Awesome-VAEs

Awesome work on the VAE, disentanglement, representation learning, and generative models.

I gathered these resources (currently @ ~900 papers) as literature for my PhD, and thought it may come in useful for others. This list includes works relevant to various topics relating to VAEs. Sometimes this spills over to topics e.g. adversarial training and GANs, general disentanglement, variational inference, flow-based models and auto-regressive models. Always keen to expand the list - feel free to contribute or email me if I've missed your paper off the list : ]

They are ordered by year (new to old).

2021

EVA: Generating Longitudinal Electronic Health Records Using Conditional Variational Autoencoders. Biswal, Ghosh, Duke, Malin, Stewart. https://arxiv.org/pdf/2012.10020.pdf

Cauchy-Schwarz Regularized Autoencoder. Tran, Prantic, Deisenroth. https://arxiv.org/pdf/2101.02149.pdf

Cross-Domain Variational Adversarial Autoencoder. Bai, Tian, Zhang, Yang. https://www.sciengine.com/doi/10.3724/SP.J.1089.2020.18115

Deep Generative Models of Gravitational Waveforms via Conditional Variational Autoencoder. Liao, Lin. https://arxiv.org/pdf/2101.06685.pdf

Face Image Inpainting via Variational Autoencoder. Zhang, Cheng, Bai, Zhang, Sun, Wang. https://www.sciengine.com/doi/10.3724/SP.J.1089.2020.17938

A Semi-supervised Approach for Early Identifying the Abnormal Carotid Arteries Using a Modified Variational Autoencoder. Huang, Cui, Wu, Li. https://ieeexplore.ieee.org/abstract/document/9313193/

Item Recommendation based on Multimedia Variational Autoencoder. Ran, Chen, Mu. https://iopscience.iop.org/article/10.1088/1755-1315/632/4/042044/pdf

Disentangled Recurrent Wasserstein Autoencoder. Han, Min, Lan, Li, Zhang. https://arxiv.org/pdf/2101.07496.pdf

Spatiotemporal Trajectories in Resting-state FMRI Revealed by Convolutional Variational Autoencoder. Zhang, Maltbie, Keilholz. https://www.biorxiv.org/content/biorxiv/early/2021/01/26/2021.01.25.427841.full.pdf

A Missing Data Imputation Method for 3D Object Reconstruction using Multi-modal Variational Autoencoder. Yu, Oh. https://arxiv.org/pdf/2101.10391.pdf

Hierarchical Domain Invariant Variational Auto-Encoding with weak domain supervision. Sun, Buettner. https://arxiv.org/pdf/2101.09436.pdf

Disentangled Sequence Clustering for Human Intention Inference. Zolotas, Demiris. https://arxiv.org/pdf/2101.09500.pdf

Improved Training of Sparse Coding Variational Autoencoder via Weight Normalization. Jiang, de la Iglesia. https://ui.adsabs.harvard.edu/abs/2021arXiv210109453P/abstract

Semi-Supervised Disentanglement of Class-Related and Class-Independent Factors in VAE. Hajimiri, Lotfi, Baghshah. https://arxiv.org/pdf/2102.00892.pdf

Video Reenactment as Inductive Bias for Content-Motion Disentanglement. Albarracin, Rivera. https://arxiv.org/pdf/2102.00324.pdf

pmVAE: Learning Interpretable Single-Cell Representations with Pathway Modules. Gut, Stark, Ratsch, Davidson. https://www.biorxiv.org/content/biorxiv/early/2021/01/30/2021.01.28.428664.full.pdf

Hierarchical Variational Autoencoder for Visual Counterfactuals. Vercheval, Pizurica. https://arxiv.org/pdf/2102.00854.pdf

Probabilistic Models with Deep Neural Networks. Masegosa, Cabanas, Langseth, Nielsen, Salmeron http://repositorio.ual.es/bitstream/handle/10835/9516/entropy-23-00117-v2.pdf?sequence=1&isAllowed=y

Variational Bayes survival analysis for unemployment modelling. Boskoski, Perne, Ramesa, Boshkoska. https://arxiv.org/pdf/2102.02295.pdf

Neighborhood Geometric Structure-Preserving Variational Autoencoder for Smooth and Bounded Data Sources. Chen, Wang, Lan, Zheng, Zeng. https://pubmed.ncbi.nlm.nih.gov/33556022/

A Method for Constructing Supervised Time Topic Model Based on Variational Autoencoder. Gou, Li, Huo. https://www.hindawi.com/journals/sp/2021/6623689/

A Variational Information Bottleneck Approach to Multi-Omics Data Integration. Lee, van der Schaar. https://arxiv.org/pdf/2102.03014.pdf

Using Deconvolutional Variational Autoencoder for Answer Selection in Community Question Answering. Boroujeni, Faili. https://ieeexplore.ieee.org/abstract/document/9345624/

Data augmentation using a variational autoencoder for estimating property prices. Lee. https://www.emerald.com/insight/content/doi/10.1108/PM-09-2020-0057/full/html

A conditional variational autoencoder based self-transferred algorithm for imbalanced classification. Zhao, Hao, Tang, Chen, Wei. https://www.sciencedirect.com/science/article/abs/pii/S0950705121000198

Layer VQE: A Variational Approach for Combinatorial Optimization on Noisy Quantum Computers. Liu, Angone, Shaydulin, Safro, Alexeev, Cincio. https://arxiv.org/pdf/2102.05566.pdf

Automatic variational inference with cascading flows. Ambrogioni, Silvestra, van Gerven. https://arxiv.org/pdf/2102.04801.pdf

On Disentanglement in Gaussian Process Variational Autoencoders. Bing, Fortuin, Ratsch. https://arxiv.org/pdf/2102.05507.pdf

Invertible local image descriptors learned with variational autoencoders. Zikakic, Pizurica. https://www.ieice.org/publications/proceedings/summary.php?expandable=8&iconf=ICTF&session_num=ICTF_5&number=ICTF2020_paper_24&year=2020

Meta-Learning Divergences for Variational Inference. Zhang, Li, Sa, Devlin, Zhang. http://proceedings.mlr.press/v130/zhang21o/zhang21o.pdf

Collaborative Denoising Graph Attention Autoencoders for Social Recommendation. Mu, Zha, Zhao, Gong. https://ksiresearch.org/seke/seke20paper/paper105.pdf

Variational Inference MPC using Tsallis Divergence. Wang, So, Gibson, Vlahov, Gandhi. https://arxiv.org/pdf/2104.00241.pdf

Dual Online Stein Variational Inference for Control and Dynamics. Barcelos, Lambert, Oliveira, Borges, Boots, Ramos. https://arxiv.org/pdf/2103.12890.pdf

DRANet: Disentangling Representation and Adaptation Networks for Unsupervised Cross-Domain Adaptation. Lee, Cho, Im. https://arxiv.org/pdf/2103.13447.pdf

SeqVAE: Sequence variational autoencoder with policy gradient. Gao, Cui, Ding. https://link.springer.com/article/10.1007/s10489-021-02374-7

Permutation-Invariant Variational Autoencoder for Graph-Level Representation Learning. Winter, Noe, Clevert. https://arxiv.org/pdf/2104.09856.pdf

Deep Mixture Generative Autoencoders. Ye, Bors. https://eprints.whiterose.ac.uk/173261/1/MixtureVAE_Dropout.pdf

Genetic Constrained Graph Variational Autoencoder for COVID-19 Drug Discovery. Cheng, Fan, Wang. https://arxiv.org/pdf/2104.11674.pdf

Transformer-based Conditional Variational Autoencoder for Controllable Story Generation. Fang, Zeng, Liu, Bo, Dong, Chen https://arxiv.org/pdf/2101.00828.pdf

Factor analysis, probabilistic principal component analysis, variational inference, and variational autoencoder: tutorial and survey. Ghojogh, Ghodsi, Karray, Crowley https://arxiv.org/pdf/2101.00734.pdf

Variational Selective Autoencoder: Learning from Partially-Observed Heterogeneous Data. Yong, Hajimisadeghi, He, Durand, Mori https://arxiv.org/pdf/2102.12679.pdf

Predicting Video with VQVAE. Walker, Razavi, van den Oord https://arxiv.org/pdf/2103.01950.pdf

A survey on Variational Autoencoders from a GreenAI perspective. Asperti, Evangelista, Piccolomini https://arxiv.org/pdf/2103.01071.pdf

crank: An Open-Source Software for Nonparallel Voice Conversion Based on Vector-Quantized Variational Autoencoder. Kobayashi, Huang, Wu, Tobing, Hayashi, Toda https://arxiv.org/pdf/2103.02858.pdf

On Disentanglement in Gaussian Process Variational Autoencoders. Bing, Fortuin, Ratsch https://arxiv.org/pdf/2102.05507.pdf

Bilateral Variational Autoencoder for Collaborative Filtering. Truong, Salah, Lauw https://dl.acm.org/doi/abs/10.1145/3437963.3441759

Variational Structured Attention Networks for Deep Visual Representation Learning. Yang, Rota, Alameda-Pineda https://arxiv.org/pdf/2103.03510.pdf

Improving Bayesian Inference in Deep Neural Networks with Variational Structured Dropout. Nguyen, Nguyen, Nguyen, Ho, Than Bui https://arxiv.org/pdf/2102.07927.pdf

A variational inference approach to learning multivariate world processes. Etesami, Trouleau, Kiyavash, Grossglauser, Thiran. http://proceedings.mlr.press/v130/etesami21a.html

Heterogeneous Hypergraph Variational Autoencoder for Link Prediction. Fan, Zhang, Wei, Li, Zou, Gao, Dai https://ieeexplore.ieee.org/abstract/document/9354594/

Certifiably Robust Variational Autoencoders. Barrett, Camuto, Willetts, Rainforth https://arxiv.org/pdf/2102.07559.pdf

Diagnosing Vulnerability of Variational Auto-Encoders to Adversarial Attacks. Kuzina, Welling, Tomczak https://arxiv.org/pdf/2103.06701.pdf

Training Generative Adversarial Networks in One Stage. Shen, Yin, Wang, LI, Song, Song https://arxiv.org/pdf/2103.00430.pdf

Parallel Variational Autoencoders for Multiple Responses Generation. Li, Fu, Lin, Wang https://conferences.computer.org/ispapub/pdfs/ISPA-BDCloud-SocialCom-SustainCom2020-61uthIiswrO37XTCl0drpO/319900a128/319900a128.pdf

VDSM: Unsupervised Video Disentanglement with State-Space Modeling and Deep Mixtures of Experts. Vowels, Camgoz, Bowden https://arxiv.org/pdf/2103.07292.pdf

A Semi-Supervised Learning Method for MiRNA-Disease Association Prediction Based on Variational Autoencoder. Ji, Wang, Go, Li, Ni, Zheng https://europepmc.org/article/med/33735084

Using latent space regression to analyze and leverage compositionality in GANs. Chai, Wulff, Isola https://arxiv.org/pdf/2103.10426.pdf

A Variational Inference Framework for Inverse Problems. Maestrini, Aykroyd, Wand. https://arxiv.org/pdf/2103.05909.pdf

On Multilevel Monte Carlo Unbiased Gradient Estimation For Deep Latent Variable Models. Shi, Cornish http://proceedings.mlr.press/v130/shi21d/shi21d.pdf

Neighbor Embedding Variational Autoencoder. Tu, Liu, Xue, Wang, Guo https://arxiv.org/pdf/2103.11349.pdf

Adversarial and Contrastive Variational Autoencoder for Sequential Recommendation. Xie, Liu, Zhang, Lu, Wang, Ding https://arxiv.org/pdf/2103.10693.pdf

Representation learning via invariant causal mechanisms. Mitrovic, McWilliams, Walker, Buesing, Blundell https://openreview.net/pdf/34eb2506b5a0b489bced58ab4bb038ff7356ade7.pdf

GLOWin: A Flow-based Invertible Generative Framework for Learning Disentangled Feature Representations in Medical Images. Sankar, Keicher, Eisawy, Parida, Pfister, Kim, Navab https://arxiv.org/pdf/2103.10868.pdf

Generative Particle Variational Inference via Estimation of Functional Gradients. Ratzlaff, Bai, Fuxin, Xu https://arxiv.org/pdf/2103.01291.pdf

Meta-Learning Divergences of Variational Inference. Zhang, Li, De Sa, Devlin, Zhang http://proceedings.mlr.press/v130/zhang21o/zhang21o.pdf

Rate-Regularization and Generalization in VAEs. Bozkurt, Esmaeili, Tristan, Brooks, Dy, van de Meent http://proceedings.mlr.press/v130/bozkurt21a/bozkurt21a.pdf

Data Generation in Low Sample Size Setting Using Manifold Sampling and a Geometry-Aware VAE. Chadebec, Allassonniere https://arxiv.org/pdf/2103.13751.pdf

Contrastive Disentanglement in Generative Adversarial Networks. Pan, Tang, Chen, Xu https://arxiv.org/pdf/2103.03636.pdf

SetVAE: Learning Hierarchical Composition for Generative Modeling of Set-Structured Data. Kim, Yoo, Lee, Hong https://arxiv.org/pdf/2103.15619.pdf

Hierarchical and Self-Attended Sequence Autoencoder. Chien, Wang https://ieeexplore.ieee.org/abstract/document/9384306/

NeRF-VAE: A Geometry Aware 3D Scene Generative Model. Kosiorek, Strathmann, Zoran, Moreno https://arxiv.org/pdf/2104.00587.pdf

Intact-VAE: Estimating Treatment Effects under Unobserved Confounding. Wu, Fukumizu https://arxiv.org/pdf/2101.06662.pdf

Dirichlet Process Prior for Student?s t Graph Variational Autoencoders. Zhao, Huang https://search.proquest.com/openview/2954e8d3c474db03241dabd98d7cac18/1?pq-origsite=gscholar&cbl=2032396

Variational Autoencoder Analysis of Ising Model Statistical Distributions and Phase Transitions. Yevick https://arxiv.org/pdf/2104.06368.pdf

2020

Emotional Dialogue Generation Based on Conditional Variational Autoencoder and Dual Emotion Framework. Deng, Lin, Huang, Lan, Luo https://www.hindawi.com/journals/wcmc/2020/8881616/

Soft-IntroVAE: Analyzing and Improving the Introspective Variational Autoencoder. Daniel, Tamar https://arxiv.org/pdf/2012.13253.pdf

Causal World Models by Unsupervised Deconfounding of Physical Dynamics. Li, Yang, Liu, Chen, Chen, Wang https://arxiv.org/pdf/2012.14228.pdf

Recent Advances in Variational Autoencoders With Representation Learning for Biomedical Informatics: A Survey. Wei, Mahmood https://ieeexplore.ieee.org/abstract/document/9311619/

Conditional out-of-distribution generation for unpaired data using transfer VAE. Lotfollahi, Naghipourfar, Theis, Wolf https://academic.oup.com/bioinformatics/article/36/Supplement_2/i610/6055927?login=true

Learning Energy-Based Model with Variational Auto-Encoder as Amortized Sampler. Zie, Zheng, Li https://arxiv.org/pdf/2012.14936.pdf

Infer-AVAE: An Attribute Inference Model Based on Adversarial Variational Autoencoder. Zhou, Ding, Liu, Shen, Tong, Guan https://arxiv.org/pdf/2012.15005.pdf

Learning Invariant Representations for Deep Latent Variable Models. Wieser https://edoc.unibas.ch/79859/1/PhDThesis_MW.pdf

Towards causal generative scene models via competition of experts. von Kugelgen, Ustyuzhaninov, Gehler, Bethge, Scholkopf https://arxiv.org/pdf/2004.12906.pdf

A correspondence variational autoencoder for unsupervised acoustic word embeddings. Peng, Kamper, Livescu https://arxiv.org/pdf/2012.02221.pdf

Industrial process modeling and fault detection with recurrent Kalman variational autoencoder. Zhang, Zhu, Liu, Ge https://ieeexplore.ieee.org/abstract/document/9275274/

A data reconstruction method based on adversarial conditional variational autoencoder. Ren, Liu, Zhang, Jiang, Luo https://ieeexplore.ieee.org/abstract/document/9275168/

Quantifying common support between multiple treatment groups using a contrastive-VAE. Dai, Stultz http://proceedings.mlr.press/v136/dai20a/dai20a.pdf

Dynamics -based peptide-MHC binding optimization by a convolutional variational autoencoder: a use-case model for CASTELO. Bell, Domeniconi, Yang, Zhou, Zhang, Cong https://arxiv.org/pdf/2012.00672.pdf

Prior flow variational autoencoder: a density estimation model for non-intrusive load monitoring. Henriques, Morgan, Colcher https://arxiv.org/pdf/2011.14870.pdf

Semi-supervised bearing fault diagnosis and classification using variational autoencoder-based deep generative models. Zhang, Ye, Wang, Habetler https://ieeexplore.ieee.org/abstract/document/9270010/

Manga filling style conversion with screentone variational autoencoder. Xie, Li, Liu, Wong https://dl.acm.org/doi/abs/10.1145/3414685.3417873

World model as a graph: learning latent landmarks for planning. Zhang, Yang, Stadie https://arxiv.org/pdf/2011.12491.pdf

A statistical evaluation of machine learning algorithms for applied data analysis. Beaulac http://probability.ca/jeff/ftpdir/cedricthesis.pdf

Unsupervised learning of disentangled representations in deep restricted kernel machines with orthogonality constraints. Tonin, Patrinos, Suykens https://arxiv.org/pdf/2011.12659.pdf

Very deep VAEs generalize autoregressive models and can outperform them on images. Anonymous https://openreview.net/forum?id=RLRXCV6DbEJ

Deep variational autoencoder for mapping functional brain networks. Qiang, Dong, Ge, Lian, et al https://ieeexplore.ieee.org/abstract/document/9204760

Variational autoencoder based unsupervised domain adaptation for semantic segmentation. Li, Togo, Ogawa, Haseyama https://ieeexplore.ieee.org/abstract/document/9190973/

Variational autoencoder bidirectional long and short-term memory neural network soft-sensor model based on batch training strategy. Xie, Wang, Xing, Guo, Guo, Zhu https://ieeexplore.ieee.org/abstract/document/9200687

On the transferability of VAE embeddings using relational knowledge with semi-supervision. Stromfelt, Dickens, Garcez, Russo https://arxiv.org/pdf/2011.07137.pdf

Mutual Information based Method for Unsupervised Disentanglement of Video Representation. Sreekar, Tiwari, Namboodiri https://arxiv.org/pdf/2011.08614.pdf

Factorized Gaussian Process Variational Autoencoders. Jazbec, Pearce, Fortuin https://arxiv.org/pdf/2011.07255.pdf

Speech prediction in silent videos using variational autoencoders. Yadav, Sardana, Namboodiri, Hegde https://arxiv.org/pdf/2011.07340.pdf

VAEPP: Variational Autoencoder with a Pull-Back Prior. Chen, Liu, Cai, Xu, Pei https://link.springer.com/chapter/10.1007/978-3-030-63836-8_31

Learning Disentangled Representations with Attentive Joint Variational Autoencoder. Li, Liu, Chen, Luo https://link.springer.com/chapter/10.1007/978-3-030-63823-8_47

Quantifying and learning disentangled representations with limited supervision. Tonnaer, Rey, Menkovski, Holenderski, Portegies https://arxiv.org/pdf/2011.06070.pdf

Face Anti-Spoofing via Disentangled Representation Learning. Zhang, Yao, Zhang, Tai, Ding, Li, Huang, Song, Ma https://link.springer.com/chapter/10.1007%2F978-3-030-58529-7_38

VCE: Variational Convertor-Encoder for One-Shot Generalization. Li, Han, Xing https://arxiv.org/pdf/2011.06246.pdf

Mixtures of variational autoencoders. Ye, Bors https://www.researchgate.net/profile/Adrian_Bors/publication/345655967_Mixtures_of_Variational_Autoencoders/links/5faa0b9392851cc286a4e201/Mixtures-of-Variational-Autoencoders.pdf

Implicit supervision for fault detection and segmentation of emerging fault types with deep variational autoencoders. Chao, Adey, Fink https://www.researchgate.net/profile/Manuel_Arias_Chao/publication/338292289_Implicit_supervision_for_fault_detection_and_segmentation_of_emerging_fault_types_with_Deep_Variational_Autoencoders/links/5f99f697299bf1b53e4ed637/Implicit-supervision-for-fault-detection-and-segmentation-of-emerging-fault-types-with-Deep-Variational-Autoencoders.pdf

Towards Effective Intrusion Detection Using Log-cosh Conditional Variational AutoEncoder. Xu Li, Yang, Shen https://ieeexplore.ieee.org/abstract/document/9244068/

Improving Variational Autoencoder for Text Modelling with Timestep-Wise Regularisation. Li, Li, Chen, Lin https://arxiv.org/pdf/2011.01136.pdf

SNF?CVAE: Computational method to predict drug?disease interactions using similarity network fusion and collective variational autoencoder. Jarada, Rokne, Alhajj https://www.sciencedirect.com/science/article/abs/pii/S0950705120307140

MAD-VAE: manifold awareness defence variational autoencoder. Morkock, Wang https://arxiv.org/pdf/2011.01755.pdf

Fraud detection via deep neural variational autoencoder oblique random forest. Anh, Khanh, Dat, Amouroux, Solanki https://ieeexplore.ieee.org/abstract/document/9242753

Counterfactual Fairness with disentangled causal effect variational autoencoder. Kim, Shin, Jang, Song, Joo, Kang, Moon https://arxiv.org/pdf/2011.11878.pdf

Integration of variational autoencoder and spatial clustering for adaptive multi-channel neural speech separation. Zmolikova, Delcroix, Burget, Makatani, Cernocky https://arxiv.org/pdf/2011.11984.pdf

Use of student's t-distribution for the latent layer in a coupled variational autoencoder. Chen, Svoboda, Nelson https://arxiv.org/pdf/2011.10879.pdf

An intelligent music generation based on variational autencoder. Wang, Liu, Jin, Li, Ma https://ieeexplore.ieee.org/abstract/document/9262797

Vector embeddings with subvector permutation invariance using a triplet enhanced autoencoder. Matties https://arxiv.org/pdf/2011.09550.pdf

CompRess: self-supervised learning by compressing representations. Koohpayegani, Tejankar, Pirsiavash https://proceedings.neurips.cc/paper/2020/file/975a1c8b9aee1c48d32e13ec30be7905-Paper.pdf

Learning latent representations to influence multi-agent interaction. Xie, Losey, Tolsma, Finn, Sadigh http://iliad.stanford.edu/pdfs/publications/xie2020learning.pdf

Wavelet flow: fast training of high resolution normalizing flows. Yu, Derpanis, Brubaker https://arxiv.org/pdf/2010.13821v1.pdf

Embedding of molecular structure using molecular hypergraph variational autoencoder with metric learning. Koge, Ono, Huang, Altaf-Ul-Amin, Kanaya https://onlinelibrary.wiley.com/doi/pdf/10.1002/minf.202000203

Anomaly detection of heat energy usage in district heating substations using LSTM based variational autoencoder combined with physical model. Zhang, Fleyeh https://ieeexplore.ieee.org/abstract/document/9248108/

Semi-supervised learning by latent space energy-based model of symbol-vector coupling. Pang, Nijkamp, Cui, Han, Wu https://arxiv.org/pdf/2010.09359.pdf

Learning disentangled representations of video with missing data. Massague, Zhang, Feric, Camps, Yu https://proceedings.neurips.cc/paper/2020/file/24f2f931f12a4d9149876a5bef93e96a-Paper.pdf

Exemplar VAE: linking generative models, nearest neighbor retrieval, and data augmentation. Norouzi, Fleet, Norouzi https://proceedings.neurips.cc/paper/2020/file/63c17d596f401acb520efe4a2a7a01ee-Paper.pdf

Learning disentangled representations and group structure of dynamical environments. Quessard, Barrett, Clements https://papers.nips.cc/paper/2020/file/e449b9317dad920c0dd5ad0a2a2d5e49-Paper.pdf

The autoencoding variational autoencoder . Cemgil, Ghaisas, Dvijotham, Gowal, Kohli https://proceedings.neurips.cc/paper/2020/file/ac10ff1941c540cd87c107330996f4f6-Paper.pdf

Gradient boosted normalizing flows. Giaquinto, Banerjee https://proceedings.neurips.cc/paper/2020/file/fb5d9e209ebda9ab6556a31639190622-Paper.pdf

The evidence lower bound of variational autoencoders converges to a sum of three entropies. Lucke, Forster, Dai https://arxiv.org/pdf/2010.14860.pdf

Statistical guarantees for transformation based models with applications to implicit variational inference. Plummer, Zhou, Bhattacharya, Dunson, Pati https://arxiv.org/pdf/2010.14056.pdf

Scalable gaussian process variational autoencoders. Jazbec, Fortuin, Pearce, Mandt, Ratsch https://arxiv.org/pdf/2010.13472.pdf

A sober look at the unsupervised learning of disentangled representations and their evaluation. Locatello, Bauer, Lucic, Ratsch, Gelly, Scholkopf, Bachem https://www.jmlr.org/papers/volume21/19-976/19-976.pdf

Verification of field data and forecast model based on variational autoencoder in the application to the mechanized fund. Volkov, Dakhova, Andrianova, Budennyy https://www.onepetro.org/conference-paper/SPE-201936-MS

Content based image retrieval using deep convolutional variational autoencoder. Deore, Patil, Patil http://proteusresearch.org/gallery/pj-2654-53-f.pdf

Discrete latent space world models for reinforcement learning. Robine, Uelwer, Harmeling https://arxiv.org/pdf/2010.05767.pdf

Deep sequential latent variable models for noisy time series prediction. Qiu https://search.proquest.com/openview/278346ea1814c782db5840ed41ee78cd/1?pq-origsite=gscholar&cbl=18750&diss=y

Geometry-aware Hamiltonian variational autoe-encoder. Chadebec, Mantoux, Allassonniere https://arxiv.org/pdf/2010.11518.pdf

Disentangling action sequences: finding correlated images. Wu, Wang https://arxiv.org/pdf/2010.11684.pdf

Max-affine spline insights into deep generative networks anonymous. https://openreview.net/pdf?id=uLwplzQgAk7

Quaternion-valued variational autoencoder. Grassucci, Comminiello, Uncini https://arxiv.org/pdf/2010.11647.pdf

Variational autoencoder based enhanced behavior characteristics classification for social robot detection. Deng, Dai, Sun, Lv https://link.springer.com/chapter/10.1007/978-981-15-9129-7_17

Learning optimal conditional priors for disentangled representations. Mita, Filippone, Michiardi https://arxiv.org/pdf/2010.09360.pdf

Unsuperivsed disentanglement of pitch and timbre for isolated musical instrument sounds. Luo, Cheuk, Nakano, Goto, Herremans https://program.ismir2020.net/static/final_papers/162.pdf

On the surprising similarities between supervised and self-supervised models. Geirohs, Narayanappa, Mitzkus, Bethge, Wichmann, Brendel https://arxiv.org/pdf/2010.08377.pdf

Sparse Gaussian process variational autoencoders. Ashman, So, Tebbutt, Fortuin, Pearce, Turner https://arxiv.org/pdf/2010.10177.pdf

Laughter synthesis: A comparison between variational autoencoder and autoencoder. Mansouri, Lachiri https://ieeexplore.ieee.org/abstract/document/9231607

Variational autoencoder with global and mediu timescale auxiliaries for emotion recognition from speech. Almotlak, Weber, Wermter https://link.springer.com/chapter/10.1007/978-3-030-61609-0_42

Non-parallel voice conversion based on hierarchical latent embedding vector quantized variational autoencoder. Ho, Akagi https://www.isca-speech.org/archive/VCC_BC_2020/pdfs/VCC2020_paper_21.pdf

Plan-CVAE: a planning-based conditional variational autoencoder for story generation. Wang, Li, Zhao, Yan http://www.cips-cl.org/static/anthology/CCL-2020/CCL-20-083.pdf

Multi-task variational autoencoder for lung cancer prognosis on clinical data. Vo, Lee, Yang http://manuscriptlink-society-file.s3.amazonaws.com/kism/conference/sma2020/presentation/SMA-2020_paper_64.pdf

Semi-supervised learning with temperoal variational auto-encoders for the diagnosis of failure severities and the prognosis of remaining useful life. Silva http://repositorio.uchile.cl/bitstream/handle/2250/177135/Semi-supervised-learning-with-temporal-variational-auto-encoders-for-the-diagnosis-of-failure-severities-and-the-prognosis-of.pdf?sequence=1

The NeteaseGames System for voice conversion challenge 2020 with vector-quantization variational autoencoder and wavenet. Zhang https://arxiv.org/pdf/2010.07630.pdf

Adversarial networks and autoencoders: the primal-dual relationship and generalization bounds. Husain, Nock, Williamson https://arxiv.org/abs/1902.00985

Self Normalizing Flows. Keller, Peters, Jaini, Hoogeboom, Forre, Welling https://arxiv.org/abs/2011.07248

VAE-SNE: a deep generative model for simultaneous dimensionality reduction and clustering. Graving, Couzin https://www.biorxiv.org/content/10.1101/2020.07.17.207993v1

Generative neurosymbolic machines. Jiang, Ahn https://arxiv.org/abs/2010.12152

Revisiting factorizing aggregated posterior in learning disentangled representations. Cheng, Li, Wang, Gu, Xu, Li, Metze https://arxiv.org/abs/2009.05739

Baseline system of voice conversion challenge 2020 with cyclic variational autoencoder and parallel waveGAN. Tobing, Wu, Toda https://arxiv.org/pdf/2010.04429.pdf

Dirichlet graph variational autoencoder. Li, Yu, Li, Zhang, Zhao, Rong, Cheng, Huang https://arxiv.org/pdf/2010.04408.pdf

Condition-transforming variational autoencoder for generating diverse short text conversations. Ruan, Ling, Zhu https://dl.acm.org/doi/abs/10.1145/3402884

A variational autoencoder for music generation controlled by tonal tension. Guo, Simpson, Magnusson, Kiefer, Herremans https://arxiv.org/pdf/2010.06230.pdf

Adaptive neural speech enhancement with a denoising variational autoencoder. Bando, Sekiguchi, Yoshii https://indico2.conference4me.psnc.pl/event/35/contributions/3960/attachments/1008/1049/Wed-1-11-6.pdf

Semi-supervised self-produced speech enhancement and suppression based on joint souce modeling of air- and body-conducted signals using variational autoencoder. Seki, Takada, Toda https://indico2.conference4me.psnc.pl/event/35/contributions/3047/attachments/797/835/Thu-2-1-3.pdf

A coding perspective on deep latent variable models. Ullrich https://dare.uva.nl/search?identifier=2d6e0b96-90d3-4683-bbbe-00d2a7f1dd54

Probabilistic character motion synthesis using a hierarchical deep latent variable model. Ghorbani, Wloka, Etemad, Brubaker, Troje http://diglib.eg.org/handle/10.1111/cgf14116

Neighborhood-aware autoencoder for missing value imputation Aidos, Tomas https://www.eurasip.org/Proceedings/Eusipco/Eusipco2020/pdfs/0001542.pdf

Learning disentangled representations with the Wasserstein autoencoder. Gaujac, Feige, Barber https://arxiv.org/pdf/2010.03459.pdf

Learning deep-latent hierarchies by stacking wasserstein autoencoders. Gaujac, Feige, Barber https://arxiv.org/pdf/2010.03467.pdf

Discriminative mixture variational autoencoder for semisupervised classification. Chen, Du, Liao https://pubmed.ncbi.nlm.nih.gov/33027027/

Complex-valued variational autoencoder: a novel generative model for direct representation of complex spectra. Nakashika https://indico2.conference4me.psnc.pl/event/35/contributions/3042/attachments/446/471/Wed-1-3-3.pdf

Sequential learning and regularization in variational recurrent autoencoder. Chien, Tsai https://www.eurasip.org/Proceedings/Eusipco/Eusipco2020/pdfs/0001613.pdf

NCP-VAE: Variational autoencoders with noise contrastive priors. Aneja, Schwing, Kautz, Vahdat https://arxiv.org/pdf/2010.02917.pdf

LEGAN: disentangled manipulation of directional lighting and facial expressions by leveraging human perceptual judgements. Banerjee, Joshi, Majanajan, Bhattacharya, Kyal, Mishra https://arxiv.org/pdf/2010.01464.pdf

Unsupervised hierarchical concept learning. Roychowdhury, Sontakke, Puri, Sarkar, Aggarwal, Badjatiya, Krishnamurthy https://arxiv.org/pdf/2010.02556.pdf

Disentangled generative causal representation learning. Shen, Liu, Dong, Lian, Chen, Zhang https://arxiv.org/pdf/2010.02637.pdf

Disentangled representations for sequence data using information bottleneck principle. Yamada, Kim, Miyoshi, Iwata, Yamakawa http://proceedings.mlr.press/v129/yamada20a/yamada20a.pdf

Unbiased gradient estimation for variational auto-encoders using coupled Markov chains. Ruiz, Titsias, Cemgil, Doucet https://arxiv.org/pdf/2010.01845.pdf

RG-flow: a hierarhcical and explainable flow model based on renormalization group and sparse prior . Hu, Wu, You, Olshausen, Chen https://arxiv.org/pdf/2010.00029.pdf

Targeted VAE: structured inference and targeted learning for causal parameter estimation. Vowels, Camgoz, Bowden https://arxiv.org/pdf/2009.13472.pdf

Amortized mixture prior for variational sequence generation. Chien, Tsai https://ieeexplore.ieee.org/abstract/document/9206667

Collective dynamics of repeated inference in variational autoencoder rapidly find cluster structure. Naano, Karakida, Okada https://www.nature.com/articles/s41598-020-72593-4

Physics-constrained predictive molecular latent space discovery with graph scattering variational autoencoder. Shervani-Tabar, Zabaras https://arxiv.org/pdf/2009.13878.pdf

Hierarchical sparse variational autoencoder for text encoding. Prokhovov, Li, Shareghi, Collier https://arxiv.org/pdf/2009.12421.pdf

Discrete memory addressing variational autoencoder for visual concept learning. Min, Su, Zhu, Zhang https://ieeexplore.ieee.org/abstract/document/9206745/

Embedding and generation of indoor climbing routes with variational autoencoder. Lo https://arxiv.org/pdf/2009.13271.pdf

Semi-supervised deep learning in motor imagery-based brain-computer interfaces with stacked variational autoencoder. Chen, Yu, Gu https://iopscience.iop.org/article/10.1088/1742-6596/1631/1/012007/pdf

A dimensionalty reduction algorithm for mapping tokamak operation regimes using variational autoencoder neural network. Wei, brooks, chandra, levesque https://meetings.aps.org/Meeting/DPP20/Session/NP16.7

Multi-adversarial variational autoencoder nets for simultaneous image generation and classification. Imran, Terzopoulos https://link.springer.com/chapter/10.1007/978-981-15-6759-9_11

VAE-BRIDGE: variational autoencoder filter for Bayesian ridge imputation of missing data. Pereira, Abreu, Rodrigues https://www.researchgate.net/profile/Ricardo_Cardoso_Pereira/publication/342513773_VAE-BRIDGE_Variational_Autoencoder_Filter_for_Bayesian_Ridge_Imputation_of_Missing_Data/links/5f352e1b92851cd302f16ca5/VAE-BRIDGE-Variational-Autoencoder-Filter-for-Bayesian-Ridge-Imputation-of-Missing-Data.pdf

Variational online learning of neural dynamics. Zhao, Park https://openreview.net/pdf/9cae7375baff24b407ed87f731912eb212015301.pdf

Improving robustness and generality of NLP models using disentangled representations. Wu, Li, Ao, Meng, Wu, Li https://arxiv.org/pdf/2009.09587.pdf

A robust image watermarking approach using cycle variational autoencoder. Wei, Wang, Zhang https://www.hindawi.com/journals/scn/2020/8869096/

RVAE-ABFA: robust anomaly detection for high dimensional data using variational autoencoder. Gao, Shi, Dong, Chen, Mi, Huang, Shi https://ieeexplore.ieee.org/abstract/document/9202465/

Variational autoencoding dialogue sub-structures using a novel hierarchical annotation scheme. Tewari, Persiani, Umea https://www.diva-portal.org/smash/record.jsf?pid=diva2%3A1469903&dswid=-2871

dynamicVAE: decoupling reconstruction error and disentangled representation learning. Shao, Lin, Yang, Yao, Zhao, Abdelzaher https://arxiv.org/pdf/2009.06795.pdf

Deep transparent prediction through latent representation analysis. Kollias, Bouas, Vlaxos, Brillakis, Seferis, Kollia et al https://arxiv.org/pdf/2009.07044.pdf

Interpretable operational risk classification with semi-supervised variational autoencoder. Fan, Zhang, Yang https://repository.ust.hk/ir/Record/1783.1-104743

Content-collaborative disentanglement representation learning for enhances recommendation. Zhang, Zhu, Caverlee http://people.tamu.edu/~zhan13679/Paper/content-collaborative-dsentanglement.pdf

Optimized k-means clustering algorithm using an intelligent stable-plastic variational autoencoder with self-intrinsic cluster validation mechanism. Gikera, Mambo, Mwaura https://dl.acm.org/doi/abs/10.1145/3415088.3415125

Identifying treatment effects under unobserved confounding by causal representation learning. Anonymous https://openreview.net/forum?id=D3TNqCspFpM

Unsupervised discovery of interpretable latent manipulations in language VAEs . Anonymous https://openreview.net/pdf?id=DGttsPh502x

VideoGen: Generative modeling of videos using VQ-VAE and transformers. Anonymous https://openreview.net/forum?id=3InxcRQsYLf

Goal-conditioned variational autoencoder trajectory primatives with continuous and discrete latent codes. Osa, Ikemoto https://link.springer.com/article/10.1007/s42979-020-00324-7

Self-supervised disentanglement of modality-specific and shared factors improves multimodal generative models. Daunhawer, Sutter, Marcinkevics, Vogt https://mds.inf.ethz.ch/fileadmin/user_upload/gcpr_100_v01.pdf

Decoupling representation learning from reinforcement learning . Stooke, Lee, Abbeel, Laskin https://arxiv.org/pdf/2009.08319.pdf

DCAVN: Cervical cancer prediction and classification using deep convolutional and variational autoencoder network. Khamparia, Gupta, Rodrigues, de Albuquerque https://link.springer.com/article/10.1007/s11042-020-09607-w

Learning sampling in financial statement audits using vector quantised variational autoencoder neural networks. Schreyer, Sattarov, Gierbl, Reimer, Borth https://www.alexandria.unisg.ch/260768/1/ICAIF_2020_finale.pdf

Multilinear latent conditioning for generating unseen attribute combinations. Georgopoulos, Chrysos, Pantic, Panagakis https://arxiv.org/pdf/2009.04075.pdf

Ordinal-content VAE: Isolating ordinal-valued content factors in deep latent variable models. Kim, Pavlovic https://arxiv.org/pdf/2009.03034.pdf

Quasi-symplectic Langevin variational autoencoder. Wang, Delingette https://arxiv.org/pdf/2009.01675.pdf

Trajectory prediction by using contextual LSTM based variational autoencoder. Cho, Cha https://www.koreascience.or.kr/article/CFKO202024664105425.page

Dynamical variational autoencoders: a comprehensive review. Girin, Leglaive, Bie, Diard, Hueber, Alameda-Pineda https://arxiv.org/pdf/2008.12595.pdf

Metrics for exposing the biases of content-style disentanglement. Liu, Thermos, Valvano, Chartsias, O'Neil, Tsaftaris https://arxiv.org/pdf/2008.12378.pdf

Speech source separation using variational autoencoder and bandpass filter. Do, Tran, Chau https://ieeexplore.ieee.org/abstract/document/9178274/

Variationals in variational autoencoders - a comparative evaluation. Wei, Garcia, El-Sayed, Peterson, Mahmood https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9171997

Variational information bottleneck for semi-supervised classification. Voloshynovskiy, Taran Kondah, Holotyak, Rezende https://www.mdpi.com/1099-4300/22/9/943

Conditional introspective variational autoencoder for image synthesis. Zheng, Cheng, Kang, Yao, Tian https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9172064

Deep generative models in inversion: a reiew and development of a new approach based on a variational autoencoder. Lopez-Alvis, Laloy, Nguyen, Hermans https://arxiv.org/pdf/2008.12056.pdf

Robust vision-based workout analysis using diversified deep latent variable model. Xiong, Berkovsky, Sharan, Liu, Coiera https://ieeexplore.ieee.org/abstract/document/9175454/

Variational autoencoders. Fleuret https://fleuret.org/ee559-draft/materials/ee559-slides-7-4-VAE.pdf

Disentangling multiple features in video sequences using Gaussian processes in variational autoencoders. Bhagat, Uppal, Yin, Lim https://arxiv.org/abs/2001.02408

Improved techniques for training score-based generative models. Song, Ermon https://arxiv.org/abs/2006.09011

Optimal variance control of the score function gradient estimator for importance weighted bounds. Lievin, Dittadi, Christensen, Winther https://arxiv.org/abs/2008.01998

Rewriting a deep generative model. Bau, Liu, Wang, Zhu, Torralba https://arxiv.org/pdf/2007.15646.pdf

SRFlow: learning the super-resolution space with normalizing flow. Lugmayr, Danelljan, Gool, Timofte http://de.arxiv.org/pdf/2006.14200/

Generalized energy based models. Arbe, Zhou, Gretton https://arxiv.org/abs/2003.05033

Variational autoencoder for anti-cancer drug response prediction. Xie, Dong, Jing, Ren https://arxiv.org/pdf/2008.09763.pdf

Unsupervised clustering through Gaussian mixture variational autoencoder with non-reparameterized variational inference and std annealing. Li, Zhao, Chen, Xu, Li, Pei https://netman.aiops.org/wp-content/uploads/2020/08/PID6423661.pdf

Toward discriminating and synthesizing motion traces using deep probabilistic generative models. Zhou, Liu, Zhang, Trajcevski https://ieeexplore.ieee.org/abstract/document/9165954

Generating in-between images through learned latent space representation using variational autoencoders. Cristovao, Nakada, Tanimura, Asoh https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9166477

xGAIL: explainable generative adversarial imitation learning for explainable human decision analysis . Pan, Huang, Li, Zhou, Juo https://dl.acm.org/doi/abs/10.1145/3394486.3403186

A survey on generative adversarial networks for imbalance problems in computer vision tasks. Sampath, Maurtua, Martin, Gutierrez https://assets.researchsquare.com/files/rs-45616/v1_stamped.pdf

Linear disentangled representations and unsupervised action estimation. Painter, Hare, Prugel-Bennett https://arxiv.org/pdf/2008.07922.pdf

Learning interpretable representation for controllable polyphonic music generation. Wang, Wang, Zhang, Xia https://arxiv.org/pdf/2008.07122.pdf

Disentangled item representation for recommender systems. Cui, Yu, Wu, Liu, Wang https://arxiv.org/pdf/2008.07178.pdf

Joint variational autoencoders for recommendation with implicit feedback. Askari, Szlichta, Salehi-Abari https://arxiv.org/pdf/2008.07577.pdf

Transferred discrepancy: quantifying the difference between representations. Feng, Zhai, He, Wang, Dong https://arxiv.org/pdf/2007.12446.pdf

What should not be contrastive in contrastive learning. Xiao, Wang, Efros, Darrell https://arxiv.org/pdf/2008.05659.pdf

SCAN: learning to classify images without labels. Gansbeke, Vandehende, Georgoulis, Proesmans, Gool http://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123550273.pdf

SG-VAE: scene grammar variational autoencoder to generative new indoor scenes. Purkait, Zach, Reid http://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123690154.pdf

Unsupervised domain adaptation in the wild via disentangling representation learning. Li, Wan, Wang, Kot https://link.springer.com/article/10.1007/s11263-020-01364-5

Variational autoencoder for generation of antimicrobial peptides. Dean, Walper https://pubs.acs.org/doi/full/10.1021/acsomega.0c00442

Multimodal deep generative models for trajectory prediction: a conditional variational autoencoder approach. Ivanovic, Leung, Schmerling, Pavone https://arxiv.org/pdf/2008.03880.pdf

A conditional variational autoencoder algorithm for reconstructing defect data of magnetic flux leakage. Lu, Wu, Zhang https://ieeexplore.ieee.org/abstract/document/9164107/

CRUDS: Counterfactual recourse using disentangled subspaces. Downs, Chu, Yacoby, Doshi-Velez, Pan https://finale.seas.harvard.edu/files/finale/files/cruds-_counterfactual_recourse_using_disentangled_subspaces.pdf

Using deep variational autoencoder networks for recognizing geochemical anomalies. Luo, Xiong, Zuo https://www.sciencedirect.com/science/article/abs/pii/S088329272030202X

SeCo: exploring sequence supervision for unsupervised representation learning. Yao, Zhang, Qiu, Pan, Mei https://arxiv.org/pdf/2008.00975.pdf

LoCo: local contrastive representation learning. Xiong, Ren, Urtasum https://arxiv.org/pdf/2008.01342.pdf

Geometrically enriched latent spaces. Arvanitidis, Hauberg, Scholkopf https://arxiv.org/pdf/2008.00565.pdf

PDE-driven spatiotemporal disentanglement. Dona, Franceschi, Lamprier, Gallinari https://arxiv.org/pdf/2008.01352.pdf

Dynamics generalization via information bottleneck in deep reinforcement learning. Lu, Lee, Abbeel, Tiomkin https://arxiv.org/pdf/2008.00614.pdf

Semi-supervised adversarial variational autoencoder . Zemouri https://www.preprints.org/manuscript/202008.0051/v1

Improving sample quality by training and sampling from latent energy. Xiao, Yan, Amit https://invertibleworkshop.github.io/accepted_papers/pdfs/4.pdf

Quantitative understanding of VAE by interpreting ELBO as rate distortion cost of transform coding. Nakagawa, Kato https://arxiv.org/pdf/2007.15190.pdf

dMELODIES: a musuc dataset for disentanglement learning. Oati, Gururani, Lerch https://arxiv.org/pdf/2007.15067.pdf

Privacy-preserving voice analysis via disentangled representations. Aloufi, Haddadi, Boyle https://arxiv.org/pdf/2007.15064.pdf

Approximation based variance reduction for reparameterization gradients. Geffner, Domke https://arxiv.org/pdf/2007.14634.pdf

Online variational learning of dirichlet process mixtures of scaled dirichlet distributions. Manouchehri, Nguyen, Koochemeshkian, Bouguila, Fan https://link.springer.com/article/10.1007/s10796-020-10027-2

A commentary on the unsupervised learning of disentangled representations. Locatello, Bauer, Lucic, Ratsch, Gelly, Scholkopf, Bachem https://arxiv.org/pdf/2007.14184.pdf

Learning disentangled representations with latent variation predictability. Zhu, Xu, Tao https://arxiv.org/pdf/2007.12885.pdf

TDAE: autoencoder-based automatic feature learning method for the detection of DNS tunnel. Wu, Zhang, Yin https://ieeexplore.ieee.org/abstract/document/9149162/

A variational autoencoder mixture model for online behavior recommendation. Nguyen, Cho https://ieeexplore.ieee.org/document/9144583/?denied=

Towards nonlinear disentanglement in natural data with temporal sparse coding. Klindt, Schott, Sharma, et al. https://arxiv.org/pdf/2007.10930.pdf

Improving generative modelling in VAEs using multimodal prior. Abrol, Sharma, Patra https://ora.ox.ac.uk/objects/uuid:d4a7306e-6d5c-4e84-9525-4363723328f8 Generative flows with matrix exponential Xiao, Liu https://arxiv.org/pdf/2007.09651.pdf

Undirected graphical models as approximate posteriors. Vahdat, Andriyash, Macready https://proceedings.icml.cc/static/paper_files/icml/2020/1354-Paper.pdf

DMRAE: discriminative manifold regularized autoencoder for sparse and robust feature learning. Farajian, Adibi https://link.springer.com/article/10.1007/s13748-020-00211-5

Variational Bayesian quantization. Yang, Bamler, Mandt https://proceedings.icml.cc/static/paper_files/icml/2020/6168-Paper.pdf

Dispersed exponential family mixture VAEs for interpretable text generation. Shi, Zhou, Miao, Li https://proceedings.icml.cc/static/paper_files/icml/2020/3242-Paper.pdf

Empirical study of the benefits of overparameterization in learning latent variable models. Buhai, Halpern, Kim, Risteksi, Sontag https://proceedings.icml.cc/static/paper_files/icml/2020/5645-Paper.pdf

Relaxed-responsibility hierarchical discrete VAEs. Willetts,Miscouridou, Roberts, Holmes https://arxiv.org/pdf/2007.07307.pdf

Deep generative video compression with temporal autoregressive transforms. Yang, Yang, Marino, Yang, Mandt https://joelouismarino.github.io/files/papers/2020/seq_flows_compression/seq_flows_compression.pdf

Learning invariances for interpretability using supervised VAE Nguyen, Martinez https://arxiv.org/pdf/2007.07591.pdf

Towards a theoretical understanding of the robustness of variational autoencoders. Camuto, Willetts, Roberts, Holmes, Rainforth https://arxiv.org/pdf/2007.07365.pdf

Hierarchical linear disentanglement of data-driven conceptual spaces. Alshaikh, Bouraoui, Schockaert https://www.ijcai.org/Proceedings/2020/0494.pdf

Distribution augmentation for generative modeling. Jun, Child, Chen, Schulman, Ramesh, Radford, Sutskever https://proceedings.icml.cc/static/paper_files/icml/2020/6095-Paper.pdf

Deep heterogeneous autoencoder for subspace clustering of sequential data. Siddique, Mozhdehi, Medeiros https://arxiv.org/pdf/2007.07175.pdf

Self-reflective variational autoencoder. Apostolopoulou, Rosenfeld, Dubrawksi https://arxiv.org/pdf/2007.05166.pdf

Disentangled variational autoencoder based multi-label classification with covariance-aware multivariate probit model. Bai, Kong, Gomes https://arxiv.org/pdf/2007.06126.pdf

InfoGAN-CR and ModelCentrality: self-supervised model training and selection for disentangling GANs. Lin, Thekumparampil, Fanti, Oh https://proceedings.icml.cc/static/paper_files/icml/2020/4410-Paper.pdf

Reconstruction bottlenecks in object-centric generative models. Engelcke, Jones, Posner https://arxiv.org/pdf/2007.06245.pdf

Variational learning of Bayesian neural networks via Bayesian dark knowledge. Shen, Chen, Deng https://www.researchgate.net/profile/Zhi-Hong_Deng2/publication/342798883_Variational_Learning_of_Bayesian_Neural_Networks_via_Bayesian_Dark_Knowledge/links/5f0db9a5a6fdcc3ed7056bb0/Variational-Learning-of-Bayesian-Neural-Networks-via-Bayesian-Dark-Knowledge.pdf

A look inside the black-box: towards the interpretability of conditioned variational autoencoder for collaborative filtering. Carraro, Polato, Aiolli https://dl.acm.org/doi/abs/10.1145/3386392.3399305

Topologically-based variational autoencoder for time series classification. Rivera-Castro, Moustafa, Pilyugina, Burnaev https://www.latinxinai.org/assets/pdf/icml2020/all_posters/pdf/Poster_Rodrigo_Rivera.pdf

Modeling and interpreting road geometry from a driver's perspective using variational autoencoders. Wang, Chen, Wijnands, Guo https://onlinelibrary.wiley.com/doi/abs/10.1111/mice.12594

Do compressed representations generalize better? Hafez-Kolahi, Kasaei, Soleymani-Baghshah https://www.researchgate.net/profile/Mahdieh_Soleymani/publication/335989891_Do_Compressed_Representations_Generalize_Better/links/5ed54369299bf1c67d32500f/Do-Compressed-Representations-Generalize-Better.pdf

PRI-VAE: principle-of-relevant-information variational autoencoders. Li, Yu, Principe, Li, Wu https://arxiv.org/abs/2007.06503

Latent variable modelling with hyperbolic nomalizing flows. Bose, Smofsky, Liao, Panangaden, Hamilton. https://arxiv.org/abs/2002.06336

Object-centric learning with slot attention. Locatello, Weissenborn, Unterthiner, Mahendran, Heigold, Uszkoreit, Dosovitskiy, Kipf https://arxiv.org/abs/2006.15055

NVAE: A deep hierarchical variational autoencoder. Vahadat, Kautz https://arxiv.org/abs/2007.03898

Variational inference for sequential data with future likelihood estimates. Kim, Jang, Yang, Kim http://ailab.kaist.ac.kr/papers/pdfs/KJYK2020.pdf

Exponential tilting of generative models: improving sample quality by training and sampling from latent energy. Xiao, Yan, Amit https://arxiv.org/pdf/2006.08100.pdf

Hierarchical path VAE-GAN: generating diverse videos from a single sample. Gur, Benaim, Wolf https://arxiv.org/pdf/2006.12226.pdf

Contrastive code representations learning. Jain, Jain, Zhang, Abbeel, Gonzalez, Stoica https://arxiv.org/pdf/2007.04973.pdf

Efficiet learning of generative models via finite-difference score matching. Pang, Xu, Li, Song, Ermon, Zhu https://arxiv.org/pdf/2007.03317.pdf

Towards recurrent autoregressive flow models. Mern, Morales, Kochenderfer https://arxiv.org/pdf/2006.10096.pdf

Benefiting deep latent variable models via learning the prior and removing latent regularization. Morrow, Chiu https://arxiv.org/pdf/2007.03640.pdf

VAEs in the presence of missing data Collier, Nazabal, Williams https://arxiv.org/pdf/2006.05301.pdf

Mixture of discrete normalizing flows for variational inference. Kusmierczyk, Klami https://arxiv.org/pdf/2006.15568.pdf

Spatial revising variational autoencoder-based feature extraction method for hyperspectral images. Yu, Zhang, Shen https://ieeexplore.ieee.org/abstract/document/9109663/

Monitoring of nonlinear processes with multiple operating modes through a novel Gaussian mixture variational autoencoder model. Tang, Peng, Dong, Zhang, Zhao https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9119397

A new approach for smoking event detection using a variational autoencoder and neural decision forest. Fan, Gao https://ieeexplore.ieee.org/abstract/document/9129702/

Isometric Gaussian process latent variable model for dissimilarity data. Jorgensen, Hauberg https://arxiv.org/pdf/2006.11741.pdf

VAEM: a deep generative model for heterogeneous mixed type data. Ma, Tschiatschek, Hernandez-Lobato, Turner https://arxiv.org/pdf/2006.11941.pdf

Disentangling by subspace diffusion. Pfau, Higgins, Botev, Racaniere https://arxiv.org/pdf/2006.12982.pdf

Latent variable modeling with random features. Gundersen, Zhang, Engelhardt https://arxiv.org/pdf/2006.11145.pdf

Variational orthogonal features. Burt, Rasmussen, van der Wilk https://arxiv.org/pdf/2006.13170.pdf

Scale-space autoencoders for unsupervised anomaly segmentations in brain MRI. Bauer, Wistler, Albarquouni, Navab https://arxiv.org/pdf/2006.12852.pdf

Learning from demonstration with weakly supervised disentanglement. Hristov, Ramamoorthy. https://arxiv.org/pdf/2006.09107.pdf

A tutorial on VAES: from Bayes' rule to lossless compression. Yu https://arxiv.org/pdf/2006.10273.pdf

Density deconvolution with normalizing flows. Dockhorn, Ritchie, Yu, Murray https://arxiv.org/pdf/2006.09396.pdf

Rethinking sem-supervised learning in VAEs. Joy, Schmon, Torr, Siddharth, Rainforth https://arxiv.org/pdf/2006.10102.pdf

DisARM: An antithetic gradient estimator for binary latent variables. Dong, Mnih, Tucker https://arxiv.org/pdf/2006.10680.pdf

On casting importance weighted autoencoder to an EM algorithm to learn deep generative models. Kim, Hwang, Kim http://proceedings.mlr.press/v108/kim20b/kim20b.pdf

Sparsity enforcement on latent variables for better disentanglement in VAE. Crsitovao, Nakada, Tanimura, Asoh https://www.jstage.jst.go.jp/article/pjsai/JSAI2020/0/JSAI2020_2K6ES202/_pdf

Isometric autoencoders. Atzmon, Gropp, Lipman https://arxiv.org/pdf/2006.09289.pdf

Constraining variational inference with geometric Jensen-Shannon divergence. Deasy, Simidjievski, Lio https://arxiv.org/pdf/2006.10599.pdf

Neural decomposition: functional ANOVA with variational autoencoders. Martens, Yau http://proceedings.mlr.press/v108/martens20a/martens20a.pdf

Variational autoencoder with learned latent structure. Connor, Canal, Rozell https://arxiv.org/pdf/2006.10597.pdf

Transfer learning approach for botnet detection based on recurrent variational autoencoder. Kim , Sim, Kim, Wu, Hahm https://dl.acm.org/doi/abs/10.1145/3391812.3396273

Anomaly-based intrusion detection from network flow features using variational autoencoder. Zavrak, Iskefiyeli https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9113298

Longitudinal variational autoencoder. Racmchandran, Tikhonov, Koskinen, Lahdesmaki https://arxiv.org/pdf/2006.09763.pdf

Gaussian mixture variational atueoncoder for semi-supervised topic modeling. Zhou, Ban, Zhang, Li, Zhang https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9112154

Structural autoencoders improve representations for generation and transfer. Leeb, Annadani, Bauer, Scholkopf https://arxiv.org/pdf/2006.07796.pdf

High-dimensional similarity search with quantum-assisted variational autoencoder. Gao, Wilson, Vandal, Vinci, Nemani, Rieffel https://arxiv.org/pdf/2006.07680.pdf

Robust variational autoencoder for tabular data with beta divergence . Akrami, Aydore, Leahy, Joshi https://arxiv.org/pdf/2006.08204.pdf

Evidence-aware inferential text generation with vector quantised variational autoencoder. Guo, Tang, Duan, Yin, Jiang, Zhou https://arxiv.org/pdf/2006.08101.pdf

LaRVAE: label replacement VAE for semi-supervised disentanglement learning. Nie, Wang, Patel, Baraniuk https://arxiv.org/pdf/2006.07460.pdf

AR-DAE: towards unbiased neural entropy gradient estimation. Lim, Courville, Pal, Huang https://arxiv.org/pdf/2006.05164.pdf

Learning latent space energy-based prior model. Pang, Han, Nijkamp, Zhu, Wu https://arxiv.org/pdf/2006.08205.pdf

Disentanglement for discriminative visual recognition. Liu https://arxiv.org/pdf/2006.07810.pdf

Deep critiquing for VAE-based recommender systems. Luo, Yang, Wu, Sanner https://ssanner.github.io/papers/sigir20_cevae.pdf

To regularize or not to regularize? The bias variance trade-off in regularized VAEs. Mondal, Asnani, Singla https://arxiv.org/pdf/2006.05838.pdf

DisCont: self-supervised visual attribute disentanglement using context vectors. Bhagat, Udandarao, Uppal https://arxiv.org/pdf/2006.05895.pdf

Interpretable deep graph generation with node-edge co-disentanglement. Guo, Zhao, Qin, Wu, Shehu, Ye https://arxiv.org/pdf/2006.05385.pdf

Output-relevant variational autoencoder for just-in-time soft sensor modeling with missing data. Guo, Bai, Huang https://www.sciencedirect.com/science/article/pii/S0959152420302195

Deep variational autoencoder: an efficient tool for PHM frameworks. Zemouri, Levesque, Amyot, Hudon, Kokoko https://ieeexplore.ieee.org/abstract/document/9115491/

Model extraction defence using modified variational autoencoder. Gupta http://etd.iisc.ac.in/handle/2005/4430

Variational variance: simple and reliable predictive variance parameterization. Stirn, Knowles https://arxiv.org/pdf/2006.04910.pdf

Probabilistic autoencoder. Bohm, Seljak https://arxiv.org/pdf/2006.05479.pdf

Deep latent-variable models for natural language understanding and generation. Shen https://dukespace.lib.duke.edu/dspace/bitstream/handle/10161/20848/Shen_duke_0066D_15473.pdf?sequence=1

Generalization via information bottleneck in deep reinforcement learning. Lu, Tiomkin, Abbeel https://www2.eecs.berkeley.edu/Pubs/TechRpts/2020/EECS-2020-56.pdf

Optimal configuration of concentrating solar power in multienergy power systems with an improved variational autoencoder. Qi, Hu, Dong, Fan, Dong, Xiao https://www.sciencedirect.com/science/article/abs/pii/S030626192030636X

tvGP-VAE: tensor-variate gaussian process prior variational autoencoder. Campbell, Lio https://arxiv.org/pdf/2006.04788.pdf

OC-FakeDect: classifying deepfakes using one-class variational autoencoder. Khalid, Woo http://openaccess.thecvf.com/content_CVPRW_2020/papers/w39/Khalid_OC-FakeDect_Classifying_Deepfakes_Using_One-Class_Variational_Autoencoder_CVPRW_2020_paper.pdf

Tuning a variational autoencoder for data accountability problem in the Mars science laboratory ground data system. Lakhmiri, Alimo, Le Digabel https://arxiv.org/pdf/2006.03962.pdf

Generate high fidelity images with generative variational autoencoder. Sagar https://d1wqtxts1xzle7.cloudfront.net/63577040/GVAE20200609-33737-2ojfbd.pdf?1591724283=&response-content-disposition=inline%3B+filename%3DGenerate_High_Fidelity_Images_With_Gener.pdf&Expires=1592933681&Signature=NI4uAK8CTTGPoWx-KYkCl5giVzyEfhUsIkGh4lM4bSTXmWOc-oCX4T~gX5x2HB4gJVX4ZtZy8qghJf7qGJ2GSrP~89PMb1dzX3KTyMUbWRvK1InS28wuc86KMEanX7gj7Tu0IrwMoRLjpdZZnc7Jt00Ga9A1N79n8MNj4fdeRFkZE5h8BgUTY9u11zN4pVSj~Rz3clsb~RIJldCmSZ3np31Qo8RAnVWap9MMJMoYWPq8EnBJ367G3ip~mSHh1lDZLGRCuVupWLxIzF1q4SAWfLvG75~CTacPvQneelwUQnTRwf93H9FRw7FpbrbpuJrOu-7tcZJdowAIRsDh-EVHEg__&Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA

PuppeteerGAN: arbitrary portrait animation with semantic-aware appearance transformation. Chen, Wang, yuan, Tao http://openaccess.thecvf.com/content_CVPR_2020/papers/Chen_PuppeteerGAN_Arbitrary_Portrait_Animation_With_Semantic-Aware_Appearance_Transformation_CVPR_2020_paper.pdf

Joint training of variational auto-encoder and latent energy-based model. Han, Nijkamp, Zhou, Pang, Zhu, Wu http://openaccess.thecvf.com/content_CVPR_2020/papers/Han_Joint_Training_of_Variational_Auto-Encoder_and_Latent_Energy-Based_Model_CVPR_2020_paper.pdf

Feature-based generative design of mechanisms with a variational autoencoder. Brandt https://search.proquest.com/docview/2408896683?pq-origsite=gscholar&fromopenview=true

Denoising diffusion probabilistic models. Ho, Jain, Abbeel https://arxiv.org/pdf/2006.11239.pdf

Simple and effective VAE training with calibrated decoders. Rybkin, Daniilidis, Levine https://arxiv.org/abs/2006.13202

SurVAE Flows: surjections to bridge the gap between VAEs and flows. Nielsen, Jaini, Hoogeboom, Winther, Welling https://arxiv.org/pdf/2007.02731.pdf

Mutual information gradient estimation for representation learning. Wen, Zhou, He, Zhou, Xu https://arxiv.org/pdf/2005.01123.pdf

Cross-VAE: towards disentangling expression from identity for human faces. Wu, Jia, Xie, Qi, Shi, Tian https://ieeexplore.ieee.org/abstract/document/9053608

CONFIG: controllable neural face image generation. Kowalski, Garbin, Estellers, Baltrusaitis, Johnson, Shotton https://arxiv.org/abs/2005.02671

Variance constrained autoencoding. Braithwaite, O'Connor, Kleijn https://arxiv.org/pdf/2005.03807.pdf

Jigsaw-VAE: towards balancing features in variational autoencoders. Taghanaki, Havaei, Lamb, Sanghi https://arxiv.org/pdf/2005.05496.pdf

The usefulness of the deep learning method of variational autoencoder to reduce measurement noise in Glaucomatous visual fields. Asaoka, Murata, Asano, Matsuura, Fujino et al. https://www.nature.com/articles/s41598-020-64869-6

methCancer-gen: a DNA methylome dataset generator for user-specified cancer type based on conditional variational autoencoder. Choi, Chae https://bmcbioinformatics.biomedcentral.com/articles/10.1186/s12859-020-3516-8

Deep latent variable model for longitudinal group factor analysis. Qiu, Chinchilli, Lin https://arxiv.org/pdf/2005.05210.pdf

Prototypical contrastive learning of unsupervised representations. Li, Zhou, Xiong, Socher, Hoi https://arxiv.org/pdf/2005.04966.pdf

A semi-supervised approach for identifying abnormal heart sounds using variational autoencoder. Banerjee, Ghose https://ieeexplore.ieee.org/abstract/document/9054632

Semi-supervised neural chord estimation based on a variational autoencoder with discrete labels and continuous textures of chords. Wu, Carsault, Nakamura, Yoshii https://arxiv.org/pdf/2005.07091.pdf

A deeper look at the unsupervised learning of disentangled representations in beta-VAE from the perspective of core object recognition. Sikka https://arxiv.org/pdf/2005.07114.pdf

Many-to-many voice conversion using cycle-consistent variational autoencoder with multiple decoders/ Yook, Leem, Lee, Yoo https://www.isca-speech.org/archive/Odyssey_2020/pdfs/32.pdf

HyperVAE: a minimum description length variational hyper-encoding network. Nguyen, Tran, Gupta, Rana, Dam, Venkatesh https://arxiv.org/pdf/2005.08482.pdf

Disentangling in latent space by harnessing a pretrained generator. Nitzan, Bermano, Li, Cohen-Or https://arxiv.org/pdf/2005.07728.pdf

Attention mechanism for human motion prediction. Al-aqel, Khan https://ieeexplore.ieee.org/abstract/document/9096777

Brain lesion detection using a robust variational autoencoder and transfer learning. Akrami, Joshi, Li, Aydore, Leahy https://ieeexplore.ieee.org/abstract/document/9098405

Deep variational autoencoder for modeling functional brain networks and ADHD identification. Qiang, Dong, Sun, Ge, Liu https://ieeexplore.ieee.org/abstract/document/9098480

Dual autoencoders generative adversarial network for imbalanced classification problem. Wu, Cui, Welsch https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9093005

Pairwise supervised hashing with bernoulli variational auto-encoder and self-control gradient estimator. Dadaneh, Boluki, Yin, Zhou, Qian https://arxiv.org/pdf/2005.10477.pdf

S3VAE: self-supervised sequential VAE for representation disentanglement and data generation. Zhu, Min, Kadav, Graf, https://arxiv.org/pdf/2005.11437.pdf

VMI-VAE: variational mutual information maximization framework for VAE with discrete and continuous priors. Serdega, Kim https://arxiv.org/pdf/2005.13953.pdf

Variational autoencoder with embedded student-t mixture model for authorship attribution. Boenninghoff, Zeiler, Nickel, Kolossa https://arxiv.org/pdf/2005.13930.pdf

Deep learning on the 2-dimensional ising model to extract the crossover region with a variational autoencoder. Walker, Tam, Jarrell https://arxiv.org/pdf/2005.13742.pdf

Context-dependent token-wise variational autoencoder for topic modeling. Masada High-fidelity audio generation and representation learning with guided adversarial autoencoder. Haque, Rana, Schuller https://arxiv.org/pdf/2006.00877.pdf

Adaptive efficient coding: a variational auto-encoder approach. Aridor, Grechi, Woodford https://www.biorxiv.org/content/biorxiv/early/2020/05/31/2020.05.29.124453.full.pdf

Noise-to-compression variational autoencoder for efficient end-to-end optimized image coding. Luo, Li, Dai, Xu, Cheng, Li, Xiong https://ieeexplore.ieee.org/abstract/document/9105715

Guided image generation with conditional invertible neural networks. Ardizzone, Luth, Kruse, Rother, Kothe https://arxiv.org/pdf/1907.02392.pdf

Vector quantization-based regularization for autoencoders . Wu, Flierl https://arxiv.org/abs/1905.11062 https://github.com/AlbertOh90/Soft-VQ-VAE

MHVAE: a human-inspired deep hierarchical generative model for multimodal representations learning. Vasco, Melo, Paiva https://arxiv.org/pdf/2006.02991.pdf

NewtonianVAE: proportional control and goal identification from pixels via physical latent spaces. Jaques, Burke, Hospedales https://arxiv.org/pdf/2006.01959.pdf

Constrained variational autoencoder for improving EEG based speech recognition systems. Krishna, Tran, Carnahan, Tewfik https://arxiv.org/pdf/2006.02902.pdf

Variational mutual information maximization framework for VAE latent codes with continuous and discrete priors. Serdega https://arxiv.org/pdf/2006.02227.pdf

Monitoring and prediction of big process data with deep latent variable models and parallel computing. Yang, Ge https://www.sciencedirect.com/science/article/pii/S0959152420302171

Polarized-VAE: proximity based disentangled representation learning for text generation. Balasubramanian, Kobyzev, Bahuleyan, Shapiro, Vechtomova https://arxiv.org/pdf/2004.10809.pdf

Discretized bottleneck: posterior-collapse-free sequence-to-sequence learning. Zhao, Yu, Mahapatra, Su, Chen https://arxiv.org/pdf/2004.10603.pdf

Remote sensing image captioning via Variational Autoencoder and Reinforcement learning. Shen, Liu, Zhou, Zhao, Liu https://www.sciencedirect.com/science/article/abs/pii/S0950705120302586

Conditioned variational autoencoder for top-N item recommendation Polato, Carraro, Aiolli. https://arxiv.org/pdf/2004.11141.pdf

Multi-speaker and multi-domain emotional voice conversion using factorized hierarchical variational autoencoder. Elgaar, Park, Lee https://ieeexplore.ieee.org/abstract/document/9054534

beta-variational autoencoder as an entanglement classifier. Sa, Roditi https://arxiv.org/pdf/2004.14420.pdf

Preventing posterior collapse with Levenshtein variational autoencoder. Havrylov, Titov https://arxiv.org/pdf/2004.14758.pdf

Multi-decoder RNN autoencoder based on variational Bayes method. Kaji, Watanabe, Kobayashi https://arxiv.org/pdf/2004.14016.pdf

Bootstrap latent-predictive representations for multitask reinforcement learning. Guo, Pries, Piot, Grill, Altche, Munoz, Azar https://arxiv.org/pdf/2004.14646.pdf

Anomaly detection of time series with smoothness-inducing sequential variational auto-encoder. Li, Yan, Wang, Jin https://ieeexplore.ieee.org/abstract/document/9064715

A batch normalized inference network keeps the KL vanishing away. Zhu, Bi, Liu, Ma, Li, Wu https://arxiv.org/pdf/2004.12585.pdf

From symbols to signals: symbolic variational autoencoders. Devaraj, Chowdhury, Jain, Kubricth, Tu, Santa https://ieeexplore.ieee.org/abstract/document/9054016

Unsupervised real image super-resolution via generative variational autoencoder. Liu, Sui, Wang, Li, Cani, Chan https://arxiv.org/pdf/2004.12811.pdf

Interpreting rate-distortion of variational autoencoder and using model uncertainty for anomaly detection. Park, Adosoglou, Pardalos https://arxiv.org/pdf/2005.01889.pdf

Computational representation of Chinese characters: comparison between Singular Value Decomposition and Variational Autoencoder. Tseng, Hsieh http://www.papersearch.net/thesis/article.asp?key=3766591

Curiosity-driver variational autoencoder for deep q network. Han, Zhang, Mao https://link.springer.com/chapter/10.1007/978-3-030-47426-3_59

6GCVAE: gated convolutional variational autoencoder for IPv6 Target Generation. Cui, Gou, Xiong https://link.springer.com/chapter/10.1007/978-3-030-47426-3_47

Text-based malicious domain names detection based on variational autoencoder and supervised learning. Sun, Chong, Ochiai https://ieeexplore.ieee.org/abstract/document/9086229/

Mutual information gradient estimation for representation learning. Wen, Zhou, He, Zhou, Xu https://arxiv.org/pdf/2005.01123.pdf

CausalVAE: structured causal disentanglement in variational autoencoder. Yang, Liu, Chen, Shen, Hao, Wang https://arxiv.org/pdf/2004.08697.pdf

Vroc: Variational autoencoder-aided multi-task rumor classifier based on text. Cheng, Nazarian, Bogdan https://dl.acm.org/doi/pdf/10.1145/3366423.3380054

On the encoder-decoder incompatibility in variational text modeling and beyond . Wu, Wang, Wang https://arxiv.org/pdf/2004.09189.pdf

Esimate the implicit likelihoods of GANs with application to anomaly detection. Ren, Li, Zhou, Li https://dl.acm.org/doi/pdf/10.1145/3366423.3380293

Emotional response generation using conditional variational autoencoder. Lee, Choi https://ieeexplore.ieee.org/abstract/document/9070547

PatchVAE: learning local latent codes for recognition. Gupta, Singh, Shrivastava https://arxiv.org/pdf/2004.03623.pdf

Generating tertiary protein structures via an interpretative variational autoencoder. Guo, Tadepalli, Zhao, Shehu https://arxiv.org/pdf/2004.07119.pdf

Attribute-based regularization of VAE latent spaces. Pati, Lerch https://arxiv.org/pdf/2004.05485.pdf

Controllable variational autoencoder. Shao, Yao, Sun, Zhang, Liu, Liu, Wang, Abdelzaher https://arxiv.org/pdf/2004.05988.pdf

Variational autoencoder-based dimensionality reduction for high-dimensional small-sample data classification. Mahmud, Huang, Fu https://www.worldscientific.com/doi/abs/10.1142/S1469026820500029

Normalizing flows with multi-scale autoreressive priors. Mahajan, Bhattacharyya, Fritz, Schiele, Roth https://arxiv.org/pdf/2004.03891.pdf

Adversarial latent autoencoders. Pidhorskyi, Adjeroh, Doretto https://arxiv.org/pdf/2004.04467.pdf OPTIMUS: organizing sentences via pre-trained modeling of latent space Li, Gao, Li, Li, Peng, Zhang, Gao https://arxiv.org/pdf/2004.04092.pdf

Learning discrete structured representations by adversarially maximizing mutual information. Stratos, Wiseman https://arxiv.org/pdf/2004.03991.pdf

AI giving back to statistics? Discovery of the coordinate system of univariate distributions by beta variational autoencoder. Glushkovsky https://arxiv.org/pdf/2004.02687.pdf

Towards democratizing music production with AI - design of variational autoencoder-based rhythm generator as a DAW plugin. Tokui https://arxiv.org/pdf/2004.01525.pdf

Decomposed adversarial learned inference. Li, Wang, Chen, Gao https://arxiv.org/abs/2004.10267

Fast NLP Model Pretraining with Vampire https://www.lighttag.io/blog/fast-nlp-pretraining-with-vampire/ - Blog post describing AllenAI work on use of VAEs to pre-train NLP models

A robust speaker clustering method based on discrete tied variational autoencoder. Feng, Wang, Li, Peng, Xiao https://arxiv.org/pdf/2003.01955.pdf

mmFall: Fall detection using 4D mmwave radar and variational recurrent autoencoder. Jin, Sengupta, Cao https://arxiv.org/pdf/2003.02386.pdf

Variational auto-encoders: not all failures are equal. Berger, Sebag https://arxiv.org/abs/2003.01972

Fully convolutional variational autoencoder for feature extraction of fire detection system. Hugroho, Susanty, Irawan, Koyimatu, Yunita Time-varying item feature conditional variational autoencoder for collaborative filtering. Kim https://ieeexplore.ieee.org/abstract/document/9006014

Multi-objective variational autoencoder: an application for smart infrastructure maintenance. Anaissi, Zandavi https://arxiv.org/pdf/2003.05070.pdf

Variational autoencoder with optimizing gaussian mixture model priors. Guo, Zhou, Chen, Ying, Zhang, Zhou, https://ieeexplore.ieee.org/abstract/document/9020116

Combining model predictive path integral with Kalman variational autoencoder for robot control from raw images. Kwon, Kaneko, Tsurumine, Sasaki, Motonaka, Miyoshi, Matsubara https://ieeexplore.ieee.org/abstract/document/9025842

Botnet detection using recurrent variational autoencoder. Kim, Sim, Kim, Wu https://arxiv.org/abs/2004.00234

A flow-based deep latent variable model for speech spectrogram modeling and enhancement Nugraha, Sekiguchi, Yoshii https://ieeexplore.ieee.org/abstract/document/9028147

A variational autoencoder with deep embedding model for generalized zero-shot learning Ma, Hu https://www.aaai.org/Papers/AAAI/2020GB/AAAI-MaP.2796.pdf

Continuous representation of molecules using graph variational autoencoder Tavakoli, Baldi http://ceur-ws.org/Vol-2587/article_12.pdf

IntroVNMT: an introspective model for variational neural machine translation Sheng, Xu, Guo, Liu, Zhao, Xu https://www.aaai.org/Papers/AAAI/2020GB/AAAI-ShengX.3632.pdf

Epitomic variational graph autoencoder Khan, Kleinsteuber https://arxiv.org/pdf/2004.01468.pdf

Variance loss in variational autoencoders Asperti https://arxiv.org/pdf/2002.09860.pdf

Dynamic narrowing of VAE bottlenecks using GECO and L0 regularization Boom, Wauthier, Verbelen, Dhoedt https://arxiv.org/pdf/2003.10901.pdf

q-VAE for disentangled representation learning and latent dynamical systems Koboyashi https://arxiv.org/pdf/2003.01852.pdf

Remaining useful life prediction via a variational autoencoder and a time-window-based sequence neural network Su, Li, Wen https://onlinelibrary.wiley.com/doi/epdf/10.1002/qre.2651

A lower bound for the ELBO of the Bernoulli variational autoencoder Sicks, Korn, Schwaar https://arxiv.org/pdf/2003.11830.pdf

VaB-AL: incorporating class imbalance and difficulty with variational Bayes for active learning Choi, Yi, Kim, Choo, Kim, Chang, Gwon, Chang https://arxiv.org/pdf/2003.11249.pdf

Inferring personalized and race-specific causal effecs of genomic aberrations on Gleason scores: a deep latent variable model Chen, Edwards, Hicks, Zhang https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7082760/

SCALOR: generative world models with scalable object representations Jiang, Janghorbani, Melo, Ahn https://pdfs.semanticscholar.org/02a0/1ed64f4a1bdfece5e1a83da5d9756397b0a1.pdf

Draft and Edit: Automatic Storytelling Through Multi-Pass Hierarchical Conditional Variational Autoencoder. Yu, Li, Liu, Tang, Zhang, Zhao, Yan https://www.aaai.org/Papers/AAAI/2020GB/AAAI-YuM.8133.pdf

Reverse variational autoencoder for visual attribute manipulation and anomaly detection. Gauerhof, Gu http://openaccess.thecvf.com/content_WACV_2020/papers/Lydia_Reverse_Variational_Autoencoder_for_Visual_Attribute_Manipulation_and_Anomaly_Detection_WACV_2020_paper.pdf

Bridged variational autoencoders for joint modeling of images and attributes. Yadav, Sarana, Namboodiri, Hegde http://openaccess.thecvf.com/content_WACV_2020/papers/Yadav_Bridged_Variational_Autoencoders_for_Joint_Modeling_of_Images_and_Attributes_WACV_2020_paper.pdf

Treatment effect estimation with disentangled latent factors. anon https://arxiv.org/abs/2001.10652

Unbalanced GANS: pre-training the generator of generative adversarial network using variational autoencoder. Ham, Jun, Kim https://arxiv.org/pdf/2002.02112.pdf

Regularized autoencoders via relaxed injetive probability flow. Kumar, Poole, Murphy https://arxiv.org/abs/2002.08927

Out-of-distribution detection with distance guarantee in deep generative models. Zhang, Liu, Chen, Wang, Liu, Li, Wei, Chen https://arxiv.org/abs/2002.03328

Balancing reconstruction error and Kullback-Leibler divergence in variational autoencoders. Asperti, Trentin https://arxiv.org/pdf/2002.07514.pdf

Data augmentation for historical documents via cascade variational auto-encoder. Cao, Kamata https://ieeexplore.ieee.org/abstract/document/8977737

Controlling generative models with continuous factors of variations. Plumerault, Borgne, Hudelot https://arxiv.org/pdf/2001.10238.pdf

Towards a controllable disentanglement network. Song, Koyejo, Zhang https://arxiv.org/abs/2001.08572

Knowledge-induced learning with adaptive sampling variational autoencoders for open set fault diagnostics. Chao, Adey, Fink https://arxiv.org/abs/1912.12502

NestedVAE: isolating common factors via weak supervision. Vowels, Camgoz, Bowden https://arxiv.org/abs/2002.11576

Leveraging cross feedback of user and item embeddings for variational autoencoder based collaborative filtering. Jin, Zhao, Du, Liu, Gao, Li, Xu https://arxiv.org/pdf/2002.09145.pdf

K-autoencoders deep clustering. Opochinsky, Chazan, Gannot, Goldberger http://www.eng.biu.ac.il/goldbej/files/2020/02/ICASSP_2020_Yaniv.pdf

D2D-TM: a cycle VAE-GAN for multi-domain collaborative filtering. Nguyen, Ishigaki https://ieeexplore.ieee.org/abstract/document/9006461/

Disentangling controllable object through video prediction improves visual reinforcement learning. Zhong, Schwing, Peng https://arxiv.org/pdf/2002.09136.pdf

A deep adversarial variational autoencoder model for dimensionality reduction in single-cell RNA sequencing analysis. Lin, Mukherjee, Kannan https://bmcbioinformatics.biomedcentral.com/articles/10.1186/s12859-020-3401-5

Context conditional variational autoencoder for predicting multi-path trajectories in mixed traffic. Cheng, Liao, Yang, Sester, Rosenhahn https://arxiv.org/pdf/2002.05966.pdf

Optimizing variational graph autoencoder for community detection with dual optimization. Choong, Liu, Murata

Learning flat latent manifolds with VAEs. Chen, Klushyn, Ferroni, Bayer, van der Smagt https://arxiv.org/pdf/2002.04881.pdf

Learning discrete distributions by dequantization. Hoogeboom, Cohen, Tomczak https://arxiv.org/pdf/2001.11235.pdf

Learning discrete and continuous factors of data via alternating disentanglement. Jeong, Song http://proceedings.mlr.press/v97/jeong19d/jeong19d.pdf https://github.com/snu-mllab/DisentanglementICML19

Electrocardiogram generation and feature extraction using a variational autoencoder. Kuznetsov, Moskalenko, Zolotykh https://arxiv.org/pdf/2002.00254.pdf

CosmoVAE: variational autoencoder for CMB image inpainting. Yi, Guo, Fan, Hamann, Wang https://arxiv.org/pdf/2001.11651.pdf

Unsupervised representation disentanglement using cross domain features and adversarial learning in variational autoencoder based voice conversion. Huang, Luo, Hwang, Lo, Peng, Tsao, Wang https://arxiv.org/pdf/2001.07849.pdf

On implicit regularization in beta VAEs. Kumar, Poole https://arxiv.org/pdf/2002.00041.pdf

Weakly-supervised disentanglement without compromises. Locatello, Poole, Ratsch, Scholkopf, Bachem, Tschannen https://arxiv.org/pdf/2002.02886.pdf

An integrated framework based on latent variational autoencoder for providing early warning of at-risk students. Du, Yang, Hung https://ieeexplore.ieee.org/abstract/document/8952699

Variational autoencoder and friends. Zheng https://www.cs.cmu.edu/~xunzheng/files/vae_single.pdf

High-fidelity synthesis with disentangled representation. Lee, Kim, Hong, Lee https://arxiv.org/pdf/2001.04296.pdf

Neurosymbolic knowledge representation for explainable and trustworthy AI. Malo https://www.preprints.org/manuscript/202001.0163/v1

Adversarial disentanglement with grouped observations. Nemeth https://arxiv.org/pdf/2001.04761.pdf

AE-OT-GAN: Training GANs from data specific latent distribution. An, Guo, Zhang, Qi, Lei, Yau, Gu https://arxiv.org/pdf/2001.03698.pdf

AE-OT: a new generative model based on extended semi-discrete optimal transport. An, Guo, Lei, Luo, Yau, Gu https://openreview.net/pdf?id=HkldyTNYwH

Disentanglement by nonlinear ICA with general incompressible-flow networks (GIN). Sorrenson, Rother, Kothe https://arxiv.org/pdf/2001.04872.pdf

Phase transitions for the information bottleneck in representation learning. Wu, Fischer https://arxiv.org/pdf/2001.01878.pdf

Bayesian deep learning: a model-based interpretable approach. Matsubara https://www.jstage.jst.go.jp/article/nolta/11/1/11_16/_article

SPACE: unsupervised object-oriented scene representation via spatial attention and decomposition. Lin, Wu, Peri, Sun, Singh, Deng, Jiang, Ahn https://openreview.net/forum?id=rkl03ySYDH

A variational stacked autoencoder with harmony search optimizer for valve train fault diagnosis of diesel engine. Chen, Mao, Zhao, Jiang, Zhang https://www.mdpi.com/1424-8220/20/1/223

Evaluating loss compression rates of deep generative models. anon https://openreview.net/forum?id=ryga2CNKDH

Progressive learning and disentanglement of hierarchical representations. anon https://openreview.net/forum?id=SJxpsxrYPS

Learning group structure and disentangled representations of dynamical environments. Quessard, Barrett, Clements https://arxiv.org/abs/2002.06991

A simple framework for contrastive learning of visual representations. Chen, Kornblith, Norouzi, Hinton https://arxiv.org/abs/2002.05709

Out-of-distribution detection in multi-label datasets using latent space of beta VAE Sundar, Ramakrishna, Rahiminasab, Easwaran, Dubey https://arxiv.org/pdf/2003.08740.pdf

Stochastic virtual battery modeling of uncertain electrical loads using variational autoencoder Chakraborty, Nandanoori, Kundu, Kalsi https://arxiv.org/pdf/2003.08461.pdf

A variational autoencoder solution for road traffic forecasting systems: missing data imputation, dimension reduction, model selection and anomaly detection Boquet, Morell, Serrano, Vicario https://www.sciencedirect.com/science/article/pii/S0968090X19309611

Detecting adversarial examples in learning-enabled cyber-physical systems using variational autoencoder for regression Cai, Li, Koutsoukos https://arxiv.org/pdf/2003.10804.pdf

Variational autoencoders with Riemannian brownian motion priors. Kalatzis, Eklund, Arvanitidis, Hauberg https://arxiv.org/abs/2002.05227

2019

Unsupervised representation learning in interactive environements. Racah https://papyrus.bib.umontreal.ca/xmlui/bitstream/handle/1866/23788/Racah_Evan_2019_memoire.pdf?sequence=2

Representing closed transformation paths in encoded network latent space. Connor, Rozell https://arxiv.org/pdf/1912.02644.pdf

Variational diffusion autoencoders with random walk sampling. Li, Lindenbaum, Cheng, Cloninger https://arxiv.org/abs/1905.12724

Diffusion variational autoencoders. Rey, Menkovski, Portegies https://arxiv.org/abs/1901.08991

A wrapped normal distribution on hyperbolic space for gradient-based learning. Nagano, Yamaguchi, Fujita, Koyama https://arxiv.org/abs/1902.02992

Reparameterizing distributions on Lie groups. Falorsi, Haan, Davidson, Forre https://arxiv.org/abs/1903.02958

Prescribed generative adversarial networks. Dieng, Ruiz, Blei, Titsias https://arxiv.org/abs/1910.04302

On the dimensionality of embeddings for sparse features and data Naumov https://arxiv.org/abs/1901.02103

Deep variational autoencoders for breast cancer tissue modeling and synthesis in SFDI Pardo, Lopez-Higuera, Pogue, Conde https://repositorio.unican.es/xmlui/bitstream/handle/10902/18323/DeepVariationalAutoencoders.pdf?sequence=1

Unsupervised anomaly detection of industrial robots using sliding-window convolution variational autoencoder Chen, Liu, Xia, Wang, Lai https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9023488

Discriminator optimal transport Tanaka https://arxiv.org/abs/1910.06832

Fine-tuning generative models Khandelwal https://dspace.mit.edu/bitstream/handle/1721.1/124252/1145123030-MIT.pdf?sequence=1&isAllowed=y

Disentangling and learning robust representations with naturual clustering . Antoran, Miguel https://arxiv.org/abs/1901.09415

Inherent tradeoffs in learning fair representations. Zhao, Gordon https://arxiv.org/abs/1906.08386

Affine variational autoencoders: an efficient approach for improving generalization and robustness to distribution shift. Bidart, Wong https://arxiv.org/pdf/1905.05300.pdf

Learning deep controllable and structured representations for image synthesis, structured prediction and beyond. Yan https://deepblue.lib.umich.edu/handle/2027.42/153334

Continual unsupervised representation learning . Rao, Visin, Rusu, The, Pascanu, Hadsell https://arxiv.org/pdf/1910.14481.pdf

Group-based learning of disentangled representations with generalizability for novel contents. Hosoya https://www.ijcai.org/Proceedings/2019/0348.pdf

Task-Conditioned variational autoencoders for learning movement primitives. Noseworthy, Paul, Roy, Park, Roy https://groups.csail.mit.edu/rrg/papers/noseworthy_corl_19.pdf

Multimodal generative models for compositional representation learning. Wu, Goodman https://arxiv.org/pdf/1912.05075.pdf

dpVAEs: fixing sample generation for regularized VAEs. Bhalodia, Lee, Elhabian https://arxiv.org/pdf/1911.10506.pdf

From variational to deterministic autoencoders. Ghosh, Sajjadi, Vergai, Black, Scholkopf https://arxiv.org/pdf/1903.12436.pdf

Learning representations by maximizing mutual information in variational autoencoder. Rezaabad, Vishwanath https://arxiv.org/pdf/1912.13361.pdf

Disentangled representation learning with Wasserstein total correlation. Xiao, Wang https://arxiv.org/pdf/1912.12818.pdf

Wasserstein dependency measure for representation learning. Ozair, Lynch, Bengio, van den Oord, Levine, Sermanent https://arxiv.org/pdf/1903.11780.pdf

GP-VAE: deep probabilistic time series imputation. Fortuin, Baranchuk, Ratsch, Mandt https://arxiv.org/pdf/1907.04155.pdf https://github.com/ratschlab/GP-VAE

Likelihood contribution based multi-scale architecture for generative flows. Das, Abbeel, Spanos https://arxiv.org/pdf/1908.01686.pdf

Gated Variational Autoencoders: Incorporating weak supervision to encourage disentanglement. Vowels, Camgoz, Bowden https://arxiv.org/pdf/1911.06443.pdf

An introduction to variational autoencoders. Kingma, Welling https://arxiv.org/pdf/1906.02691.pdf

Adaptive density estimation for generative models Lucas, Shmelkov, Schmid, Alahari, Verbeek https://papers.nips.cc/paper/9370-adaptive-density-estimation-for-generative-models.pdf

Data efficient mutual information neural estimator Lin, Sur, Nastase, Divakaran, Hasson, Amer https://arxiv.org/pdf/1905.03319.pdf

RecVAE: a new variational autoencoder for Top-N recommendations with implicit feedback. Shenbin, Alekseev, Tutubalina, Malykh, Nikolenko https://arxiv.org/pdf/1912.11160.pdf

Vibration signal generation using conditional variational autoencoder for class imbalance problem. Ko, Kim, Kong, Lee, Youn http://icmr2019.ksme.or.kr/wp/pdf/190090.pdf

The usual suspects? Reassessing blame for VAE posterior collapse. Dai, Wang, Wipf https://arxiv.org/pdf/1912.10702.pdf

What does the free energy principle tell us about the brain? Gershman https://arxiv.org/pdf/1901.07945.pdf

Sub-band vector quantized variational autoencoder for spectral envelope quantization. Srikotr, Mano https://ieeexplore.ieee.org/abstract/document/8929436

A variational-sequential graph autoencoder for neural performance prediction. Friede, Lukasik, Stuckenschmidt, Keuper https://arxiv.org/pdf/1912.05317.pdf

Explicit disentanglement of appearance and perspective in generative models. Skafte, Hauberg https://papers.nips.cc/paper/8387-explicit-disentanglement-of-appearance-and-perspective-in-generative-models.pdf

Disentangled behavioural representations. Dezfouli, Ashtiani, Ghattas, Nock, Dayan, Ong https://papers.nips.cc/paper/8497-disentangled-behavioural-representations.pdf

Learning disentangled representations for robust person re-identification. Eom, Ham https://papers.nips.cc/paper/8771-learning-disentangled-representation-for-robust-person-re-identification.pdf

Towards latent space optimality for auto-encoder based generative models. Mondal, Chowdhury, Jayendran, Singla, Asnani, AP https://arxiv.org/pdf/1912.04564.pdf

Don't blame the ELBO! A linear VAE perspective on posterior collapse. Lucas, Tucker, Grosse, Norouzi https://128.84.21.199/pdf/1911.02469.pdf

Bridging the ELBO and MMD. Ucar https://arxiv.org/pdf/1910.13181.pdf

Learning disentangled representations for counterfactual regression. Hassanpour, Greiner https://pdfs.semanticscholar.org/1df4/204e14da51b05a14781e2a4dc3e0d7da562d.pdf

Learning disentangled representations for recommendation. Ma, Zhou, Cui, Yang, Zhu https://arxiv.org/pdf/1910.14238.pdf

A vector quantized variational autoencoder (VQ-VAE) autoregressive neural F0 model for statistical parametric speech synthesis. Wang, Takaki, Yamagishi, King, Tokuda https://ieeexplore.ieee.org/abstract/document/8884734

Diversity-aware event prediction based on a conditional variational autoencoder with reconstruction. Kiyomaru, Omura, Murawaki, Kawahara, Kurohashi https://www.aclweb.org/anthology/D19-6014.pdf

Learning multimodal representations with factorized deep generative models. Tsai, Liang, Zadeh, Morency, Salakhutdinov https://pdfs.semanticscholar.org/7416/6384ad391513e8e8bf48cbeaff2516b8c332.pdf

High-dimensional nonlinear profile monitoring based on deep probabilistic autoencoders. Sergin, Yan https://arxiv.org/pdf/1911.00482.pdf

Leveraging directed causal discovery to detect latent common causes. Lee, Hart, Richens, Johri https://arxiv.org/pdf/1910.10174.pdf

Robust discrimination and generation of faces using compact, disentangled embeddings. Browatzki, Wallraven http://openaccess.thecvf.com/content_ICCVW_2019/papers/RSL-CV/Browatzki_Robust_Discrimination_and_Generation_of_Faces_using_Compact_Disentangled_Embeddings_ICCVW_2019_paper.pdf

Coulomb Autoencoders. Sansone, Ali, Sun https://arxiv.org/pdf/1802.03505.pdf

Contrastive learning of structured world models. Kipf, Pol, Welling https://arxiv.org/pdf/1911.12247.pdf

No representation without transformation. Giannone, Masci, Osendorfer https://pgr-workshop.github.io/img/PGR007.pdf

Neural density estimation. Papamakarios https://arxiv.org/pdf/1910.13233.pdf

Variational autoencoder-based approach for rail defect identification. Wei, Ni http://www.dpi-proceedings.com/index.php/shm2019/article/view/32432

Variational learning with disentanglement-pytorch. Abdi, Abolmaesumi, Fels https://openreview.net/pdf?id=rJgUsFYnir

PVAE: learning disentangled representations with intrinsic dimension via approximated L0 regularization. Shi, Glocker, Castro https://openreview.net/pdf?id=HJg8stY2oB

Mixed-curvature variational autoencoders. Skopek, Ganea, Becigneul https://arxiv.org/pdf/1911.08411.pdf

Continuous hierarchical representations with poincare variational autoencoders. Mathieu, Le Lan, Maddison, Tomioka https://arxiv.org/pdf/1901.06033.pdf

VIREL: A variational inference framework for reinforcement learning. Fellows, Mahajan, Rudner, Whiteson https://arxiv.org/pdf/1811.01132.pdf

Disentangling video with independent prediction. Whitney, Fergus https://arxiv.org/pdf/1901.05590.pdf

Disentangling state space representations Miladinovic, Gondal, Scholkopf, Buhmann, Bauer https://arxiv.org/pdf/1906.03255.pdf

Likelihood conribution based multi-scale architecture for generative flows. Das, Abbeel, Spanos https://arxiv.org/pdf/1908.01686.pdf

AlignFlow: cycle consistent learning from multiple domains via normalizing flows Grover, Chute, Shu, Cao, Ermon https://arxiv.org/pdf/1905.12892.pdf

IB-GAN: disentangled representation learning with information bottleneck GAN. Jeon, Lee, Kim https://openreview.net/forum?id=ryljV2A5KX

Learning hierarchical priors in VAEs. Klushyn, Chen, Kurle, Cseke, van der Smagt https://papers.nips.cc/paper/8553-learning-hierarchical-priors-in-vaes.pdf

ODE2VAE: Deep generative second order ODEs with Bayesian neural networks. Yildiz, Heinonen, Lahdesmaki https://papers.nips.cc/paper/9497-ode2vae-deep-generative-second-order-odes-with-bayesian-neural-networks.pdf

Explicitly disentangling image content from translation and rotation with spatial-VAE. Bepler, Zhong, Kelley, Brignole, Berger https://papers.nips.cc/paper/9677-explicitly-disentangling-image-content-from-translation-and-rotation-with-spatial-vae.pdf

A primal-dual link between GANs and autoencoders. Husain, Nock, Williamson https://papers.nips.cc/paper/8333-a-primal-dual-link-between-gans-and-autoencoders.pdf

Exact rate-distortion in autoencoders via echo noise. Brekelmans, Moyer, Galstyan, ver Steeg https://papers.nips.cc/paper/8644-exact-rate-distortion-in-autoencoders-via-echo-noise.pdf

Direct optimization through arg max for discrete variational auto-encoder. Lorberbom, Jaakkola, Gane, Hazan https://papers.nips.cc/paper/8851-direct-optimization-through-arg-max-for-discrete-variational-auto-encoder.pdf

Semi-implicit graph variational auto-encoders. Hasanzadeh, Hajiramezanali, Narayanan, Duffield, Zhou, Qian https://papers.nips.cc/paper/9255-semi-implicit-graph-variational-auto-encoders.pdf

The continuous Bernoulli: fixing a pervasive error in variational autoencoders. Loaiza-Ganem, Cunningham https://papers.nips.cc/paper/9484-the-continuous-bernoulli-fixing-a-pervasive-error-in-variational-autoencoders.pdf

Provable gradient variance guarantees for black-box variational inference. Domke https://papers.nips.cc/paper/8325-provable-gradient-variance-guarantees-for-black-box-variational-inference.pdf

Conditional structure generation through graph variational generative adversarial nets. Yang, Zhuang, Shi, Luu, Li https://papers.nips.cc/paper/8415-conditional-structure-generation-through-graph-variational-generative-adversarial-nets.pdf

Scalable spike source localization in extracellular recordings using amortized variational inference. Hurwitz, Xu, Srivastava, Buccino, Hennig https://papers.nips.cc/paper/8720-scalable-spike-source-localization-in-extracellular-recordings-using-amortized-variational-inference.pdf

A latent variational framework for stochastic optimization. Casgrain https://papers.nips.cc/paper/8802-a-latent-variational-framework-for-stochastic-optimization.pdf

MAVEN: multi-agent variational exploration. Mahajan, Rashid, Samvelyan, Whiteson https://papers.nips.cc/paper/8978-maven-multi-agent-variational-exploration.pdf

Variational graph recurrent neural networks. Hajiramezanali, Hasanzadeh, Narayanan, Duffield, Zhou, Qian https://papers.nips.cc/paper/9254-variational-graph-recurrent-neural-networks.pdf

The thermodynamic variational objective. Masrani, Le, Wood https://papers.nips.cc/paper/9328-the-thermodynamic-variational-objective.pdf

Variational temporal abstraction. Kim, Ahn, Bengio https://papers.nips.cc/paper/9332-variational-temporal-abstraction.pdf

Exploiting video sequences for unsupervised disentangling in generative adversarial networks. Tuesca, Uzal https://arxiv.org/pdf/1910.11104.pdf

Couple-VAE: mitigating the encoder-decoder incompatibility in variational text modeling with coupled deterministic networks. https://openreview.net/pdf?id=SJlo_TVKwS

Variational mixture-of-experts autoencoders for multi-modal deep generative models. Shi, Siddharth, Paige, Torr https://papers.nips.cc/paper/9702-variational-mixture-of-experts-autoencoders-for-multi-modal-deep-generative-models.pdf

Invertible convolutional flow. Karami, Schuurmans, Sohl-Dickstein, Dinh, Duckworth https://papers.nips.cc/paper/8801-invertible-convolutional-flow.pdf

Implicit posterior variational inference for deep Gaussian processes. Yu, Chen, Dai, Low, Jaillet https://papers.nips.cc/paper/9593-implicit-posterior-variational-inference-for-deep-gaussian-processes.pdf

MaCow: Masked convolutional generative flow. Ma, Kong, Zhang, Hovy https://papers.nips.cc/paper/8824-macow-masked-convolutional-generative-flow.pdf

Residual flows for invertible generative modeling. Chen, Behrmann, Duvenaud, Jacobsen https://papers.nips.cc/paper/9183-residual-flows-for-invertible-generative-modeling.pdf

Discrete flows: invertible generative models of discrete data. Tran, Vafa, Agrawal, Dinh, Poole https://papers.nips.cc/paper/9612-discrete-flows-invertible-generative-models-of-discrete-data.pdf

Re-examination of the role of latent variables in sequence modeling. Lai, Dai, Yang, Yoo https://papers.nips.cc/paper/8996-re-examination-of-the-role-of-latent-variables-in-sequence-modeling.pdf

Learning-in-the-loop optimization: end-to-end control and co-design of soft robots through learned deep latent representations. Spielbergs, Zhao, Hu, Du, Matusik, Rus https://papers.nips.cc/paper/9038-learning-in-the-loop-optimization-end-to-end-control-and-co-design-of-soft-robots-through-learned-deep-latent-representations.pdf

Triad constraints for learning causal structure of latent variables. Cai, Xie, Glymour, Hao, Zhang https://papers.nips.cc/paper/9448-triad-constraints-for-learning-causal-structure-of-latent-variables.pdf

Disentangling influence: using disentangled representations to audit model predictions. Marx, Phillips, Friedler, Scheidegger, Venkatasubramanian https://papers.nips.cc/paper/8699-disentangling-influence-using-disentangled-representations-to-audit-model-predictions.pdf

Symmetry-based disentangled representation learning requires interaction with environments. Caselles-Dupre, Ortiz, Filliat https://papers.nips.cc/paper/8709-symmetry-based-disentangled-representation-learning-requires-interaction-with-environments.pdf

Weakly supervised disentanglement with guarantees. Shu, Chen, Kumar, Ermon, Poole https://arxiv.org/pdf/1910.09772.pdf

Demystifying inter-class disentanglement. Gabbay, Hoshen https://arxiv.org/pdf/1906.11796.pdf

Spectral regularization for combating mode collapse in GANs. Liu, Tang, Xie, Qiu https://arxiv.org/pdf/1908.10999.pdf

Geometric disentanglement for generative latent shape models. Aumentado-Armstrong, Tsogkas, Jepson, Dickinson https://arxiv.org/pdf/1908.06386.pdf

Cross-dataset person re-identification via unsupervised pose disentanglement and adaptation. Li, Lin, Lin, Wang https://arxiv.org/pdf/1909.09675.pdf

Identity from here, pose from there: self-supervised disentanglement and generation of objects using unlabeled videos. Xiao, Liu, Lee https://web.cs.ucdavis.edu/~yjlee/projects/iccv2019_disentangle.pdf

Content and style disentanglement for artistic style transfer. Kotovenko, Sanakoyeu, Lang, Ommer https://compvis.github.io/content-style-disentangled-ST/paper.pdf

Unsupervised robust disentangling of latent characteristics for image synthesis. Esser, Haux, Ommer https://arxiv.org/pdf/1910.10223.pdf

LADN: local adversarial disentangling network for facial makeup and de-makeup. Gu, Wang, Chiu, Tai, Tang https://arxiv.org/pdf/1904.11272.pdf

Video compression with rate-distortion autoencoders. Habibian, van Rozendaal, Tomczak, Cohen https://arxiv.org/pdf/1908.05717.pdf

Variable rate deep image compression with a conditional autoencoder. Choi, El-Khamy, Lee https://arxiv.org/pdf/1909.04802.pdf

Memorizing normality to detect anomaly: memory-augmented deep autoencoder for unsupervised anomaly detection. Gong, Liu, Le, Saha https://arxiv.org/pdf/1904.02639.pdf

AVT: unsupervise d learning of transformation equivariant representations by autoencoding variational transformations. Qi, Zhang, Chen, Tian https://arxiv.org/pdf/1903.10863.pdf

Deep clustering by Gaussian mixture variational autoencoders with graph embedding. Yang, Cheung, Li, Fang http://openaccess.thecvf.com/content_ICCV_2019/papers/Yang_Deep_Clustering_by_Gaussian_Mixture_Variational_Autoencoders_With_Graph_Embedding_ICCV_2019_paper.pdf

Variational adversarial active learning. Sinha, Ebrahimi, Darrell https://arxiv.org/pdf/1904.00370.pdf

Variational few-shot learning. Zhang, Zhao, Ni, Xu, Yang http://openaccess.thecvf.com/content_ICCV_2019/papers/Zhang_Variational_Few-Shot_Learning_ICCV_2019_paper.pdf

Multi-angle point cloud-VAE: unsupervised feature learning for 3D point clouds from multiple angles by joint self-reconstruction and half-to-half prediction. Han, Wang, Liu, Zwicker https://arxiv.org/pdf/1907.12704.pdf

LayoutVAE: stochastic scene layout generation from a label set. Jyothi, Durand, He, Sigal, Mori https://arxiv.org/pdf/1907.10719.pdf

VV-NET: Voxel VAE Net with group convolutions for point cloud segmentation. Meng, Gao, Lai, Manocha https://arxiv.org/pdf/1811.04337.pdf

Bayes-Factor-VAE: hierarchical bayesian deep auto-encoder models for factor disentanglement. Kim, Wang, Sahu, Pavlovic https://arxiv.org/pdf/1909.02820.pdf

Robust ordinal VAE: Employing noisy pairwise comparisons for disentanglement. Chen, Batmanghelich https://arxiv.org/pdf/1910.05898.pdf

Evaluating disentangled representations. Sepliarskaia, A. and Kiseleva, J. and de Rijke, M. https://arxiv.org/pdf/1910.05587.pdf

A stable variational autoencoder for text modelling. Li, R. and Li, X. and Lin, C. and Collinson, M. and Mao, R. https://abdn.pure.elsevier.com/en/publications/a-stable-variational-autoencoder-for-text-modelling

Hamiltonian generative networks. Toth, Rezende, Jaegle, Racaniere, Botev, Higgins https://128.84.21.199/pdf/1909.13789.pdf

LAVAE: Disentangling location and appearance. Dittadi, Winther https://arxiv.org/pdf/1909.11813.pdf

Interpretable models in probabilistic machine learning. Kim https://ora.ox.ac.uk/objects/uuid:b238ed7d-7155-4860-960e-6227c7d688fb/download_file?file_format=pdf&safe_filename=PhD_Thesis_of_University_of_Oxford.pdf&type_of_work=Thesis

Disentangling speech and non-speech components for building robust acoustic models from found data. Gurunath, Rallabandi, Black https://arxiv.org/pdf/1909.11727.pdf

Joint separation, dereverberation and classification of multiple sources using multichannel variational autoencoder with auxiliary classifier. Inoue, Kameoka, Li, Makino http://pub.dega-akustik.de/ICA2019/data/articles/000906.pdf

SuperVAE: Superpixelwise variational autoencoder for salient object detection. Li, Sun, Guo https://www.aaai.org/ojs/index.php/AAAI/article/view/4876

Implicit discriminator in variational autoencoder. Munjal, Paul, Krishnan https://arxiv.org/pdf/1909.13062.pdf

TransGaGa: Geometry-aware unsupervised image-to-image translation. Wu, Cao, Li, Qian, Loy http://openaccess.thecvf.com/content_CVPR_2019/papers/Wu_TransGaGa_Geometry-Aware_Unsupervised_Image-To-Image_Translation_CVPR_2019_paper.pdf

Variational attention using articulatory priors for generating code mixed speech using monolingual corpora. Rallabandi, Black. https://www.isca-speech.org/archive/Interspeech_2019/pdfs/1103.pdf

One-class collaborative filtering with the queryable variational autoencoder. Wu, Bouadjenek, Sanner. https://people.eng.unimelb.edu.au/mbouadjenek/papers/SIGIR_Short_2019.pdf

Predictive auxiliary variational autoencoder for representation learning of global speech characteristics. Springenberg, Lakomkin, Weber, Wermter. https://www.isca-speech.org/archive/Interspeech_2019/pdfs/2845.pdf

Data augmentation using variational autoencoder for embedding based speaker verification. Wu, Wang, Qian, Yu https://zhanghaowu.me/assets/VAE_Data_Augmentation_proceeding.pdf

One-shot voice conversion with disentangled representations by leveraging phonetic posteriograms. Mohammadi, Kim. https://www.isca-speech.org/archive/Interspeech_2019/pdfs/1798.pdf

EEG-based adaptive driver-vehicle interface using variational autoencoder and PI-TSVM. Bi, Zhang, Lian https://www.researchgate.net/profile/Luzheng_Bi2/publication/335619300_EEG-Based_Adaptive_Driver-Vehicle_Interface_Using_Variational_Autoencoder_and_PI-TSVM/links/5d70bb234585151ee49e5a30/EEG-Based-Adaptive-Driver-Vehicle-Interface-Using-Variational-Autoencoder-and-PI-TSVM.pdf

Neural gaussian copula for variational autoencoder Wang, Wang https://arxiv.org/pdf/1909.03569.pdf

Enhancing VAEs for collaborative filtering: Flexible priors and gating mechanisms. Kim, Suh http://delivery.acm.org/10.1145/3350000/3347015/p403-kim.pdf?ip=86.162.136.199&id=3347015&acc=OPEN&key=4D4702B0C3E38B35%2E4D4702B0C3E38B35%2E4D4702B0C3E38B35%2E6D218144511F3437&__acm__=1568726810_89cfa7cbc7c1b0663405d4446f9fce85

Riemannian normalizing flow on variational wasserstein autoencoder for text modeling. Wang, Wang https://arxiv.org/pdf/1904.02399.pdf

Disentanglement with hyperspherical latent spaces using diffusion variational autoencoders. Rey https://openreview.net/pdf?id=SylFDSU6Sr

Learning deep representations by mutual information estimation and maximization. Hjelm, Fedorov, Lavoie-Marchildon, Grewal, Bachman, Trischler, Bengio https://arxiv.org/pdf/1808.06670.pdf https://github.com/rdevon/DIM

Novel tracking approach based on fully-unsupervised disentanglement of the geometrical factors of variation. Vladymyrov, Ariga https://arxiv.org/pdf/1909.04427.pdf

Real time trajectory prediction using conditional generative models. Gomez-Gonzalez, Prokudin, Scholkopf, Peters https://arxiv.org/pdf/1909.03895.pdf

Disentanglement challenge: from regularization to reconstruction. Qiao, Li, Cai https://openreview.net/pdf?id=ByecPrUaHH

Improved disentanglement through aggregated convolutional feature maps. Seitzer https://openreview.net/pdf?id=ryxOvH86SH

Linked variational autoencoders for inferring substitutable and supplementary items. Rakesh, Wang, Shu http://www.public.asu.edu/~skai2/files/wsdm_2019_lvae.pdf

On the fairness of disentangled representations. Locatello, Abbati, Rainforth, Bauer, Scholkopf, Bachem https://arxiv.org/pdf/1905.13662.pdf

Learning robust representations by projecting superficial statistics out. Wang, He, Lipton, Xing https://openreview.net/pdf?id=rJEjjoR9K7

Understanding posterior collapse in generative latent variable models. Lucas, Tucker, Grosse, Norouzi https://openreview.net/pdf?id=r1xaVLUYuE

On the transfer of inductive bias from simulation to the real world: a new disentanglement dataset. Gondal, Wuthrich, Miladinovic, Locatello, Breidt, Volchkv, Akpo, Bachem, Scholkopf, Bauer https://arxiv.org/pdf/1906.03292.pdf https://github.com/rr-learning/disentanglement_dataset

DIVA: domain invariant variational autoencoder. Ilse, Tomczak, Louizos, Welling https://arxiv.org/pdf/1905.10427.pdf https://github.com/AMLab-Amsterdam/DIVA

Comment: Variational Autoencoders as empirical Bayes. Wang, Miller, Blei http://www.stat.columbia.edu/~yixinwang/papers/WangMillerBlei2019.pdf

Fast MVAE: joint separation and classification of mixed sources based on multichannel variational autoencoder with auxiliary classifier. Li, Kameoka, Makino https://ieeexplore.ieee.org/abstract/document/8682623

Reweighted expectation maximization. Dieng, Paisley https://arxiv.org/pdf/1906.05850.pdf https://github.com/adjidieng/REM

Semisupervised text classification by variational autoencoder. Xu, Tan https://ieeexplore.ieee.org/abstract/document/8672806

Learning deep latent-variable MRFs with amortized Bethe free-energy minimization. Wiseman https://openreview.net/pdf?id=ByeMHULt_N

Contrastive variational autoencoder enhances salient features. Abid, Zou https://arxiv.org/pdf/1902.04601.pdf https://github.com/abidlabs/contrastive_vae

Learning latent superstructures in variational autoencoders for deep multidimensional clustering. Li, Chen, Poon, Zhang https://openreview.net/pdf?id=SJgNwi09Km

Tighter variational bounds are not necessarily better. Rainforth, Kosiorek, Le, Maddison, Igl, Wood, The https://arxiv.org/pdf/1802.04537.pdf https://github.com/lxuechen/DReG-PyTorch

ISA-VAE: Independent subspace analysis with variational autoencoders. Anon. https://openreview.net/pdf?id=rJl_NhR9K7

Manifold mixup: better representations by interpolating hidden states. Verma, Lamb, Beckham, Najafi, Mitliagkas, Courville, Lopez-Paz, Bengio. https://arxiv.org/pdf/1806.05236.pdf https://github.com/vikasverma1077/manifold_mixup

Bit-swap: recursive bits-back coding for lossless compression with hierarchical latent variables. Kingma, Abbeel, Ho. http://proceedings.mlr.press/v97/kingma19a/kingma19a.pdf https://github.com/fhkingma/bitswap

Practical lossless compression with latent variables using bits back coding. Townsend, Bird, Barber. https://arxiv.org/pdf/1901.04866.pdf https://github.com/bits-back/bits-back

BIVA: a very deep hierarchy of latent variables for generative modeling. Maaloe, Fraccaro, Lievin, Winther. https://arxiv.org/pdf/1902.02102.pdf

Flow++: improving flow-based generative models with variational dequantization and architecture design. Ho, Chen, Srinivas, Duan, Abbeel. https://arxiv.org/pdf/1902.00275.pdf https://github.com/aravindsrinivas/flowpp

Sylvester normalizing flows for variational inference. van den Berg, Hasenclever, Tomczak, Welling. https://arxiv.org/pdf/1803.05649.pdf https://github.com/riannevdberg/sylvester-flows

Unbiased implicit variational inference. Titsias, Ruiz. https://arxiv.org/pdf/1808.02078.pdf

Robustly disentangled causal mechanisms: validating deep representations for interventional robustness. Suter, Miladinovic, Scholkopf, Bauer. https://arxiv.org/pdf/1811.00007.pdf

Tutorial: Deriving the standard variational autoencoder (VAE) loss function. Odaibo https://arxiv.org/pdf/1907.08956.pdf

Learning disentangled representations with reference-based variational autoencoders. Ruiz, Martinez, Binefa, Verbeek. https://arxiv.org/pdf/1901.08534

Disentangling factors of variation using few labels. Locatello, Tschannen, Bauer, Ratsch, Scholkopf, Bachem https://arxiv.org/pdf/1905.01258.pdf

Disentangling disentanglement in variational autoencoders Mathieu, Rainforth, Siddharth, The, https://arxiv.org/pdf/1812.02833.pdf https://github.com/iffsid/disentangling-disentanglement

LIA: latently invertible autoencoder with adversarial learning Zhu, Zhao, Zhang https://arxiv.org/pdf/1906.08090.pdf

Emerging disentanglement in auto-encoder based unsupervised image content transfer. Press, Galanti, Benaim, Wolf https://openreview.net/pdf?id=BylE1205Fm https://github.com/oripress/ContentDisentanglement

MAE: Mutual posterior-divergence regularization for variational autoencoders Ma, Zhou, Hovy https://arxiv.org/pdf/1901.01498.pdf https://github.com/XuezheMax/mae

Overcoming the disentanglement vs reconstruction trade-off via Jacobian supervision. Lezama https://openreview.net/pdf?id=Hkg4W2AcFm https://github.com/jlezama/disentangling-jacobian https://github.com/jlezama/disentangling-jacobian/tree/master/unsupervised_disentangling

Challenging common assumptions in the unsupervised learning of disentangled representations. Locatello, Bauer, Lucic, Ratsch, Gelly, Scholkopf, Bachem https://arxiv.org/abs/1811.12359 https://github.com/google-research/disentanglement_lib/blob/master/README.md

Variational prototyping encoder: one shot learning with prototypical images. Kim, Oh, Lee, Pan, Kweon http://openaccess.thecvf.com/content_CVPR_2019/papers/Kim_Variational_Prototyping-Encoder_One-Shot_Learning_With_Prototypical_Images_CVPR_2019_paper.pdf

Diagnosing and enchanving VAE models (conf and journal paper both available). Dai, Wipf https://arxiv.org/pdf/1903.05789.pdf https://github.com/daib13/TwoStageVAE

Disentangling latent hands for image synthesis and pose estimation. Yang, Yao http://openaccess.thecvf.com/content_CVPR_2019/papers/Yang_Disentangling_Latent_Hands_for_Image_Synthesis_and_Pose_Estimation_CVPR_2019_paper.pdf

Rare event detection using disentangled representation learning. Hamaguchi, Sakurada, Nakamura http://openaccess.thecvf.com/content_CVPR_2019/papers/Hamaguchi_Rare_Event_Detection_Using_Disentangled_Representation_Learning_CVPR_2019_paper.pdf

Disentangling latent space for VAE by label relevant/irrelvant dimensions. Zheng, Sun https://arxiv.org/pdf/1812.09502.pdf https://github.com/ZhilZheng/Lr-LiVAE

Variational autoencoders pursue PCA directions (by accident). Rolinek, Zietlow, Martius https://arxiv.org/pdf/1812.06775.pdf

Disentangled Representation learning for 3D face shape. Jiang, Wu, Chen, Zhang https://arxiv.org/pdf/1902.09887.pdf https://github.com/zihangJiang/DR-Learning-for-3D-Face

Preventing posterior collapse with delta-VAEs. Razavi, van den Oord, Poole, Vinyals https://arxiv.org/pdf/1901.03416.pdf https://github.com/mattjj/svae

Gait recognition via disentangled representation learning. Zhang, Tran, Yin, Atoum, Liu, Wan, Wang https://arxiv.org/pdf/1904.04925.pdf

Hierarchical disentanglement of discriminative latent features for zero-shot learning. Tong, Wang, Klinkigt, Kobayashi, Nonaka http://openaccess.thecvf.com/content_CVPR_2019/papers/Tong_Hierarchical_Disentanglement_of_Discriminative_Latent_Features_for_Zero-Shot_Learning_CVPR_2019_paper.pdf

Generalized zero- and few-shot learning via aligned variational autoencoders. Schonfeld, Ebrahimi, Sinha, Darrell, Akata https://arxiv.org/pdf/1812.01784.pdf https://github.com/chichilicious/Generalized-Zero-Shot-Learning-via-Aligned-Variational-Autoencoders

Unsupervised part-based disentangling of object shape and appearance. Lorenz, Bereska, Milbich, Ommer https://arxiv.org/pdf/1903.06946.pdf

A semi-supervised Deep generative model for human body analysis. de Bem, Ghosh, Ajanthan, Miksik, Siddaharth, Torr http://www.robots.ox.ac.uk/~tvg/publications/2018/W21P20.pdf

Multi-object representation learning with iterative variational inference. Greff, Kaufman, Kabra, Watters, Burgess, Zoran, Matthey, Botvinick, Lerchner https://arxiv.org/pdf/1903.00450.pdf https://github.com/MichaelKevinKelly/IODINE

Generating diverse high-fidelity images with VQ-VAE-2. Razavi, van den Oord, Vinyals https://arxiv.org/pdf/1906.00446.pdf https://github.com/deepmind/sonnet/blob/master/sonnet/examples/vqvae_example.ipynb https://github.com/rosinality/vq-vae-2-pytorch

MONet: unsupervised scene decomposition and representation. Burgess, Matthey, Watters, Kabra, Higgins, Botvinick, Lerchner https://arxiv.org/pdf/1901.11390.pdf

Structured disentangled representations and Hierarchical disentangled representations. Esmaeili, Wu, Jain, Bozkurt, Siddarth, Paige, Brooks, Dy, van de Meent https://arxiv.org/pdf/1804.02086.pdf

Spatial Broadcast Decoder: A simple architecture for learning disentangled representations in VAEs. Watters, Matthey, Burgess, Lerchner https://arxiv.org/pdf/1901.07017.pdf https://github.com/lukaszbinden/spatial-broadcast-decoder

Resampled priors for variational autoencoders. Bauer, Mnih https://arxiv.org/pdf/1802.06847.pdf

Weakly supervised disentanglement by pairwise similiarities. Chen, Batmanghelich https://arxiv.org/pdf/1906.01044.pdf

Deep variational information bottleneck. Aelmi, Fischer, Dillon, Murphy https://arxiv.org/pdf/1612.00410.pdf https://github.com/alexalemi/vib_demo

Generalized variational inference. Knoblauch, Jewson, Damoulas https://arxiv.org/pdf/1904.02063.pdf

Variational autoencoders and nonlinear ICA: a unifying framework. Khemakhem, Kingma https://arxiv.org/pdf/1907.04809.pdf

Lagging inference networks and posterior collapse in variational autoencoders. He, Spokoyny, Neubig, Berg-Kirkpatrick https://arxiv.org/pdf/1901.05534.pdf https://github.com/jxhe/vae-lagging-encoder

Avoiding latent variable collapse with generative skip models. Dieng, Kim, Rush, Blei https://arxiv.org/pdf/1807.04863.pdf

Distribution Matching in Variational inference. Rosca, Lakshminarayana, Mohamed https://arxiv.org/pdf/1802.06847.pdf A variational auto-encoder model for stochastic point process. Mehrasa, Jyothi, Durand, He, Sigal, Mori https://arxiv.org/pdf/1904.03273.pdf

Sliced-Wasserstein auto-encoders. Kolouri, Pope, Martin, Rohde https://openreview.net/pdf?id=H1xaJn05FQ https://github.com/skolouri/swae

A deep generative model for graph layout. Kwon, Ma https://arxiv.org/pdf/1904.12225.pdf

Differentiable perturb-and-parse semi-supervised parsing with a structured variational autoencoder. Corro, Titov https://openreview.net/pdf?id=BJlgNh0qKQ https://github.com/FilippoC/diffdp

Variational autoencoders with jointly optimized latent dependency structure. He, Gong, Marino, Mori, Lehrmann https://openreview.net/pdf?id=SJgsCjCqt7 https://github.com/ys1998/vae-latent-structure

Unsupervised learning of spatiotemporally coherent metrics Goroshin, Bruna, Tompson, Eigen, LeCun https://arxiv.org/pdf/1412.6056.pdf

Temporal difference variational auto-encoder. Gregor, Papamakarios, Besse, Buesing, Weber https://arxiv.org/pdf/1806.03107.pdf https://github.com/xqding/TD-VAE

Representation learning with contrastive predictive coding. van den Oord, Li, Vinyals https://arxiv.org/pdf/1807.03748.pdf https://github.com/davidtellez/contrastive-predictive-coding

Representation disentanglement for multi-task learning with application to fetal ultrasound Meng, Pawlowski, Rueckert, Kainz https://arxiv.org/pdf/1908.07885.pdf

M$2$VAE - derivation of a multi-modal variational autoencoder objective from the marginal joint log-likelihood. Korthals https://arxiv.org/pdf/1903.07303.pdf

Predicting visual memory schemas with variational autoencoders. Kyle-Davidson, Bors, Evans https://arxiv.org/pdf/1907.08514.pdf

T-CVAE: Transformer -based conditioned variational autoencoder for story completion. Wang, Wan https://www.ijcai.org/proceedings/2019/0727.pdf https://github.com/sodawater/T-CVAE

PuVAE: A variational autoencoder to purify adversarial examples. Hwang, Park, Jang, Yoon, Cho https://arxiv.org/pdf/1903.00585.pdf

Coupled VAE: Improved accuracy and robustness of a variational autoencoder. Cao, Li, Nelson https://arxiv.org/pdf/1906.00536.pdf

D-VAE: A variational autoencoder for directed acyclic graphs. Zhang, Jiang, Cui, Garnett, Chen https://arxiv.org/abs/1904.11088 https://github.com/muhanzhang/D-VAE

Are disentangled representations helpful for abstract reasoning? van Steenkiste, Locatello, Schmidhuber, Bachem https://arxiv.org/pdf/1905.12506.pdf

A heuristic for unsupervised model selection for variational disentangled representation learning. Duan, Watters, Matthey, Burgess, Lerchner, Higgins https://arxiv.org/pdf/1905.12614.pdf

Dual space learning with variational autoencoders. Okamoto, Suzuki, Higuchi, Ohsawa, Matsuo https://pdfs.semanticscholar.org/ea70/6495d4a6214b3d6174bb7fd99c5a9c34c2e6.pdf

Variational autoencoders for sparse and overdispersed discrete data. Zhao, Rai, Du, Buntine https://arxiv.org/pdf/1905.00616.pdf

Variational auto-decoder. Zadeh, Lim, Liang, Morency. https://arxiv.org/pdf/1903.00840.pdf

Causal discovery with attention-based convolutional neural networks. Naura, Bucur, Seifert https://www.mdpi.com/2504-4990/1/1/19/pdf

Variational laplace autoencoders. Park, Kim, Kim http://proceedings.mlr.press/v97/park19a/park19a.pdf

Variational autoencoders with normalizing flow decoders. https://openreview.net/forum?id=r1eh30NFwB

Gaussian process priors for view-aware inference. Hou, Heljakka, Solin https://arxiv.org/pdf/1912.03249.pdf

SGVAE: sequential graph variational autoencoder. Jing, Chi, Tang https://arxiv.org/pdf/1912.07800.pdf

improving multimodal generative models with disentangled latent partitions. Daunhawer, Sutter, Vogt http://bayesiandeeplearning.org/2019/papers/103.pdf

Cross-population variational autoencoders. Davison, Severson, Ghosh https://openreview.net/pdf?id=r1eWdlBFwS http://bayesiandeeplearning.org/2019/papers/96.pdf

Evidential disambiguation of latent multimodality in conditional variational autoencoders. Itkina, Ivanovic, Senanayake, Kochenderfer, Pavone http://bayesiandeeplearning.org/2019/papers/34.pdf

Increasing the generalisation capacity of conditional VAEs. Klushyn, Chen, Cseke, Bayer, van der Smagt https://link.springer.com/chapter/10.1007/978-3-030-30484-3_61

Multi-source neural variational inference. Kurle, Gunnemann, van der Smagt https://wvvw.aaai.org/ojs/index.php/AAAI/article/view/4311

Early integration for movement modeling in latent spaces. Hornung, Chen, van der Smagt https://books.google.co.uk/books?hl=en&lr=&id=M1WfDwAAQBAJ&oi=fnd&pg=PA305&dq=info:MRhvAh4qD7wJ:scholar.google.com&ots=hN84xN5saO&sig=TBMgkFo6z9wrL64TcvzjU4G5gCQ&redir_esc=y#v=onepage&q&f=false

Building face recognition system with triplet-based stacked variational denoising autoencoder. LEe, Hart, Richens, Johri https://dl.acm.org/citation.cfm?id=3369707

Cross-domain variational autoencoder for recommender systems. Shi, Wang https://ieeexplore.ieee.org/abstract/document/8935901 Predictive coding, variational autoencoders, and biological connections. Marino https://openreview.net/pdf?id=SyeumQYUUH

A general and adaptive robust loss function Barron https://arxiv.org/pdf/1701.03077.pdf

Variational autoencoder trajectory primitives and discrete latent. Osa, Ikemoto https://arxiv.org/pdf/1912.04063.pdf

Faster attend-infer-repeat with tractable probabilistic models. Stelzner, Peharz, Kersting http://proceedings.mlr.press/v97/stelzner19a/stelzner19a.pdf https://github/stelzner/supair

Learning predictive models from observation and interaction. Schmeckpeper, Xie, Rybkin, Tian, Daniilidis, Levine, Finn https://arxiv.org/pdf/1912.12773.pdf

Translating visual art into music Muller-Eberstein, van Noord http://openaccess.thecvf.com/content_ICCVW_2019/papers/CVFAD/Muller-Eberstein_Translating_Visual_Art_Into_Music_ICCVW_2019_paper.pdf

Non-parallel voice conversion with controllable speaker individuality using variational autoencoder. Ho, Akagi http://www.apsipa.org/proceedings/2019/pdfs/68.pdf

Derivation of the variational Bayes equations. Maren https://arxiv.org/pdf/1906.08804.pdf

2018

TVAE: Triplet-Based Variational Autoencoder using Metric Learning. Ishfaq, Hoogi, Rubin. https://arxiv.org/abs/1802.04403

Conditional neural processes. Garnelo, Rosenbaum, Maddison, Ramalho, Saxton, Shanahan, The, Rezende, Eslami https://arxiv.org/abs/1807.01613

The variational homoencoder: learning to learn high capacity generative models from few examples. Hewitt, Nye, Gane, Jaakkola, Tenebaum https://arxiv.org/abs/1807.08919

Wasserstein variational inference. Ambrogioni, Guclu, Gucluturk, Hinne, Maris, van Gerven https://arxiv.org/abs/1805.11284

The dreaming variational autoencoder for reinforcement learning environments Andersen, Goodwin, Granmo https://arxiv.org/pdf/1810.01112v1.pdf

DVAE++: Discrete variational autoencoders wth overlapping transformations. Vahdat, Macready, Bian,Khoshaman, Andriyash http://proceedings.mlr.press/v80/vahdat18a/vahdat18a.pdf

FFJORD: free-form continuous dynamics for scalable reversible generative models. Grathwohl, Chen, Bettencourt, Sutskever, Duvenaud https://arxiv.org/pdf/1810.01367.pdf

A general method for amortizing variational filtering. Marino, Cvitkovic, Yue https://arxiv.org/pdf/1811.05090.pdf https://github.com/joelouismarino/amortized-variational-filtering

Handling incomplete heterogeneous data using VAEs. Nazabal, Olmos, Ghahramani, Valera https://arxiv.org/pdf/1807.03653.pdf

Sequential attend, infer, repeat: generative modeling of moving objects. Kosiorek, Kim, Posner, Teh https://arxiv.org/pdf/1806.01794.pdf https://github.com/akosiorek/sqair https://www.youtube.com/watch?v=-IUNQgSLE0c&feature=youtu.be

Doubly reparameterized gradient estimators for monte carlo objectives. Tucker, Lawson, Gu, Maddison https://arxiv.org/pdf/1810.04152.pdf

Interpretable intuitive physics model. Ye, Wang, Davidson, Gupta https://arxiv.org/pdf/1808.10002.pdf https://github.com/tianye95/interpretable-intuitive-physics-model

Normalizing Flows Tutorial, Part 2: Modern Normalizing Flows. Eric Jang https://blog.evjang.com/2018/01/nf2.html

Neural autoregressive flows. Huang, Krueger, Lacoste, Courville https://medium.com/element-ai-research-lab/neural-autoregressive-flows-f164d6b8e462 https://arxiv.org/pdf/1804.00779.pdf https://github.com/CW-Huang/NAF

Gaussian process prior variational autoencoders. Casale, Dalca, Sagletti, Listgarten, Fusi https://papers.nips.cc/paper/8238-gaussian-process-prior-variational-autoencoders.pdf

ACVAE-VC: non-parallel many-to-many voice conversion with auxiliary classifier variational autoencoder. Kameoka, Kaneko, Tanaka, Hojo https://arxiv.org/pdf/1808.05092.pdf

Discovering interpretable representations for both deep generative and discriminative models. Adel, Ghahramani, Weller http://mlg.eng.cam.ac.uk/adrian/ICML18-Discovering.pdf

Autoregressive quantile networks for generative modelling . Ostrovski, Dabey, Munos https://arxiv.org/pdf/1806.05575.pdf

Probabilistic video generation using holistic attribute control. He, Lehrmann, Marino, Mori, Sigal https://arxiv.org/pdf/1803.08085.pdf

Bias and generalization in deep generative models: an empirical study. Zhao, Ren, Yuan, Song, Goodman, Ermon https://arxiv.org/pdf/1811.03259.pdf https://ermongroup.github.io/blog/bias-and-generalization-dgm/ https://github.com/ermongroup/BiasAndGeneralization/tree/master/Evaluate

On variational lower bounds of mutual information. Poole, Ozair, van den Oord, Alemi, Tucker http://bayesiandeeplearning.org/2018/papers/136.pdf

GAN - why it is so hard to train generative adversarial networks . Hui https://medium.com/@jonathan_hui/gan-why-it-is-so-hard-to-train-generative-advisory-networks-819a86b3750b

Counterfactuals uncover the modular structure of deep generative models. Besserve, Sun, Scholkopf. https://arxiv.org/pdf/1812.03253.pdf

Learning independent causal mechanisms. Parascandolo, Kilbertus, Rojas-Carulla, Scholkopf https://arxiv.org/pdf/1712.00961.pdf

Emergence of invariance and disentanglement in deep representations. Achille, Soatto https://arxiv.org/pdf/1706.01350.pdf

Variational memory encoder-decoder. Le, Tran, Nguyen, Venkatesh https://arxiv.org/pdf/1807.09950.pdf https://github.com/thaihungle/VMED

Variational autoencoders for collaborative filtering. Liang, Krishnan, Hoffman, Jebara https://arxiv.org/pdf/1802.05814.pdf

Invariant representations without adversarial training. Moyer, Gao, Brekelmans, Steeg, Galstyan http://papers.nips.cc/paper/8122-invariant-representations-without-adversarial-training.pdf https://github.com/dcmoyer/inv-rep

Density estimation: Variational autoencoders. Rui Shu http://ruishu.io/2018/03/14/vae/

TherML: The thermodynamics of machine learning. Alemi, Fishcer https://arxiv.org/pdf/1807.04162.pdf

Leveraging the exact likelihood of deep latent variable models. Mattei, Frellsen https://arxiv.org/pdf/1802.04826.pdf

What is wrong with VAEs? Kosiorek http://akosiorek.github.io/ml/2018/03/14/what_is_wrong_with_vaes.html

Stochastic variational video prediction. Babaeizadeh, Finn, Erhan, Campbell, Levine https://arxiv.org/pdf/1710.11252.pdf https://github.com/alexlee-gk/video_prediction

Variational attention for sequence-to-sequence models. Bahuleyan, Mou, Vechtomova, Poupart https://arxiv.org/pdf/1712.08207.pdf https://github.com/variational-attention/tf-var-attention

FactorVAE Disentangling by factorizing. Kim, Minh https://arxiv.org/pdf/1802.05983.pdf

Disentangling factors of variation with cycle-consistent variational autoencoders. Jha, Anand, Singh, Veeravasarapu https://arxiv.org/pdf/1804.10469.pdf https://github.com/ananyahjha93/cycle-consistent-vae

Isolating sources of disentanglement in VAEs. Chen, Li, Grosse, Duvenaud https://arxiv.org/pdf/1802.04942.pdf

VAE with a VampPrior. Tomczak, Welling https://arxiv.org/pdf/1705.07120.pdf

A Framework for the quantitative evaluation of disentangled representations. Eastwood, Williams https://openreview.net/pdf?id=By-7dz-AZ https://github.com/cianeastwood/qedr

Recent advances in autoencoder based representation learning. Tschannen, Bachem, Lucic https://arxiv.org/pdf/1812.05069.pdf

InfoVAE: Balancing learning and inference in variational autoencoders. Zhao, Song, Ermon https://arxiv.org/pdf/1706.02262.pdf

Understanding disentangling in Beta-VAE. Burgess, Higgins, Pal, Matthey, Watters, Desjardins, Lerchner https://arxiv.org/pdf/1804.03599.pdf

Hidden Talents of the Variational autoencoder. Dai, Wang, Aston, Hua, Wipf https://arxiv.org/pdf/1706.05148.pdf

Variational Inference of disentangled latent concepts from unlabeled observations. Kumar, Sattigeri, Balakrishnan https://arxiv.org/abs/1711.00848

Self-supervised learning of a facial attribute embedding from video. Wiles, Koepke, Zisserman http://www.robots.ox.ac.uk/~vgg/publications/2018/Wiles18a/wiles18a.pdf

Wasserstein auto-encoders. Tolstikhin, Bousquet, Gelly, Scholkopf https://arxiv.org/pdf/1711.01558.pdf

A two-step disentanglement. method Hadad, Wolf, Shahar http://openaccess.thecvf.com/content_cvpr_2018/papers/Hadad_A_Two-Step_Disentanglement_CVPR_2018_paper.pdf https://github.com/naamahadad/A-Two-Step-Disentanglement-Method

Taming VAEs. Rezende, Viola https://arxiv.org/pdf/1810.00597.pdf https://github.com/denproc/Taming-VAEs https://github.com/syncrostone/Taming-VAEs

IntroVAE Introspective variational autoencoders for photographic image synthesis. Huang, Li, He, Sun, Tan https://arxiv.org/pdf/1807.06358.pdf https://github.com/dragen1860/IntroVAE-Pytorch

Information constraints on auto-encoding variational bayes. Lopez, Regier, Jordan, Yosef https://papers.nips.cc/paper/7850-information-constraints-on-auto-encoding-variational-bayes.pdf https://github.com/romain-lopez/HCV

Learning disentangled joint continuous and discrete representations. Dupont https://papers.nips.cc/paper/7351-learning-disentangled-joint-continuous-and-discrete-representations.pdf https://github.com/Schlumberger/joint-vae

Neural discrete representation learning. van den Oord, Vinyals, Kavukcuoglu https://arxiv.org/pdf/1711.00937.pdf https://github.com/1Konny/VQ-VAE https://github.com/ritheshkumar95/pytorch-vqvae

Disentangled sequential autoencoder. Li, Mandt https://arxiv.org/abs/1803.02991 https://github.com/yatindandi/Disentangled-Sequential-Autoencoder

Variational Inference: A review for statisticians. Blei, Kucukelbir, McAuliffe https://arxiv.org/pdf/1601.00670.pdf Advances in Variational Inferece. Zhang, Kjellstrom https://arxiv.org/pdf/1711.05597.pdf

Auto-encoding total correlation explanation. Goa, Brekelmans, Steeg, Galstyan https://arxiv.org/abs/1802.05822 Closest: https://github.com/gregversteeg/CorEx

Fixing a broken ELBO. Alemi, Poole, Fischer, Dillon, Saurous, Murphy https://arxiv.org/pdf/1711.00464.pdf

The information autoencoding family: a lagrangian perspective on latent variable generative models. Zhao, Song, Ermon https://arxiv.org/pdf/1806.06514.pdf https://github.com/ermongroup/lagvae

Debiasing evidence approximations: on importance-weighted autoencoders and jackknife variational inference. Nowozin https://openreview.net/pdf?id=HyZoi-WRb https://github.com/microsoft/jackknife-variational-inference

Unsupervised discrete sentence representation learning for interpretable neural dialog generation. Zhao, Lee, Eskenazi https://vimeo.com/285802293 https://arxiv.org/pdf/1804.08069.pdf https://github.com/snakeztc/NeuralDialog-LAED

Dual swap disentangling. Feng, Wang, Ke, Zeng, Tao, Song https://papers.nips.cc/paper/7830-dual-swap-disentangling.pdf

Multimodal generative models for scalable weakly-supervised learning. Wu, Goodman https://papers.nips.cc/paper/7801-multimodal-generative-models-for-scalable-weakly-supervised-learning.pdf https://github.com/mhw32/multimodal-vae-public https://github.com/panpan2/Multimodal-Variational-Autoencoder

Do deep generative models know what they don't know? Nalisnick, Matsukawa, The, Gorur, Lakshminarayanan https://arxiv.org/pdf/1810.09136.pdf

Glow: generative flow with invertible 1x1 convolutions. Kingma, Dhariwal https://arxiv.org/pdf/1807.03039.pdf https://github.com/openai/glow https://github.com/pytorch/glow

Inference suboptimality in variational autoencoders. Cremer, Li, Duvenaud https://arxiv.org/pdf/1801.03558.pdf https://github.com/chriscremer/Inference-Suboptimality

Adversarial Variational Bayes: unifying variational autoencoders and generative adversarial networks. Mescheder, Mowozin, Geiger https://arxiv.org/pdf/1701.04722.pdf https://github.com/LMescheder/AdversarialVariationalBayes

Semi-amortized variational autoencoders. Kim, Wiseman, Miller, Sontag, Rush https://arxiv.org/pdf/1802.02550.pdf https://github.com/harvardnlp/sa-vae

Spherical Latent Spaces for stable variational autoencoders. Xu, Durrett https://arxiv.org/pdf/1808.10805.pdf https://github.com/jiacheng-xu/vmf_vae_nlp

Hyperspherical variational auto-encoders. Davidson, Falorsi, De Cao, Kipf, Tomczak https://arxiv.org/pdf/1804.00891.pdf https://github.com/nicola-decao/s-vae-tf https://github.com/nicola-decao/s-vae-pytorch

Fader networks: manipulating images by sliding attributes. Lample, Zeghidour, Usunier, Bordes, Denoyer, Ranzato https://arxiv.org/pdf/1706.00409.pdf https://github.com/facebookresearch/FaderNetworks

Training VAEs under structured residuals. Dorta, Vicente, Agapito, Campbell, Prince, Simpson https://arxiv.org/pdf/1804.01050.pdf https://github.com/Garoe/tf_mvg

oi-VAE: output interpretable VAEs for nonlinear group factor analysis. Ainsworth, Foti, Lee, Fox https://arxiv.org/pdf/1802.06765.pdf https://github.com/samuela/oi-vae

infoCatVAE: representation learning with categorical variational autoencoders. Lelarge, Pineau https://arxiv.org/pdf/1806.08240.pdf https://github.com/edouardpineau/infoCatVAE

Iterative Amortized inference. Marino, Yue, Mandt https://arxiv.org/pdf/1807.09356.pdf https://vimeo.com/287766880 https://github.com/joelouismarino/iterative_inference

On unifying Deep Generative Models. Hu, Yang, Salakhutdinov, Xing https://arxiv.org/pdf/1706.00550.pdf

Diverse Image-to-image translation via disentangled representations. Lee, Tseng, Huang, Singh, Yang https://arxiv.org/pdf/1808.00948.pdf https://github.com/HsinYingLee/DRIT

PIONEER networks: progressively growing generative autoencoder. Heljakka, Solin, Kannala https://arxiv.org/pdf/1807.03026.pdf https://github.com/AaltoVision/pioneer

Towards a definition of disentangled representations. Higgins, Amos, Pfau, Racaniere, Matthey, Rezende, Lerchner https://arxiv.org/pdf/1812.02230.pdf

Life-long disentangled representation learning with cross-domain latent homologies. Achille, Eccles, Matthey, Burgess, Watters, Lerchner, Higgins file:///Users/matthewvowels/Downloads/Life-Long_Disentangled_Representation_Learning_wit.pdf

Learning deep disentangled embeddings with F-statistic loss. Ridgeway, Mozer https://arxiv.org/pdf/1802.05312.pdf https://github.com/kridgeway/f-statistic-loss-nips-2018

Learning latent subspaces in variational autoencoders. Klys, Snell, Zemel https://arxiv.org/pdf/1812.06190.pdf

On the latent space of Wasserstein auto-encoders. Rubenstein, Scholkopf, Tolstikhin. https://arxiv.org/pdf/1802.03761.pdf https://github.com/tolstikhin/wae

Learning disentangled representations with Wasserstein auto-encoders. Rubenstein, Scholkopf, Tolstikhin https://openreview.net/pdf?id=Hy79-UJPM

The mutual autoencoder: controlling information in latent code representations. Phuong, Kushman, Nowozin, Tomioka, Welling https://openreview.net/pdf?id=HkbmWqxCZ https://openreview.net/pdf?id=HkbmWqxCZ http://2017.ds3-datascience-polytechnique.fr/wp-content/uploads/2017/08/DS3_posterID_048.pdf

Auxiliary guided autoregressive variational autoencoders. Lucas, Verkbeek https://openreview.net/pdf?id=HkGcX--0- https://github.com/pclucas14/aux-vae

Interventional robustness of deep latent variable models. Suter, Miladinovic, Bauer, Scholkopf https://pdfs.semanticscholar.org/8028/a56d6f9d2179416d86837b447c6310bd371d.pdf?_ga=2.190184363.1450484303.1564569882-397935340.1548854421

Understanding degeneracies and ambiguities in attribute transfer. Szabo, Hu, Portenier, Zwicker, Facaro http://openaccess.thecvf.com/content_ECCV_2018/papers/Attila_Szabo_Understanding_Degeneracies_and_ECCV_2018_paper.pdf DNA-GAN: learning disentangled representations from multi-attribute images. Xiao, Hong, Ma https://arxiv.org/pdf/1711.05415.pdf https://github.com/Prinsphield/DNA-GAN

Normalizing flows. Kosiorek http://akosiorek.github.io/ml/2018/04/03/norm_flows.html

Hamiltonian variational auto-encoder Caterini, Doucet, Sejdinovic https://arxiv.org/pdf/1805.11328.pdf

Causal generative neural networks. Goudet, Kalainathan, Caillou, Guyon, Lopez-Paz, Sebag. https://arxiv.org/pdf/1711.08936.pdf https://github.com/GoudetOlivier/CGNN

Flow-GAN: Combining maximum likelihood and adversarial learning in generative models. Grover, Dhar, Ermon https://arxiv.org/pdf/1705.08868.pdf https://github.com/ermongroup/flow-gan

Linked causal variational autoencoder for inferring paired spillover effects. Rakesh, Guo, Moraffah, Agarwal, Liu https://arxiv.org/pdf/1808.03333.pdf https://github.com/rguo12/CIKM18-LCVA

Unsupervised anomaly detection via variational auto-encoder for seasonal KPIs in web applications. Xu, Chen, Zhao, Li, Bu, Li, Liu, Zhao, Pei, Feng, Chen, Wang, Qiao https://arxiv.org/pdf/1802.03903.pdf

Mutual information neural estimation. Belghazi, Baratin, Rajeswar, Ozair, Bengio, Hjelm. https://arxiv.org/pdf/1801.04062.pdf https://github.com/sungyubkim/MINE-Mutual-Information-Neural-Estimation- https://github.com/mzgubic/MINE

Explorations in homeomorphic variational auto-encoding. Falorsi, de Haan, Davidson, Cao, Weiler, Forre, Cohen. https://arxiv.org/pdf/1807.04689.pdf https://github.com/pimdh/lie-vae

Hierarchical variational memory network for dialogue generation. Chen, Ren, Tang, Zhao, Yin http://delivery.acm.org/10.1145/3190000/3186077/p1653-chen.pdf?ip=86.162.136.199&id=3186077&acc=OPEN&key=4D4702B0C3E38B35%2E4D4702B0C3E38B35%2E4D4702B0C3E38B35%2E6D218144511F3437&__acm__=1569938843_c07ad21d173fc64a44a22fd6521140cb

World models. Ha, Schmidhuber https://arxiv.org/pdf/1803.10122.pdf

2017

Grammar variational autoencoders. Kusner, Paige, Hernandez-Lobato https://arxiv.org/pdf/1703.01925.pdf

The multi-entity variational autoencoder. Nash, Eslami, Burgess, Higgins, Zoran, Weher, Battaglia https://charlienash.github.io/assets/docs/mevae2017.pdf

Towards a neural statistician. Edwards, Storkey https://arxiv.org/abs/1606.02185

The concrete distribution: a continuous relaxation of discrete random variables. Maddison, Mnih, The https://arxiv.org/pdf/1611.00712.pdf

Categorical reparameterization with Gumbel-Softmax. Jang, Gu, Poole https://arxiv.org/abs/1611.01144

Opening the black box of deep neural networks via information. Schwartz-Ziv, Tishby https://arxiv.org/pdf/1703.00810.pdf https://www.youtube.com/watch?v=gOn8Po_NPe4

Discovering causal signals in images . Lopez-Paz, Nishihara, Chintala, Scholkopf, Bottou https://arxiv.org/pdf/1605.08179.pdf

Autoencoding variational inference for topic models. Srivastava, Sutton https://arxiv.org/pdf/1703.01488.pdf

Hidden Markov model variational autoencoder for acoustic unit discovery. Ebbers, Heymann, Drude, Glarner, Haeb-Umbach, Raj https://www.isca-speech.org/archive/Interspeech_2017/pdfs/1160.PDF

Application of variational autoencoders for aircraft turbomachinery design. Zalger http://cs229.stanford.edu/proj2017/final-reports/5231979.pdf

Semi-supervised learning with variational autoencoders. Keng http://bjlkeng.github.io/posts/semi-supervised-learning-with-variational-autoencoders/

Causal effect inference with deep latent variable models. Louizos, Shalit, Mooij, Sontag, Zemel, Welling https://arxiv.org/pdf/1705.08821.pdf https://github.com/AMLab-Amsterdam/CEVAE

beta-VAE: learning basic visual concepts with a constrained variational framework. Higgins, Matthey, Pal, Burgess, Glorot, Botvinick, Mohamed, Lerchner https://openreview.net/pdf?id=Sy2fzU9gl

Challenges in disentangling independent factors of variation. Szabo, Hu, Portenier, Facaro, Zwicker https://arxiv.org/pdf/1711.02245.pdf https://github.com/ananyahjha93/challenges-in-disentangling

Composing graphical models with neural networks for structured representations and fast inference. Johnson, Duvenaud, Wiltschko, Datta, Adams https://arxiv.org/pdf/1603.06277.pdf

Split-brain autoencoders: unsupervised learning by cross-channel prediction. Zhang, Isola, Efros https://arxiv.org/pdf/1611.09842.pdf

Learning disentangled representations with semi-supervised deep generative models.Siddharth, Paige, van de Meent, Desmaison, Goodman, Kohli, Wood, Torr https://papers.nips.cc/paper/7174-learning-disentangled-representations-with-semi-supervised-deep-generative-models.pdf https://github.com/probtorch/probtorch

Learning hierarchical features from generative models. Zhao, Song, Ermon https://arxiv.org/pdf/1702.08396.pdf https://github.com/ermongroup/Variational-Ladder-Autoencoder

Multi-level variational autoencoder: learning disentangled representations from grouped observations. Bouchacourt, Tomioka, Nowozin https://arxiv.org/pdf/1705.08841.pdf

Neural Face editing with intrinsic image disentangling. Shu, Yumer, Hadap, Sankavalli, Shechtman, Samaras http://openaccess.thecvf.com/content_cvpr_2017/papers/Shu_Neural_Face_Editing_CVPR_2017_paper.pdf https://github.com/zhixinshu/NeuralFaceEditing

Variational Lossy Autoencoder. Chen, Kingma, Salimans, Duan, Dhariwal, Schulman, Sutskever, Abbeel https://arxiv.org/abs/1611.02731 https://github.com/jiamings/tsong.me/blob/master/_posts/reading/2016-11-08-lossy-vae.md

Unsupervised learning of disentangled and interpretable representations from sequential data. Hsu, Zhang, Glass https://papers.nips.cc/paper/6784-unsupervised-learning-of-disentangled-and-interpretable-representations-from-sequential-data.pdf https://github.com/wnhsu/FactorizedHierarchicalVAE https://github.com/wnhsu/ScalableFHVAE

Factorized variational autoencoder for modeling audience reactions to movies. Deng, Navarathna, Carr, Mandt, Yue, Matthews, Mori http://www.yisongyue.com/publications/cvpr2017_fvae.pdf

Learning latent representations for speech generation and transformation. Hsu, Zhang, Glass https://arxiv.org/pdf/1704.04222.pdf https://github.com/wnhsu/SpeechVAE

Unsupervised learning of disentangled representations from video. Denton, Birodkar https://papers.nips.cc/paper/7028-unsupervised-learning-of-disentangled-representations-from-video.pdf https://github.com/ap229997/DRNET

Laplacian pyramid of conditional variational autoencoders. Dorta, Vicente, Agapito, Campbell, Prince, Simpson http://cs.bath.ac.uk/~nc537/papers/cvmp17_LapCVAE.pdf

Neural Photo Editing with Inrospective Adverarial Networks. Brock, Lim, Ritchie, Weston https://arxiv.org/pdf/1609.07093.pdf https://github.com/ajbrock/Neural-Photo-Editor

Discrete Variational Autoencoder. Rolfe https://arxiv.org/pdf/1609.02200.pdf https://github.com/QuadrantAI/dvae

Reinterpreting importance-weighted autoencoders. Cremer, Morris, Duvenaud https://arxiv.org/pdf/1704.02916.pdf https://github.com/FighterLYL/iwae

Density Estimation using realNVP. Dinh, Sohl-Dickstein, Bengio https://arxiv.org/pdf/1605.08803.pdf https://github.com/taesungp/real-nvp https://github.com/chrischute/real-nvp

JADE: Joint autoencoders for disentanglement. Banijamali, Karimi, Wong, Ghosi https://arxiv.org/pdf/1711.09163.pdf Joint Multimodal learning with deep generative models. Suzuki, Nakayama, Matsuo https://openreview.net/pdf?id=BkL7bONFe https://github.com/masa-su/jmvae

Towards a deeper understanding of variational autoencoding models. Zhao, Song, Ermon https://arxiv.org/pdf/1702.08658.pdf https://github.com/ermongroup/Sequential-Variational-Autoencoder

Lagging inference networks and posterior collapse in variational autoencoders. Dilokthanakul, Mediano, Garnelo, Lee, Salimbeni, Arulkumaran, Shanahan https://arxiv.org/pdf/1611.02648.pdf https://github.com/Nat-D/GMVAE https://github.com/psanch21/VAE-GMVAE

On the challenges of learning with inference networks on sparse, high-dimensional data. Krishnan, Liang, Hoffman https://arxiv.org/pdf/1710.06085.pdf https://github.com/rahulk90/vae_sparse

Stick-breaking Variational Autoencoder. https://arxiv.org/pdf/1605.06197.pdf https://github.com/sporsho/hdp-vae

Deep variational canonical correlation analysis. Wang, Yan, Lee, Livescu https://arxiv.org/pdf/1610.03454.pdf https://github.com/edchengg/VCCA_pytorch

Nonparametric variational auto-encoders for hierarchical representation learning. Goyal, Hu, Liang, Wang, Xing https://arxiv.org/pdf/1703.07027.pdf https://github.com/bobchennan/VAE_NBP/blob/master/report.markdown

PixelSNAIL: An improved autoregressive generative model. Chen, Mishra, Rohaninejad, Abbeel https://arxiv.org/pdf/1712.09763.pdf https://github.com/neocxi/pixelsnail-public

Improved Variational Inference with inverse autoregressive flows. Kingma, Salimans, Jozefowicz, Chen, Sutskever, Welling https://arxiv.org/pdf/1606.04934.pdf https://github.com/kefirski/bdir_vae

It takes (only) two: adversarial generator-encoder networks. Ulyanov, Vedaldi, Lempitsky https://arxiv.org/pdf/1704.02304.pdf https://github.com/DmitryUlyanov/AGE

Symmetric Variational Autoencoder and connections to adversarial learning. Chen, Dai, Pu, Li, Su, Carin https://arxiv.org/pdf/1709.01846.pdf

Reconstruction-based disentanglement for pose-invariant face recognition. Peng, Yu, Sohn, Metaxas, Chandraker https://arxiv.org/pdf/1702.03041.pdf https://github.com/zhangjunh/DR-GAN-by-pytorch

Is maximum likelihood useful for representation learning? Huszár https://www.inference.vc/maximum-likelihood-for-representation-learning-2/

Disentangled representation learning GAN for pose-invariant face recognition. Tran, Yin, Liu http://zpascal.net/cvpr2017/Tran_Disentangled_Representation_Learning_CVPR_2017_paper.pdf https://github.com/kayamin/DR-GAN

Improved Variational Autoencoders for text modeling using dilated convolutions. Yang, Hu, Salakhutdinov, Berg-kirkpatrick https://arxiv.org/pdf/1702.08139.pdf

Improving variational auto-encoders using householder flow. Tomczak, Welling https://arxiv.org/pdf/1611.09630.pdf https://github.com/jmtomczak/vae_householder_flow

Sticking the landing: simple, lower-variance gradient estimators for variational inference. Roeder, Wu, Duvenaud. http://proceedings.mlr.press/v97/kingma19a/kingma19a.pdf https://github.com/geoffroeder/iwae

VEEGAN: Reducing mode collapse in GANs using implicit variational learning. Srivastava, Valkov, Russell, Gutmann. https://arxiv.org/pdf/1705.07761.pdf https://github.com/akashgit/VEEGAN

Discovering discrete latent topics with neural variational inference. Miao, Grefenstette, Blunsom https://arxiv.org/pdf/1706.00359.pdf

Variational approaches for auto-encoding generative adversarial networks. Rosca, Lakshminarayana, Warde-Farley, Mohamed https://arxiv.org/pdf/1706.04987.pdf

Variational Autoencoder and extensions. Courville https://ift6266h17.files.wordpress.com/2017/03/vae1.pdf

A neural representation of sketch drawings. Ha, Eck https://arxiv.org/pdf/1704.03477.pdf

2016

One-shot generalization in deep generative models. Rezende, Danihelka, Gregor, Wierstra https://arxiv.org/abs/1603.05106

Attend, infer, repeat: fast scene understanding with generative models. Eslami, Heess, Weber, Tassa, Szepesvari, Kavukcuoglu, Hinton https://arxiv.org/pdf/1603.08575.pdf http://akosiorek.github.io/ml/2017/09/03/implementing-air.html https://github.com/aleju/papers/blob/master/neural-nets/Attend_Infer_Repeat.md

Deep feature consistent variational autoencoder. Hou, Shen, Sun, Qiu https://arxiv.org/pdf/1610.00291.pdf https://github.com/sbavon/Deep-Feature-Consistent-Variational-AutoEncoder-in-Tensorflow

Neural variational inference for text processing. Miao, Yu, Grefenstette, Blunsom. https://arxiv.org/pdf/1511.06038.pdf

Domain-adversarial training of neural networks. Ganin, Ustinova, Ajakan, Germain, Larochelle, Laviolette, Marchand, Lempitsky https://arxiv.org/pdf/1505.07818.pdf

Tutorial on Variational Autoencoders. Doersch https://arxiv.org/pdf/1606.05908.pdf

How to train deep variational autoencoders and probabilistic ladder networks. Sonderby, Raiko, Maaloe, Sonderby, Winther https://orbit.dtu.dk/files/121765928/1602.02282.pdf

ELBO surgery: yet another way to carve up the variational evidence lower bound. Hoffman, Johnson http://approximateinference.org/accepted/HoffmanJohnson2016.pdf

Variational inference with normalizing flows. Rezende, Mohamed https://arxiv.org/pdf/1505.05770.pdf

The Variational Fair Autoencoder. Louizos, Swersky, Li, Welling, Zemel https://arxiv.org/pdf/1511.00830.pdf https://github.com/dendisuhubdy/vfae

Information dropout: learning optimal representations through noisy computations. Achille, Soatto https://arxiv.org/pdf/1611.01353.pdf

Domain separation networks. Bousmalis, Trigeorgis, Silberman, Krishnan, Erhan https://arxiv.org/pdf/1608.06019.pdf https://github.com/fungtion/DSN https://github.com/farnazj/Domain-Separation-Networks

Disentangling factors of variation in deep representations using adversarial training. Mathieu, Zhao, Sprechmann, Ramesh, LeCunn https://arxiv.org/pdf/1611.03383.pdf https://github.com/ananyahjha93/disentangling-factors-of-variation-using-adversarial-training

Variational autoencoder for semi-supervised text classification. Xu, Sun, Deng, Tan https://arxiv.org/pdf/1603.02514.pdf https://github.com/wead-hsu/ssvae related: https://github.com/isohrab/semi-supervised-text-classification

Learning what and where to draw. Reed, Sohn, Zhang, Lee https://arxiv.org/pdf/1610.02454.pdf

Attribute2Image: Conditional image generation from visual attributes. Yan, Yang, Sohn, Lee https://arxiv.org/pdf/1512.00570.pdf

Variational inference with normalizing flows. Rezende, Mohamed https://arxiv.org/pdf/1505.05770.pdf https://github.com/ex4sperans/variational-inference-with-normalizing-flows

Wild Variational Approximations. Li, Liu http://approximateinference.org/2016/accepted/LiLiu2016.pdf

Importance Weighted Autoencoders. Burda, Grosse, Salakhutdinov https://arxiv.org/pdf/1509.00519.pdf https://github.com/yburda/iwae https://github.com/xqding/Importance_Weighted_Autoencoders https://github.com/abdulfatir/IWAE-tensorflow

Stacked What-Where Auto-encoders. Zhao, Mathieu, Goroshin, LeCunn https://arxiv.org/pdf/1506.02351.pdf https://github.com/yselivonchyk/Tensorflow_WhatWhereAutoencoder

Disentangling nonlinear perceptual embeddings with multi-query triplet networks. Veit, Belongie, Karaletsos https://www.researchgate.net/profile/Andreas_Veit/publication/301837223_Disentangling_Nonlinear_Perceptual_Embeddings_With_Multi-Query_Triplet_Networks/links/57e2997308ae040ae3c2f3a3/Disentangling-Nonlinear-Perceptual-Embeddings-With-Multi-Query-Triplet-Networks.pdf

Ladder Variational Autoencoders. Sonderby, Raiko, Maaloe, Sonderby, Winther https://arxiv.org/pdf/1602.02282.pdf Variational autoencoder for deep learning of images, labels and captions. Pu, Gan Henao, Yuan, Li, Stevens, Carin https://papers.nips.cc/paper/6528-variational-autoencoder-for-deep-learning-of-images-labels-and-captions.pdf

Approximate inference for deep latent Gaussian mixtures. Nalisnick, Hertel, Smyth https://pdfs.semanticscholar.org/f6fe/5e8e25994c188ba6a124462e2cc55f2c5a67.pdf https://github.com/enalisnick/mixture_density_VAEs

Auxiliary Deep Generative Models. Maaloe, Sonderby, Sonderby, Winther https://arxiv.org/pdf/1602.05473.pdf https://github.com/larsmaaloee/auxiliary-deep-generative-models

Variational methods for conditional multimodal deep learning. Pandey, Dukkipati https://arxiv.org/pdf/1603.01801.pdf

PixelVAE: a latent variable model for natural images. Gulrajani, Kumar, Ahmed, Taiga, Visin, Vazquez, Courville https://arxiv.org/pdf/1611.05013.pdf https://github.com/igul222/PixelVAE https://github.com/kundan2510/pixelVAE

Adversarial autoencoders. Makhzani, Shlens, Jaitly, Goodfellow, Frey https://arxiv.org/pdf/1511.05644.pdf https://github.com/conan7882/adversarial-autoencoders

A hierarchical latent variable encoder-decoder model for generating dialogues. Serban, Sordoni, Lowe, Charlin, Pineau, Courville, Bengio http://www.cs.toronto.edu/~lcharlin/papers/vhred_aaai17.pdf

Infinite variational autoencoder for semi-supervised learning. Abbasnejad, Dick https://arxiv.org/pdf/1611.07800.pdf

f-GAN: Training generative neural samplers using variational divergence minimization. Nowozin, Cseke https://arxiv.org/pdf/1606.00709.pdf https://github.com/LynnHo/f-GAN-Tensorflow

DISCO Nets: DISsimilarity Coefficient networks Bouchacourt, Kumar, Nowozin https://arxiv.org/pdf/1606.02556.pdf https://github.com/oval-group/DISCONets

Information dropout: learning optimal representations through noisy computations. Achille, Soatto https://arxiv.org/pdf/1611.01353.pdf

Weakly-supervised disentangling with recurrent transformations for 3D view synthesis. Yang, Reed, Yang, Lee https://arxiv.org/pdf/1601.00706.pdf https://github.com/jimeiyang/deepRotator

Autoencoding beyond pixels using a learned similarity metric. Boesen, Larsen, Sonderby, Larochelle, Winther https://arxiv.org/pdf/1512.09300.pdf https://github.com/andersbll/autoencoding_beyond_pixels

Generating images with perceptual similarity metrics based on deep networks Dosovitskiy, Brox. https://arxiv.org/pdf/1602.02644.pdf https://github.com/shijx12/DeepSim

A note on the evaluation of generative models. Theis, van den Oord, Bethge. https://arxiv.org/pdf/1511.01844.pdf

InfoGAN: interpretable representation learning by information maximizing generative adversarial nets. Chen, Duan, Houthooft, Schulman, Sutskever, Abbeel https://arxiv.org/pdf/1606.03657.pdf https://github.com/openai/InfoGAN

Disentangled representations in neural models. Whitney https://arxiv.org/abs/1602.02383

A recurrent latent variable model for sequential data. Chung, Kastner, Dinh, Goel, Courville, Bengio https://arxiv.org/pdf/1506.02216.pdf

Unsupervised learning of 3D structure from images. Rezende, Eslami, Mohamed, Battaglia, Jaderberg, Heess https://arxiv.org/pdf/1607.00662.pdf

A survey of inductive biases for factorial representation-learning. Ridgeway https://arxiv.org/pdf/1612.05299.pdf

Short notes on variational bounds with rescaled terms. Rezende https://danilorezende.com/2016/06/27/short-notes-on-variational-bounds-with-rescaled-terms/

2015

Deep learning and the information bottleneck principle Tishby, Zaslavsky https://arxiv.org/pdf/1503.02406.pdf

Training generative neural networks via Maximum Mean Discrepancy optimization. Dziugaite, Roy, Ghahramani https://arxiv.org/pdf/1505.03906.pdf

NICE: non-linear independent components estimation. Dinh, Krueger, Bengio https://arxiv.org/pdf/1410.8516.pdf

Deep convolutional inverse graphics network. Kulkarni, Whitney, Kohli, Tenenbaum https://arxiv.org/pdf/1503.03167.pdf https://github.com/yselivonchyk/TensorFlow_DCIGN

Learning structured output representation using deep conditional generative models. Sohn, Yan, Lee https://papers.nips.cc/paper/5775-learning-structured-output-representation-using-deep-conditional-generative-models.pdf https://github.com/wsjeon/ConditionalVariationalAutoencoder

Latent variable model with diversity-inducing mutual angular regularization. Xie, Deng, Xing https://arxiv.org/pdf/1512.07336.pdf

DRAW: a recurrent neural network for image generation. Gregor, Danihelka, Graves, Rezende, Wierstra. https://arxiv.org/pdf/1502.04623.pdf https://github.com/ericjang/draw

Variational Inference II. Xing, Zheng, Hu, Deng https://www.cs.cmu.edu/~epxing/Class/10708-15/notes/10708_scribe_lecture13.pdf

2014

Auto-encoding variational Bayes. Kingma, Welling https://arxiv.org/pdf/1312.6114.pdf

Learning to disentangle factors of variation with manifold interaction. Reed, Sohn, Zhang, Lee http://proceedings.mlr.press/v32/reed14.pdf

Semi-supervised learning with deep generative models. Kingma, Rezende, Mohamed, Welling https://papers.nips.cc/paper/5352-semi-supervised-learning-with-deep-generative-models.pdf https://github.com/saemundsson/semisupervised_vae https://github.com/Response777/Semi-supervised-VAE

Stochastic backpropagation and approximate inference in deep generative models. Rezende, Mohamed, Wierstra https://arxiv.org/pdf/1401.4082.pdf https://github.com/ashwindcruz/dgm/tree/master/adgm_mnist

Representation learning: a review and new perspectives. Bengio, Courville, Vincent https://arxiv.org/pdf/1206.5538.pdf

2011

Transforming Auto-encoders. Hinton, Krizhevsky, Wang https://www.cs.toronto.edu/~hinton/absps/transauto6.pdf

2008

Graphical models, exponential families, and variational inference. Wainwright, Jordan et al

2004

Variational learning and bits-back coding: an information-theoretic view to Bayesian learning. Honkela, Valpola https://www.cs.helsinki.fi/u/ahonkela/papers/infview.pdf

2000

The information bottleneck method. Tishby, Pereira, Bialek https://arxiv.org/pdf/physics/0004057.pdf