Joint-Embedding Predictive Architecture

Also known as JEPA

Ask about this topic

Overview

Joint-Embedding Predictive Architectures learn useful representations by predicting a target encoder’s latent features from visible or past context, rather than reconstructing every input detail. Common approaches use masked context-target prediction, online or EMA target encoders, and regularizers such as SIGReg to prevent collapse; action-conditioned variants model latent dynamics for planning. These methods are being applied to images, video, robotics, medical and scientific data, and time series, with evaluations ranging from linear probes to control and forecasting benchmarks. A central open tension is that predictable, non-collapsed features are not necessarily the features needed for a task: work tests how to preserve control-relevant or diagnostic information and how well prediction metrics reflect downstream performance.

Latest papers

CardsList

250 papers60 papers in the last four weeks, up 88% on the four weeks before. 0.3% of all new papers.

  1. JEDI: Joint Embedding Diffusion World Model for Online Model-Based Reinforcement Learning

    May 13, 2026Jing Yu Lim, Rushi Shah, Zarif Ikram +4World Model LearningJoint-Embedding Predictive Architecture

    National University of Singapore · usc

  2. Clin-JEPA: A Multi-Phase Co-Training Framework for Joint-Embedding Predictive Pretraining on EHR Patient Trajectories

    May 11, 2026Yixuan Yang, Mehak Arora, Ryan Zhang +10Self-Supervised Pre-TrainingHealthcare

    Duke University, Durham, NC, USA

  3. Sub-JEPA: Subspace Gaussian Regularization for Stable End-to-End World Models

    May 10, 2026Kai Zhao, Dongliang Nie, Yuchen Lin +4Representation LearningRepresentation Collapse

    1Shanghai University · 2The University of Manchester · 3Nankai University

  4. ProteinJEPA: Latent prediction improves protein language model pretraining

    May 8, 2026Dan Ofer, Dafna Shahaf, Michal LinialLanguage Model PretrainingMasked Language Modeling

    Department of Biological Chemistry The Hebrew University of Jerusalem · School of Computer Science and Engineering The Hebrew University of Jerusalem

  5. AeroJEPA: Learning Semantic Latent Representations for Scalable 3D Aerodynamic Field Modeling

    May 7, 2026Francisco Giral, Abhijeet Vishwasrao, Andrea Arroyo Ramo +8Joint-Embedding Predictive ArchitecturePDE Surrogate Modeling

    Universidad Politécnica de Madrid · University of Michigan · Universitat Politècnica de València +3

  6. DART: A Vision-Language Foundation Model for Comprehensive Rope Condition Monitoring

    May 6, 2026Anju Rani, Daniel Ortiz-Arroyo, Petar DurdevicJoint-Embedding Predictive ArchitectureLarge Vision-Language Models

    Department of Energy Aalborg University Esbjerg, Denmark 6700

  7. Text-Conditional JEPA for Learning Semantically Rich Visual Representations

    May 5, 2026Chen Huang, Xianhang Li, Vimal Thilak +2Joint-Embedding Predictive ArchitecturePredictive Representation Learning

    Apple, Cupertino, United States

  8. CGM-JEPA: Learning Consistent Continuous Glucose Monitor Representations via Predictive Self-Supervised Pretraining

    May 1, 2026Hada Melino Muhammad, Zechen Li, Flora Salim +1Cross-Modal Representation LearningSelf-Supervised Time Series Representation Learning

    University of New South Wales · Google Research

  9. Why Self-Supervised Encoders Want to Be Normal

    Apr 30, 2026Yuval DombRepresentation CollapseSelf-Supervised Learning

  10. The Global Neural World Model: Spatially Grounded Discrete Topologies for Action-Conditioned Planning

    Apr 17, 2026Noureddine KermicheWorld Model LearningWorld Model-Based Planning

    Western Digital Corporation, Irvine, CA, USA

  11. Predict and Reconstruct: Joint Objectives for Self-Supervised Language Representation Learning

    Apr 16, 2026Aimen BoukhariJoint-Embedding Predictive ArchitectureMasked Language Modeling

    ´Ecole Nationale Sup´erieure d’Informatique (ESI), Algiers , Algeria

  12. From Alignment to Prediction: A Study of Self-Supervised Learning and Predictive Representation Learning

    Apr 15, 2026Mintu Dutta, Ritesh Vyas, Mohendra RoySelf-Supervised LearningPredictive Representation Learning

    Department of Information and Communication Technology, School of Technology, Pandit Deendayal Energy University, Gandhinagar, Gujarat 382007, India

  13. PI-JEPA: Label-Free Surrogate Pretraining for Coupled Multiphysics Simulation via Operator-Split Latent Prediction

    Apr 1, 2026Brandon Yee, Pairie KohMultiphysics SimulationPDE Surrogate Modeling

    Physics Lab, Yee Collins Research Group · Graduate School of Business, Stanford University

  14. Mine-JEPA: In-Domain Self-Supervised Learning for Mine-Like Object Classification in Side-Scan Sonar

    Apr 1, 2026Taeyoun Kwon, Youngwon Choi, Hyeonyu Kim +3ClassificationSelf-Supervised Learning

    Maum AI Inc. · Seoul National University · KAIST +1

  15. Le MuMo JEPA: Multi-Modal Self-Supervised Representation Learning with Learnable Fusion Tokens

    Mar 25, 2026Ciem Cornelissen, Sam Leroux, Pieter SimoensMultimodal SSLMultimodal Learning

    IDLab, Department of Information Technology, Ghent University - imec, Belgium

  16. Pretext Matters: An Empirical Study of SSL Methods in Medical Imaging

    Mar 23, 2026Vedrana Ivezić, Mara Pleasure, Ashwath Radhachandran +7Self-Supervised LearningMedical Image Representation Learning

    Biomedical AI Research Lab, University of California, Los Angeles, Los Angeles, CA, USA · Department of Radiology, University of California, Los Angeles, Los Angeles, CA, USA · Department of Bioengineering, University of California, Los Angeles, Los Angeles, CA, USA +4

  17. ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model

    Mar 23, 2026Haichao Zhang, Yijiang Li, Shwai He +5Latent World ModelsTrajectory Prediction

    Northeastern University · University of California San Diego · University of Maryland +2

  18. Var-JEPA: A Variational Formulation of the Joint-Embedding Predictive Architecture - Bridging Predictive and Generative Self-Supervised Learning

    Mar 20, 2026Moritz Gögl, Christopher YauJoint-Embedding Predictive ArchitectureSelf-Supervised Learning

    University of Oxford, UK · Health Data Research UK

  19. Probing the Latent World: Emergent Discrete Symbols and Physical Structure in Latent Representations

    Mar 20, 2026Liu hung mingRepresentation LearningVideo Representation Learning

    PARRAWA AI

  20. LuMamba: Latent Unified Mamba for Electrode Topology-Invariant and Efficient EEG Modeling

    Mar 19, 2026Danaé Broustail, Anna Tegon, Thorir Mar Ingolfsson +2EEG Foundation ModelsElectroencephalography

    Integrated Systems Laboratory, ETH Zürich, Zürich, Switzerland · School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore · DEI, University of Bologna, Bologna, Italy

  21. Laya: A LeJEPA Approach to EEG via Latent Prediction over Reconstruction

    Mar 17, 2026Saarang Panchavati, Uddhav Panchavati, Hiroki Nariai +2EEG Foundation ModelsSelf-Supervised Time Series Representation Learning

    Department of Medical Informatics UCLA Los Angeles, USA · Department of Cognitive Science UCSD San Diego, USA · David Geffen School of Medicine UCLA Mattel Children’s Hospital Los Angeles, USA

  22. V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning

    Mar 15, 2026Lorenzo Mur-Labadia, Matthew Muckley, Amir Bar +6Self-Supervised Visual Representation LearningVisual Representation Learning

    FAIR at Meta · Universidad de Zaragoza

  23. Is the reconstruction loss culprit? An attempt to outperform JEPA

    Mar 14, 2026Alexey Potapov, Oleg Shcherbakov, Ivan KravchenkoPredictive Representation LearningAutoencoders

    SingularityNET

  24. Sat-JEPA-Diff: Bridging Self-Supervised Learning and Generative Diffusion for Remote Sensing

    Mar 14, 2026Kursat Komurcu, Linas PetkeviciusSpatiotemporal ForecastingDiffusion-Based Image Generation

    Vilnius University, Faculty of Mathematics and Informatics, Institute of Computer Science, Artificial Intelligence Methods Lab, Vilnius, LT-03225, Lithuania

  25. LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

    Mar 13, 2026Lucas Maes, Quentin Le Lidec, Damien Scieur +2World Model LearningJoint-Embedding Predictive Architecture

    Mila & Université de Montréal · New York University · Samsung SAIL +1

  26. Representation Learning for Spatiotemporal Physical Systems

    Mar 13, 2026Helen Qu, Rudy Morel, Michael McCabe +4Representation LearningScientific ML

    Flatiron Institute · Princeton University · Université Paris-Saclay, Université Paris Cité, CEA, CNRS, AIM +1

  27. Temporal Straightening for Latent Planning

    Mar 12, 2026Ying Wang, Oumayma Bounou, Gaoyue Zhou +4Latent-Space PlanningWorld Model-Based Planning

    New York University · Brown University · University of Toronto

  28. Semantic Tube Prediction: Beating LLM Data Efficiency with JEPA

    Feb 26, 2026Hai Huang, Yann LeCun, Randall BalestrieroEfficient Language Model TrainingLLM Training

    Atlassian · NYU · Brown

  29. Knowledge, Rules and Their Embeddings: Two Paths towards Neuro-Symbolic JEPA

    Feb 25, 2026Yongchao Huang, Hassan RazaDifferentiable LogicNeuro-Symbolic Reasoning

  30. US-JEPA: A Joint Embedding Predictive Architecture for Ultrasound

    Feb 22, 2026Ashwath Radhachandran, Vedrana Ivezić, Shreeram Athreya +2Joint-Embedding Predictive ArchitectureUltrasound Imaging

    Biomedical Artificial Intelligence Research Lab, University of California, Los Angeles, Los Angeles, United States of America · Medical Informatics, University of California, Los Angeles, Los Angeles, United States of America · Department of Electrical and Computer Engineering, University of California, Los Angeles, Los Angeles, United States of America +3