Joint-Embedding Predictive Architecture

Also known as JEPA

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

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

ArtNet: A JEPA-Like Articulatory Predictive Framework for Robust Zero-Shot Phoneme Recognition
Jun 15, 2026Zeqian Hu, Fuliang Weng, Shu Shang +1Zero-Shot Learning Joint-Embedding Predictive Architecture
Fudan University, China · Pedawise, Shanghai, China
Phys-JEPA: Physics-Informed Latent World Models for Multivariate Time-Series Forecasting
Jun 15, 2026Weizhi Nie, Weichao Liu, Honglin Guo +1Multivariate Time Series Forecasting Latent Dynamics Modeling
Tianjin University
Learning Sparse Latent Predictive Foundation Model for Multimodal Neuroimaging
Jun 12, 2026Haoxu Huang, Long Chen, Jingyun Chen +8Medical Imaging Foundation Models Joint-Embedding Predictive Architecture
New York University, Center for Data Science, New York, NY, 10001, USA · NYU Grossman School of Medicine, Department of Radiology, New York, NY, 10016, USA · State University of New York at Binghamton, School of Computing, Binghamton, NY 13902, USA +7
JetParticle-JEPA: An Efficient Self-Supervised Representation Learning method for Jet Tagging in High-Energy Physics
Jun 12, 2026Guillaume Letellier, Antonin Vacheret, Frédéric JurieSelf-Supervised Learning Joint-Embedding Predictive Architecture
LPCC · GREYC, Normandy University, Unicaen, ENSICAEN, UMR CNRS 6072, F-14000 Caen, France · LPC, Normandy University, Unicaen, ENSICAEN, IN2P3, UMR CNRS 6534, F-14000 Caen, France
Masked and Predictive Self-Supervised Pretraining for Brain MRI: Effects of Objective Design on Disease Detection
Jun 11, 2026Esra Ergün, Hersh Chandarana, Dan Sodickson +1Medical Imaging Foundation Models Masked Autoencoders
Department of Computer Engineering, Istanbul Technical University, Istanbul, 34469, Türkiye · Department of Radiology, NYU Grossman School of Medicine, New York, NY, 10016, United States · Department of AI and Data Engineering, Istanbul Technical University, Istanbul, 34469, Türkiye
EPM-JEPA: Operator-Side Experience Modulation in JEPA-Family World Models
Jun 11, 2026Vedant PandyaTest-Time Adaptation World Model Learning
School of Artificial Intelligence and Data Engineering (SAIDE) Indian Institute of Technology Jodhpur
RePAIR: Predictive Self-Supervised Representation Learning in Chess
Jun 10, 2026Christoph Koller, Johannes Fürnkranz, Timo BertramMasked Autoencoders Joint-Embedding Predictive Architecture
JKU Linz, Austria
FF-JEPA: Long-Horizon Planning in World Models with Latent Planners
Jun 8, 2026Sergi Masip, Jonathan Swinnen, Yutong Hu +2Hierarchical Planning Long-Horizon Robotic Manipulation
PSI, ESAT, KU Leuven · RAM, MECH, KU Leuven
CF-JEPA: Mask-free forward prediction with asymmetric encoder utilization for time-series representation learning
Jun 5, 2026Jaehoon Lee, Sunghyun SimMultivariate Time Series Forecasting Time Series Classification
aGraduate School of Artificial Intelligence Convergence Engineering, Changwon National University, Changwon, South Korea · bDepartment of Artificial Intelligence Engineering, Changwon National University, Changwon, South Korea
LatentWave: JEPA Pretraining for Wireless Foundation Models
Jun 4, 2026Ahmed Mohamed, Ahmed Aboulfotouh, Hatem Abou-ZeidWireless Foundation Models Self-Supervised Pre-Training
Department of Electrical and Software Engineering, University of Calgary, Canada
VISReg: Variance-Invariance-Sketching Regularization for JEPA training
Jun 1, 2026Haiyu Wu, Randall Balestriero, Morgan LevineRepresentation Collapse Joint-Embedding Predictive Architecture
Altos Labs · Brown University
Echo: A Joint-Embedding Predictive Architecture for Speaker Diarization and Speech Recognition in a Shared Latent Space
Jun 1, 2026Louis MouchonAudio Representation Learning Joint-Embedding Predictive Architecture
Independent Research
UR-JEPA: Uniform Rectifiability as a Regularizer for Joint-Embedding Predictive Architectures
May 31, 2026Triet M. LeJoint-Embedding Predictive Architecture Geometric Representation Learning
BRo-JEPA: Learning Modular Arithmetic in Latent Space
May 31, 2026Divyansh Jha, Yuanfang Xie, Varan Mehra +1Zero-Shot Learning Joint-Embedding Predictive Architecture
1Georgia Institute of Technology · 2NYU Langone Health
CR-JEPA: Cross-Modal Joint-Embedding Predictive Learning for Remote Sensing Image Retrieval
May 30, 2026Md Aminur Hossain, Ayush V. Patel, Nitant Dube +1Cross-Modal Representation Learning Joint-Embedding Predictive Architecture
Space Applications Centre, Indian Space Research Organisation, Ahmedabad, India · Centre of Studies in Resources Engineering, Indian Institute of Technology Bombay, Mumbai, India
Giving Sensors a Voice: Multimodal JEPA for Semantic Time-Series Embeddings
May 29, 2026Utsav Dutta, Gerardo Pastrana, Sina Khoshfetrat Pakazad +1Multivariate Time Series Forecasting Joint-Embedding Predictive Architecture
C3 AI, Redwood City, CA, USA
Subspace-Decomposed JEPAs: Disentangling Progression and Content in Latent World Models
May 29, 2026Lucas Thil, Jesse Read, Rim Kaddah +1Disentangled Representation Learning Representation Learning
LIX, École Polytechnique Palaiseau, France · IRT SystemX Palaiseau, France · Safran Tech Chateaufort, France
HQ-JEPA: Hybrid Quantum Joint-Embedding Predictive Architecture for Cross-Modal Remote Sensing Representation Learning
May 29, 2026Md Aminur Hossain, Ayush V. Patel, Sanjay K. Singh +1Representation Learning Cross-Modal Representation Learning
Space Applications Centre, Indian Space Research Organisation, Ahmedabad, India · Centre of Studies in Resources Engineering, Indian Institute of Technology Bombay, Mumbai, India
SPHERE-JEPA: Spherical Prediction with Homogeneous Embeddings
May 26, 2026L{é}o Nicollier, Max Dunitz, Marc Pic +3Self-Supervised Learning Joint-Embedding Predictive Architecture
CB,ATT · ATT · CB,IFUMI +1
When Does LeJEPA Learn a World Model?
May 25, 2026David Klindt, Yann LeCun, Randall BalestrieroWorld Model Learning Representation Identifiability
Cold Spring Harbor Laboratory · New York University · Brown University
UWM-JEPA: Predictive World Models That Imagine in Belief Space
May 25, 2026Santosh Kumar Radha, Oktay GoktasWorld Model Learning Latent Dynamics Modeling
AgentField AI, Toronto, Canada
DLLM-JEPA: Joint Embedding Predictive Architectures for Masked Diffusion Language Models
May 24, 2026Sangdae NamMasked Diffusion Models Joint-Embedding Predictive Architecture
VESSL AI
Demo-JEPA: Joint-Embedding Predictive Architecture for One-shot Cross-Embodiment Imitation
May 20, 2026Jingyang He, Guangrun Li, Jieyu Zhang +3Robot Skill Learning World Models for Robotics
State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University · Beijing Innovation Center of Humanoid Robotics · University of Washington
Beyond Isotropy in JEPAs: Hamiltonian Geometry and Symplectic Prediction
May 19, 2026Robert Jenkinson AlvarezJoint-Embedding Predictive Architecture Geometric Representation Learning
PEIRA: Learning Predictive Encoders through Inter-View Regressor Alignment
May 17, 2026Michael Arbel, Basile Terver, Jean PonceUnsupervised Learning Visual Representation Learning
Univ. Grenoble Alpes, Inria · CNRS, Grenoble INP, LJK · Ecole Normale Supérieure / PSL +2
Factorized Latent Dynamics for Video JEPA: An Empirical Study of Auxiliary Objectives
May 16, 2026Santosh PremiDisentangled Representation Learning Latent Dynamics Modeling
Entity-Centric World Models: Interaction-Aware Masking for Causal Video Prediction
May 14, 2026Santosh Kumar PaidiWorld Model Learning Causal World Models
Genentech, Inc.
Representation Without Reward: A JEPA Audit for LLM Fine-Tuning
May 14, 2026Biswa SenguptaLLM Auditing LLM Fine-Tuning
LLM Suite Team, JPMorgan Chase & Co.
Crys-JEPA: Accelerating Crystal Discovery via Embedding Screening and Generative Refinement
May 14, 2026Nian Liu, Nikita Kazeev, Stephen Gregory Dale +8Joint-Embedding Predictive Architecture Generative Modeling
1National University of Singapore · 2Loyola Marymount University · 3New York University +1
Mini-JEPA Foundation Model Fleet Enables Agentic Hydrologic Intelligence
May 13, 2026Mashrekur RahmanGeospatial Foundation Models Geospatial Representation Learning
Dartmouth Libraries, Dartmouth College, 6025 Baker-Berry Library, Hanover, 03755, NH, USA

Jun 15, 2026J/K move · Enter open · S save

ArtNet: A JEPA-Like Articulatory Predictive Framework for Robust Zero-Shot Phoneme Recognition

Zeqian Hu, Fuliang Weng, Shu Shang, Yaqian Zhou

Fudan University, China · Pedawise, Shanghai, China

Zero-Shot Learning Joint-Embedding Predictive Architecture Speech Processing Self-Supervised Speech Representation Learning Variational Information Bottleneck Cross-Lingual Transfer

Open paper AskPDF arXiv

Zero-shot cross-lingual phoneme recognition is often hindered by the fragility of direct acoustic-to-symbol mapping, which is susceptible to language-specific variations. Echoing joint-embedding predictive architecture (JEPA) work in vision, we propose ArtNet, a framework that explores a structured feature prediction task based on articulatory features to enhance acoustic robustness. Specifically, ArtNet integrates an articulatory predictor, designed to extract universal articulatory representations from self-supervised learning (SSL) features, with a variational information bottleneck (VIB) to suppress language-specific variations. Experiments on seven unseen languages demonstrate that ArtNet, particularly when synergized with the proposed vector-space inventory alignment (VSIA) strategy, significantly outperforms competitive baselines, achieving a 20.56% relative reduction in phoneme error rate (PER) and 7.01% in phoneme feature error rate (PFER).