Disentangled Representation Learning

Follow this topic Ask about this topic

Momentum

12 papers in the last four weeks, up 200% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 163

All topics

Soft-Constrained Optimization of Latent Space in Variational Autoencoders
Jul 26, 2026Ye ShiVariational Autoencoders Disentangled Representation Learning
Elmore Family School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, 47906 USA
Disentangling Multi-View Scanning in Mamba for Network Traffic Anomaly Detection
Jul 24, 2026Xinglin Lian, Chengtai Cao, Ting Zhong +1Mamba Disentangled Representation Learning
University of Electronic Science and Technology of China · Chengdu, Sichuan, China · City University of Hong Kong +1
Decafs: Disentangled Conditional adversarial Flows
Jul 21, 2026Anirudh jain, Sakshi Varshney, Samuel Kaski +1Disentangled Representation Learning Normalizing Flows
Orion Pharma · Aalto University, Finland · Aalto University +3
To Blend In, First Decouple: Rethinking Camouflage Image Generation via Context-Decoupled Representations
Jul 20, 2026Wenzhuang Wang, Yifan Zhao, Mingcan Ma +4Disentangled Representation Learning Conditional Image Generation
State Key Laboratory of Virtual Reality Technology and Systems, SCSE & QRI, Beihang University · Geely Automobile Research Institute (Ningbo) Co., Ltd, AI Center, Geely
Coordinated Disentanglement with Iterative Mode Discovery Under Hidden Correlations
Jul 19, 2026Rong Hu, Ling ChenDisentangled Representation Learning Latent Variable Models
State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China · College of Computer Science and Technology, Zhejiang University, Hangzhou, China
Contrastive-Augmented Flow Matching for Style-Content Disentanglement
Jul 14, 2026Yusong Li, Pingchuan Ma, Ming Gui +2Flow Matching Disentangled Representation Learning
Computer Vision & Learning Group at the University of Munich
Metadata Supervised Imaging Representations for Modelling and Controlling Acquisition Variability
Jul 13, 2026Mehmet Yigit Avci, Pedro Borges, Virginia Fernandez +5Disentangled Representation Learning Medical Image Analysis
School of Biomedical Engineering & Imaging Sciences, King’s College London, London, UK. · University College London, London, UK. · deepc GMBH, Munich, Germany.
SPORT: Structure-Aware Prototype Disentanglement for Incomplete Multi-View Clustering
Jul 11, 2026Yaoyuan Guo, Zhibin Gu, Songhe Feng +2Multi-View Consistency Disentangled Representation Learning
College of Computer and Cyberspace Security, Hebei Normal University, Shijiazhuang 050024, China · Department of Statistics and Data Science, Southern University of Science and Technology, Shenzhen 518055, China · Key Laboratory of Tibetan Information Processing, Ministry of Education, Qinghai Normal University, Xining 810008, China +2
Learn2Chat: Rethinking Dyadic Talking Heads via Interaction-Modulated Monologic Priors
Jul 11, 2026Zikai Huang, Siyue Chen, Xuemiao Xu +4Disentangled Representation Learning Human Motion Generation
School of Computer Science and Engineering, South China University of Technology, Guangdong, China · School of Design, South China University of Technology, Guangdong, China · Guangdong Engineering Center for Large Model and GenAI Technology +2
What Images Cannot Say: Language-Guided Olfactory Representation Learning
Jul 7, 2026Eleftherios Tsonis, Xi Wang, Vicky KalogeitonDisentangled Representation Learning Representation Learning
LIX, École Polytechnique, IP Paris, CNRS
Steering Optimisation Trajectories in Diffusion Representation Learning
Jul 6, 2026Rajat Rasal, Avinash Kori, Tian Xia +1Disentangled Representation Learning Representation Learning
Imperial College London
Pretraining Curricula Enable Selective Fine-tuning
Jul 6, 2026Sebastian A. Bruijns, Jirko Rubruck, Mia H. Whitefield +3Disentangled Representation Learning Fine-Tuning
University of Oxford · University of Oxford & Martian · Martian
CURE: Controllable Unified Image Restoration for Complex Degradations
Jul 3, 2026Boseong Kim, Donghyeon ChoDisentangled Representation Learning All-in-One Image Restoration
Department of Computer Science, Hanyang University, Seoul, South Korea
BrainFIBRE: A Foundation Model via Information Decomposition for Brain Microstructure
Jul 1, 2026Zijian Dong, Yi Lin, Ji Fang +3Disentangled Representation Learning Medical Imaging Foundation Models
National University of Singapore, Singapore
Beyond Cross-Reconstruction: Probing-Based Disentanglement Evaluation for Acoustic Teleportation Codecs
Jun 30, 2026Philipp Grundhuber, Emanuël A. P. HabetsDisentangled Representation Learning Neural Audio Codecs
Fraunhofer Institute for Integrated Circuits (IIS), Erlangen, Germany · International Audio Laboratories Erlangen∗, Erlangen, Germany
CMSL: Constructive Multi-Sequence Learning for Recommendation Systems
Jun 26, 2026Zikun Cui, Renzhi Wu, Junjie Yang +10Sequential Recommendation Disentangled Representation Learning
Meta MRS · Meta PyTorch · Meta FB Monetization
EMOSH: Expressive Motion and Shape Disentanglement for Human Animation
Jun 26, 2026Dongbin Zhang, Hao Liu, Binquan Dai +5Disentangled Representation Learning Human Motion Generation
1Tsinghua Shenzhen International Graduate School, Tsinghua University · 2WeChat Vision, Tencent Inc.
Disco-LoRA: Disentangled Composition of Content, Style, and Motion for Multi-concept Video Customization
Jun 25, 2026Xuancheng Xu, Gengyun Jia, Bing-Kun BaoDisentangled Representation Learning Video Diffusion Models
Nanjing University of Posts and Telecommunications · Hefei University of Technology · Peng Cheng Laboratory
CrossAccent-TTS: Cross-Lingual Accent-Intensity Controllable Text-to-Speech via Disentangled Speaker and Accent Representations
Jun 24, 2026Ram Annamdevula, Ankit Tatawat, Ashishkumar P. Gudmalwar +2Disentangled Representation Learning TTS Synthesis
Media Analysis, Sony Research India
Dual-Branch Cross-Projection Debiasing through Diffusion-based Disentanglement
Jun 23, 2026Xiangqian Zhao, Xinyang Jiang, Zhipeng Xu +5Disentangled Representation Learning Debiased ML
Xidian University · Shaanxi, China · Microsoft Research Asia +1
OrthoMotion:Disentangling Camera and Subject Motion via Geometry Semantics Orthogonal Attention
Jun 22, 2026Zijie MengCamera-Controlled Video Generation Disentangled Representation Learning
Peking University, China
AugCodec: A Low-Bitrate Disentangled Neural Speech Codec via Data Augmentation
Jun 20, 2026Dongmei Wang, Xiaohang Sun, Yang Liu +10Disentangled Representation Learning Audio Representation Learning
Amazon, USA
Unsupervised Disentanglement Without Compromises : How Functional Orthogonality Enforces Identifiability
Jun 19, 2026Mathieu Cyrille Simon, Pascal Frossard, Christophe De VleeschouwerUnsupervised Learning Disentangled Representation Learning
1UCLouvain, ICTEAM, Louvain-la-Neuve, Belgium · 2EPFL, LTS4 laboratory, Lausanne, Switzerland.
Dual-Channel Grounded World Modeling (DCGWM): Structural Prevention of Objective Interference Collapse via Heterogeneous External Grounding with Inward-Only Gradient Flow
Jun 17, 2026Akshay HazareDisentangled Representation Learning World Model Learning
Independent Researcher
Structured Representation Learning with Locally Linear Embeddings and Adaptive Feature Fusion
Jun 16, 2026Somjit Nath, Jackson J Cone, Derek Nowrouzezahrai +1Disentangled Representation Learning State Representation Learning
Department of Electrical and Computer Engineering McGill University Mila – Quebec AI Institute · Department of Psychology Department of Biomedical Engineering University of Calgary Canada Research Chair in Computational Behavioural Neuroscience (Tier II) · Department of Electrical and Software Engineering Schulich School of Engineering University of Calgary Mila – Quebec AI Institute Canada CIFAR AI Chair
Learning task-specific subspaces via interventional post-training of speech foundation models
Jun 16, 2026Jack Cox, Jon BarkerContrastive Learning Disentangled Representation Learning
University of Sheffield, United Kingdom
Joycent: Multi-Accent TTS via Disentangled Accent Modeling and Layer-Specific Conditioning
Jun 15, 2026Xintong Wang, Junchuan Zhao, Ye WangDisentangled Representation Learning TTS Synthesis
School of Computing, National University of Singapore, Singapore
Privacy-Preserving Text Sanitization for Distributed Agents Collaboration via Disentangled Representations
Jun 13, 2026Xuan Liu, Hefeng Zhou, Sicheng Chen +6Disentangled Representation Learning Privacy-Preserving ML
Shanghai Artificial Intelligence Laboratory
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.
DIMOS: Disentangling Instance-level Moving Object Segmentation
Jun 11, 2026Hongxiang Huang, Hongwei Ren, Xiaopeng Lin +3Event-Based Vision Disentangled Representation Learning
The Hong Kong University of Science and Technology (Guangzhou) Guangzhou, China

Jul 26, 2026, cs.LGJ/K move · Enter open · S save

Soft-Constrained Optimization of Latent Space in Variational Autoencoders

Ye Shi

Elmore Family School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, 47906 USA

Variational Autoencoders Disentangled Representation Learning Latent Space Optimization Entropy Regularization

Open paper AskPDF arXiv

The usefulness of a variational autoencoder (VAE) depends on two properties of its latent space that are hard to obtain together: high encoding capacity in the individual latent variables, and a low-dimensional, disentangled organization of those variables. Weakening the Kullback-Leibler regularization raises capacity but degrades disentanglement, while strengthening it prunes latent variables away entirely. We formulate VAE training as a soft-constrained optimization problem that addresses both. First, we impose an entropy-based constraint (EC) on individual latent variables, showing that the entropy of a latent code upper-bounds the mutual information it carries about the generative factors of the data. Second, we propose a weight-filter method that exploits the slack of the soft constraint to prune low-entropy dimensions during downstream training. On dSprites, the EC raises the aggregate latent-variable activation score by 43-62% over a vanilla VAE, attains the highest FactorVAE score among the \b{eta} \b{eta}-VAE variants (0.891 vs 0.847), and lowers reconstruction error by up to 38%. On MNIST, the weight filter reduces the latent dimensionality supplied to a downstream classifier from ten to two while holding accuracy above 90%, converging in 37% fewer epochs than the same procedure without the EC. We also find that low-entropy discrete factors tend to merge into a single latent variable, whereas high-entropy continuous factors are distributed across several.

Momentum

Related topics

Latest papers 163