Variational Autoencoders

Also known as VAE

Follow this topic Ask about this topic

Momentum

10 papers in the last four weeks, up 25% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 124

All topics

Smoothing Dark Areas in Molecular Latent Diffusion
Jun 11, 2026Xi Wang, Jiahan Li, Yuxuan Xia +3Variational Autoencoders Latent Diffusion Models
New York University · Stanford University
Hybrid Classical-Quantum Variational Autoencoder for Neural Topic Modeling
Jun 11, 2026Ivan KankeuVariational Autoencoders Topic Modeling
Generative Modeling of Bach-Style Symbolic Music: A Comparative Study of Autoregressive, Latent-Variable, and Adversarial Approaches
Jun 11, 2026Dezhi Yu, Kyuil Lee, Yongkang HuangVariational Autoencoders Latent Variable Models
Hölder++: Improving the Quality-Coherence Trade-off in Multimodal VAEs
Jun 11, 2026Huyen Vo, María Martínez-García, Isabel ValeraVariational Autoencoders Multi-View Consistency
Department of Computer Science, Saarland University, DE · MPI-SWS, Saarland Informatics Campus, DE.
DeepRHP: A Hybrid Variational Autoencoder for Designing Random Heteropolymers as Protein Mimics
Jun 10, 2026Shuni Li, Zhiyuan Ruan, Andy Shen +3Variational Autoencoders Protein Design
University of California Berkeley; Berkeley, California, 94720, USA.
SARA: A Dual-Stream VAE for High-Fidelity Speech Generation via Integrating Semantic and Acoustic Representations
Jun 10, 2026Peijie Chen, Wenhao Guan, Weijie Wu +7Variational Autoencoders Audio Representation Learning
School of Informatics, Xiamen University, China · School of Electronic Science and Engineering, Xiamen University, China · DiDi Global Inc., Beijing, China
Discovering and decoding latent mean-field structure with variational autoencoders
Jun 7, 2026Marco Biroli, Max Welling, Vincenzo VitelliVariational Autoencoders Mean-Field Theory
Department of Physics and the James Franck Institute, University of Chicago, Chicago, IL, USA · CuspAI, Cambridge, England · AMLab, University of Amsterdam, Amsterdam, Netherlands +1
Constructing VAE Latent Spaces with Prescribed Topology
Jun 5, 2026Jilles S. van Hulst, Jakub M. Tomczak, W. P. M. H. Heemels +1Variational Autoencoders Manifold Learning
Control Systems Technology Section, Department of Mechanical Engineering, Eindhoven University of Technology, 5600 MB Eindhoven, The Netherlands. · The research is carried out as part of the ITEA4 20216 ASIMOV project.
Real-Time Generation of Streamable Talking Portrait Video with Reference-Guided Deep Compression VAEs
Jun 1, 2026Sicheng Xu, Yu Deng, Shoukang Hu +5Variational Autoencoders Audio-Video Generation
1Microsoft Research · 2Microsoft AI
Wavelet-Fusion Diffusion Model for Multimodal Brain MRI Synthesis with Modality and Metadata Conditioning
May 30, 2026Muhammad Nabi Yasinzai, Remika Mito, Mangor PedersenVariational Autoencoders Latent Diffusion Models
Department of Psychology & Neuroscience, Auckland University of Technology, Auckland, New Zealand. · Department of Psychiatry, University of Melbourne, Melbourne, Victoria 3053, Australia. · Auckland University of Technology, Auckland, New Zealand.
How Neural Losses Shape VAE Latents
May 30, 2026Giorgio Strano, Luca Cerovaz, Michele Mancusi +2Variational Autoencoders Neural Representation Geometry
1Sapienza University of Rome · 2Paradigma, Inc. · 3Moises Systems, Inc. +1
MergeTok: Unified Continuous and Discrete Visual Tokenization via Token Merging
May 29, 2026Luyuan Zhang, Siyuan Li, Zedong Wang +7Variational Autoencoders Token Merging
1Tsinghua University · 2Westlake University · 3Zhejiang University +3
Foundation VAEs for 3D CT Reconstruction, Augmentation, and Generation
May 29, 2026Qi Chen, Shuhan Ding, Yu Gu +5Variational Autoencoders Medical Imaging Foundation Models
Department of Computer Science, Johns Hopkins University · 2Duke-NUS Medical School · 3Microsoft Research
The Little Book of Generative AI Foundations: An Intuitive Mathematical Primer
May 28, 2026Tianhua ChenVariational Autoencoders Generative Modeling
School of Computing and Engineering[cs.LG] University of Huddersfield
High-Dimensional Latents Should Be Diagnosed Through Phase Structure
May 23, 2026Alejandro Ascarate, Leo Lebrat, Rodrigo Santa Cruz +2Variational Autoencoders Autoencoders
School of Electrical Engineering and Robotics, Faculty of Engineering, Queensland University of Technology, Brisbane, Queensland, Australia
Commutator-Induced Uncertainty in VAEs
May 22, 2026Tahereh Dehdarirad, Michael Felsberg, Gabriel Eilertsen +1Variational Autoencoders Disentangled Representation Learning
Computer Vision and Learning Systems (CVL), Linköping University, Sweden · Department of Science and Technology, Linköping University, Sweden
Posterior Collapse as Automatic Spectral Pruning
May 21, 2026Johannes HirnVariational Autoencoders Posterior Collapse
1Image Processing Laboratory (IPL), Universitat de València, Paterna, València 46980, Spain∗
ChronoVAE-HOPE: Beyond Attention -- A Next-Generation VAE Foundation Model for Specialized Time Series Classification
May 21, 2026José Alberto Rodríguez, Luis Balderas, Miguel Lastra +2Variational Autoencoders Disentangled Representation Learning
Department of Computer Science and Artificial Intelligence DiCITS, iMUDS, DaSCI University of Granada, Granada, Spain 18071 · Advanced Medical Imaging Group, Instituto de Investigación Biosanitaria de Granada (ibs.Granada) · Department of Software Engineering DiCITS, iMUDS, DaSCI University of Granada, Granada, Spain 18071 +1
What Makes a Representation Good for Single-Cell Perturbation Prediction?
May 19, 2026Wenkang Jiang, Yuhang Liu, Yichao Cai +5Variational Autoencoders Disentangled Representation Learning
Australian Institute for Machine Learning, Adelaide University, Australia · Responsible AI Research Centre, Australia · College of Computer Science and Artificial Intelligence, Fudan University, China +3
Markov Chain Decoders Overcome the Heavy-Tail Limitations of Lipschitz Generative Models
May 18, 2026Abdelhakim Ziani, Andras Horvath, Paolo BallariniVariational Autoencoders Generative Modeling
Université Paris Saclay, Lab. MICS, CentraleSupélec, Gif-sur-Yvette, France · Università di Torino, Torino, Italy
A Simplex Witness Certificate and Escape Force for Constant Collapse in Variational Autoencoders
May 18, 2026Zegu Zhang, Jian ZhangVariational Autoencoders Representation Learning
Independent Researcher
Taming Audio VAEs via Target-KL Regularization
May 16, 2026Prem Seetharaman, Rithesh KumarVariational Autoencoders Text-to-Audio Generation
Adobe Research, San Francisco, CA
Isolating Nonlinear Independent Sources in fMRI with $β$ -TCVAE Models
May 15, 2026Qiang Li, Shujian Yu, Jesus Malo +3Variational Autoencoders Disentangled Representation Learning
1Tri-Institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS), Georgia State University, Georgia Institute of Technology, and Emory University, Atlanta, GA, USA · Department of Computer Science, Vrije Universiteit Amsterdam, Amsterdam, the Netherlands · 3Image Processing Laboratory, University of Valencia, Valencia, Spain +2
GraViti: Graph-Level Variational Autoencoders with Relaxed Permutation Invariance
May 15, 2026Roman Bresson, Konstantinos Divriotis, Johannes F. Lutzeyer +2Variational Autoencoders Molecular Graph Generation
Mohamed bin Zayed University of Artificial Intelligence · LIX, CNRS, École Polytechnique, IP Paris
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
Entropy-Based Characterisation of the Polarised Regime in Latent Variable Models
May 15, 2026Peter Clapham, Lisa Bonheme, Marek GrzesVariational Autoencoders Latent Variable Models
School of Computing, University of Kent, Canterbury, United Kingdom · International Agency for Research on Cancer (IARC/WHO), Genomic Epidemiology Branch, Lyon, France
GenAI for Energy-Efficient and Interference-Aware Compressed Sensing of GNSS Signals on a Google Edge TPU
May 14, 2026Thorben Wegner, Lucas Heublein, Tobias Feigl +3Variational Autoencoders Energy-Efficient ML
Fraunhofer Institute for Integrated Circuits IIS, 90411 Nürnberg, Germany · Friedrich-Alexander-Universität Erlangen-Nürnberg, 91058 Erlangen, Germany
Unsupervised learning of acquisition variability in structural connectomes via hybrid latent space modeling
May 13, 2026Gaurav Rudravaram, Lianrui Zuo, Karthik Ramadass +17Variational Autoencoders Latent Variable Models
Department of Electrical and Computer Engineering, Vanderbilt University, Nashville, TN, USA
Qwen-Image-VAE-2.0 Technical Report
May 13, 2026Zekai Zhang, Deqing Li, Kuan Cao +27Variational Autoencoders Learned Image Compression
Qwen Team
ArcVQ-VAE: A Spherical Vector Quantization Framework with ArcCosine Additive Margin
May 13, 2026Jaeyung Kim, YoungJoon YooVariational Autoencoders Image Generation
Department of Artificial Intelligence, Chung-Ang University, Seoul, Republic of Korea · SNUAILAB, Seoul, Republic of Korea

Jun 11, 2026, cs.LGJ/K move · Enter open · S save

Smoothing Dark Areas in Molecular Latent Diffusion

Xi Wang, Jiahan Li, Yuxuan Xia, Yingcheng Wu+2

New York University · Stanford University

Variational Autoencoders Latent Diffusion Models 3D Molecular Generation Molecular Generation Molecular Representation Learning

Open paper AskPDF arXiv

Latent diffusion is a promising framework for scalable 3D molecular generation, but it requires a latent space that remains smooth, valid, and navigable beyond posterior samples. Existing molecular VAEs, however, are typically learned through reconstruction-based objectives, which do not guarantee such a latent space. We show that this leads to dark areas: regions of latent space that are reachable during diffusion sampling but decode to disconnected or chemically invalid molecules. Unlike in image generation, molecular decoding requires strict structural and chemical precision, so even small latent perturbations can produce catastrophic failures. We therefore propose TopVAE, a topology-optimized VAE that reduces dark areas by making the decoder internalize structural and chemical constraints during training, eliminating the need for test-time chemical correction. TopVAE greatly improves off-posterior robustness, and when paired with a standard DiT, achieves

77\%

lower FCD-3D on QM9, the highest V&C,

52\%

lower FCD-3D on GEOM-Drugs, and

1.29{\times}

more stable and connected molecules on zero-shot scaffold inpainting.

Momentum

Related topics

Latest papers 124