Variational Autoencoders

Also known as VAE

Variational autoencoders learn probability distributions over compact latent codes and decode samples from them, typically by balancing reconstruction quality against a KL-divergence regularizer in the evidence lower bound. Common approaches use Gaussian, mixture, flow-based, spherical, or heavy-tailed priors, and add hierarchical, disentangling, temporal, multimodal, geometric, or physics-informed structure. They are used for image, video, audio, molecule, medical, and scientific data, both as generative models and as compact representations for downstream prediction or diffusion. A central tension is that stronger regularization can make generation easier while causing posterior collapse or losing useful detail; reconstruction scores alone also do not guarantee good samples, calibrated uncertainty, or useful latent structure.

Latest papers

210 papers30 papers in the last four weeks, up 131% on the four weeks before. 0.2% of all new papers.

MO-RiskVAE: A Multi-Omics Variational Autoencoder for Survival Risk Modeling in Multiple MyelomaMO-RiskVAE
Apr 7, 2026Zixuan Chen, Heng Zhang, YuPeng Qin +5Latent-Space Regularization Cancer Survival Prediction
Binjiang Institute of Zhejiang University · Zhejiang University · School of Medicine, Zhejiang University
Mitigating Data Scarcity in Spaceflight Applications for Offline Reinforcement Learning Using Physics-Informed Deep Generative Models
Apr 2, 2026Alex E. Ballentine, Nachiket U. Bapat, Raghvendra V. CowlagiPhysics-Informed Generative Modeling Variational Autoencoders
Graduate Research Assistant, Aerospace Engineering Department, Worcester Polytechnic Institute, MA. · Associate Professor, Aerospace Engineering Department. AIAA Senior Member. Corresponding Author.
Variational Encoder--Multi-Decoder (VE-MD) for Privacy-by-functional-design (Group) Emotion Recognition
Apr 2, 2026Anderson Augusma, Dominique Vaufreydaz, Fédérique LetuéEmotion Recognition Privacy-Preserving ML
UGA, LIG, M-PSI · Univ. Grenoble Alpes, CNRS, Grenoble INP, LIG, 38000 Grenoble, France · Univ. Grenoble Alpes, CNRS, Grenoble INP, LJK, 38000 Grenoble, France +2
Multi-Mode Quantum Annealing for Generative Representation Learning with Boltzmann Priors
Apr 1, 2026Gilhan Kim, Daniel K. ParkQuantum Generative Modeling Variational Autoencoders
Department of Statistics and Data Science, Yonsei University, Seoul 03722, Republic of Korea · Department of Applied Statistics, Yonsei University, Seoul 03722, Republic of Korea · Department of Quantum Information, Yonsei University, Seoul 03722, Republic of Korea
Embedded Variational Neural Stochastic Differential Equations for Learning Heterogeneous Dynamics
Apr 1, 2026Sandeep Kumar Samota, Reema Gupta, Snehashish ChakravertyLatent Dynamics Modeling Time Series Forecasting
Department of Mathematics, National Institute of Technology, Rourkela, India · Poverty Alleviation Research Centre, National Institute of Technology, Rourkela, India
Improving Generalization of Deep Learning for Brain Metastases Segmentation Across Institutions
Apr 1, 2026Yuchen Yang, Shuangyang Zhong, Haijun Yu +4Medical Image Segmentation Brain Tumor Segmentation
Institute of Medical Technology, Peking University Health Science Center, Beijing, China · Beijing Key Laboratory of Intelligent Neuromodulation and Brain Disorder Treatment, Beijing, China · Department of Radiation Oncology, University Hospital Erlangen, Erlangen, Germany
HyVIC: A Metric-Driven Spatio-Spectral Hyperspectral Image Compression Architecture Based on Variational Autoencoders
Mar 27, 2026Martin Hermann Paul Fuchs, Behnood Rasti, Begüm DemirLearned Image Compression Hyperspectral Imaging
Faculty of Electrical Engineering and Computer Science, Technische Universität Berlin, 10587 Berlin, Germany
SAHMM-VAE: A Source-Wise Adaptive Hidden Markov Prior Variational Autoencoder for Unsupervised Blind Source Separation
Mar 26, 2026Yuan-Hao WeiVariational Autoencoders Hidden Markov Models
TopoMesh: High-Fidelity Mesh Autoencoding via Topological Unification
Mar 25, 2026Guan Luo, Xiu Li, Rui Chen +6Autoencoders Variational Autoencoders
Tsinghua University · ByteDance Seed · HKUST
Beyond Static Uncertainty: Modeling Temporal Uncertainty Dynamics for Probabilistic Time Series Forecasting
Mar 25, 2026Yijun Wang, Qiyuan Zhuang, Larysa Marchanka +1Probabilistic Time Series Forecasting Uncertainty Quantification
Department of Computer Science, Southeast University, Nanjing, China · Francisk Skorina Gomel State University, Belarus
TrajLoom: Dense Future Trajectory Generation from Video
Mar 23, 2026Zewei Zhang, Jia Jun Cheng Xian, Kaiwen Liu +4Trajectory Prediction Video Prediction
McMaster University · University of British Columbia · Vector Institute +2
A Variational Latent-Space Framework for Uncertainty-Aware Spectral Image Emulation
Mar 23, 2026Chedly Ben Azizi, Claire Guilloteau, Gilles Roussel +1Neural Surrogate Modeling Variational Autoencoders
Univ. Littoral Côte d’Opale, LISIC – UR 4491, 62219, Longuenesse, France
Posterior-Calibrated Causal Circuits in Variational Autoencoders: Why Image-Domain Interpretability Fails on Tabular Data
Mar 22, 2026Dip Roy, Rajiv Misra, Sanjay Kumar Singh +1Variational Autoencoders Causal Interpretability
Department of Computer Science and Engineering, Indian Institute of Technology, Patna, India · Department of Computer Science, Rajarshi School of Management Technology, Varanasi, India · Department of Electronics and Communication Engineering, Jaypee Institute of Information Technology, Noida
DMMRL: Disentangled Multi-Modal Representation Learning via Variational Autoencoders for Molecular Property Prediction
Mar 22, 2026Long Xu, Junping Guo, Jianbo Zhao +2Molecular Representation Learning Multimodal Disentangled Representation Learning
Guangxi Key Lab of Human-machine Interaction and Intelligent Decision, Nanning Normal University, Nanning, China · College of Big Data and Software Engineering, Zhejiang Wanli University, Ningbo, China
PDGMM-VAE: A Variational Autoencoder with Adaptive Per-Dimension Gaussian Mixture Model Priors for Nonlinear ICA
Mar 20, 2026Yuan-Hao Wei, Yan-Jie SunIndependent Component Analysis Variational Autoencoders
Hong Kong Polytechnic University
GeMA: Learning Latent Manifold Frontiers for Benchmarking Complex Systems
Mar 17, 2026Jia Ming Li, Anupriya, Daniel J. GrahamManifold Learning Variational Autoencoders
Transport Strategy Centre, Imperial College London, London, SW7 2AZ, United Kingdom.
Evaluating Latent Space Structure in Timbre VAEs: A Comparative Study of Unsupervised, Descriptor-Conditioned, and Perceptual Feature-Conditioned Models
Mar 17, 2026Joseph Cameron, Alan BlackwellVariational Autoencoders Audio Representation Learning
Department of Computer Science & Technology, University of Cambridge, Cambridge, United Kingdom
Spectrum Matching: a Unified Perspective for Superior Diffusability in Latent Diffusion
Mar 15, 2026Mang Ning, Mingxiao Li, Le Zhang +4Latent Diffusion Models Diffusion-Based Image Generation
Utrecht University · KU Leuven · Mila +1
Distilling Latent Manifolds: Resolution Extrapolation by Variational Autoencoders
Mar 15, 2026Jiaming Chu, Tao Wang, Lei JinPosition Extrapolation Variational Autoencoders
School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China
AR-Flow VAE: A Structured Autoregressive Flow Prior Variational Autoencoder for Unsupervised Blind Source Separation
Mar 15, 2026Yuan-Hao Wei, Fu-Hao Deng, Lin-Yong Cui +1Variational Autoencoders Flow-Based Generative Modeling
Hong Kong Polytechnic University · Wuhan University of Technology · The University of Hong Kong
A Unified Latent Space Disentanglement VAE Framework with Robust Disentanglement Effectiveness Evaluation
Mar 11, 2026Xiaoan Lang, Md Mostafizer Rahman, Fang LiuVariational Autoencoders Disentangled Representation Learning
Department of Applied and Computational Mathematics and Statistics University of Notre Dame, Notre Dame, IN, USA · Lucy Family Institute for Data & Society University of Notre Dame, Notre Dame, IN, USA
Spherical VAE with Cluster-Aware Feasible Regions: Guaranteed Prevention of Posterior Collapse
Mar 11, 2026Zegu Zhang, Jian ZhangVariational Autoencoders Posterior Collapse
Independent Researcher
Riemannian Geometry-Preserving Variational Autoencoder for MI-BCI Data Augmentation
Mar 11, 2026Viktorija Poļaka, Ivo Pascal de Jong, Andreea Ioana SburleaSynthetic Data Augmentation Variational Autoencoders
Faculty of Science and Engineering, University of Groningen, Groningen, The Netherlands
Geometric Autoencoder for Diffusion Models
Mar 11, 2026Hangyu Liu, Jianyong Wang, Yutao SunLatent Diffusion Models Diffusion Models
Shanghai Innovation Institute · Tsinghua University
Image Generation Models: A Technical History
Mar 8, 2026Rouzbeh ShirvaniImage Generation Diffusion-Based Image Generation
Implementation of Quantum Implicit Neural Representation in Deterministic and Probabilistic Autoencoders for Image Reconstruction/Generation Tasks
Mar 6, 2026Saadet Müzehher ErenVariational Autoencoders Quantum Generative Modeling
Department of Physics, Izmir Institute of Technology, Gülbahçe, Urla, 35430, Izmir, Turkey.
RAC: Rectified Flow Auto Coder
Mar 6, 2026Sen Fang, Yalin Feng, Yanxin Zhang +6Autoencoders Variational Autoencoders
Making Reconstruction FID Predictive of Diffusion Generation FID
Mar 5, 2026Tongda Xu, Mingwei He, Shady Abu-Hussein +6Diffusion Models Variational Autoencoders
Tsinghua University · University of Cambridge · Peking University +1
CoVAE: correlated multimodal generative modeling
Mar 2, 2026Federico Caretti, Guido SanguinettiMultimodal Generation Variational Autoencoders
Scuola Internazionale Superiore di Studi Avanzati, Trieste, Italy
Phase-Type Variational Autoencoders for Heavy-Tailed Data
Mar 2, 2026Abdelhakim Ziani, András Horváth, Paolo BallariniVariational Autoencoders Heavy-Tailed Distributions
Université Paris Saclay, Lab. MICS, CentraleSupélec, Gif-sur-Yvette, France · Università di Torino, Torino, Italy

Apr 7, 2026J/K move · Enter open · S save

MO-RiskVAE: A Multi-Omics Variational Autoencoder for Survival Risk Modeling in Multiple MyelomaMO-RiskVAE

Zixuan Chen, Heng Zhang, YuPeng Qin, WenPeng Xing+4

Binjiang Institute of Zhejiang University · Zhejiang University · School of Medicine, Zhejiang University

Latent-Space Regularization Cancer Survival Prediction Multimodal Survival Analysis Variational Autoencoders

Open paper AskPDF arXiv

Multimodal variational autoencoders (VAEs) have emerged as a powerful framework for survival risk modeling in multiple myeloma by integrating heterogeneous omics and clinical data. However, when trained under survival supervision, standard latent regularization strategies often fail to preserve prognostically relevant variation, leading to unstable or overly constrained representations. Despite numerous proposed variants, it remains unclear which aspects of latent design fundamentally govern performance in this setting. In this work, we conduct a controlled investigation of latent modeling choices for multimodal survival prediction within a unified extension of the MyeVAE framework. By systematically isolating regularization scale, posterior geometry, and latent space structure under identical architectures and optimization protocols, we show that survival-driven training is primarily sensitive to the magnitude and structure of latent regularization rather than the specific divergence formulation. In particular, moderate relaxation of KL regularization consistently improves survival discrimination, while alternative divergence mechanisms such as MMD and HSIC provide limited benefit without appropriate scaling. We further demonstrate that structuring the latent space can improve alignment between learned representations and survival risk gradients. A hybrid continuous--discrete formulation based on Gumbel--Softmax enhances global risk ordering in the continuous latent subspace, even though stable discrete subtype discovery does not emerge under survival supervision. Guided by these findings, we instantiate a robust multimodal survival model, termed MO-RiskVAE, which consistently improves risk stratification over the original MyeVAE without introducing additional supervision or complex training heuristics.