Image de couverture de livre

Subspace-Decomposed JEPAs: Disentangling Progression and Content in Latent World Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Thil, Lucas, Read, Jesse, Kaddah, Rim, Doquet, Guillaume
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

STEP: Learning STructured Embeddings for Progressive Time Series
par: Thil, Lucas, et autres
Publié: (2026)

I-GLIDE: Input Groups for Latent Health Indicators in Degradation Estimation
par: Thil, Lucas, et autres
Publié: (2025)

Uncertainty Quantification as a Complementary Latent Health Indicator for Remaining Useful Life Prediction on Turbofan Engines
par: Thil, Lucas, et autres
Publié: (2025)

A Machine Learning Framework for Turbofan Health Estimation via Inverse Problem Formulation
par: Leyli-Abadi, Milad, et autres
Publié: (2026)

Parameter-Efficient Distributional RL via Normalizing Flows and a Geometry-Aware Cramér Surrogate
par: C., Simo Alami, et autres
Publié: (2025)

Beyond Isotropy in JEPAs: Hamiltonian Geometry and Symplectic Prediction
par: Alvarez, Robert Jenkinson
Publié: (2026)

Beyond Patient Invariance: Learning Cardiac Dynamics via Action-Conditioned JEPAs
par: Fernandes, Jose Geraldo, et autres
Publié: (2026)

Enhancing JEPAs with Spatial Conditioning: Robust and Efficient Representation Learning
par: Littwin, Etai, et autres
Publié: (2024)

Learning from Data Streams: An Overview and Update
par: Read, Jesse, et autres
Publié: (2022)

Gaussian Embeddings: How JEPAs Secretly Learn Your Data Density
par: Balestriero, Randall, et autres
Publié: (2025)

Decomposing Representation Space into Interpretable Subspaces with Unsupervised Learning
par: Huang, Xinting, et autres
Publié: (2025)

Generative Modeling of Discrete Data Using Geometric Latent Subspaces
par: Gonzalez-Alvarado, Daniel, et autres
Publié: (2026)

Estimating Conditional Covariance between labels for Multilabel Data
par: Park, Laurence A. F., et autres
Publié: (2025)

Branches: Efficiently Seeking Optimal Sparse Decision Trees with AO*
par: Chaouki, Ayman, et autres
Publié: (2024)

Online Learning of Decision Trees with Thompson Sampling
par: Chaouki, Ayman, et autres
Publié: (2024)

Enhanced Latent Multi-view Subspace Clustering
par: Shi, Long, et autres
Publié: (2023)

Dependent Latent Class Models
par: Bowers, Jesse, et autres
Publié: (2022)

Disentangling Interpretable Factors with Supervised Independent Subspace Principal Component Analysis
par: Su, Jiayu, et autres
Publié: (2024)

Disentangled Latent Spaces for Reduced Order Models using Deterministic Autoencoders
par: Schwarz, Henning, et autres
Publié: (2025)

Equivalence Set Restricted Latent Class Models (ESRLCM)
par: Bowers, Jesse, et autres
Publié: (2024)

Probabilistic Decomposed Linear Dynamical Systems for Robust Discovery of Latent Neural Dynamics
par: Chen, Yenho, et autres
Publié: (2024)

A Unified Latent Space Disentanglement VAE Framework with Robust Disentanglement Effectiveness Evaluation
par: Lang, Xiaoan, et autres
Publié: (2026)

Disentanglement Analysis in Deep Latent Variable Models Matching Aggregate Posterior Distributions
par: Saha, Surojit, et autres
Publié: (2025)

Hierarchical Planning with Latent World Models
par: Zhang, Wancong, et autres
Publié: (2026)

Factored Latent Action World Models
par: Wang, Zizhao, et autres
Publié: (2026)

Group-Aware Matrix Estimation and Latent Subspace Recovery
par: Golubovic, Hamza, et autres
Publié: (2026)

CORAL: Disentangling Latent Representations in Long-Tailed Diffusion
par: Rodriguez, Esther, et autres
Publié: (2025)

Reflections on Disentanglement and the Latent Space
par: Schaerf, Ludovica
Publié: (2024)

Latent Concept Disentanglement in Transformer-based Language Models
par: Hong, Guan Zhe, et autres
Publié: (2025)

A Conditional GAN for Tabular Data Generation with Probabilistic Sampling of Latent Subspaces
par: Akritidis, Leonidas, et autres
Publié: (2025)

LatentGAN Autoencoder: Learning Disentangled Latent Distribution
par: Kalwar, Sanket, et autres
Publié: (2022)

Co-Evolving Latent Action World Models
par: Wang, Yucen, et autres
Publié: (2025)

Disentangled Latent Dynamics Manifold Fusion for Solving Parameterized PDEs
par: Liang, Zhangyong
Publié: (2026)

Disentangled Latent Spaces Facilitate Data-Driven Auxiliary Learning
par: Skenderi, Geri, et autres
Publié: (2023)

Disentangling Disentangled Representations: Towards Improved Latent Units via Diffusion Models
par: Jun, Youngjun, et autres
Publié: (2024)

Joint Identifiability of Cross-Domain Recommendation via Hierarchical Subspace Disentanglement
par: Du, Jing, et autres
Publié: (2024)

Annealed Co-Generation: Disentangling Variables via Progressive Pairwise Modeling
par: Zhang, Hantao, et autres
Publié: (2026)

Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model Disentanglement
par: Wang, Zhi, et autres
Publié: (2024)

Isometric Representation Learning for Disentangled Latent Space of Diffusion Models
par: Hahm, Jaehoon, et autres
Publié: (2024)

IMWM: Intuition Models Complement World Models for Latent Planning
par: Gao, Baoqi, et autres
Publié: (2026)