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

DSReg: Provably Recovering Individual World Latents without Reconstruction
Oct 7, 2026Yujia Zheng, David Klindt, Randall Balestriero +1Representation Identifiability Latent World Models
University of Illinois Urbana-Champaign · Cold Spring Harbor Laboratory · Brown University +2
Learning Disentangled Representations with Quantum Variational Autoencoders
Oct 5, 2026Gaoyuan Wang, Jerry Tan, Mark GersteinVariational Autoencoders Disentangled Representation Learning
Program in Computational Biology and Bioinformatics, Yale University, New Haven, Connecticut 06520, USA · Department of Molecular Biophysics and Biochemistry, Yale University, New Haven, Connecticut 06520, USA · Department of Computer Science, Yale University, New Haven, Connecticut 06520, USA +2
Operational Abstractions of Neural Network Concepts via Topological Representations
Oct 4, 2026Mathieu Pont, Christoph GarthDisentangled Representation Learning Model Editing
RPTU Kaiserslautern-Landau RPTU Kaiserslautern-Landau Kaiserslautern, Germany
Towards Fast and Disentangled Counterfactuals for Visual Foundation Models
Oct 1, 2026Sidney Bender, Benedikt Kunz, Ahmed Zeid +3Disentangled Representation Learning Counterfactual Explanations
Berlin Institute for the Foundations of Learning and Data (BIFOLD), Berlin, Germany · Machine Learning Group, Technische Universität Berlin, Berlin, Germany
Values as Style: Disentangling Values from Semantics with One-Way Mixing for Low-Damage LLM Steering
Sep 30, 2026Jiale Dai, Hongcan Deng, Liuxian Ma +2Disentangled Representation Learning LLM Alignment
State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University · University of Chinese Academy of Sciences · College of Artificial Intelligence, Tsinghua University
SAGE: Salient Factor Discovery and Generation with Visual Foundation Representations
Sep 30, 2026Shuang Liang, Lejun Liao, Shiyuan Zhang +5Disentangled Representation Learning Conditional Image Generation
HKU · Boston College · University of Virginia +1
Reimagine Video Dynamics
Sep 29, 2026Yu Yuan, Yawen Lu, Guoxian Song +5Disentangled Representation Learning Video Editing
Adobe · Purdue University
Adversarial Consistency-Guided Representation Learning for Multi-view Clustering
Sep 28, 2026Yuchen Lin, Kunpeng Xu, Ying Fang +1Multi-View Consistency Adversarial Representation Learning
School of Computer and Cyber Security, Fujian Normal University, Fuzhou 350000, China · Digital Fujian Internet-of-Things Laboratory of Environmental Monitoring, Fujian Normal University, Fuzhou 350000, China · School of Computer Science, McGill University, Montreal H3A 2A7, Quebec, Canada
DRIFT: Disentangled Responsive-Invariant Flow Transport for Single-Cell Perturbation Prediction
Sep 28, 2026Mustapha Bounoua, Giulio Franzese, Pietro MichiardiDisentangled Representation Learning Conditional Flow Matching
Department of Data Science EURECOM, France
LRC-JEPA: Disentangling Dynamics and Residual Context for Efficient World Models
Sep 28, 2026Luzhe Huang, Lei Chu, Jingyi Liang +1Disentangled Representation Learning World Models for Robotics
Independent researcher
When Entanglement Lower-Bounds Disparity: Auditing and Repairing Demographic Fairness in Audio Understanding Models
Sep 23, 2026Kian Shamsaie, Iman ModarressiDisentangled Representation Learning Audio Representation Learning
People Make Things
Breaking Weather-Content Coupling: Type-Severity Guided Progressive Disentanglement for All-in-One Infrared Restoration
Sep 23, 2026Xinyao Wang, Lijun He, Zhihan Ren +1Disentangled Representation Learning All-in-One Image Restoration
Shaanxi Key Laboratory of Deep Space Exploration Intelligent Information Technology, School of Information and Communications Engineering, Xi’an Jiaotong University, Xi’an, 710049, Shaanxi, China
Untangling the Geometry and Speed for RF Sensing Spectrograms
Sep 22, 2026Mert Torun, Darius Cuenca, Yasamin MostofiDisentangled Representation Learning Physics-Informed ML
Department of Electrical and Computer Engineering, University of California, Santa Barbara
Certified Topological Interaction in Neural Representations: Class Disentanglement Is Mostly Pairwise
Sep 8, 2026Sushovan MajhiDisentangled Representation Learning Neural Representation Geometry
Data Science Program, George Washington University, Washington, D.C., USA.
SAUF-Net: Structure--Appearance Representation Learning with Uncertainty Feedback for Semi-Supervised Medical Image Segmentation
Sep 2, 2026Qin Lu, Zheyang Jing, Yujie Yang +3Semi-Supervised Medical Image Segmentation Consistency Regularization
Nanchang Hangkong University, Nanchang, China
PRISM: Predictive Recomposition via Semantic Latent Decomposition for View-invariant Video Representation Learning
Aug 31, 2026Youngchae Chee, Hosu Lee, Sungjune Park +2Disentangled Representation Learning Egocentric Video Understanding
KAIST · University of Illinois Urbana-Champaign
Mind the Context: Continual Learning of Socially Appropriate Robot Actions via Environmental-Social Disentanglement
Aug 13, 2026Rafal Robert Karpinski, Fethiye Irmak Dogan, Nikhil Churamani +4Disentangled Representation Learning Continual Robot Learning
Utrecht University, Utrecht, The Netherlands · Department of Computer Science and Technology, University of Cambridge, UK
Decodable but Not Accessible: Auditing Distance-Based Reliability Estimation on Disentangled Skin-Lesion Representations
Aug 10, 2026Duc-Vinh TranDomain-Adversarial Learning Disentangled Representation Learning
School of Information and Communication Technology, Hanoi University of Science and Technology, 1 Dai Co Viet Road, Hai Ba Trung, Hanoi 100000, Vietnam
Marginal Matching Does Not License Factorized Sampling: Auditing Conditional Style Leakage in Factorized Generative Models
Aug 5, 2026Duong Bach, Hai Nguyen Hong, Cuong DoDisentangled Representation Learning Latent Variable Models
Smart Health Center (VISHC), VinUniversity, Ha Noi, Viet Nam
DisMix: Order-Aware Mixup for Medical Imaging via Disentangling Ordinal and Non-Ordinal Features
Aug 5, 2026Dileepa Pitawela, Gustavo Carneiro, Hsiang-Ting ChenDisentangled Representation Learning Data Augmentation
1AIML, Adelaide University, Australia · 2CVSSP, University of Surrey, UK
EmbodiedVAE: Disentangled Video VAE for Efficient and Controllable Embodied Manipulation
Aug 4, 2026Jiayi Luo, Hanxin Zhu, Chen Gao +5Variational Autoencoders Disentangled Representation Learning
Beihang University · Zhongguancun Academy · University of Science and Technology of China +3
Disentangled Contrastive Learning for Zero-Shot Multilingual Dense Retrieval
Aug 3, 2026Chao Huang, Yufeng Chen, Changhao Guan +3Contrastive Learning Disentangled Representation Learning
Key Laboratory of Big Data & Artificial Intelligence in Transportation (Beijing Jiaotong University), Ministry of Education · School of Computer Science and Technology, Beijing Jiaotong University
Learning Molecular Representations from Cellular Phenotypes with Structure Preservation
Aug 3, 2026Xuan Lin, Jingyu Sheng, Tengfei Ma +2Disentangled Representation Learning Cross-Modal Representation Learning
School of Computer Science, Xiangtan University, Xiangtan, Hunan, China · College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China · School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China +1
FactorJEPA: Factorizing Monolithic Futures into Layout-Agent-Interaction Channels for Crowded and Chaotic Global South Urban Worlds
Aug 2, 2026Kapil Wanaskar, Gaytri Jena, Aman Chadha +3Autonomous Driving Datasets Disentangled Representation Learning
San Jose State University, USA · UC Berkeley, USA · Apple, USA +3
RadPRISM: Schema-stratified radiology-report supervision for concept-disentangled image representations and visual grounding
Jul 31, 2026Fabian Drexel, Marlene Fritzsche, Era Stambollxhiu +15Chest X-Ray Classification Disentangled Representation Learning
Chair for AI in Healthcare and Medicine, Technical University of Munich (TUM) and TUM University Hospital, Munich, Germany · Technical University of Munich, School of Medicine and Health, TUM University Hospital, Klinikum rechts der Isar, Department of Diagnostic and Interventional Radiology, Munich, Germany · Department of Radiology, Charité – Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt Universität zu Berlin, Berlin, Germany +5
Split and Drive: Dual-Axis Disentanglement for Real-Time Gaussian Head Avatars
Jul 30, 2026MD Wahiduzzaman Khan, Mingshan Jia, Xiaolin Zhang +23D Gaussian Splatting Disentangled Representation Learning
University of Technology Sydney, Australia · Shandong University of Science and Technology, China
Interpretable Representation via LLM-Driven Generative Disentanglement for Local-Life Service Recommendation
Jul 30, 2026Long Zhang, Hao Jiang, Sheng Yu +3Semantic ID Recommendation Disentangled Representation Learning
Kuaishou Technology Beijing, China
Knowledge-guided Disentanglement with Atomic Actions for Action Recognition
Jul 28, 2026Tianci Wu, Siqi Cao, Guangming Zhu +6Disentangled Representation Learning Video Action Recognition
Xidian University Xi’an, China · National University of Defense Technology Changsha, China · Hunan Institute of Advanced Technology Changsha, China +1
DreamStyle3D: Efficient 3D Stylized Asset Generation via Dual-Attention Disentanglement
Jul 27, 2026Kai Wang, Ziheng Ouyang, Xuying Zhang +2Disentangled Representation Learning 3D Asset Generation
VCIP, Nankai University Tianjin, China · Zhongguancun Academy Beijing, China · Joy Future Academy, JD Beijing, China +1
Self-Supervised Consistency Enhanced Disentangled Learning for Neural Decoding Generalization in Brain-Machine Interface
Jul 27, 2026Jiyu Wei, Di Hong, Zhanjie Zhang +3Disentangled Representation Learning Brain-Computer Interfaces
College of Computer Science and Technology, Zhejiang University, Hangzhou, China · Nanhu Brain-Computer Interface Institute, Hangzhou, China

Oct 7, 2026, cs.LGJ/K move · Enter open · S save

DSReg: Provably Recovering Individual World Latents without Reconstruction

Yujia Zheng, David Klindt, Randall Balestriero, Bernhard Schölkopf

University of Illinois Urbana-Champaign · Cold Spring Harbor Laboratory · Brown University+2

Representation Identifiability Latent World Models Disentangled Representation Learning Joint-Embedding Predictive Architecture

Open paper AskPDF arXiv

Methods that recover individual latent variables of the world, from nonlinear ICA to dictionary learning and causal representation learning, anchor the latents to observations through reconstruction, auxiliary supervision, or distributional asymmetries such as non-Gaussianity. Methods without these anchors, including joint-embedding predictive architectures (JEPAs), identify the latent state only up to a linear transformation, so individual latents remain mixed. We close this gap: individual world latents can be provably recovered with no reconstruction, no decoder, and no labels. The key condition is Structural Diversity: different latents leave distinct dependency footprints on observations, just as no two snowflakes are alike. Building on the linear identifiability that LeJEPA provides, we prove that under Structural Diversity, DSReg (Dependency-Sparsity Regularization) recovers individual world latents up to signed permutation, without reconstruction or a decoder. It applies post hoc to any linearly identified representation, reusing trained checkpoints at no loss over joint training, and establishes the first fully identifiable JEPA that recovers every world latent. Moreover, as a condition on dependency footprints, Structural Diversity is strictly weaker than all structural conditions of prior identifiable latent variable models. Across synthetic regimes, world model probes, learned visual encoders, and external renderers, DSReg preserves dense prediction while improving individual-latent recovery and downstream use with scales.

Momentum

Related topics

Latest papers 163