Overview

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

CardsList

166 papers17 papers in the last four weeks, down 32% on the four weeks before. 0.1% of all new papers.

  1. The Rhythm of Generated Video: Latent Chunking Leaves Periodic Traces in Compressed Bitstreams

    Nov 17, 2026Chen Ye Gan, Bryan Zhen Zhang, Gene Wen +1Video ForensicsDeepfake Detection

  2. Evaluating and Improving Natural Language Autoencoders

    Nov 14, 2026Marco Bazzani, Dan MossingAutoencodersNeural Network Interpretability

  3. Physics-Constrained Autoencoder for Interpretable Health Representation Learning in Turbofan Engines

    Nov 10, 2026Leonardo Baldo, Jokin Alcibar Ibarzabal, Daniel Cisneros Acevedo +2AutoencodersPredictive Maintenance

  4. AudioCodex: Streaming Autoencoders for Live Audio

    Nov 9, 2026Marco Pasini, Javier Nistal, Cyran Aouameur +2Neural Audio CodecsAutoencoders

  5. Adapters as Data: The Latent Space of LoRAs

    Nov 5, 2026Moritz Grävinghoff, Konstantin Wehmeyer, Aron Asefaw +2Low-Rank AdaptationAutoencoders

  6. Design of Multi-UAV Cooperative Deep Semantic Autoencoders for Communication Networks

    Nov 5, 2026Xiaoling Han, Bin Lin, Nan Wu +1UAV CommunicationCommunication-Efficient Collaborative Perception

  7. Latent Terrain: Adapting Neural Audio Autoencoders as Design Materials in NIME

    Nov 4, 2026Shuoyang Jasper Zheng, Keigo Yoshida, Nico García-Peguinho +4AutoencodersAudio Generation

  8. Alternatives to Shallow Autoencoders for Collaborative Filtering

    Nov 4, 2026Mario Mallea, Angela Nebot, Francisco MugicaCollaborative FilteringRecommender Systems

  9. Self-Supervised Learning of Universal Latent Spaces for Operator Learning

    Nov 3, 2026Sepehr Mousavi, Levi Lingsch, Siddhartha Mishra +1PDE Operator LearningNeural Operators

  10. UniRA: Unified Representation Alignment and Auto-Encoding for Efficient Diffusion Generation

    Oct 29, 2026An Lanji, Dawei Liu, Jin Li +3Diffusion-Based Image GenerationDiffusion Models

  11. Detecting bus delays and service anomalies in Niterói with autoencoder latent feature representations

    Oct 26, 2026Matheus Germano, Claudio E. C. CampeloAnomaly DetectionFault Detection

  12. Discovering Topics from Linear Autoencoders

    Oct 26, 2026Jutiyakhun Srisoparp, Donlapark PonnopratRecommender SystemsExplainable Recommendation

  13. Principled Nonlinear Concept Erasure and Steering

    Oct 23, 2026Idan Simai, Shauli Ravfogel, Uri ShahamConcept ErasurePrivacy-Preserving Representation Learning

  14. Verbalizing Activation Differences with Natural Language Autoencoders

    Oct 22, 2026Andrea Blasi Núñez, Gianluca Barmina, Federico Torrielli +3LLM InterpretabilityAutoencoders

  15. Rethinking Video Autoencoders for Interactive World Models

    Oct 21, 2026Adrien Ramanana Rahary, Yutong Bai, Nicolas Dufour +2Video World ModelsAutoencoders

  16. Train to Stitch: Topology-Preserving Regularization for Interoperable Representations

    Oct 14, 2026Akshay Malhotra, Nicolas Zilberstein, Shahab Hamidi-RadModel StitchingLatent Space Alignment

  17. Spectral Considerations on Unsupervised Time-domain EEG Representation Learning with Deep Networks

    Oct 12, 2026David Aquilué-Llorens, Abel Puigseslloses, Angel Blanco +2Unsupervised Representation LearningAutoencoders

  18. VGGA: Geometry-Grounded Autoencoder for Video Generation

    Oct 12, 2026Chaofan Gan, Yian Zhao, Shijie Li +4Video GenerationAutoencoders

  19. scHFBiMamba: a bidirectional Mamba autoencoder for cardiac disease-state classification from single-nucleus RNA-seq data

    Oct 10, 2026Ugo Lomoio, Pietro Hiram Guzzi, Pierangelo VeltriAutoencodersSingle-Cell RNA Sequencing

  20. Decoding Register Tokens Preserves Global Scene Details

    Oct 9, 2026David Jacob Drexlin, Julius Hense, Jonas DippelVision TransformerImage Reconstruction

  21. Lossy Compressive Text Autoencoders

    Oct 7, 2026Vinko Sabolčec, Angelos Katharopoulos, David GrangierAutoencodersRepresentation Learning

  22. KGATE : a Knowledge Graph Embedding Training Environment

    Oct 7, 2026Benjamin Loire, Galadriel Brière, Célia Brahimi +2KG EmbeddingGraph Autoencoders

  23. Pooling Representation Autoencoders for Efficient Diffusion

    Oct 7, 2026Ramón Calvo-González, Youssef Saied, François FleuretAutoencodersDiffusion-Based Image Generation

  24. Broken scale symmetries in undercomplete linear autoencoders

    Oct 2, 2026Farhad Pashakhanloo, Jacob A. Zavatone-VethNeural Network Training DynamicsSymmetry Breaking

  25. Sphere Encoder 2

    Oct 1, 2026Kaiyu Yue, Sean McLeish, Ruchit Rawal +3AutoencodersImage Generation

  26. Rethinking Generative Image Compression at Extremely Low Bitrates

    Sep 30, 2026Tianyu Zhang, Zhaoyang Jia, Houqiang Li +1Learned Image CompressionAutoencoders