Variational Autoencoders

ICLR 2025arXiv:2410.11758

#2

Latent Action Pretraining from Videos

Seonghyeon Ye, Joel Jang, Byeongguk Jeon et al.

vision-language-action modelsunsupervised pretrainingaction quantizationlatent action learning+4

168

ECCV 2024arXiv:2403.16292

#3

latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction

Christopher Wewer, Kevin Raj, Eddy Ilg et al.

3d reconstructionvariational gaussianslatent space representationsemantic gaussians+3

106

ICCV 2025arXiv:2504.10483

#4

REPA-E: Unlocking VAE for End-to-End Tuning of Latent Diffusion Transformers

Xingjian Leng, Jaskirat Singh, Yunzhong Hou et al.

latent diffusion modelsvariational auto-encoderend-to-end trainingrepresentation-alignment loss+3

85

ICML 2025arXiv:2410.13928

#5

Automatically Interpreting Millions of Features in Large Language Models

Gonçalo Paulo, Alex Mallen, Caden Juang et al.

61

ICML 2025arXiv:2502.03444

#6

Masked Autoencoders Are Effective Tokenizers for Diffusion Models

Hao Chen, Yujin Han, Fangyi Chen et al.

52

ICML 2025arXiv:2502.09509

#7

EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling

Theodoros Kouzelis, Ioannis Kakogeorgiou, Spyros Gidaris et al.

51

ICLR 2024arXiv:2310.02619

#8

Generative Modeling of Regular and Irregular Time Series Data via Koopman VAEs

Ilan Naiman, N. Benjamin Erichson, Pu Ren et al.

44

ICLR 2025arXiv:2502.04878

#9

Sparse Autoencoders Do Not Find Canonical Units of Analysis

Patrick Leask, Bart Bussmann, Michael Pearce et al.

sparse autoencodersmechanistic interpretabilityfeature decompositionsae stitching+4

41

ICML 2025arXiv:2502.14831

#10

Improving the Diffusability of Autoencoders

Ivan Skorokhodov, Sharath Girish, Benran Hu et al.

39

ICLR 2025arXiv:2410.06424

#11

Restructuring Vector Quantization with the Rotation Trick

Christopher Fifty, Ronald Junkins, Dennis Duan et al.

38

CVPR 2025arXiv:2411.17459

#12

WF-VAE: Enhancing Video VAE by Wavelet-Driven Energy Flow for Latent Video Diffusion Model

Zongjian Li, Bin Lin, Yang Ye et al.

34

NEURIPS 2025arXiv:2503.01822

#13

Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry

Sai Sumedh R. Hindupur, Ekdeep S Lubana, Thomas Fel et al.

34

ICLR 2025arXiv:2410.08201

#14

Efficient Dictionary Learning with Switch Sparse Autoencoders

Anish Mudide, Josh Engels, Eric Michaud et al.

30

CVPR 2025arXiv:2411.06449

#15

Improved Video VAE for Latent Video Diffusion Model

Pingyu Wu, Kai Zhu, Yu Liu et al.

video vaelatent video diffusiontemporal-spatial compressionkeyframe-based compression+4

20

NEURIPS 2025arXiv:2504.02821

#16

Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models

Mateusz Pach, Shyamgopal Karthik, Quentin Bouniot et al.

20

ICLR 2024arXiv:2401.12517

#17

DDMI: Domain-agnostic Latent Diffusion Models for Synthesizing High-Quality Implicit Neural Representations

Dogyun Park, Sihyeon Kim, Sojin Lee et al.

16

ICLR 2024arXiv:2310.19789

#18

DiffEnc: Variational Diffusion with a Learned Encoder

Beatrix M. G. Nielsen, Anders Christensen, Andrea Dittadi et al.

16

AAAI 2024arXiv:2312.07126

#19

Deep Hierarchical Video Compression

Ming Lu, Zhihao Duan, Fengqing Zhu et al.

15

CVPR 2025arXiv:2503.09419

#20

Alias-Free Latent Diffusion Models: Improving Fractional Shift Equivariance of Diffusion Latent Space

Yifan Zhou, Zeqi Xiao, Shuai Yang et al.

14

ICLR 2024arXiv:2310.03111

#21

Multi-modal Gaussian Process Variational Autoencoders for Neural and Behavioral Data

Rabia Gondur, Usama Bin Sikandar, Evan Schaffer et al.

14

COLM 2025arXiv:2504.11695

#22

Interpreting the linear structure of vision-language model embedding spaces

Isabel Papadimitriou, Huangyuan Su, Thomas Fel et al.

vision-language modelsinterpretabilitycross-modality meaning

14

ICML 2025arXiv:2502.01567

#23

Latent Thought Models with Variational Bayes Inference-Time Computation

Deqian Kong, Minglu Zhao, Dehong Xu et al.

13

ICML 2025arXiv:2410.04081

#24

Epsilon-VAE: Denoising as Visual Decoding

Long Zhao, Sanghyun Woo, Ziyu Wan et al.

13

ECCV 2024arXiv:2303.12001

#25

ViC-MAE: Self-Supervised Representation Learning from Images and Video with Contrastive Masked Autoencoders

Jefferson Hernandez, Ruben Villegas, Vicente Ordonez

masked autoencoderscontrastive learningrepresentation learningvideo classification+3

13

representation disentanglementdiffusion-based autoencoderlatent space navigationunsupervised learning+4

#26

Closed-Loop Unsupervised Representation Disentanglement with $\beta$-VAE Distillation and Diffusion Probabilistic Feedback

Xin Jin, Bohan Li, Baao Xie et al.

ECCV 2024

ICLR 2025arXiv:2409.00127

#27

Latent-EnSF: A Latent Ensemble Score Filter for High-Dimensional Data Assimilation with Sparse Observation Data

Phillip Si, Peng Chen

data assimilationensemble score filtersvariational autoencoderlatent representation learning+4

ICLR 2025arXiv:2303.15244

#28

Manifold Learning by Mixture Models of VAEs for Inverse Problems

Giovanni S. Alberti, Johannes Hertrich, Matteo Santacesaria et al.

manifold learningvariational autoencodersmixture modelsinverse problems+3

ICLR 2025arXiv:2410.01280

#29

Sparse Autoencoders Reveal Temporal Difference Learning in Large Language Models

Can Demircan, Tankred Saanum, Akshay Jagadish et al.

ICCV 2025arXiv:2501.11746

#30

SILO: Solving Inverse Problems with Latent Operators

Ron Raphaeli, Sean Man, Michael Elad

11

NEURIPS 2025arXiv:2506.15691

#31

What Do Latent Action Models Actually Learn?

Chuheng Zhang, Tim Pearce, Pushi Zhang et al.

latent action modelscontrollable changesexogenous noiseprincipal component analysis+4

11

ICLR 2025arXiv:2409.04185

#32

Residual Stream Analysis with Multi-Layer SAEs

Tim Lawson, Lucy Farnik, Conor Houghton et al.

sparse autoencoderstransformer language modelsresidual stream analysisinterpretability methods+4

11

AAAI 2024arXiv:2312.16983

#33

PG-LBO: Enhancing High-Dimensional Bayesian Optimization with Pseudo-Label and Gaussian Process Guidance

Taicai Chen, Yue Duan, Dong Li et al.

10

ICML 2024arXiv:2311.13664

#34

Sample as you Infer: Predictive Coding with Langevin Dynamics

Umais Zahid, Qinghai Guo, Zafeirios Fountas

predictive codinglangevin dynamicsgenerative model learningvariational inference+3

10

CVPR 2025arXiv:2412.17726

#35

VidTwin: Video VAE with Decoupled Structure and Dynamics

Yuchi Wang, Junliang Guo, Xinyi Xie et al.

9

ICLR 2024arXiv:2109.12679

#36

Be More Active! Understanding the Differences Between Mean and Sampled Representations of Variational Autoencoders

Lisa Bonheme, Marek Grzes

AAAI 2025arXiv:2409.09564

#37

TG-LLaVA: Text Guided LLaVA via Learnable Latent Embeddings

Dawei Yan, Pengcheng Li, Yang Li et al.

ICLR 2024arXiv:2306.05023

#38

Beyond Vanilla Variational Autoencoders: Detecting Posterior Collapse in Conditional and Hierarchical Variational Autoencoders

Hien Dang, Tho-Huu Tran, Tan Nguyen et al.

posterior collapsevariational autoencodersconditional vaehierarchical vae+3

ICML 2025arXiv:2507.03910

#39

Return of the Latent Space COWBOYS: Re-thinking the use of VAEs for Bayesian Optimisation of Structured Spaces

Henry Moss, Sebastian Ober, Tom Diethe

AAAI 2024arXiv:2312.11532

#40

Topic-VQ-VAE: Leveraging Latent Codebooks for Flexible Topic-Guided Document Generation

YoungJoon Yoo, Jongwon Choi

topic modelinglatent codebooksvector-quantized variational autoencoderdocument generation+4

7

NEURIPS 2025arXiv:2506.15679

#41

Dense SAE Latents Are Features, Not Bugs

Xiaoqing Sun, Alessandro Stolfo, Joshua Engels et al.

sparse autoencodersinterpretable featureslanguage modelsresidual stream analysis+4

7

ICLR 2024arXiv:2312.01133

#42

Robust Multimodal Survival Prediction with Conditional Latent Differentiation Variational AutoEncoder

Junjie Zhou, Jiao Tang, Yingli Zuo et al.

$t^3$-Variational Autoencoder: Learning Heavy-tailed Data with Student's t and Power Divergence

Juno Kim, Jaehyuk Kwon, Mincheol Cho et al.

7

data assimilationvariational autoencoderweather forecastingnon-gaussian distributions+3

#44

VAE-Var: Variational Autoencoder-Enhanced Variational Methods for Data Assimilation in Meteorology

Yi Xiao, Qilong Jia, Kun Chen et al.

ICLR 2025

ICLR 2025arXiv:2408.08558

#45

Linear combinations of latents in generative models: subspaces and beyond

Erik Bodin, Alexandru Stere, Dragos Margineantu et al.

latent variable manipulationgenerative model subspacesdiffusion modelsflow matching+4

ICCV 2025arXiv:2503.14325

#46

LeanVAE: An Ultra-Efficient Reconstruction VAE for Video Diffusion Models

Yu Cheng, Fajie Yuan

latent video diffusionvideo variational autoencodersvideo compressionwavelet transforms+4

ICML 2025arXiv:2411.13117

#47

Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders

Charles O'Neill, Alim Gumran, David Klindt

NEURIPS 2025arXiv:2503.15567

#48

Towards Unified and Lossless Latent Space for 3D Molecular Latent Diffusion Modeling

Yanchen Luo, ZHIYUAN LIU, Yi Zhao et al.

ICLR 2025arXiv:2502.11037

#49

Deep Incomplete Multi-view Learning via Cyclic Permutation of VAEs

Xin Gao, Jian Pu

ICML 2025arXiv:2502.18147

#50

Jacobian Sparse Autoencoders: Sparsify Computations, Not Just Activations

Lucy Farnik, Tim Lawson, Conor Houghton et al.

ICLR 2025arXiv:2503.00639

#51

Synergy Between Sufficient Changes and Sparse Mixing Procedure for Disentangled Representation Learning

Zijian Li, Shunxing Fan, Yujia Zheng et al.

ICML 2025arXiv:2505.23017

#52

$K^2$VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecasting

Xingjian Wu, Xiangfei Qiu, Hongfan Gao et al.

ICCV 2025arXiv:2507.09984

#53

Latent Diffusion Models with Masked AutoEncoders

Junho Lee, Jeongwoo Shin, Hyungwook Choi et al.

ICML 2025arXiv:2507.11789

#54

Enforcing Latent Euclidean Geometry in Single-Cell VAEs for Manifold Interpolation

Alessandro Palma, Sergei Rybakov, Leon Hetzel et al.

ECCV 2024arXiv:2409.12952

#55

The Gaussian Discriminant Variational Autoencoder (GdVAE): A Self-Explainable Model with Counterfactual Explanations

Anselm Haselhoff, Kevin Trelenberg, Fabian Küppers et al.

counterfactual explanationsvariational autoencodergaussian discriminant analysisself-explainable models+4

ICML 2024arXiv:2405.13910

#56

DR-VAE: Debiased and Representation-enhanced Variational Autoencoder for Collaborative Recommendation

Fan Wang, Chaochao Chen, Weiming Liu et al.

Learning Latent Space Hierarchical EBM Diffusion Models

Jiali Cui, Tian Han

energy-based modelslatent space hierarchyprior hole problemdiffusion probabilistic models+4

AAAI 2024arXiv:2312.16083

#58

A Variational Autoencoder for Neural Temporal Point Processes with Dynamic Latent Graphs

Sikun Yang, Hongyuan Zha

ICLR 2025arXiv:2502.01084

#59

Continuous Autoregressive Modeling with Stochastic Monotonic Alignment for Speech Synthesis

Weiwei Lin, Chenhang HE

NEURIPS 2025arXiv:2410.19315

#60

Brain-like Variational Inference

Hadi Vafaii, Dekel Galor, Jacob Yates

variational inferenceevidence lower boundvariational autoencoderspiking neural networks+4

AAAI 2025arXiv:2412.20487

#61

Multimodal Variational Autoencoder: A Barycentric View

Peijie Qiu, Wenhui Zhu, Sayantan Kumar et al.

multimodal representation learningvariational autoencodermissing modalitiesproduct of experts+4

ICLR 2025arXiv:2409.06142

#62

Variational Search Distributions

Dan Steinberg, Rafael Oliveira, Cheng Soon Ong et al.

variational inferenceactive generationcombinatorial designsequence design+3

ICLR 2025arXiv:2502.04730

#63

PhyloVAE: Unsupervised Learning of Phylogenetic Trees via Variational Autoencoders

Tianyu Xie, David Harry Tyensoung Richman, Jiansi Gao et al.

phylogenetic tree representationvariational autoencodersunsupervised learningtree topology generation+2

CVPR 2024arXiv:2403.17502

#64

SeNM-VAE: Semi-Supervised Noise Modeling with Hierarchical Variational Autoencoder

Dihan Zheng, Yihang Zou, Xiaowen Zhang et al.

semi-supervised noise modelingvariational autoencoderimage denoisingimage super-resolution+4

ICLR 2025arXiv:2410.10174

#65

High-Dimensional Bayesian Optimisation with Gaussian Process Prior Variational Autoencoders

Siddharth Ramchandran, Manuel Haussmann, Harri Lähdesmäki

Energy-Clibrated VAE with Test Time Free Lunch

Yihong Luo, Siya Qiu, Xingjian Tao et al.

Balanced Neural ODEs: nonlinear model order reduction and Koopman operator approximations

Julius Aka, Johannes Brunnemann, Jörg Eiden et al.

ICLR 2025arXiv:2502.19718

#68

Learning Mask Invariant Mutual Information for Masked Image Modeling

Tao Huang, Yanxiang Ma, Shan You et al.

masked image modelingmasked autoencodersself-supervised learninginformation bottleneck principle+3

ICML 2025arXiv:2501.19406

#69

Low-Rank Adapting Models for Sparse Autoencoders

Matthew Chen, Josh Engels, Max Tegmark

ICML 2024arXiv:2312.12616

#70

Online Variational Sequential Monte Carlo

Alessandro Mastrototaro, Jimmy Olsson

state-space modelsvariational inferencesequential monte carloonline learning+4

ICML 2025arXiv:2502.13757

#71

Identifying Metric Structures of Deep Latent Variable Models

Stas Syrota, Yevgen Zainchkovskyy, Johnny Xi et al.

ICML 2024arXiv:2311.03534

#72

PcLast: Discovering Plannable Continuous Latent States

ANURAG KOUL, Shivakanth Sujit, Shaoru Chen et al.

goal-conditioned planninglatent representation learningmulti-step inverse dynamicsstate reachability+3

AAAI 2024arXiv:2310.02744

#73

SALSA: Semantically-Aware Latent Space Autoencoder

Kathryn Kirchoff, Travis Maxfield, Alexander Tropsha et al.

molecular representation learningsmiles sequence processinggraph-to-graph similaritycontrastive learning+4

AAAI 2025arXiv:2412.14536

#74

Multi-Modal Latent Variables for Cross-Individual Primary Visual Cortex Modeling and Analysis

Yu Zhu, Bo Lei, Chunfeng Song et al.

ICLR 2024arXiv:2402.15710

#75

A Statistical Analysis of Wasserstein Autoencoders for Intrinsically Low-dimensional Data

Saptarshi Chakraborty, Peter Bartlett

ICCV 2025arXiv:2503.14530

#76

SAUCE: Selective Concept Unlearning in Vision-Language Models with Sparse Autoencoders

Jiahui Geng, Qing Li

ICML 2024arXiv:2406.07083

#77

Efficient Mixture Learning in Black-Box Variational Inference

Alexandra Hotti, Oskar Kviman, Ricky Molén et al.

black box variational inferencemixture variational distributionsevidence lower boundmultiple importance sampling vae+3

ICML 2024arXiv:2401.12588

#78

Interpreting Equivariant Representations

Andreas Abildtrup Hansen, Anna Calissano, Aasa Feragen

equivariant representationsinvariant projectionslatent representation analysispermutation equivariant vae+4

NEURIPS 2025arXiv:2509.02327

#79

Variational Uncertainty Decomposition for In-Context Learning

I. Shavindra Jayasekera, Jacob Si, Filippo Valdettaro et al.

in-context learninguncertainty decompositionbayesian uncertainty estimationepistemic uncertainty+4

ICLR 2025arXiv:2309.00380

#80

Learning multi-modal generative models with permutation-invariant encoders and tighter variational objectives

Marcel Hirt, Domenico Campolo, Victoria Leong et al.

ICCV 2025arXiv:2504.03501

#81

LV-MAE: Learning Long Video Representations through Masked-Embedding Autoencoders

Ilan Naiman, Emanuel Baruch Baruch, Oron Anschel et al.

AAAI 2025arXiv:2401.02739

#82

Community-Aware Variational Autoencoder for Continuous Dynamic Networks

Junwei Cheng, Chaobo He, Pengxing Feng et al.

Denoising Diffusion Variational Inference: Diffusion Models as Expressive Variational Posteriors

Wasu Top Piriyakulkij, Yingheng Wang, Volodymyr Kuleshov

diffusion modelsvariational inferencelatent variable modelsapproximate posteriors+4

NEURIPS 2025arXiv:2505.11029

#84

Exploiting the Asymmetric Uncertainty Structure of Pre-trained VLMs on the Unit Hypersphere

Li Ju, Max Andersson, Stina Fredriksson et al.

vision-language modelsuncertainty quantificationprobabilistic embeddingsunit hypersphere+3

ICCV 2025arXiv:2504.02817

#85

Efficient Autoregressive Shape Generation via Octree-Based Adaptive Tokenization

Kangle Deng, Hsueh-Ti Derek Liu, Yiheng Zhu et al.

ICML 2025arXiv:2506.14767

#86

A Variational Framework for Improving Naturalness in Generative Spoken Language Models

Li-Wei Chen, Takuya Higuchi, Zakaria Aldeneh et al.

ICLR 2025arXiv:2411.19556

#87

Differentiable Causal Discovery for Latent Hierarchical Causal Models

Parjanya Prashant, Ignavier Ng, Kun Zhang et al.

ICLR 2025arXiv:2506.00849

#88

Generalization in VAE and Diffusion Models: A Unified Information-Theoretic Analysis

Qi Chen, Jierui Zhu, Florian Shkurti

variational autoencodersdiffusion modelsinformation-theoretic analysisencoder generalization+3

ICCV 2025arXiv:2503.08737

#89

SSC-VAE: Structured Sparse Coding Based Variational Autoencoder for Detail Preserved Image Reconstruction

Hao Wang, Lu Wang, Zhongyu Wang et al.

Representing 3D Shapes With 64 Latent Vectors for 3D Diffusion Models

In Cho, Youngbeom Yoo, Subin Jeon et al.

variational autoencoder3d diffusion modelslatent space compressionpoint cloud encoding+3

ICML 2025arXiv:2505.01134

#91

Aggregation of Dependent Expert Distributions in Multimodal Variational Autoencoders

Rogelio A. Mancisidor, Robert Jenssen, Shujian Yu et al.

ICML 2024arXiv:2402.05758

#92

Latent variable model for high-dimensional point process with structured missingness

Maksim Sinelnikov, Manuel Haussmann, Harri Lähdesmäki

latent variable modelgaussian processesvariational autoencoderamortised variational inference+4

ICML 2025arXiv:2505.16481

#93

Neighbour-Driven Gaussian Process Variational Autoencoders for Scalable Structured Latent Modelling

Xinxing Shi, Xiaoyu Jiang, Mauricio Álvarez

ICML 2025arXiv:2506.04859

#94

Sparse Autoencoders, Again?

Yin Lu, Xuening Zhu, Tong He et al.

COLM 2025arXiv:2507.12990

#95

Teach Old SAEs New Domain Tricks with Boosting

Nikita Koriagin, Yaroslav Aksenov, Daniil Laptev et al.

LLMInterpretabilitySAE

NEURIPS 2025arXiv:2506.12903

#96

Variational Learning Finds Flatter Solutions at the Edge of Stability

Avrajit Ghosh, Bai Cong, Rio Yokota et al.

variational learningedge of stabilityimplicit regularizationflat solutions+3

NEURIPS 2025arXiv:2509.26074

#97

Limited Preference Data? Learning Better Reward Model with Latent Space Synthesis

Leitian Tao, Xuefeng Du, Sharon Li

NEURIPS 2025arXiv:2505.18427

#98

Learning Latent Variable Models via Jarzynski-adjusted Langevin Algorithm

James Cuin, Davide Carbone, O. Deniz Akyildiz

NEURIPS 2025arXiv:2512.12905

#99

PAC-Bayes Bounds for Multivariate Linear Regression and Linear Autoencoders

Ruixin Guo, Ruoming Jin, Xinyu Li et al.

pac-bayes boundsmultivariate linear regressionlinear autoencoderstheoretical generalizability+4

joint image-video tokenizationcausal variational autoencodervideo compression networkspatio-temporal downsampling+4

#100

High-Quality Joint Image and Video Tokenization with Causal VAE

Dawit Mureja Argaw, Xian Liu, Qinsheng Zhang et al.

ICLR 2025