. We present techniques for solving the difficult learning problem presented by this model, demonstrate its effectiveness in imputing missing words, explore many interesting properties of the model's latent sentence space, and present negative results on the use of the model in language modeling.

Key facts. Cited by 612 papers in the map (data through 14 Oct 2026). First posted on arXiv 19 Nov 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 185; 2022: 139; 2023: 103; 2024: 70; 2025: 66; 2026: 49.

612 papers.

Sort:

By area:

  1. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  2. 2023The Linear Representation Hypothesis and the Geometry of Large Language Modelscited by 716
  3. 2021Score-based Generative Modeling in Latent Spacecited by 636
  4. 2021HuMoR: 3D Human Motion Model for Robust Pose Estimationcited by 324
  5. 2021Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Modelscited by 252
  6. 2022Extracting Latent Steering Vectors from Pretrained Language Modelscited by 225
  7. 2023Text Embeddings Reveal (Almost) As Much As Textcited by 192
  8. 2021GPT3Mix: Leveraging Large-scale Language Models for Text Augmentationcited by 187
  9. 2021Symbolic Music Generation with Diffusion Modelscited by 154
  10. 2021Probabilistic Embeddings for Cross-Modal Retrievalcited by 151
  11. 2022What Matters in Language Conditioned Robotic Imitation Learning over Unstructured Datacited by 138
  12. 2021Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Predictioncited by 131
38 more
  1. 2021A Survey on Data Augmentation for Text Classificationcited by 111
  2. 2021Step-unrolled Denoising Autoencoders for Text Generationcited by 102
  3. 2021An Empirical Survey of Data Augmentation for Limited Data Learning in NLPcited by 101
  4. 2021Survey of Low-Resource Machine Translationcited by 92
  5. 2021Variational Transformer Networks for Layout Generationcited by 88
  6. 2022ZeroEGGS: Zero-shot Example-based Gesture Generation from Speechcited by 84
  7. 2022Compositional Human-Scene Interaction Synthesis with Semantic Controlcited by 83
  8. 2021Visual Alignment Constraint for Continuous Sign Language Recognitioncited by 80
  9. 2021Is Automated Topic Model Evaluation Broken?: The Incoherence of Coherencecited by 74
  10. 2021Learning to Extend Molecular Scaffolds with Structural Motifscited by 71
  11. 2021Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codescited by 71
  12. 2021Directed Acyclic Graph Neural Networkscited by 70
  13. 2022Latent Diffusion Energy-Based Model for Interpretable Text Modelingcited by 67
  14. 2022Decoding Visual Neural Representations by Multimodal Learning of Brain-Visual-Linguistic Featurescited by 63
  15. 2023Uncertainty in Natural Language Generation: From Theory to Applicationscited by 61
  16. 2022MUSE-VAE: Multi-Scale VAE for Environment-Aware Long Term Trajectory Predictioncited by 59
  17. 2023PLANNER: Generating Diversified Paragraph via Latent Language Diffusion Modelcited by 58
  18. 2023CktGNN: Circuit Graph Neural Network for Electronic Design Automationcited by 58
  19. 2021HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learningcited by 57
  20. 2022Fine-mixing: Mitigating Backdoors in Fine-tuned Language Modelscited by 57
  21. 2023Posterior Collapse and Latent Variable Non-identifiabilitycited by 57
  22. 2023On the Creativity of Large Language Modelscited by 57
  23. 2021Topic-Driven and Knowledge-Aware Transformer for Dialogue Emotion Detectioncited by 56
  24. 2022FLAG: Flow-based 3D Avatar Generation from Sparse Observationscited by 55
  25. 2021Consistency Regularization for Variational Auto-Encoderscited by 51
  26. 2021Variational Information Bottleneck for Effective Low-Resource Fine-Tuningcited by 51
  27. 2021Improving black-box optimization in VAE latent space using decoder uncertaintycited by 51
  28. 2021A Primer on Pretrained Multilingual Language Modelscited by 49
  29. 2022Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Taskscited by 49
  30. 2021G-Transformer for Document-level Machine Translationcited by 46
  31. 2023De Novo Molecular Generation via Connection-aware Motif Miningcited by 46
  32. 2021Generating Syntactically Controlled Paraphrases without Using Annotated Parallel Pairscited by 45
  33. 2022A Causal Lens for Controllable Text Generationcited by 45
  34. 2021Transformer-based Conditional Variational Autoencoder for Controllable Story Generationcited by 44
  35. 2021Generate, Prune, Select: A Pipeline for Counterspeech Generation against Online Hate Speechcited by 42
  36. 2021MuseMorphose: Full-Song and Fine-Grained Piano Music Style Transfer with One Transformer VAEcited by 40
  37. 2024A Comprehensive Survey on Data Augmentationcited by 40
  38. 2022Recent Advances for Quantum Neural Networks in Generative Learningcited by 39

50 most cited of 612 All 612 (JSON)