mlsanityData to 14 Oct 2026

Ladder Variational Autoencoders

arXiv 1602.02282 ↗First posted 6 Feb 2016stat.ML cs.LGcited by 318

Not on the map. Why?

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

Abstract (arXiv)

Variational Autoencoders are powerful models for unsupervised learning. However deep models with several layers of dependent stochastic variables are difficult to train which limits the improvements obtained using these highly expressive models. We propose a new inference model, the Ladder Variational Autoencoder, that recursively corrects the generative distribution by a data dependent approximate likelihood in a process resembling the recently proposed Ladder Network. We show that this model provides state of the art predictive log-likelihood and tighter log-likelihood lower bound compared to the purely bottom-up inference in layered Variational Autoencoders and other generative models. We provide a detailed analysis of the learned hierarchical latent representation and show that our new inference model is qualitatively different and utilizes a deeper more distributed hierarchy of latent variables. Finally, we observe that batch normalization and deterministic warm-up (gradually turning on the KL-term) are crucial for training variational models with many stochastic layers.

Key facts. Cited by 318 papers in the map (data through 14 Oct 2026). First posted on arXiv 6 Feb 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 63; 2022: 61; 2023: 67; 2024: 52; 2025: 50; 2026: 25.

318 papers.

Sort:

By area:

  1. 2021Score-based Generative Modeling in Latent Spacecited by 636
  2. 2022Understanding Diffusion Models: A Unified Perspectivecited by 340
  3. 2021Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Modelscited by 252
  4. 2021Explainable artificial intelligence (XAI) in deep learning-based medical image analysiscited by 147
  5. 2021ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesiscited by 122
  6. 2022GFlowNets and variational inferencecited by 106
  7. 2022DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latentscited by 104
  8. 2021Priors in Bayesian Deep Learning: A Reviewcited by 101
  9. 2023Human Motion Generation: A Surveycited by 96
  10. 2022Tutorial on amortized optimizationcited by 83
  11. 2022An Introduction to Neural Data Compressioncited by 79
  12. 2021SetVAE: Learning Hierarchical Composition for Generative Modeling of Set-Structured Datacited by 78
38 more
  1. 2021Greedy Hierarchical Variational Autoencoders for Large-Scale Video Predictioncited by 75
  2. 2021Multimodal Conditional Image Synthesis with Product-of-Experts GANscited by 75
  3. 2022AirFormer: Predicting Nationwide Air Quality in China with Transformerscited by 73
  4. 2022MUSE-VAE: Multi-Scale VAE for Environment-Aware Long Term Trajectory Predictioncited by 59
  5. 2021Hierarchical VAEs Know What They Don't Knowcited by 58
  6. 2023High Fidelity Image Counterfactuals with Probabilistic Causal Modelscited by 53
  7. 2023Aligning Optimization Trajectories with Diffusion Models for Constrained Design Generationcited by 52
  8. 2021Learning Disentangled Representations in the Imaging Domaincited by 46
  9. 2021Clockwork Variational Autoencoderscited by 42
  10. 2022Long Document Summarization with Top-down and Bottom-up Inferencecited by 42
  11. 2021MuseMorphose: Full-Song and Fine-Grained Piano Music Style Transfer with One Transformer VAEcited by 40
  12. 2022Recent Advances for Quantum Neural Networks in Generative Learningcited by 39
  13. 2024SwitchTab: Switched Autoencoders Are Effective Tabular Learnerscited by 38
  14. 2021Efficient Iterative Amortized Inference for Learning Symmetric and Disentangled Multi-Object Representationscited by 36
  15. 2021Diagonal Attention and Style-based GAN for Content-Style Disentanglement in Image Generation and Translationcited by 35
  16. 2022Lossy Image Compression with Quantized Hierarchical VAEscited by 35
  17. 2022Identifying Weight-Variant Latent Causal Modelscited by 34
  18. 2023Measuring axiomatic soundness of counterfactual image modelscited by 34
  19. 2023QARV: Quantization-Aware ResNet VAE for Lossy Image Compressioncited by 32
  20. 2022VAEL: Bridging Variational Autoencoders and Probabilistic Logic Programmingcited by 31
  21. 2023Where to Diffuse, How to Diffuse, and How to Get Back: Automated Learning for Multivariate Diffusionscited by 29
  22. 2024On Discrete Prompt Optimization for Diffusion Modelscited by 29
  23. 2021Multi-Facet Clustering Variational Autoencoderscited by 28
  24. 2021Unsupervised Speech Enhancement using Dynamical Variational Auto-Encoderscited by 28
  25. 2023HQ-VAE: Hierarchical Discrete Representation Learning with Variational Bayescited by 27
  26. 2021Interpretable Unsupervised Diversity Denoising and Artefact Removalcited by 26
  27. 2022Efficient-VDVAE: Less is morecited by 26
  28. 2021Conditional Image Generation by Conditioning Variational Auto-Encoderscited by 25
  29. 2021Bayesian Attention Belief Networkscited by 25
  30. 2021Diffusion Priors In Variational Autoencoderscited by 25
  31. 2022Unifying Generative Models with GFlowNets and Beyondcited by 24
  32. 2021Sawtooth Factorial Topic Embeddings Guided Gamma Belief Networkcited by 23
  33. 2023SeeGera: Self-supervised Semi-implicit Graph Variational Auto-encoders with Maskingcited by 23
  34. 2021Disentangled Recurrent Wasserstein Autoencodercited by 22
  35. 2023End-To-End Latent Variational Diffusion Models for Inverse Problems in High Energy Physicscited by 22
  36. 2023From Identifiable Causal Representations to Controllable Counterfactual Generation: A Survey on Causal Generative Modelingcited by 22
  37. 2024Benchmarking Counterfactual Image Generationcited by 22
  38. 2021A Structural Causal Model for MR Images of Multiple Sclerosiscited by 21

50 most cited of 318 All 318 (JSON)