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

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

Jun 15, 2026

Phys-JEPA: Physics-Informed Latent World Models for Multivariate Time-Series Forecasting

Multivariate forecasting in physical systems requires models that predict coupled temporal variables while preserving meaningful state evolution. Deep forecasters can fit temporal correlations, and physics-informed models can regularize predictions with scientific constraints, but these directions are often connected only at the decoded-output level. As a result, the hidden predictive state that generates future trajectories may remain statistically useful but physically unstructured. We introduce Phys-JEPA, a physics-informed joint-embedding predictive architecture for multivariate time-series forecasting. Phys-JEPA learns a latent world model in which predictive states are decomposed into physical and residual components, and physical consistency is imposed directly on latent states and latent transitions rather than only on decoded forecasts. This formulation uses known physical variables to organize the representation space while retaining residual capacity for unresolved dynamics. On Jena Climate 2009--2016, Phys-JEPA reduces aggregate MSE from 0.12482 to 0.12273 and temperature MSE from 0.01892 to 0.01831 at H=24. On Traffic, full Phys-JEPA improves aggregate MSE over the supervised baseline across all tested horizons, reducing H=192 MSE from 0.800784 to 0.773873. On Electricity, the best variant depends on horizon: static latent consistency is strongest at H=24 and H=48, while full Phys-JEPA gives the best aggregate and target-variable MSE at H=192. These initial results suggest that moving physics-informed learning from output space to latent predictive state space is a promising direction for interpretable temporal world models.

Weizhi Nie, Weichao Liu, Honglin Guo +1

Tianjin University

Multivariate Time Series ForecastingLatent Dynamics ModelingJoint-Embedding Predictive ArchitecturePhysics-Informed ML
AskPDF
Jun 12, 2026

Learning Sparse Latent Predictive Foundation Model for Multimodal Neuroimaging

Brain MRIs are routinely acquired as multiple complementary sequences with unique contrast weighting, including T1-weighed imaging (T1w) anatomic and fluid-sensitive T2-weighted (T2w) contrasts. However, methods for learning unified representations across the multitude of MRI contrast mechanisms at health-system scale are lacking. In this study, we introduce Neuro-JEPA, a sparse multimodal neuroimaging foundation model that combines a latent predictive objective with a Mixture-of-Experts architecture to encode brain MRI across core T1w, T2w, and fluid-suppressed FLAIR imaging (FLAIR). We further provide a systematic methodological study of architectural, masking, objective, and sparsity design choices beneficial for robust neuroimaging multimodal representation learning. Neuro-JEPA was pretrained on 1,551,862 scans from 428,647 studies after modality-specific preprocessing with data curation across three core structural brain MRI sequences. We evaluated the learned representations across clinical and research settings, including 25 tasks from three health systems: NYU Langone, NYU Long Island, and Massachusetts General Hospital, and 22 tasks from 12 public datasets, covering unimodal, multimodal and cross-domain evaluation configurations. Across these benchmarks, existing neuroimaging foundation models showed inconsistent gains over a simple convolutional neural network (CNN) baseline, whereas Neuro-JEPA achieved stronger and more consistent performance across all evaluated settings. These results establish a scalable methodological framework for multimodal neuroimaging representation learning and highlight the need for foundation model evaluation protocols that include simple baselines, clinically heterogeneous cohorts and controlled multimodal comparisons.

Haoxu Huang, Long Chen, Jingyun Chen +8

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

Medical Imaging Foundation ModelsJoint-Embedding Predictive ArchitectureMultimodal PretrainingPredictive Representation LearningNeuroimaging
AskPDF
Jun 12, 2026

JetParticle-JEPA: An Efficient Self-Supervised Representation Learning method for Jet Tagging in High-Energy Physics

Jet tagging at the Large Hadron Collider increasingly relies on deep learning models trained on massive simulated datasets, leading to high computational costs and limited robustness to detector mismodeling. We introduce JetParticle-JEPA (JP-JEPA), a self-supervised Joint-Embedding Predictive Architecture that learns physically meaningful jet representations directly from continuous particle clouds without tokenization or reconstruction of raw inputs. Built on a Particle Transformer backbone, JP-JEPA predicts latent representations of masked particles while preserving fine-grained kinematic correlations. On the JetClass benchmark, JP-JEPA achieves performance comparable to fully supervised state-of-the-art methods on the full dataset, surpasses supervised baselines in low-label regimes, and significantly outperforms existing SSL approaches. On Top Quark and Quark-Gluon Tagging benchmarks, it remains on par with supervised methods. The learned representations also exhibit strong robustness to missing detector information and improved uncertainty behavior, highlighting JP-JEPA as a promising foundation-model framework for robust and data-efficient jet physics at the LHC.

Guillaume Letellier, Antonin Vacheret, Frédéric Jurie

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

Self-Supervised LearningJoint-Embedding Predictive ArchitectureJet TaggingHigh-Energy PhysicsData-Efficient Learning
AskPDF
Jun 11, 2026

Masked and Predictive Self-Supervised Pretraining for Brain MRI: Effects of Objective Design on Disease Detection

MRI self-supervised learning (SSL) has largely emphasized segmentation and dense prediction, while controlled studies of how alternative pretraining objectives shape transferable representations for MRI-based disease detection remain limited. We compare reconstruction-based Masked Autoencoders (MAE) and latent-predictive Joint Embedding Predictive Architectures (JEPA) for 3D structural MRI. We further introduce a spectral-domain reconstruction loss for MAE to promote sensitivity to fine-grained anatomical structure and integrate variance-covariance regularization (VCR) into JEPA to encourage broader, less redundant latent representations. Models are pretrained on heterogeneous MRI datasets using individual single-contrast inputs. Across seven dataset-task settings spanning four clinical problem domains, downstream transfer depends on both the pretraining paradigm and how the representational bias induced by a specific objective aligns with the downstream task. Spectral regularization provides its clearest gains for Alzheimer's disease classification and tumor grading, while its benefit is smaller for NC vs. MCI and ASD. VCR yields its strongest improvements when discrimination appears to involve multiple sources of structural variation. Overall, MAE-based pretraining generally outperforms baseline JEPA, with SL-MAE providing the strongest gains in several disease-detection settings. Representation analyses show that fine-tuning reorganizes learned representations in an objective-, depth-, and task-dependent manner. VCR-JEPA maintains broader effective dimensionality across depth and greater cross-task representational alignment than baseline JEPA. We publicly release subject-level pretraining and downstream evaluation splits.

Esra Ergün, Hersh Chandarana, Dan Sodickson +1

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

Medical Imaging Foundation ModelsMasked AutoencodersSelf-Supervised Pre-TrainingJoint-Embedding Predictive ArchitectureImage ReconstructionBrain MRI
AskPDF
Jun 11, 2026

EPM-JEPA: Operator-Side Experience Modulation in JEPA-Family World Models

JEPA-family world models use a static predictor whose weights do not adapt when test-time dynamics diverge from training. We compare two mechanisms for incorporating accumulated experience into a JEPA predictor under distribution shift: operand-side injection, where a compressed experience representation is added as a residual to the predictor's hidden state (EI-JEPA), and operator-side modulation, where the same representation generates low-rank weight deltas via LoRA applied to the predictor's weights (EPM-JEPA). On a pre-registered comparison (Moving MNIST, gravity shift), EPM-JEPA (D_shift^{n=50} = 0.7848 +/- 0.0078, three seeds) differs from EI-JEPA (0.8238) by delta = 4.74% - Outcome C: a null result - by our stated criterion, a valid outcome. As a secondary, non-pre-registered observation, EPM-JEPA improves 1.90% over a no-memory baseline (0.8000), consistently across seeds, while EI-JEPA underperforms the baseline, indicating the benefit is specific to weight-level modulation. Our primary contribution is a mechanism analysis: the D_shift^{n=50} trajectory reflects three independent dynamical processes - buffer cycling, EMA target drift, and an intrinsic LoRA settling transient of +0.021 - rather than convergence to equilibrium. These findings motivate PEM-JEPA, a physics-grounded successor addressing this dynamical-peak limitation.

Vedant Pandya

School of Artificial Intelligence and Data Engineering (SAIDE) Indian Institute of Technology Jodhpur

Test-Time AdaptationWorld Model LearningJoint-Embedding Predictive ArchitectureTemporal Distribution ShiftParameter-Efficient Fine-Tuning
AskPDF
Jun 10, 2026

RePAIR: Predictive Self-Supervised Representation Learning in Chess

In this paper, we introduce Representation Prediction via Autoencoding using Iterative Refinement (RePAIR) - a novel self-supervised representation learning architecture that synthesizes Masked Autoencoders (MAE), Joint Embedding Predictive Architectures (JEPA), and Bidirectional Encoder Representations from Transformers (BERT). We demonstrate how it can be used to encode objects in sequential data like consecutive chess positions into compact yet meaningful representations. The basic principle of the architecture is to mask large portions of a sequence of latent states, similar to BERT and MAE. Then, we apply a lightweight Predictor to the latent representations that repairs gaps in the sequence in a lower-dimensional embedding space akin to JEPA. Our experiments in the domain of chess show that the Encoder refines the board representations such that meaningful chess concepts emerge clustered in the latent space. Furthermore, reconstructions of the masked board states show that the model is able to reason about the piece movements without relying on costly reinforcement learning methods. Lastly, we find that the resulting representation space allows for quick and intuitive dissections of chess games by observing the game path trajectories in this semantically rich space.

Christoph Koller, Johannes Fürnkranz, Timo Bertram

JKU Linz, Austria

Masked AutoencodersJoint-Embedding Predictive ArchitecturePredictive Representation LearningChessState Representation Learning
AskPDF
Jun 8, 2026

FF-JEPA: Long-Horizon Planning in World Models with Latent Planners

Joint Embedding Predictive Architectures (JEPAs) have shown promising world modeling capabilities, enabling planning in latent space by optimizing action trajectories using methods like the Cross-Entropy Method (CEM). These methods are, however, too computationally expensive and ineffective for long-horizon planning. Furthermore, these methods typically require an explicit image of the goal state, which is not always possible in real-world tasks. In this work, we tackle these limitations by proposing Forward-Forward-JEPA (FF-JEPA), a hierarchical approach leveraging two forward dynamics models. Alongside a standard action-conditioned forward model, we introduce an action-free latent planner that predicts the next subgoal given the current state. This approach removes the need for goal images and enables long-horizon planning by decomposing complex trajectories into a sequence of tractable, short-term optimization problems. Preliminary results on PushT demonstrate that FF-JEPA successfully overcomes flat world models' long-horizon collapse, highlighting this approach as a promising direction for goal-free planning.

Sergi Masip, Jonathan Swinnen, Yutong Hu +2

PSI, ESAT, KU Leuven · RAM, MECH, KU Leuven

Hierarchical PlanningLong-Horizon Robotic ManipulationWorld Model-Based PlanningJoint-Embedding Predictive ArchitectureLong-Horizon PlanningModel-Based Planning+1
AskPDF
Jun 5, 2026

CF-JEPA: Mask-free forward prediction with asymmetric encoder utilization for time-series representation learning

Self-supervised learning (SSL) for time-series representation learning is dominated by two paradigms: contrastive methods, which face challenges in constructing positive or negative pairs, and masking-based methods, which disrupt the temporal continuity of time-series signals. Joint-Embedding Predictive Architecture (JEPA) offers a promising alternative by predicting in representation space rather than reconstructing raw inputs. However, existing time-series JEPA variants still rely on masking and therefore inherit its continuity problem. Crop-based Forward JEPA (CF-JEPA) is proposed as an innovative mask-free framework that replaces masking with multi-horizon forward prediction: random crops serve as context views, and short-, mid-, and long-horizon future representations are predicted in the forward temporal direction, directly leveraging the inherent temporal ordering of time-series data as a learning signal. A strong asymmetry is also identified between the online encoder and the exponential moving average (EMA) target encoder, both produced from a single training run: the online encoder develops higher-rank discriminative features, while the EMA target encoder develops smoother, lower-rank temporal features. Exploiting this asymmetry, classification is routed to the online encoder and forecasting or anomaly detection to the EMA target encoder, achieving a 27% reduction in multivariate forecasting mean squared error (MSE) at no additional training cost. Across 126 University of California, Riverside (UCR) and 26 University of East Anglia (UEA) classification datasets, eight electricity transformer temperature forecasting benchmarks, and Key Performance Indicator /Yahoo anomaly detection, CF-JEPA achieves the highest average accuracy and rank on UCR and UEA among self-supervised baselines and ranks second on univariate forecasting and k-nearest neighbors-scored anomaly detection.

Jaehoon Lee, Sunghyun Sim

aGraduate School of Artificial Intelligence Convergence Engineering, Changwon National University, Changwon, South Korea · bDepartment of Artificial Intelligence Engineering, Changwon National University, Changwon, South Korea

Multivariate Time Series ForecastingTime Series ClassificationSelf-Supervised Time Series Representation LearningJoint-Embedding Predictive ArchitectureTime-Series Anomaly Detection
AskPDF
Jun 4, 2026

LatentWave: JEPA Pretraining for Wireless Foundation Models

Wireless foundation models have emerged as a promising alternative to building separate models for each wireless task. However, existing approaches rely on masked input reconstruction, which can bias representations toward low-level signal details. In this paper, we propose LatentWave, a wireless foundation model pretrained using a Joint-Embedding Predictive Architecture (JEPA) on diverse wireless spectrograms and channel state information (CSI). By predicting masked regions in latent space, LatentWave learns representations that are more transferable out of the box across diverse downstream tasks. The proposed architecture employs per-channel patch embeddings with stochastic channel sampling during pretraining, allowing it to process variable antenna counts and improving usability across heterogeneous wireless configurations. We evaluate LatentWave on four downstream tasks: RF signal classification, 5G NR positioning, beam prediction, and LoS/NLoS classification, comparing against a masked-modeling baseline (WavesFM) pretrained on the same data. Additionally, we show that the masking geometry introduces a task-dependent inductive bias: frequency masking strongly favors channel-related tasks such as positioning and beam prediction, while region masking better preserves discriminability for signal classification.

Ahmed Mohamed, Ahmed Aboulfotouh, Hatem Abou-Zeid

Department of Electrical and Software Engineering, University of Calgary, Canada

Wireless Foundation ModelsSelf-Supervised Pre-TrainingJoint-Embedding Predictive ArchitectureWireless Communications
AskPDF
Jun 1, 2026

VISReg: Variance-Invariance-Sketching Regularization for JEPA training

Self-supervised learning methods prevent embedding collapse via modeling heuristics or explicit regularization of the embedding space. Among the latter, VICReg decomposes regularization into variance and covariance objectives, offering flexibility and interpretability. However, covariance captures only second-order statistics -- encouraging decorrelation but failing to enforce the full distributional shape needed for stable training. Sketching-based methods such as SIGReg address this by aligning embeddings to an isotropic Gaussian, but lack flexibility and suffer from vanishing gradients under collapse. We propose Variance-Invariance-Sketching Regularization (VISReg), which replaces covariance with a Sliced-Wasserstein-based sketching objective that enforces full distributional shape, while retaining a variance term for scale control. By decoupling scale and shape, VISReg combines VICReg's flexibility with the distributional rigor of sketching methods, providing robust gradients even under collapse. We show that VISReg scales linearly, outperforms existing regularization on low-quality datasets, and is resilient to long-tailed and low-rank regimes. Pre-trained on ImageNet-1K, VISReg achieves state-of-the-art performance on out-of-distribution datasets. Pre-trained on ImageNet-22K, it matches DINOv2's OOD performance despite the latter using 10x more data (LVD-142M). Project and code: https://haiyuwu.github.io/visreg.

Haiyu Wu, Randall Balestriero, Morgan Levine

Altos Labs · Brown University

Representation CollapseJoint-Embedding Predictive ArchitectureSliced Wasserstein DistanceSelf-Supervised Visual Representation Learning
AskPDF
Jun 1, 2026

Echo: A Joint-Embedding Predictive Architecture for Speaker Diarization and Speech Recognition in a Shared Latent Space

We present Echo, a proof-of-concept audio system built around a single 25 M-parameter ViT encoder. The encoder is pretrained with a JEPA objective and then specialised by stages to carry speaker identity, phonetic content, and dynamic source routing in the same 512-dimensional latent space, with no per-task fine-tuning at deployment. Light heads handle diarization (ArcFace + VBx) and dynamic source separation (null-target K-set prediction). On synthetic VoxCeleb2 mixtures with unknown K, the canonical stack reaches 15.00% blind DER, 97.80% PIT separation accuracy with +9.52 dB latent SI-SDR, and a +53.50-point speaker/content factorisation gap on a held-out k-NN probe. The point of Echo is not a new SOTA on any single task but the joint coexistence of three tasks on one encoder at this footprint. We document the design stage by stage, report the dead-ends, and identify the structural wall on end-to-end ASR through the VQ bottleneck that still bounds the PoC.

Louis Mouchon

Independent Research

Audio Representation LearningJoint-Embedding Predictive ArchitectureSpeech ProcessingAudio UnderstandingAutomatic Speech RecognitionSpeaker Diarization+1
AskPDF
May 31, 2026

UR-JEPA: Uniform Rectifiability as a Regularizer for Joint-Embedding Predictive Architectures

A central difficulty in training Joint-Embedding Predictive Architectures (JEPAs) is preventing representation collapse. LeJEPA addresses this by enforcing an isotropic Gaussian target on the embeddings via Sketched Isotropic Gaussian Regularization (SIGReg). This target is in tension with the manifold hypothesis, which expects embeddings to concentrate on a low-dimensional subset of the ambient space. We propose UR-JEPA, which targets a uniformly nn-rectifiable measure of local tangent dimension nn at small scales, realized through a Gaussian-kernel smoothed Carleson-type square function LCGLT\mathcal{L}^{\text{CGLT}}, with a complementary Jones ββ-number formulation. On Inet10, UR-JEPA(LCGLT\mathcal{L}^{\text{CGLT}}) attains 0.9141±0.00140.9141 \pm 0.0014 for a +0.83+0.83,pp gain over LeJEPA(LSIGReg\mathcal{L}^{\text{SIGReg}}) with ∼30%\sim 30\% lower seed standard deviation; on matched-recipe Galaxy10~SDSS, a single-seed ImageNet-100100 run, and a 33-seed EuroSAT remote-sensing run, the two methods lie in the same peak-accuracy band at convergence, with UR-JEPA retaining its lower-seed-variance signature. On EuroSAT the in-domain pair is competitive at 96.096.0 to 96.1%96.1\% with large remote-sensing foundation-model transfer at a 25×25\times smaller backbone. The distinction is geometric: direct visualization of the projector output distribution shows that on all four datasets UR--JEPA(LCGLT\mathcal{L}^{\text{CGLT}}) produces a global PCA spectrum with a 44 to 55 order-of-magnitude drop at index ∼20\sim 20 to 2525 out of D=32D = 32, while LeJEPA's spectrum is near-flat (top-to-bottom ratio at most 3.63.6). Per-dimension marginals are simultaneously near-Gaussian for both methods (mean Shapiro-Wilk W∈[0.992,0.996]W \in [0.992, 0.996]) as a Diaconis-Freedman consequence. At matched accuracy the two regularizers therefore yield structurally distinct projected representations.

Triet M. Le

Joint-Embedding Predictive ArchitectureGeometric Representation LearningSelf-Supervised Visual Representation LearningLatent-Space Regularization
AskPDF
May 31, 2026

BRo-JEPA: Learning Modular Arithmetic in Latent Space

Can neural networks learn abstract algebraic rules, or do they merely memorize training patterns? We investigate this using MNIST digits as states and modular arithmetic operations as actions in a JEPA-style latent world model. Standard supervised baselines and JEPA models with additive operation embeddings fit seen operations but fail to extrapolate reliably to unseen ones. To bridge this gap, we introduce a block-rotation predictor that imposes the circular structure of modulo-10 arithmetic in latent space. This enables strong zero-shot generalization, with the best ResNet-based JEPA block-rotation model achieving 99.46% zero-shot and 99.46% rollout accuracy. Our results suggest that latent world models can learn symbolic transformation rules when architecture matches the structure of the problem. Our code can be accessed here.

Divyansh Jha, Yuanfang Xie, Varan Mehra +1

1Georgia Institute of Technology · 2NYU Langone Health

Zero-Shot LearningJoint-Embedding Predictive ArchitectureLatent World ModelsModular ArithmeticAlgorithmic GeneralizationModular Addition
AskPDF
May 30, 2026

CR-JEPA: Cross-Modal Joint-Embedding Predictive Learning for Remote Sensing Image Retrieval

Cross-modal remote sensing image retrieval aims to retrieve semantically related scenes across heterogeneous sensing modalities. This remains challenging because paired observations may differ substantially in imaging physics, spatial resolution, spectral configuration, and visual appearance. Moreover, a single retrieval projection trained with one objective may be insufficient to jointly support cross-modal semantic alignment and same-modal neighbourhood preservation. We propose CR-JEPA, a Cross-modal Retrieval Joint-Embedding Predictive Architecture for dual-modality remote sensing retrieval. The model uses modality-specific stems, a shared transformer trunk, and JEPA-style predictive objectives to estimate masked latent target features within and across modalities. Inspired by LeJEPA, we apply Sketched Isotropic Gaussian Regularization to raw retrieval projections to stabilize embeddings and mitigate collapse. CR-JEPA further employs a decoupled-head design with a unified retrieval head for same-modal retrieval and a cross-modal retrieval head for cross-modal search. We evaluate CR-JEPA on BEN-14K, CBRSIR_VS, and DSRSID. On BEN-14K, CR-JEPA improves S1 to S2 retrieval from 61.23% to 75.82% and S2 to S1 retrieval from 63.73% to 75.40% over X-JEPA, while also achieving competitive same-modal retrieval with fewer parameters.

Md Aminur Hossain, Ayush V. Patel, Nitant Dube +1

Space Applications Centre, Indian Space Research Organisation, Ahmedabad, India · Centre of Studies in Resources Engineering, Indian Institute of Technology Bombay, Mumbai, India

Cross-Modal Representation LearningJoint-Embedding Predictive ArchitectureRemote SensingCross-Modal Retrieval
AskPDF
May 29, 2026

Giving Sensors a Voice: Multimodal JEPA for Semantic Time-Series Embeddings

Transformer-based architectures have advanced sequence modeling in language and vision, yet general-purpose representation learning for heterogeneous multivariate time series remains underexplored. We introduce CHARM (Channel-Aware Representation Model), which incorporates channel-level textual descriptions into a Transformer encoder equivariant to channel order. CHARM is trained with a Joint Embedding Predictive Architecture (JEPA) and a novel loss promoting informative, temporally stable embeddings; latent-space prediction encourages robustness to sensor noise while description-aware gating provides interpretability through learned inter-channel relationships. Across anomaly detection, classification, and short- and long-term forecasting, the learned embeddings achieve strong performance using only a linear probe. Performance is driven primarily by the JEPA objective and conditioning architecture, with text descriptions serving as channel identifiers for cross-dataset generalization.

Utsav Dutta, Gerardo Pastrana, Sina Khoshfetrat Pakazad +1

C3 AI, Redwood City, CA, USA

Multivariate Time Series ForecastingJoint-Embedding Predictive ArchitectureMultimodal EmbeddingTime Series Representation LearningTime-Series Anomaly DetectionTemporal Representation Learning
AskPDF
May 29, 2026

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

World models used for planning learn to predict how a scene evolves, yet they rarely hold a global view of how far a task has progressed. We argue that such a view should be part of the representation, and that it can be compact: describing a scene takes many dimensions, but where the scene stands on its way to the goal can be summarised by only a few. We propose SD-JEPA, a joint-embedding predictive world model whose latent is split into a small progression subspace and a large content subspace. A temporal triplet loss keeps consecutive frames of a trajectory close in the progression coordinates and separates different trajectories, while a distributional regulariser keeps the content coordinates from collapsing. On four control benchmarks, the model plans as well as the same architecture without the split. In return, its latent becomes easier to read. A few percent of its dimensions are enough to predict progress within an episode, and the angle they form follows the task, moves backward when the agent backtracks and changes fastest around events such as grasps and releases. Surprise also becomes anchored in the trajectory: when the scene changes mid-episode, the angle spikes and then relocalizes on a new part of the progression, anchoring surprise in the agent's own map of the task.

Lucas Thil, Jesse Read, Rim Kaddah +1

LIX, École Polytechnique Palaiseau, France · IRT SystemX Palaiseau, France · Safran Tech Chateaufort, France

Disentangled Representation LearningRepresentation LearningJoint-Embedding Predictive ArchitectureLatent World Models
AskPDF
May 29, 2026

HQ-JEPA: Hybrid Quantum Joint-Embedding Predictive Architecture for Cross-Modal Remote Sensing Representation Learning

We introduce HQ-JEPA, a hybrid quantum-classical joint-embedding predictive architecture for cross-modal remote sensing representation learning. The proposed framework extends JEPA-style masked latent prediction to paired Sentinel-1 and Sentinel-2 imagery by predicting masked target representations from visible context regions while aligning heterogeneous modality features in a shared embedding space. To improve representation quality, HQ-JEPA combines four complementary objectives: latent token prediction, cross-modal token alignment, SIGReg-based Gaussian regularization in the fused latent space, and a differentiable SWAP-test-based Fidelity Quantum Similarity (FQS) loss. Unlike pixel reconstruction methods, HQ-JEPA learns semantic representations directly in latent space and uses quantum state-overlap-based similarity as an additional regularization signal. We evaluate the pretrained encoder on GeoBench classification and segmentation tasks under linear probing and fine-tuning settings. Results show that HQ-JEPA achieves competitive and often superior performance over strong self-supervised and remote sensing foundation-model baselines, demonstrating the benefit of integrating predictive self-supervision, cross-modal geometric regularization, and quantum fidelity-based representation learning for remote sensing applications.

Md Aminur Hossain, Ayush V. Patel, Sanjay K. Singh +1

Space Applications Centre, Indian Space Research Organisation, Ahmedabad, India · Centre of Studies in Resources Engineering, Indian Institute of Technology Bombay, Mumbai, India

Representation LearningCross-Modal Representation LearningCross-Modal AlignmentJoint-Embedding Predictive ArchitectureHybrid Quantum-Classical MLSelf-Supervised Visual Representation Learning
AskPDF
May 26, 2026

SPHERE-JEPA: Spherical Prediction with Homogeneous Embeddings

A fundamental open question in self-supervised learning (SSL) is the explicit characterization of the optimal geometry of the learned representations. Recently, LeJEPA identified isotropic Gaussian embeddings as optimal for minimizing downstream prediction risk in Euclidean spaces. However, the corresponding problem for distributions supported on lower-dimensional manifolds, such as the hypersphere, remains unexplored. In this work, we demonstrate that extending this minimax analysis to smooth distributions on Riemannian manifolds fundamentally changes the optimal solution. We show that, under a worst-case formulation, both k-nearest neighbors and kernel ridge regression induce hyperspherical uniformity. More precisely, we show that uniform distributions on manifolds are optimal for k-nearest neighbors, and that the uniform distribution on the sphere is optimal for kernel ridge regression with both the exponential dot-product kernel and the linear kernel. This theoretical insight reveals a fundamental limitation of Gaussian embeddings: their non-uniform density induces anisotropic k-NN neighborhoods, severely biasing the estimator. To correct this, we introduce SPHERE-JEPA, a theoretically grounded SSL framework. We adapt LeJEPA's Cram{é}r-Wold projection mechanism to enforce hyperspherical uniformity rather than a Gaussian prior. Empirically, SPHERE-JEPA yields significant improvements, boosting texture retrieval mAP by over 6%, while consistently matching or outperforming LeJEPA on standard benchmarks-including a +1.8% linear probing gain on ImageNet-1K (ViT-B/14).

L{é}o Nicollier, Max Dunitz, Marc Pic +3

CB,ATT · ATT · CB,IFUMI +1

Self-Supervised LearningJoint-Embedding Predictive ArchitectureHyperspherical Representation LearningGeometric Representation LearningManifold LearningLatent Space Geometry
AskPDF
May 25, 2026

When Does LeJEPA Learn a World Model?

A representation that scrambles the true degrees of freedom of the world cannot support reliable planning or compositional generalization. We prove that LeJEPA (alignment plus Gaussian regularization) linearly recovers the world's latent variables from nonlinear observations, a property known as linear identifiability, in a broad class of worlds where latents evolve under stationary, additive-noise transitions. Our main result is that among all such worlds, the Gaussian is the unique latent distribution for which this guarantee holds. The forward direction rests on a spectral decomposition in which each degree of nonlinearity is strictly penalized by alignment, making the linear map the optimum; the converse rules out every non-Gaussian alternative. We further prove an approximate identifiability result where the guarantee degrades gracefully, and show that linear, orthogonal identifiability enables optimal latent-space planning. We validate the theory with experiments ranging from 2D examples to 1024-dimensional latents, including distributional ablations and pixel-based robotic control. Our theory turns an empirically successful recipe into a mathematical guarantee, providing the foundation for building World Models that provably recover the structure of the world.

David Klindt, Yann LeCun, Randall Balestriero

Cold Spring Harbor Laboratory · New York University · Brown University

World Model LearningRepresentation IdentifiabilityParameter IdentifiabilityLatent Dynamics ModelingJoint-Embedding Predictive ArchitectureModel-Based Planning
AskPDF
May 25, 2026

UWM-JEPA: Predictive World Models That Imagine in Belief Space

World models for partially observed environments must imagine multiple compatible hidden futures and steer between them under counterfactual actions. Joint Embedding Predictive Architectures (JEPAs) do this in latent space, but a vector-valued latent has no internal structure for carrying the belief over hidden continuations through blind rollout. We introduce the Unitary World Model JEPA (UWM-JEPA), a JEPA world model with a density-matrix latent on a joint system-environment space and a learned unitary predictor. The construction preserves the joint-state spectrum exactly during rollout, so the predictor itself cannot dissipate the represented uncertainty. On a hidden-velocity indicator task requiring five-step forward simulation under a given action sequence with the target observation masked, UWM-JEPA reaches 0.77 accuracy and degrades monotonically as actions are perturbed; a parameter-matched LSTM-JEPA trained under the same counterfactual-target objective and action head collapses to majority-class accuracy (0.53) under every action condition. Under blind rollout, UWM-JEPA loses fewer than ten points of probe R^2 at short horizons while vector-latent baselines lose forty-one and sixty-eight; both nevertheless tie on a held-out context probe, locating the separation in the predictor rather than the encoder. Action sensitivity itself requires training against counterfactual rather than teacher-forced targets, a finding that applies beyond the unitary parameterisation. For JEPA world models to imagine under partial observability, latent geometry and predictor dynamics matter, not frozen context-encoding capacity alone.

Santosh Kumar Radha, Oktay Goktas

AgentField AI, Toronto, Canada

World Model LearningLatent Dynamics ModelingJoint-Embedding Predictive ArchitectureAction-Conditioned World Models
AskPDF
May 24, 2026

DLLM-JEPA: Joint Embedding Predictive Architectures for Masked Diffusion Language Models

Joint Embedding Predictive Architectures (JEPAs) have reshaped self-supervised representation learning in vision. The recent LLM-JEPA ported JEPA to autoregressive language models but inherited two steep costs from the causal-attention substrate: it demands explicit multi-view data (e.g., text-code pairs), and it requires two gradient-carrying forward passes per step. We introduce DLLM-JEPA, which pairs JEPA with masked-diffusion language models to eliminate both costs at once. The bidirectional attention of diffusion models yields two semantically distinct views of the same input via different masking rates -- no explicit pairs needed -- and supports a single gradient-carrying forward pass, cutting training FLOPs by 33% relative to LLM-JEPA. DLLM-JEPA improves over diffusion-only fine-tuning in every (task, architecture) combination we evaluate: up to +18.7 pp on LLaDA-8B GSM8K and +11.4 pp on Dream-7B GSM8K, with consistent positive gains on Spider, NL-RX-SYNTH, and Django. Beyond accuracy, DLLM-JEPA exhibits a dual-win property: on LLaDA-8B with the Wide-t configuration, it simultaneously raises GSM8K accuracy (67.1 vs. 65.2, +1.8 pp), drives held-out Wikitext loss below the pre-trained base, and preserves MMLU accuracy at base level across three fine-tuning seeds -- whereas an L2-to-base parameter anchor matches baseline accuracy with no task gain. Layer-wise probing reveals the mechanism: a geometric-functional drift dissociation in which the fine-tuned backbone moves further from the pre-trained weights than the baseline yet forgets less on held-out Wikitext, with the amplification concentrated in middle transformer layers. The pattern appears on Dream-7B as well, indicating the phenomenon is not specific to a single backbone.

Sangdae Nam

VESSL AI

Masked Diffusion ModelsJoint-Embedding Predictive ArchitectureDiffusion Model Fine-TuningDiffusion Language Models
AskPDF
May 20, 2026

Demo-JEPA: Joint-Embedding Predictive Architecture for One-shot Cross-Embodiment Imitation

Robotic imitation learning is often treated as reproducing demonstrated actions, but actions are inherently embodiment-specific. When demonstrations come from humans or robots with different morphology, kinematics, or action spaces, this action-centric view requires shared action spaces, heuristic retargeting, or large-scale multi-embodiment co-training. We instead view demonstrations as implicit specifications of future goals: the target agent should infer what state the demonstrator is trying to realize, rather than how the demonstrator executes it. We propose Demo-JEPA, a cross-embodiment imitation framework that decouples demonstration intent from embodiment-specific execution. Built on a JEPA-based world model, Demo-JEPA translates source visual demonstrations into target-compatible future latent trajectories in a shared predictive representation space. The target agent then uses these latent trajectories as subgoals and realizes them through planning under its own learned forward dynamics. Because Demo-JEPA avoids action-level correspondence and requires only visual demonstrations plus the target agent's own interaction experience, it supports flexible imitation across heterogeneous embodiments. Experiments on RLBench and real-world manipulation tasks show that Demo-JEPA matches specialized in-domain planners and generalizes to unseen tasks and embodiment configurations where prior methods fail.

Jingyang He, Guangrun Li, Jieyu Zhang +3

State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University · Beijing Innovation Center of Humanoid Robotics · University of Washington

Robot Skill LearningWorld Models for RoboticsJoint-Embedding Predictive ArchitectureGeneralization in Robotic ManipulationCross-Embodiment Robot LearningImitation Learning+1
AskPDF
May 19, 2026

Beyond Isotropy in JEPAs: Hamiltonian Geometry and Symplectic Prediction

JEPAs often regularize one-view embeddings toward an isotropic Gaussian, implicitly baking Euclidean symmetry into the representation. We show that this is not merely a benign default. For a known structured downstream geometry H≻0H\succ0, the minimax and maximum-entropy covariance under a Hamiltonian energy budget is (c/d)H−1(c/d)H^{-1}, and Euclidean isotropy incurs a closed-form price of isotropy. More importantly, when the downstream geometry is unknown, no geometry-independent fixed marginal target is canonical: every fixed covariance shape can be maximally misaligned for some structured geometry. We further show that even oracle one-view marginals do not identify the JEPA view-to-view predictive coupling. These results suggest that the structural bias in JEPAs should enter the cross-view coupling rather than a fixed encoder marginal. We instantiate this principle with HamJEPA, which encodes each view as a phase-space state (q,p)(q,p) and predicts view-to-view transitions with a learned Hamiltonian leapfrog map, while non-isotropic scale and spectral floors prevent collapse. In a deliberately headless token protocol, HamJEPA improves over SIGReg on CIFAR-100 by +4.89+4.89 kNN@20 and +3.52+3.52 linear-probe points at 30 epochs, and by +6.45+6.45 kNN@20 and +10.64+10.64 linear-probe points at 80 epochs, while a matched MLP predictor ablation shows that the symplectic coupling is the ingredient driving the neighborhood-geometry gain. On ImageNet-100, HamJEPA-qq improves by +4.82+4.82 kNN@20 and +7.52+7.52 linear-probe points at 45 epochs.

Robert Jenkinson Alvarez

Joint-Embedding Predictive ArchitectureGeometric Representation LearningSymplectic RNNsSelf-Supervised Visual Representation LearningHamiltonian Dynamics
AskPDF
May 17, 2026

PEIRA: Learning Predictive Encoders through Inter-View Regressor Alignment

Non-contrastive self-supervised learning (SSL) is an effective framework for predictive representation learning, but popular (and in practice effective) methods such as SimSiam, BYOL, I-JEPA or DINO, which rely on a form of self-distillation to train a teacher-student network, remain poorly understood as they typically do not minimize a well-defined objective. We analyze the dynamics of a variant of the Joint Embedding Predictive Architecture (JEPA) using a regularized linear regressor to predict the learned representations of two views of the data from one another, and fully characterize its stability: non-collapsed stable equilibria align with leading nonlinear canonical correlation subspaces, while collapsed equilibria may also be stable attractors. Motivated by this result, we introduce PEIRA, a non-contrastive SSL method with an explicit objective defined through the trace of the optimal linear regressor. We show that its only stable equilibria are nontrivial global minimizers and recover the same canonical correlation subspaces, with regularization selecting the effective dimension. Experiments on ImageNet-1K and CIFAR-10 show PEIRA is competitive with VICReg and LeJEPA baselines, and qualitative empirical results support the theory.

Michael Arbel, Basile Terver, Jean Ponce

Univ. Grenoble Alpes, Inria · CNRS, Grenoble INP, LJK · Ecole Normale Supérieure / PSL +2

Unsupervised LearningVisual Representation LearningSelf-Supervised LearningJoint-Embedding Predictive ArchitecturePredictive Representation LearningCanonical Correlation Analysis
AskPDF
May 16, 2026

Factorized Latent Dynamics for Video JEPA: An Empirical Study of Auxiliary Objectives

Joint-Embedding Predictive Architectures (JEPA) are a promising framework for self-supervised video representation learning, yet the behavior of auxiliary objectives in small-scale Video-JEPA training is not well characterized. We report a small-scale empirical study of 18 auxiliary objective variants for Video-JEPA across two pretraining regimes: single-dataset (UCF-101) and mixed-dataset (UCF-101 + Something-Something V2 + ImageNet-100). We evaluate frozen representations on three complementary benchmarks: Diving-48 (fine-grained motion), SomethingSomething V2 (temporal reasoning), and ImageNet-100 (appearance). Our experiments suggest that many auxiliary objectives exhibit capacity trade-offs: gains on one downstream capability often coincide with degradation on another. We then study FWM-HW-LD (Factorized World-Model with Hard-Region-Weighted Latent Dynamics), a training-time objective that separates the latent representation into appearance and dynamics subspaces and applies hard-region weighting to both JEPA prediction errors and latent dynamics errors. In our mixed-dataset setting, FWM-HW-LD improves ImageNet-100 by +5.92 and SSv2 by +3.21 percentage points relative to the reference baseline, while remaining within 0.30 percentage points on Diving-48. These results indicate that latent factorization is a useful direction for studying auxiliary-objective trade-offs in Video-JEPA.

Santosh Premi

Disentangled Representation LearningLatent Dynamics ModelingJoint-Embedding Predictive ArchitectureVideo Action RecognitionVideo Representation Learning
AskPDF
May 14, 2026

Entity-Centric World Models: Interaction-Aware Masking for Causal Video Prediction

Learning predictive world models from unlabelled video is a foundational challenge in artificial intelligence. While Joint Embedding Predictive Architectures (JEPA) have set new benchmarks in semantic classification, they often remain physics-blind, failing to capture the causal dynamics necessary for downstream reasoning. We hypothesize that this stems from standard patch-based masking strategies, which prioritize visual texture over rare but informative kinematic events. We propose Interaction-Aware JEPA (IA-JEPA), which utilizes a self-supervised motion-centric masking strategy to prioritize physical interactions. By specifically targeting entities engaged in collisions or momentum transfers, we force the architecture to reconstruct latent trajectories rather than static background features. Evaluated on the CLEVRER benchmark, IA-JEPA achieves 14.26% accuracy on causal reasoning tasks, a significant lead over the 3.22% achieved by standard patch-masked baselines. Crucially, we demonstrate that IA-JEPA breaks the "static bias" of standard self-supervision by inducing a higher-entropy, more discriminative latent space (+10% entropy gain) that linearizes physical energy (R2=0.43R^2=0.43). We show that this interaction bias generalizes to real-world human actions (Something-Something V2) and zero-shot physical puzzles (PHYRE-Lite). Our results provide a scalable, fully self-supervised path toward building foundational world models that begin to internalize the causal structure of the physical world.

Santosh Kumar Paidi

Genentech, Inc.

World Model LearningCausal World ModelsJoint-Embedding Predictive ArchitectureVideo PredictionCausal Reasoning in VideosPhysical Reasoning in Video+1
AskPDF
May 14, 2026

Representation Without Reward: A JEPA Audit for LLM Fine-Tuning

Joint-embedding predictive architectures (JEPAs) propose that a model should learn more useful abstractions when trained to predict latent representations rather than observed outputs. For autoregressive language-model fine-tuning the principle entails a stricter requirement: the induced hidden-state geometry must reach the language-model head and improve the decoded task metric. We test that requirement under a fixed Llama-3.2-1B-Instruct LoRA harness on natural-language-to-regex generation, comparing twenty-two training-time auxiliaries across trajectory-shape regularisation, distributional constraints, predictor/target asymmetry, Fisher-metric Jacobi residuals, and a decoder-visible JEPA objective constructed to lie in cross-entropy's positive cone. The empirical answer is a structured null: several auxiliaries clear single-cell paired α=0.10α= 0.10 without correction (T3-Local at Δ=+2.53Δ= +2.53~pp, p=0.003p = 0.003 being the strongest), but none survives Bonferroni or Holm--Bonferroni at the relevant family-wise threshold, even though many change curvature, anisotropy, variance, and gradient direction. Decoder-visible JEPA yields the first positive auxiliary--cross-entropy gradient cosine in the study, yet exact match remains inside seed noise; a full-fine-tuning replication of the same auxiliary at n=5n = 5 seeds reproduces the null on both benchmarks (TURK: Δ=+0.04Δ= +0.04~pp, ppaired=0.96p_{\text{paired}} = 0.96; SYNTH: Δ=+0.52Δ= +0.52~pp, ppaired=0.28p_{\text{paired}} = 0.28), so the null is robust across LoRA and full fine-tuning for the decoder-visible construction. Hidden-state representation work and decoded-task accuracy are therefore weakly coupled in this regime; we accordingly reframe LLM-domain JEPA evaluation as a coupling problem, in which the operative question is under which metrics useful hidden geometry becomes decoder-visible task signal.

Biswa Sengupta

LLM Suite Team, JPMorgan Chase & Co.

LLM AuditingLLM Fine-TuningJoint-Embedding Predictive ArchitectureRepresentation Geometry in Language Models
AskPDF
May 14, 2026

Crys-JEPA: Accelerating Crystal Discovery via Embedding Screening and Generative Refinement

De novo crystal generation seeks to discover materials that are not merely realistic, but also stable and novel. However, most existing generative models are trained to maximize the likelihood of observed crystals, which encourages samples to stay close to known materials yet not necessarily align with the criteria that matter in discovery. Our empirical analysis shows that current crystal generative models exhibit a clear conflict between stability and novelty: samples near the observed distribution tend to retain stability but offer limited novelty, whereas samples farther from it often lose stability rapidly. This suggests that the useful region for discovering crystals that are both stable and novel is extremely narrow. To move beyond this limitation, we introduce Crys-JEPA, a joint embedding predictive architecture for crystals that learns an energy-aware latent space preserving formation-energy differences. In this space, stability assessment can be reformulated as an embedding-based comparison against accessible training crystals, reducing the reliance on expensive energy evaluation and task-specific external references. Building on Crys-JEPA, we further develop a screening-and-refinement pipeline that identifies promising generated crystals and reintroduces them to refine the generative model. On MP-20 and Alex-MP-20 datasets, we achieve improvements over baselines up to 53.8% and 72.7% on V.S.U.N. metric, respectively.

Nian Liu, Nikita Kazeev, Stephen Gregory Dale +8

1National University of Singapore · 2Loyola Marymount University · 3New York University +1

Joint-Embedding Predictive ArchitectureGenerative ModelingCrystal Structure GenerationComputational Materials ScienceMaterials Discovery
AskPDF
May 13, 2026

Mini-JEPA Foundation Model Fleet Enables Agentic Hydrologic Intelligence

Geospatial foundation models compress multispectral observations into dense embeddings increasingly used in natural-language environmental reasoning systems. A single planetary-scale model, e.g. Google AlphaEarth, handles broad characterization well but may compromise on specialized hydrologic signals. Such generalist models are also often inaccessible, expensive, and require large-scale compute. We propose Mini-JEPAs: a fleet of small sensor-specialized Joint Embedding Predictive Architecture (JEPA) foundation models consulted by a routing agent for specialized questions. We pretrained five 22M-parameter Mini-JEPAs sharing an identical Vision Transformer backbone, JEPA recipe, and 64-d output space, using Sentinel-2 optical, Sentinel-1 SAR, MODIS thermal, multi-temporal Sentinel-2 phenology, and a topography-soil stack. Each Mini-JEPA reconstructs the variable matched to its sensor, with cross-validated R2R^2 reaching 0.97 for elevation, 0.97 for temperature, and 0.81 for precipitation. The five manifolds differ in geometric structure, with global participation ratios from 8.9 to 20.2 and local intrinsic dimensionalities from 2.3 to 9.0. Joint topography-soil and phenology models add predictive value beyond AlphaEarth alone for soil moisture, aridity, and precipitation (ΔR2ΔR^2 up to 0.031). A router LLM reads per-modality references and selects appropriate sensors with a perfect hit rate over a curated question set. In paired LLM-as-Judge evaluation, dual retrieval over AlphaEarth and the routed fleet outperforms AlphaEarth alone on physics-matched questions (Cohen's d=1.10d = 1.10, p=0.031p = 0.031). Locally-trained Mini-JEPAs can be operationalized for hydrologic intelligence with modest compute.

Mashrekur Rahman

Dartmouth Libraries, Dartmouth College, 6025 Baker-Berry Library, Hanover, 03755, NH, USA

Geospatial Foundation ModelsGeospatial Representation LearningJoint-Embedding Predictive ArchitectureRemote SensingGeospatial ReasoningHydrology
AskPDF
May 13, 2026

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

Diffusion world models have recently become competitive for online model-based reinforcement learning, but current approaches expose a tension: pixel diffusion is effective but computationally expensive while the latest latent diffusion approach improves efficiency yet performs subpar. The latter also relies on separately trained latents rather than the end-to-end world-model objectives that have driven much of modern MBRL progress. In particular, JEPA-style predictive representation learning has emerged as an especially promising direction for world modeling and MBRL. Concurrently, diffusion-style objectives have gained traction across multiple domains, with iterative refinement as a promising approach for multimodal and stochastic targets. Taken together, these trends motivate Joint Embedding DIffusion (JEDI), the first online end-to-end latent diffusion world model. JEDI learns its latent space directly from the diffusion denoising loss with a JEPA framework, using denoising to learn and predict future latents rather than relying on reconstruction and pretrained models. We provide a theoretical motivation showing that conventional JEPA objectives induce a predictive information bottleneck, and that conditional diffusion denoising admits a closely related predictive-compression decomposition. Empirically, JEDI is competitive on Atari100k and outperforms the baseline with seperately trained latents where directly comparable. Relative to the pixel diffusion baseline, JEDI uses 43% less VRAM, over 3×\times faster world-model sampling, and 2.5×\times faster training. JEDI also exhibits a markedly different task-level performance profile from the pixel baseline, suggesting that end-to-end predictive latents change more than compute alone.

Jing Yu Lim, Rushi Shah, Zarif Ikram +4

National University of Singapore · usc

World Model LearningJoint-Embedding Predictive ArchitectureRepresentation Learning for RLLatent World ModelsModel-Based RL
AskPDF