Autoencoders

Follow this topic Ask about this topic

Autoencoders learn a compact or structured latent representation by encoding data and training a decoder to reconstruct it, supporting dimensionality reduction, compression, and feature learning without labels. Common approaches include convolutional, recurrent, and transformer autoencoders; variational and sparse variants; and models with geometric, physical, or domain-specific constraints. They are used on images, audio and video, scientific simulations, medical data, and industrial time series, with evaluation ranging from reconstruction and compression to anomaly detection and downstream prediction. A central tension is that latents optimized for faithful reconstruction are not always useful for generation, interpretation, or stable long-horizon prediction, so current work increasingly evaluates and shapes representations for their intended downstream use.

Latest papers

155 papers23 papers in the last four weeks, up 64% on the four weeks before. 0.1% of all new papers.

Entropic Auto-Encoding via Implicit Free-Energy Minimization
May 15, 2026Hazhir Aliahmadi, Irina Babayan, Greg van AndersVariational Autoencoders Posterior Collapse
Department of Physics, Engineering Physics & Astronomy, Queen’s University, Kingston, ON, Canada
Product-Aware Deep Autoencoders for Robust Process Monitoring in Multi-Product Cyber-Physical Systems
May 13, 2026MD Shafikul Islam, Jordan CardenCyber-Physical Systems Autoencoders
Qwen-Image-VAE-2.0 Technical Report
May 13, 2026Zekai Zhang, Deqing Li, Kuan Cao +27Variational Autoencoders Learned Image Compression
Qwen Team
Bin Latent Transformer (BiLT): A shift-invariant autoencoder for calibration-free spectral unmixing of turbid media
May 12, 2026Martin HohmannSpectral Unmixing Autoencoders
Institute of Photonic Technologies (LPT), Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Konrad-Zuse-Straße 3/5, 91052 Erlangen, Germany
Beyond the Last Layer: Multi-Layer Representation Fusion for Visual Tokenization
May 11, 2026Xuanyu Zhu, Yan Bai, Yang Shi +4Autoencoders Visual Tokenization
Peking University · Meituan Inc · Tsinghua University +1
SMIXAE: Towards Unsupervised Manifold Discovery in Language Models
May 9, 2026Collin FrancelAutoencoders LLM Interpretability
Department of Arts and Sciences, University of Alabama, Tuscaloosa, AL, United States.
Transformer autoencoder with local attention for sparse and irregular time series with application on risk estimation
May 9, 2026Panteleimon RodisIrregular Time-Series Modeling Autoencoders
University of Macedonia, Greece
Bilinear autoencoders find interpretable manifolds
May 9, 2026Thomas Dooms, Ward Gauderis, Geraint Wiggins +1Neural Representation Geometry Autoencoders
University of Antwerp · Vrije Universiteit Brussel · University of Antwerp, sqIRL
What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion
May 8, 2026Zhengrong Yue, Taihang Hu, Mengting Chen +8Latent Diffusion Models Autoencoders
Shanghai Jiao Tong University · Alibaba Group · Beihang University +4
ViTok-v2: Scaling Native Resolution Auto-Encoders to 5 Billion Parameters
May 6, 2026Philippe Hansen-Estruch, Jiahui Chen, Vivek Ramanujan +9Image Tokenization Autoencoders
University of Texas, Austin · University of Washington · 3Stanford University +3
Attention-Based Chaotic Self-Supervision for Medical Image Classification
May 6, 2026Joao Batista Florindo, Amanda Pontes de Oliveira OrnelasDenoising Autoencoders Self-Supervised Pre-Training
Institute of Mathematics, Statistics and Scientific Computing - University of Campinas, Rua S´ergio Buarque de Holanda, 651, Campinas, Brasil
Capabilities of Auto-encoders and Principal Component Analysis of the Reduction of Microstructural Images; Application on the Acceleration of Phase-Field Simulations
May 5, 2026Seifallah Fetni, Thinh Quy Duc Pham, Truong Vinh Hoang +4Neural Surrogate Modeling Autoencoders
University of Liège, UEE Research Unit, MSM division, allée de la Découverte, 9 B52/3, B 4000 Liège, Belgium · Chair of Mathematics for Uncertainty Quantification, RWTH-Aachen University, 52056 Aachen, Germany · Institute of Strategy Development, Thu Dau Mot University, 75100 Binh Duong Province, Viet Nam
Enhancing AI-Based ECG Delineation with Deep Learning Denoising Techniques
May 4, 2026Jeff Breeding-Allison, Emil WalleserAutoencoders Electrocardiography
1Mars Petcare
Machine Learning Enhanced Laser Spectroscopy for Multi-Species Gas Detection in Complex and Harsh Environments
May 2, 2026Mohamed SyDenoising Autoencoders Autoencoders
King Abdullah University of Science and Technology Thuwal, Kingdom of Saudi Arabia
Focus on What Matters: Two-Stage ROI-Aware Refinement for Anatomy-Preserving Fetal Ultrasound Reconstruction
Apr 26, 2026Ines Abbes, Mahmood Alzubaidi, Mowafa Househ +3Autoencoders Image Reconstruction
College of Science and Engineering, Hamad Bin Khalifa University, Doha, Qatar · Sidra Medicine, Doha, Qatar
Geometric regularization of autoencoders via observed stochastic dynamics
Apr 17, 2026Sean Hill, Felix X. -F. YeLatent Dynamics Modeling Autoencoders
Department of Mathematics and Statistics, University at Albany, SUNY
Unsupervised Anomaly Detection in Process-Complex Industrial Time Series: A Real-World Case Study
Apr 15, 2026Sergej Krasnikov, Lukas Meitz, Samineh Bagheri +3Time-Series Anomaly Detection Industrial Anomaly Detection
Universität Augsburg Augsburg, Germany · Technische Hochschule Augsburg Augsburg, Germany · Independent Researcher Karlsruhe, Germany
Domain-Specific Latent Representations Improve the Fidelity of Diffusion-Based Medical Image Super-Resolution
Apr 14, 2026Sebastian Cajas, Ashaba Judith, Rahul Gorijavolu +8Medical Image Super-Resolution Diffusion Models for Image Restoration
MIT Critical Data, Massachusetts Institute of Technology, Cambridge, MA, USA. · Department of Biomedical Engineering, Mbarara University of Science and Technology, Uganda. · School of Medicine, Johns Hopkins University, Baltimore, MD, USA. +10
TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders
Apr 8, 2026Teng Li, Ziyuan Huang, Cong Chen +5Autoencoders Visual Token Compression
Inclusion AI, Ant Group · HKUST · ZJU +2
Bi-Lipschitz Autoencoder With Injectivity Guarantee
Apr 8, 2026Qipeng Zhan, Zhuoping Zhou, Zexuan Wang +2Autoencoders Representation Learning
University of Pennsylvania
Quantum-Inspired Tensor Network Autoencoders for Anomaly Detection: A MERA-Based Approach
Apr 8, 2026Emre Gurkanli, Michael SpannowskyAnomaly Detection Autoencoders
Department of Physics, Sinop University, Turkiye · Institute for Theoretical Physics, Campus Süd, Karlsruhe Institute of Technology (KIT), D-76128 Karlsruhe, Germany · Institute for Quantum Materials and Technologies, Karlsruhe Institute of Technology, Karlsruhe 76131, Germany
A Robust SINDy Autoencoder for Noisy Dynamical System Identification
Apr 6, 2026Kairui DingNonlinear System Identification System Identification
Department of Mathematics, Columbia University
A Logical-Rule Autoencoder for Interpretable Recommendations
Apr 5, 2026Jinhao Pan, Bowen Wei, Ziwei ZhuExplainable Recommendation Collaborative Filtering
Department of Computer Science, George Mason University, Fairfax, Virginia, USA
Autoencoder-Based Parameter Estimation for Superposed Multi-Component Damped Sinusoidal Signals
Apr 5, 2026Momoka Iida, Hayato Motohashi, Hirotaka TakahashiParameter Estimation Autoencoders
Graduate School of Integrative Science and Engineering, Tokyo City University, 1-28-1 Tamazutsumi, Setagaya-ku, Tokyo 158-8557, Japan · Research Center for Space Science, Advanced Research Laboratories, Tokyo City University, 1-28-1 Tamazutsumi, Setagaya-ku, Tokyo 158-8557, Japan · Department of Physics, Graduate School of Science, Tokyo Metropolitan University, 1-1 Minami-Osawa, Hachioji, Tokyo 192-0397, Japan +2
Improving Feasibility via Fast Autoencoder-Based Projections
Apr 3, 2026Maria Chzhen, Priya L. DontiConstrained Optimization Constrained RL
University of Toronto Toronto, ON, Canada · Massachusetts Institute of Technology Cambridge, MA, USA
Rare-Aware Autoencoding: Reconstructing Spatially Imbalanced Data
Apr 2, 2026Alejandro Castañeda Garcia, Jan van Gemert, Daan Brinks +1Autoencoders Image Reconstruction
Delft University of Technology (TU Delft), Delft, The Netherlands
RAE-AR: Taming Autoregressive Models with Representation Autoencoders
Apr 2, 2026Hu Yu, Hang Xu, Jie Huang +4Exposure Bias Autoregressive Image Generation
University of Science and Technology of China · JD Explore Academy · The University of Hong Kong
TopoMesh: High-Fidelity Mesh Autoencoding via Topological Unification
Mar 25, 2026Guan Luo, Xiu Li, Rui Chen +6Autoencoders Variational Autoencoders
Tsinghua University · ByteDance Seed · HKUST
End-to-End Training for Unified Tokenization and Latent Denoising
Mar 23, 2026Shivam Duggal, Xingjian Bai, Zongze Wu +5Latent Diffusion Models Image Generation
Massachusetts Institute of Technology · Adobe
Data-driven discovery of roughness descriptors for surface characterization and intimate contact modeling of unidirectional composite tapes
Mar 20, 2026Sebastian Rodriguez, Mikhael Tannous, Jad Mounayer +3Manufacturing Autoencoders
Univ Toulouse, IMT Mines Albi, INSA Toulouse, ISAE-SUPAERO, CNRS, ICA, Albi, France

May 15, 2026J/K move · Enter open · S save

Entropic Auto-Encoding via Implicit Free-Energy Minimization

Hazhir Aliahmadi, Irina Babayan, Greg van Anders

Department of Physics, Engineering Physics & Astronomy, Queen’s University, Kingston, ON, Canada

Variational Autoencoders Posterior Collapse Autoencoders Entropy Regularization

Open paper AskPDF arXiv

Despite their ubiquity, variational autoencoders (VAEs) inherently suffer from posterior collapse, a failure mode in which latent variables are effectively ignored. This failure arises because explicit prior imposition drives optimization toward loss landscape regions corresponding to uninformative latent representations. Here, we introduce Entropic Autoencoders (EAEs), a framework in which reconstruction loss is the only explicit objective, and entropy generates the latent variables' prior implicitly through a free energy-minimizing ensemble of encoders. This ensemble biases learning toward high-volume regions of near-optimal solutions, while decoder updates direct the search trajectories toward informative latent representations. We demonstrate that EAEs mitigate posterior collapse by learning non-Gaussian, multimodal latent distributions that yield diverse, data-consistent generations and preserve different forms of underlying structure in the data. As a proof-of-concept, we show that an EAE captures a superposition of the known low-dimensional dynamics of a reaction-diffusion process. Then, we show that an EAE identifies implicit categorical distinctions in MNIST latent representations, and displays a hierarchical understanding of facial structure on the CelebA dataset, from an "all-human" face to individual-dependent features.