3D Masked Autoencoders

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 36

All topics

The hidden advantage of mask resampling: a theory of masked autoencoders
Oct 1, 2026Jorge Medina Moreira, Lorenzo Bardone, Lenka Zdeborová3D Masked Autoencoders Autoencoder Architectures
Statistical Physics of Computation Laboratory, École Polytechnique Fédérale de Lausanne (EPFL), CH-1015 Lausanne, Switzerland
Reading the Whole Heart: Latent-Attention Masked Autoencoders for Multimodal Cardiac Representation Learning
Sep 14, 2026Andrea Agostini, Simon Böhi, Moritz Vandenhirtz +7Electrocardiogram Foundation Models Cardiac
Department of Computer Science, ETH Zurich, Switzerland · Department of Biomedical Engineering, University of Basel, Switzerland
MANAS-2: Constrained Reconstruction for EEG Foundation Models
Sep 12, 2026Arvasu Kulkarni, Aditya Ray Mishra, Jeet Bandhu Lahiri +5Electroencephalography Foundation Models 3D Masked Autoencoders
Mannas AI · Indian Institute of Technology, Mandi
MEOX: Compact Multimodal Mixture-of-Experts for Earth Observation
Sep 4, 2026Mohanad AlbughdadiTrustworthy Earth Observation Decisions Earth Observation
European Centre for Medium-Range Weather Forecasts Bonn, Germany
Benchmarking Cyberattack Detection in Electric Vehicle Charging Infrastructure with Benign User Updates
Aug 11, 2026Hannan Chen, Roshni Anna Jacob, Jie ZhangElectric Vehicles Threat Detection
Department of Mechanical Engineering, The University of Texas at Dallas, Richardson, TX 75080, USA
ReMiX-MAE: Learning Missing-Channel Cross-Modal Representations from RGB-Only Clinical Facial Videos for Sympathetic-Mediated Pain Assessment
Aug 3, 2026Nan Bi, Taoyue Wang, Lijun Yin +13D Masked Autoencoders Facial Expression Recognition
School of Computing, Binghamton University, Binghamton, NY, USA · Department of Anesthesiology, SUNY Upstate Medical University, Syracuse, NY, USA
Understanding and Correcting Low-Frequency Bias in EEG Foundation Model
Aug 3, 2026Junjie Yu, Zihan Deng, Jianyu Zhang +8Electroencephalography Foundation Models Electroencephalography
Department of Biomedical Engineering, Southern University of Science and Technology, Shenzhen, China · Omni-Intelligence, Shenzhen, China · College of Design and Engineering, National University of Singapore, Singapore +4
Gradient-Based Latent Decomposition Reveals Mechanisms of Feature Degradation in Weakly Supervised Mammography
Jul 24, 2026Vinceline Bertrand, Ionut Cardei3D Masked Autoencoders Gradient-Weighted Class Activation Mapping
Florida Atlantic University, Boca Raton, FL, USA
A Masked Autoencoder Approach to Unsupervised Steel Surface Defect Recognition
Jul 14, 2026Shrey PatelDefect Detection 3D Masked Autoencoders
University of Maryland, College Park · United States of America
ProsMAE: Multi-Source MAE Pretraining for ISUP Grade Classification
Jul 9, 2026Anna Jung, Kyeonghun Kim, Youngung Han +6Computational Pathology 3D Masked Autoencoders
SNU · OUTTA · GIST +1
Lift3D-VLA: Lifting VLA Models to 3D Geometry and Dynamics-Aware Manipulation
Jul 7, 2026Jiaming Liu, Qingpo Wuwu, Nuowei Han +8Diffusion-Based Vision-Language-Actions 3D Geometry
State Key Laboratory of Multimedia Information Processing and National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China · CUHK, Shatin, Hong Kong · AI2Robotics, Beijing, China
Moonstone: A Multimodal Foundation Model and Benchmark for Lunar Remote Sensing
Jul 3, 2026Ayush Prasad, Swarnalee MazumderRemote Sensing Multimodal Foundation Model
Space and Earth Observation Centre, Finnish Meteorological Institute, Finland · Data Management, German Climate Computing Centre, Germany
MindAU: EEG-Conditioned Facial Action Unit Editing via Dual-Stream Manifold Alignment
Jul 1, 2026Zhenhang Li, Xin Zhou, Hao Deng +1Electroencephalography Decoding Facial Expression Recognition
Binghamton University · Massachusetts General Hospital
SAMBA: A Scatter-Guided Masked Bidirectional Mamba Foundation Model for SAR Target Recognition
Jun 30, 2026Ke Wang, Xiaoyi Pan, Zhaoyu Gu +43D Masked Autoencoders Mamba-Based Models
College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China
Mitigating Positional Leakage in 3D Masked Autoencoders for Robust Representation Learning
Jun 30, 2026Xu Yan, Huiqun Wang, Chen Wang +23D Masked Autoencoders Autoencoder Architectures
SKLCCSE, Beihang University, Beijing, China · SCSE, Beihang University, Beijing, China · NERCBDS, EIRI, Tsinghua University, Beijing, China +1
3D Masked Autoencoders are Robust Learners of Volumetric and Multimodal Cellular Representations for Microscopy
Jun 22, 2026Amirhossein Kardoost, Lion Gleiter, Tingying Peng +13D Masked Autoencoders Microscopy
Institute of AI for Health & Helmholtz AI, Computational Health Center, Helmholtz Munich – German Research Center for Environmental Health, Neuherberg, Germany · Munich Center for Machine Learning (MCML), Munich, Germany · Department of Medicine III, Ludwig-Maximilian-University Hospital, Munich, Germany +2
Contrastive and Adaptive Multi-modal Masked Autoencoder for Spatial Transcriptomics
Jun 19, 2026Joohyeok Kim, Taejin Jeong, Jinyeong Kim +1Spatial Transcriptomics 3D Masked Autoencoders
Department of Artificial Intelligence, Yonsei University, Seoul, Republic of Korea · Department of Computer Science, Yonsei University, Seoul, Republic of Korea · Yonsei University College of Medicine, Seoul, Republic of Korea
BrainG3N: A Dual-Purpose Tokenizer for Controllable 3D Brain MRI Generation
Jun 17, 2026Max Van Puyvelde, Ibrahim Gulluk, Wim Van Criekinge +1Functional Magnetic Resonance Imaging 3D Masked Autoencoders
Department of Biomedical Data Science, Stanford University School of Medicine · Department of Mathematical Modelling, Statistics & Bioinformatics, Ghent University · Department of Electrical Engineering, Stanford University
Exploring Adaptive Masked Reconstruction for Self-Supervised Skeleton-Based Action Recognition
Jun 9, 2026Shengkai Sun, Zhiyong Cheng, Zefan Zhang +3Skeleton-Based Action Recognition 3D Masked Autoencoders
1Hefei University of Technology · 2Jilin University · 3Zhejiang Gongshang University +1
Remembering by Reconstructing: Domain Incremental Learning With Test-Time Training on Video Streams
May 29, 2026Jonathan Swinnen, Tinne TuytelaarsClass-Incremental Learning Streaming Video
ESAT, KU Leuven, Leuven, Belgium
A multifractal-based masked auto-encoder: an application to medical images
May 25, 2026Joao Batista Florindo, Viviane de Moura3D Masked Autoencoders Medical Images
Institute of Mathematics, Statistics and Scientific Computing - University of Campinas, Rua Sérgio Buarque de Holanda, 651, Cidade Universitária ”Zeferino Vaz” - Distr. Barão Geraldo, CEP 13083-859, Campinas, SP, Brasil
Semantics-Guided Multimodal Masked Autoencoder Pretraining for 3D BEV Object Detection
May 24, 2026Prabuddhi Wariyapperuma, Rajitha de Silva, Marc Hanheide +23D Object Detection 3D Masked Autoencoders
University of Lincoln, Lincoln Centre for Autonomous Systems, Lincoln, UK. · University of Cambridge, Institute for Manufacturing, Department of Engineering, Cambridge, UK.
DARE-EEG: A Foundation Model for Mining Dual-Aligned Representation of EEG
May 18, 2026Yang Shao, Peiliang Gong, Qun Dai +1Electroencephalography Foundation Models Small-Sample Electroencephalogram Datasets
College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics Nanjing, Jiangsu, China
Masked Autoencoders with Limited Data: Does It Work? A Fine-Grained Bioacoustics Case Study
May 13, 2026Wuao Liu, Mustafa Chasmai, Subhransu Maji +1Passive Acoustic Monitoring 3D Masked Autoencoders
University of Massachusetts Amherst
Biosignal Fingerprinting: A Cross-Modal PPG-ECG Foundation Model
May 10, 2026Zhangdaihong Liu, Chang Liu, Fenglin Liu +4Electrocardiogram Foundation Models Cardiac
Department of Engineering Science, University of Oxford, Oxford OX3 7DQ, UK · Oxford Suzhou Centre for Advanced Research, Suzhou, 215123, China · School of Public Health, Shanghai Jiao Tong University, Shanghai, China
OphMAE: Bridging Volumetric and Planar Imaging with a Foundation Model for Adaptive Ophthalmological Diagnosis
May 4, 2026Tienyu Chang, Zhen Chen, Renjie Liang +9Ophthalmology Optical Coherence Tomography
Department of Biostatistics and Health Data Science, Indiana University, Indianapolis, IN · Department of Biomedical Informatics and Data Science, Yale University, New Haven, CT · Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hong Kong +5
Adaptive Texture-aware Masking for Self-Supervised Learning in 3D Dental CBCT Analysis
May 3, 2026Xinquan Yang, Jianfeng Ren, Xuguang Li +4Occlusal Constraint 3D Medical Image Segmentation
School of Artiﬁcial Intelligence, Shenzhen University, Shenzhen, China. · School of Computer Science, University of Notting-ham Ningbo China, Ningbo, China. · Department of Stomatology, Shenzhen University General Hospital, Shenzhen, China.
Rhamba: Region-Aware Hybrid Attention-Mamba Framework for Self-Supervised Learning in Resting-State fMRI
May 2, 2026Ruthwik Reddy Doodipala, Pankaj Pandey, Pratheek Eranki +3Functional Magnetic Resonance Imaging Mamba-Based Models
1St. Jude Children’s Research Hospital · 2The University of Memphis
Do Masked Autoencoders Improve Downhole Prediction? An Empirical Study on Real Well Drilling Data
Apr 21, 2026Aleksander Berezowski, Hassan Hassanzadeh, Gouri GindeDrilling Data 3D Masked Autoencoders
Schulich School of Engineering Department of Electrical and Software Engineering University of Calgary Calgary, Canada · Schulich School of Engineering Department of Chemical and Petroleum Engineering University of Calgary Calgary, Canada
Better with Less: Tackling Heterogeneous Multi-Modal Image Joint Pretraining via Conditioned and Degraded Masked Autoencoder
Apr 18, 2026Bowen Peng, Yongxiang Liu, Jie Zhou +4Multimodal Pretraining 3D Masked Autoencoders
College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha 410073, China · Beijing Institute of Remote Sensing Information, Beijing 100192, China
PolarMAE: Efficient Fetal Ultrasound Pre-training via Semantic Screening and Polar-Guided Masking
Apr 17, 2026Meng Lv, Yapeng Li, Hang Su +2Prenatal Ultrasound Ultrasound
Wuhan University
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
Schulich School of Engineering Department of Electrical and Software Engineering University of Calgary Calgary, Canada · Schulich School of Engineering Department of Chemical and Petroleum Engineering University of Calgary Calgary, Canada
Beyond Independent Frames: Latent Attention Masked Autoencoders for Multi-View Echocardiography
Apr 16, 2026Simon Böhi, Irene Cannistraci, Sergio Muñoz Gonzalez +83D Masked Autoencoders Autoencoder Architectures
Department of Biomedical Engineering, University of Basel, Switzerland · Department of Computer Science, ETH Zurich, Switzerland
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
Department of Laboratory Medicine & Pathology, University of Washington, Seattle WA, USA · Electrical Engineering & Computer Science, Oregon State University, Corvallis, OR, USA · Paul G. Allen School of Computer Science & Engineering, University of Washington, Seattle WA, USA
ECGFlowCMR: Pretraining with ECG-Generated Cine CMR Helps Cardiac Disease Classification and Phenotype Prediction
Jan 28, 2026Xiaocheng Fang, Zhengyao Ding, Guangkun Nie +9Cardiac Magnetic Resonance Imaging Cardiac
State Key Laboratory of General Artificial Intelligence, Peking University · School of Intelligence Science and Technology, Peking University, Beijing, China · Polytechnic Institute of Zhejiang University, Zhejiang University, Hangzhou, China +4
pyMEAL: A Multi-Encoder Augmentation-Aware-Learning Toolbox for Robust Medical Image Translation
May 30, 2025Abdul-mojeed Olabisi Ilyas, Adeleke Maradesa, Jamal Banzi +3Unpaired Image-To-Image Translation 3D Masked Autoencoders
Hong Kong Centre for Cerebro-Cardiovascular Health Engineering (COCHE), Hong Kong, China · Department of Informatics, Sokoine University of Agriculture, Chuo Kikuu Morogoro, Tanzania · Department of Diagnostic Radiology, The University of Hong Kong, Hong Kong, China +5

Oct 1, 2026, stat.MLJ/K move · Enter open · S save

The hidden advantage of mask resampling: a theory of masked autoencoders

Jorge Medina Moreira, Lorenzo Bardone, Lenka Zdeborová

Statistical Physics of Computation Laboratory, École Polytechnique Fédérale de Lausanne (EPFL), CH-1015 Lausanne, Switzerland

3D Masked Autoencoders Autoencoder Architectures Resampling Residual Learning Theory Diversity

Open paper AskPDF arXiv

Why can masked prediction learn useful representations that unmasked reconstruction misses? We study this question in a high-dimensional model of a masked autoencoder (MAE) trained on data with shared latent structure and heterogeneous noise. We prove that masked linear reconstruction can recover the latent feature at linear sample complexity in regimes where unmasked linear reconstruction, equivalent to PCA, fails. The analysis also quantifies the statistical advantage of mask resampling, an established ingredient of masked pretraining. By introducing a fixed collection of

K

masks per sample, we characterize its effect on feature recovery and downstream performance, identifying regimes where greater mask diversity lowers sample complexity. Guided by this prediction, we find that random cropping and flipping in standard image-training pipelines can obscure the advantage of mask resampling by renewing the prediction task even when the patch mask is fixed. Removing these transformations reveals a downstream advantage for dynamic over static masking in CNN autoencoders and vision transformers. A complementary BERT pilot finds benefits from greater mask diversity on downstream language tasks. Our results separate the benefit of the masked prediction objective from that of mask diversity, and show how a tractable theory can guide experiments that uncover advantages hidden by standard training practices.

Momentum

Related topics

Latest papers 36