Autoencoder

Follow this topic Ask about this topic

Recent momentum

-64%

9 papers in the last 28 days · 0.2% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-14

1 new paper

A weekly snapshot of new work published in Autoencoder.

Period ending 2026-09-07

5 new papers

A weekly snapshot of new work published in Autoencoder.

184 papers

Latest in Autoencoder

Open your feed →

Are Sparse Autoencoder Benchmarks Reliable?
May 18, 2026David ChaninSparse Autoencoders Autoencoder
UTOPYA: A Multimodal Deep Learning Framework for Physics-Informed Anomaly Detection and Time-Series Prediction
May 18, 2026Robson W. S. Pessoa, Julien Amblard, Alessandra Russo +1Anomaly Detection Graph Anomaly Detection
Taming Audio VAEs via Target-KL Regularization
May 16, 2026Prem Seetharaman, Rithesh KumarVariational Autoencoder Latent Autoregressive Diffusion
Entropic Auto-Encoding via Implicit Free-Energy Minimization
May 15, 2026Hazhir Aliahmadi, Irina Babayan, Greg van AndersVariational Encoder Autoencoder
Seeking the Unfamiliar but Memorable: Conceptual Creativity as Meta-Learning
May 15, 2026Mengye RenCreativity Generative Models
Sparse Autoencoders enable Robust and Interpretable Fine-tuning of CLIP models
May 15, 2026Fabian Morelli, Arnas Uselis, Ankit Sonthalia +1Pre-Trained Vision-Language Models Contrastive Language-Image Pre-Training
Tadpole: Autoencoders as Foundation Models for 3D PDEs with Online Learning
May 14, 2026Qiang Liu, Felix Koehler, Benjamin Holzschuh +1Neural Partial Differential Equation Solvers Autoencoder
Product-Aware Deep Autoencoders for Robust Process Monitoring in Multi-Product Cyber-Physical Systems
May 13, 2026MD Shafikul Islam, Jordan CardenMultimodal Industrial Anomaly Detection Cyber-Physical System
Network-Aware Bilinear Tokenization for Brain Functional Connectivity Representation Learning
May 13, 2026Leo Milecki, Qingyu Hu, Bahram Jafrasteh +2Functional Networks 3D Masked Autoencoders
Masked Autoencoders with Limited Data: Does It Work? A Fine-Grained Bioacoustics Case Study
May 13, 2026Wuao Liu, Mustafa Chasmai, Subhransu Maji +1Acoustic Sensing 3D Masked Autoencoders
Rigel3D: Rig-aware Latents for Animation-Ready 3D Asset Generation
May 13, 2026Nikitas Chatzis, Marios Loizou, Evangelos Kalogerakis3D Assets Skeleton
Domain Restriction via Multi SAE Layer Transitions
May 12, 2026Elias Shaheen, Avi MendelsonDomain-Specific Language Sparse Autoencoders
Bin Latent Transformer (BiLT): A shift-invariant autoencoder for calibration-free spectral unmixing of turbid media
May 12, 2026Martin HohmannSpectra Autoencoder
The Evaluation Differential: When Frontier AI Models Recognise They Are Being Tested
May 12, 2026Varad Vishwarupe, Nigel Shadbolt, Marina Jirotka +1Artificial Intelligence Evaluation Artificial Intelligence Safety
Beyond the Last Layer: Multi-Layer Representation Fusion for Visual Tokenization
May 11, 2026Xuanyu Zhu, Yan Bai, Yang Shi +4Vision Encoders Autoencoder
On Problems of Implicit Context Compression for Software Engineering Agents
May 11, 2026Kirill Gelvan, Igor Slinko, Felix Steinbauer +3Context Length Software Engineering
DiffATS: Diffusion in Aligned Tensor Space
May 10, 2026Jinhua Lyu, Tianmin Yu, Brian Kim +3Tensor Diffusion Models
Transformer autoencoder with local attention for sparse and irregular time series with application on risk estimation
May 9, 2026Panteleimon RodisTime-Series Anomaly Detection Time Series
Bilinear autoencoders find interpretable manifolds
May 9, 2026Thomas Dooms, Ward Gauderis, Geraint Wiggins +1Sparse Autoencoders Autoencoder
Tree SAE: Learning Hierarchical Feature Structures in Sparse Autoencoders
May 8, 2026Tue M. Cao, Hoang X. Nhat, Raed Alharbi +2Improving Sparse Autoencoders Sparse Autoencoders
What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion
May 8, 2026Zhengrong Yue, Taihang Hu, Mengting Chen +8Latent Diffusion Model Diffusion Models
Estimation of Motor Unit Parameters from Surface Electromyograms using an Informed Autoencoder
May 8, 2026Kaja Balzereit, Malte Mechtenberg, Axel SchneiderSurface Electromyography Autoencoder
FastOmniTMAE: Parallel Clause Learning for Scalable and Hardware-Efficient Tsetlin Embeddings
May 7, 2026Ahmed K. Kadhim, Lei Jiao, Rishad Shafik +2Field-Programmable Gate Arrays Autoencoder
Medical Imaging Classification with Cold-Atom Reservoir Computing using Auto-Encoders and Surrogate-Driven Training
May 7, 2026Nuno Batista, Ana Morgado, Oscar Ferraz +3Quantum Neural Networks Medical Imaging
When Semantic Communication Meets Queueing: Cross-Layer Latency and Task Fidelity Optimization
May 6, 2026Yalin E. Sagduyu, Tugba ErpekSemantic Communications Wireless Resource Allocation
Feature Starvation as Geometric Instability in Sparse Autoencoders
May 6, 2026Faris Chaudhry, Keisuke Yano, Anthea MonodSparse Autoencoders Autoencoder
ViTok-v2: Scaling Native Resolution Auto-Encoders to 5 Billion Parameters
May 6, 2026Philippe Hansen-Estruch, Jiahui Chen, Vivek Ramanujan +9Vision Transformer Autoregressive Image Generation
Taming Outlier Tokens in Diffusion Transformers
May 6, 2026Xiaoyu Wu, Yifei Wang, Tsu-Jui Fu +3Diffusion Transformers Vision Transformer
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 +4Autoencoder Porous Media
Conditional Neural Field based Reduced Order Model for Dynamic Ditching Load Prediction
May 5, 2026Henning Schwarz, Pyei Phyo Lin, Jens-Peter M. Zemke +1Computational Fluid Dynamic Neural Fields
Enhancing AI-Based ECG Delineation with Deep Learning Denoising Techniques
May 4, 2026Jeff Breeding-Allison, Emil WalleserElectrocardiogram Autoencoder
Distributed Deep Variational Approach for Privacy-preserving Data Release
May 4, 2026Zahir Alsulaimawi, Huaping LiuDistributional Learning Variational Inference
Benchmarking Wireless Representations: High-Dimensional vs. Compressed Embeddings for Efficiency and Robustness
May 3, 2026Murilo Batista, Shirin Salehi, Saeed Mashdour +3Wireless Networks Convolutional Neural Network Compression
Learning Fingerprints for Medical Time Series with Redundancy-Constrained Information Maximization
Apr 30, 2026Huayu Li, ZhengXiao He, Xiwen Chen +4Representation Learning Autoencoder
Toward Scalable SDN for LEO Mega-Constellations: A Graph Learning Approach
Apr 30, 2026Sivaram Krishnan, Bassel Al Homssi, Zhouyou Gu +3Low Earth Orbit Software-Defined Networking
A Gated Hybrid Contrastive Collaborative Filtering Recommendation
Apr 29, 2026Eduardo Ferreira da Silva, Mayki dos Santos Oliveira, Joel Machado Pires +6Collaborative Filtering Recommendation
Progressive Semantic Communication for Efficient Edge-Cloud Vision-Language Models
Apr 29, 2026Cyril Shih-Huan Hsu, Wig Yuan-Cheng Cheng, Chrysa PapagianniRecent Vision-Language Models Vision-Language Reasoning
Sample Selection Using Multi-Task Autoencoders in Federated Learning with Non-IID Data
Apr 28, 2026Emre Ardıç, Yakup GençAutoencoder
Latent Inter-Frame Pruning: A Training-Free Method Bridging Traditional Video Compression and Modern Diffusion Transformers for Efficient Generation
Apr 26, 2026Dennis Menn, Chih-Hsien ChouVideo Diffusion Models Ultra-Low Bitrates
Domain-Filtered Knowledge Graphs from Sparse Autoencoder Features
Apr 26, 2026John Winnicki, Abeynaya Gnanasekaran, Eric DarveKnowledge Graphs Domain-Specific Language
Forecasting Individual NetFlows using a Predictive Masked Graph Autoencoder
Apr 22, 2026Georgios Anyfantis, Pere Barlet-RosGraph Neural Networks Accurate Traffic Forecasting
MAE-Based Self-Supervised Pretraining for Data-Efficient Medical Image Segmentation Using nnFormer
Apr 22, 2026R. M. Krishna Sureddi, T. Satyanarayana Murthy, Nomula Varsha Reddy +2Medical Image Segmentation 3D Masked Autoencoders
Do Masked Autoencoders Improve Downhole Prediction? An Empirical Study on Real Well Drilling Data
Apr 21, 2026Aleksander Berezowski, Hassan Hassanzadeh, Gouri Ginde3D Masked Autoencoders Drilling Data
Disentangling Damage from Operational Variability: A Label-Free Self-Supervised Representation Learning Framework for Output-Only Structural Damage Identification
Apr 21, 2026Xudong Jian, Charikleia Stoura, Simon Scandella +1Structural Health Monitoring Vibration
Evolutionary fine tuning of quantized convolution-based deep learning models
Apr 19, 2026Marcin PietrońLow-Bit Quantization Quantization Effects
Physics-Informed Tracking (PIT)
Apr 18, 2026Emil Hovad, Allan Peter Engsig-KarupPhysics-Informed Deep Learning Multi-Object Tracking
Geometric regularization of autoencoders via observed stochastic dynamics
Apr 17, 2026Sean Hill, Felix X. -F. YeStochastic Dynamics Latent Cluster Geometry
Diffusion Autoencoder for Unsupervised Artifact Restoration in Handheld Fundus Images
Apr 17, 2026Mathumetha Palani, Kavya Puthumana, Ayantika Das +1Fundus Images Image Restoration
CLIMB: Controllable Longitudinal Brain Image Generation using Mamba-based Latent Diffusion Model and Gaussian-aligned Autoencoder
Apr 17, 2026Duy-Phuong Dao, Muhammad Taqiyuddin, Jahae Kim +4Conditional Latent Diffusion Latent Diffusion Model
Assessing the Potential of Masked Autoencoder Foundation Models in Predicting Downhole Metrics from Surface Drilling Data
Apr 16, 2026Aleksander Berezowski, Hassan Hassanzadeh, Gouri Ginde3D Masked Autoencoders Drilling Data
Beyond Independent Frames: Latent Attention Masked Autoencoders for Multi-View Echocardiography
Apr 16, 2026Simon Böhi, Irene Cannistraci, Sergio Muñoz Gonzalez +83D Masked Autoencoders Autoencoder
VAN-AD: Visual Masked Autoencoder with Normalizing Flow For Time Series Anomaly Detection
Mar 27, 2026PengYu Chen, Shang Wan, Xiaohou Shi +3Time-Series Anomaly Detection Unsupervised Detectors
A convolutional autoencoder and neural ODE surrogate modeling framework applied to transient counterflow flames
Mar 16, 2026Mert Yakup Baykan, Weitao Liu, Mohammad Rafi Malik +4Computational Fluid Dynamic Reduced-Order Models
Deep Invertible Autoencoders for Dimensionality Reduction of Dynamical Systems
Mar 13, 2026Nicolò Botteghi, Silke Glas, Christoph BruneReduced-Order Models Autoencoder
Spatial Autoregressive Modeling of DINOv3 Embeddings for Unsupervised Anomaly Detection
Mar 3, 2026Ertunc Erdil, Nico Schulthess, Guney Tombak +1Unsupervised Anomaly Detection Anomaly Detection
AFFMAE: Scalable Vision Pre-Training for High-Resolution Microscopy Segmentation on Desktop Hardware
Feb 18, 2026David Smerkous, Zian Wang, Behzad Najafian3D Masked Autoencoders Self-Supervised Vision Transformers
Variational Sparse Paired Autoencoders (vsPAIR) for Inverse Problems and Uncertainty Quantification
Feb 3, 2026Jack Michael Solomon, Rishi Leburu, Matthias ChungInverse Problem Uncertainty Quantification
FunPhase: A Periodic Functional Autoencoder for Motion Generation via Phase Manifolds
Dec 10, 2025Marco Pegoraro, Evan Atherton, Bruno Roy +2Human Motion Generation Autoencoder
Perceptually Aligning Representations of Music via Noise-Augmented Autoencoders
Nov 7, 2025Mathias Rose Bjare, Giorgia Cantisani, Marco Pasini +2Music Understanding Autoencoder
Occlusion-Aware 3D Hand-Object Pose Estimation with Masked AutoEncoders
Jun 12, 2025Hui Yang, Wei Sun, Jian Liu +33D Hand Autoencoder

May 18, 2026 · cs.LGJ/K move · Enter open · S save

Are Sparse Autoencoder Benchmarks Reliable?

David Chanin

Decode Research, MATS, UCL

Sparse autoencoders (SAEs) are a core interpretability tool for large language models, and progress on SAE architectures depends on benchmarks that reliably distinguish better SAEs from worse ones. We audit the SAE quality metrics in SAEBench, the de-facto standard SAE evaluation suite, through three complementary lenses: reseed noise on a fixed SAE, ground-truth correlation on synthetic SAEs, and discriminability across training trajectories. We find that two of these metrics, Targeted Probe Perturbation (TPP) and Spurious Correlation Removal (SCR), fail multiple lenses at their canonical settings and should not be used to evaluate SAEs. The other metrics show higher reseed noise and lower discriminability than the field assumes. The sae-probes variant of

k

-sparse probing is the most reliable metric we tested, but even sae-probes struggles to separate variants of the same SAE architecture. Our results show the field needs better SAE benchmarks.

Sparse Autoencoders Autoencoder Model Interpretability Methods

Open paper Ask about it PDF