mlsanityData to 7 Oct 2026

A Recurrent Latent Variable Model for Sequential Data

arXiv 1506.02216 ↗First posted 7 Jun 2015cs.LGcited by 362

Not on the map. Why?

Abstract (arXiv)

In this paper, we explore the inclusion of latent random variables into the dynamic hidden state of a recurrent neural network (RNN) by combining elements of the variational autoencoder. We argue that through the use of high-level latent random variables, the variational RNN (VRNN)1 can model the kind of variability observed in highly structured sequential data such as natural speech. We empirically evaluate the proposed model against related sequential models on four speech datasets and one handwriting dataset. Our results show the important roles that latent random variables can play in the RNN dynamic hidden state.

Key facts. Cited by 362 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Jun 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 1; 2019: 2; 2020: 1; 2021: 97; 2022: 74; 2023: 58; 2024: 54; 2025: 42; 2026: 33.

362 papers.

Sort:

By area:

  1. 2024Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusioncited by 634
  2. 2018An Algorithmic Perspective on Imitation Learningcited by 455
  3. 2022Flexible Diffusion Modeling of Long Videoscited by 294
  4. 2022Self-Supervised Speech Representation Learning: A Reviewcited by 258
  5. 2022Diffusion Probabilistic Modeling for Video Generationcited by 237
  6. 2021Modeling Irregular Time Series with Continuous Recurrent Unitscited by 101
  7. 2022Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectivescited by 98
  8. 2022Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusioncited by 96
  9. 2023Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglementcited by 89
  10. 2021FitVid: Overfitting in Pixel-Level Video Predictioncited by 86
  11. 2022Tutorial on amortized optimizationcited by 83
  12. 2021AI in Finance: Challenges, Techniques and Opportunitiescited by 81
38 more
  1. 2021RAVE: A variational autoencoder for fast and high-quality neural audio synthesiscited by 72
  2. 2022SocialVAE: Human Trajectory Prediction using Timewise Latentscited by 65
  3. 2021Differentiable Particle Filtering via Entropy-Regularized Optimal Transportcited by 59
  4. 2021Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modelingcited by 59
  5. 2021Active Inference in Robotics and Artificial Agents: Survey and Challengescited by 52
  6. 2023TimesURL: Self-supervised Contrastive Learning for Universal Time Series Representation Learningcited by 51
  7. 2021Learning the Predictability of the Futurecited by 48
  8. 2023Generative Modeling of Regular and Irregular Time Series Data via Koopman VAEscited by 48
  9. 2023Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Predictioncited by 47
  10. 2023Causal Recurrent Variational Autoencoder for Medical Time Series Generationcited by 44
  11. 2021Clockwork Variational Autoencoderscited by 40
  12. 2021Anomaly Detection of Time Series with Smoothness-Inducing Sequential Variational Auto-Encodercited by 39
  13. 2022Deep Latent State Space Models for Time-Series Generationcited by 37
  14. 2022Contrastive Learning for Unsupervised Domain Adaptation of Time Seriescited by 36
  15. 2021Move2Hear: Active Audio-Visual Source Separationcited by 35
  16. 2022How many Observations are Enough? Knowledge Distillation for Trajectory Forecastingcited by 35
  17. 2023Deep networks for system identification: a Surveycited by 35
  18. 2021Contrastively Disentangled Sequential Variational Autoencodercited by 34
  19. 2023Uncertainty-aware State Space Transformer for Egocentric 3D Hand Trajectory Forecastingcited by 33
  20. 2021Temporal Latent Auto-Encoder: A Method for Probabilistic Multivariate Time Series Forecastingcited by 32
  21. 2021Imagining The Road Ahead: Multi-Agent Trajectory Prediction via Differentiable Simulationcited by 32
  22. 2021Time Series Anomaly Detection for Cyber-Physical Systems via Neural System Identification and Bayesian Filteringcited by 31
  23. 2021Deep Interactive Bayesian Reinforcement Learning via Meta-Learningcited by 29
  24. 2021Learning Interpretable Deep State Space Model for Probabilistic Time Series Forecastingcited by 29
  25. 2021Robust Predictable Controlcited by 29
  26. 2021Constructing Neural Network-Based Models for Simulating Dynamical Systemscited by 29
  27. 2021Unsupervised Speech Enhancement using Dynamical Variational Auto-Encoderscited by 28
  28. 2023Neural Continuous-Discrete State Space Models for Irregularly-Sampled Time Seriescited by 28
  29. 2024Diff-RNTraj: A Structure-aware Diffusion Model for Road Network-constrained Trajectory Generationcited by 28
  30. 2021Model-Based Reinforcement Learning via Latent-Space Collocationcited by 27
  31. 2021Temporal Dependencies in Feature Importance for Time Series Predictionscited by 27
  32. 2020Diffusion models for Handwriting Generationcited by 25
  33. 2021Bayesian Attention Belief Networkscited by 25
  34. 2021Roto-translated Local Coordinate Frames For Interacting Dynamical Systemscited by 24
  35. 2022Domain Adaptation for Time-Series Classification to Mitigate Covariate Shiftcited by 24
  36. 2021Disentangled Recurrent Wasserstein Autoencodercited by 22
  37. 2021A survey on Variational Autoencoders from a GreenAI perspectivecited by 22
  38. 2021Fully Spiking Variational Autoencodercited by 22

50 most cited of 362 All 362 (JSON)