{"total":254,"rows":[{"id":"2603.19312","title":"LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels","created":"2026-03-13","cited_by_count":273,"area":"wm"},{"id":"2603.14482","title":"V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning","created":"2026-03-15","cited_by_count":117,"area":null},{"id":"2512.10942","title":"VL-JEPA: Joint Embedding Predictive Architecture for Vision-language","created":"2025-12-11","cited_by_count":68,"area":"mllm"},{"id":"2603.12231","title":"Temporal Straightening for Latent Planning","created":"2026-03-12","cited_by_count":38,"area":"wm"},{"id":"2605.26379","title":"When Does LeJEPA Learn a World Model?","created":"2026-05-25","cited_by_count":30,"area":"wm"},{"id":"2605.21800","title":"stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation","created":"2026-05-20","cited_by_count":20,"area":"wm"},{"id":"2606.20104","title":"Sensorimotor World Models: Perception for Action via Inverse Dynamics","created":"2026-06-18","cited_by_count":20,"area":"wm"},{"id":"2606.32026","title":"AdaJEPA: An Adaptive Latent World Model","created":"2026-06-30","cited_by_count":20,"area":"wm"},{"id":"2605.07278","title":"Predictive but Not Plannable: RC-aux for Latent World Models","created":"2026-05-08","cited_by_count":19,"area":"wm"},{"id":"2602.24012","title":"InfoNCE Induces Gaussian Distribution","created":"2026-02-27","cited_by_count":16,"area":null},{"id":"2606.02572","title":"VISReg: Variance-Invariance-Sketching Regularization for JEPA training","created":"2026-06-01","cited_by_count":16,"area":null},{"id":"2605.08732","title":"Latent Geometry Beyond Search: Amortizing Planning in World Models","created":"2026-05-09","cited_by_count":15,"area":"wm"},{"id":"2606.26217","title":"Fast LeWorldModel","created":"2026-06-24","cited_by_count":15,"area":"wm"},{"id":"2606.31232","title":"Delta-JEPA: Learning Action-Sensitive World Models via Latent Difference Decoding","created":"2026-06-30","cited_by_count":15,"area":"wm"},{"id":"2602.03604","title":"A Lightweight Library for Energy-Based Joint-Embedding Predictive Architectures","created":"2026-02-03","cited_by_count":14,"area":"wm"},{"id":"2602.18639","title":"Learning Invariant Visual Representations for Planning with Joint-Embedding Predictive World Models","created":"2026-02-20","cited_by_count":13,"area":"wm"},{"id":"2512.09929","title":"Closing the Train-Test Gap in World Models for Gradient-Based Planning","created":"2025-12-10","cited_by_count":11,"area":"wm"},{"id":"2605.31111","title":"Subspace-Decomposed JEPAs: Disentangling Progression and Content in Latent World Models","created":"2026-05-29","cited_by_count":11,"area":"wm"},{"id":"2602.17162","title":"JEPA-DNA: Grounding Genomic Foundation Models through Joint-Embedding Predictive Architectures","created":"2026-02-19","cited_by_count":9,"area":null},{"id":"2606.23444","title":"SkyJEPA: Learning Long-Horizon World Models for Zero-Shot Sim-to-Real Control of Quadrotors","created":"2026-06-22","cited_by_count":9,"area":"wm"},{"id":"2607.10362","title":"A Control Theory of Predictability in Latent World Models","created":"2026-07-11","cited_by_count":9,"area":"wm"},{"id":"2607.22430","title":"On the Identifiability of Controlled World Models","created":"2026-07-24","cited_by_count":9,"area":"wm"},{"id":"2512.19605","title":"KerJEPA: Kernel Discrepancies for Euclidean Self-Supervised Learning","created":"2025-12-22","cited_by_count":8,"area":null},{"id":"2606.03971","title":"Video-Mirai: Autoregressive Video Diffusion Models Need Foresight","created":"2026-06-02","cited_by_count":8,"area":"diffusion"},{"id":"2607.25337","title":"Temporal-Distance JEPA: Plan-Aware Representation Learning for Latent World Model Predictive Control","created":"2026-07-28","cited_by_count":8,"area":"wm"},{"id":"2608.06799","title":"Is Forward Prediction Enough? Physical State Grounding for JEPA World Models","created":"2026-08-07","cited_by_count":8,"area":"wm"},{"id":"2608.22764","title":"LpWM: A Case for Sparse Representations in World Models","created":"2026-08-24","cited_by_count":8,"area":"wm"},{"id":"2608.18746","title":"Decision-Metric Alignment in Latent World Models: Diagnostics and Action-Conditioned Objectives for MPC Planning","created":"2026-08-19","cited_by_count":7,"area":"wm"},{"id":"2604.01987","title":"Curia-2: Scaling Self-Supervised Learning for Radiology Foundation Models","created":"2026-04-02","cited_by_count":6,"area":null},{"id":"2606.30534","title":"Orca: The World is in Your Mind","created":"2026-06-29","cited_by_count":6,"area":null},{"id":"2608.05720","title":"PhyLatent: Learning Dynamics-Relevant Representations for JEPA World Models","created":"2026-08-06","cited_by_count":6,"area":"wm"},{"id":"2602.12540","title":"Self-Supervised JEPA-based World Models for LiDAR Occupancy Completion and Forecasting","created":"2026-02-13","cited_by_count":5,"area":"wm"},{"id":"2602.19373","title":"Stable Deep Reinforcement Learning via Isotropic Gaussian Representations","created":"2026-02-22","cited_by_count":5,"area":"deeprl"},{"id":"2605.23993","title":"Nano World Models: A Minimalist Implementation of Future Video Prediction","created":"2026-05-17","cited_by_count":5,"area":"wm"},{"id":"2605.26900","title":"SPHERE-JEPA: Spherical Prediction with Homogeneous Embeddings","created":"2026-05-26","cited_by_count":5,"area":null},{"id":"2606.15956","title":"You Don't Need Strong Assumptions: Visual Representation Learning via Temporal Differences","created":"2026-06-14","cited_by_count":5,"area":null},{"id":"2606.27014","title":"A Generalization Theory for JEPA-Based World Models","created":"2026-06-25","cited_by_count":5,"area":"wm"},{"id":"2607.00958","title":"LeNEPA: No-Augmentation Next-Latent Prediction for Time-Series Representation Learning","created":"2026-07-01","cited_by_count":5,"area":null},{"id":"2607.02403","title":"ACID: Action Consistency via Inverse Dynamics for Planning with World Models","created":"2026-07-02","cited_by_count":5,"area":"wm"},{"id":"2607.28415","title":"QQWorld: Quantile-Quantile Matching for World Model Regularization","created":"2026-07-30","cited_by_count":5,"area":"wm"},{"id":"2608.17542","title":"No Gaussian Required: Contrastive Inverse Dynamics for JEPA World Models","created":"2026-08-18","cited_by_count":5,"area":"wm"},{"id":"2511.17354","title":"DSeq-JEPA: Discriminative Sequential Joint-Embedding Predictive Architecture","created":"2025-11-21","cited_by_count":4,"area":null},{"id":"2603.16281","title":"Laya: A LeJEPA Approach to EEG via Latent Prediction over Reconstruction","created":"2026-03-17","cited_by_count":4,"area":null},{"id":"2603.19100","title":"LuMamba: Latent Unified Mamba for Electrode Topology-Invariant and Efficient EEG Modeling","created":"2026-03-19","cited_by_count":4,"area":"ssm"},{"id":"2603.20111","title":"Var-JEPA: A Variational Formulation of the Joint-Embedding Predictive Architecture - Bridging Predictive and Generative Self-Supervised Learning","created":"2026-03-20","cited_by_count":4,"area":null},{"id":"2603.25981","title":"Policy-Guided World Model Planning for Language-Conditioned Visual Navigation","created":"2026-03-26","cited_by_count":4,"area":"wm"},{"id":"2605.03517","title":"Understanding Self-Supervised Learning via Latent Distribution Matching","created":"2026-05-05","cited_by_count":4,"area":null},{"id":"2605.05586","title":"AeroJEPA: Learning Semantic Latent Representations for Scalable 3D Aerodynamic Field Modeling","created":"2026-05-07","cited_by_count":4,"area":null},{"id":"2605.14759","title":"Crys-JEPA: Accelerating Crystal Discovery via Embedding Screening and Generative Refinement","created":"2026-05-14","cited_by_count":4,"area":null},{"id":"2605.15960","title":"Imperfect World Models are Exploitable","created":"2026-05-15","cited_by_count":4,"area":"wm"},{"id":"2606.15594","title":"Pixels to Proofs: Probabilistically-Safe Latent World Model Control via Parallel Conformal Robust MPC","created":"2026-06-14","cited_by_count":4,"area":"wm"},{"id":"2607.04978","title":"Qantara: Bridge-Flow Training for Multi-Paradigm JEPA Control","created":"2026-07-06","cited_by_count":4,"area":"wm"},{"id":"2607.26924","title":"Temporally Centered SIGReg Improves LeWorldModel Representations for Robot Policy Learning","created":"2026-07-29","cited_by_count":4,"area":"wm"},{"id":"2607.27924","title":"ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow","created":"2026-07-30","cited_by_count":4,"area":"wm"},{"id":"2607.29613","title":"WCM: A World Critic Model for Vision-Language-Action Reinforcement Learning","created":"2026-07-31","cited_by_count":4,"area":"vla"},{"id":"2608.16287","title":"SCALE: State-Calibrated Latent Embeddings for JEPA Planning in the Right Geometry","created":"2026-08-17","cited_by_count":4,"area":"wm"},{"id":"2608.19613","title":"What Matters for Latent Actions in Robot Learning","created":"2026-08-20","cited_by_count":4,"area":null},{"id":"2601.22128","title":"The Patient is not a Moving Document: A World Model Training Paradigm for Longitudinal EHR","created":"2026-01-29","cited_by_count":3,"area":"wm"},{"id":"2602.01536","title":"UniDWM: Towards a Unified Driving World Model via Multifaceted Representation Learning","created":"2026-02-02","cited_by_count":3,"area":"wm"},{"id":"2603.21786","title":"The Universal Normal Embedding","created":"2026-03-23","cited_by_count":3,"area":"diffusion"},{"id":"2603.22649","title":"Pretext Matters: An Empirical Study of SSL Methods in Medical Imaging","created":"2026-03-23","cited_by_count":3,"area":null},{"id":"2603.23308","title":"Curriculum-Driven 3D CT Report Generation via Language-Free Visual Grafting and Zone-Constrained Compression","created":"2026-03-24","cited_by_count":3,"area":null},{"id":"2605.00742","title":"Position: agentic AI orchestration should be Bayes-consistent","created":"2026-05-01","cited_by_count":3,"area":"agents"},{"id":"2605.20107","title":"Beyond Isotropy in JEPAs: Hamiltonian Geometry and Symplectic Prediction","created":"2026-05-19","cited_by_count":3,"area":null},{"id":"2605.23033","title":"Uncovering the Latent Potential of Deep Intermediate Representations","created":"2026-05-21","cited_by_count":3,"area":null},{"id":"2606.09457","title":"$\\omega$-EVA: Envision, Verify, and Act with Latent Interactive World Models","created":"2026-06-08","cited_by_count":3,"area":"wm"},{"id":"2606.14813","title":"JetParticle-JEPA: An Efficient Self-Supervised Representation Learning method for Jet Tagging in High-Energy Physics","created":"2026-06-12","cited_by_count":3,"area":null},{"id":"2606.17603","title":"Expanding SPHERE-JEPA: A Family of Statistical Regularizers for the Hypersphere","created":"2026-06-16","cited_by_count":3,"area":null},{"id":"2607.27017","title":"What Can Latent World Models Know? Physical Parameter Identifiability in Multimodal Predictive Representations","created":"2026-07-29","cited_by_count":3,"area":"wm"},{"id":"2608.01926","title":"ProWorld: Progress-Aware Hyperbolic World Models for Long-Horizon Visual Goal Reaching","created":"2026-08-03","cited_by_count":3,"area":"wm"},{"id":"2608.27395","title":"LeVJEPA: Efficient & Scalable Video Pretraining without the Heuristics","created":"2026-08-27","cited_by_count":3,"area":null},{"id":"2602.03282","title":"Global Geometry Is Not Enough for Vision Representations","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2603.05924","title":"Weak-SIGReg: Covariance Regularization for Stable Deep Learning","created":"2026-03-06","cited_by_count":2,"area":null},{"id":"2604.08960","title":"Efficient Hierarchical Implicit Flow Q-learning for Offline Goal-conditioned Reinforcement Learning","created":"2026-04-10","cited_by_count":2,"area":"offlinerl"},{"id":"2604.18058","title":"Sonata: A Hybrid World Model for Inertial Kinematics under Clinical Data Scarcity","created":"2026-04-20","cited_by_count":2,"area":"wm"},{"id":"2605.11130","title":"HEPA: A Self-Supervised Horizon-Conditioned Event Predictive Architecture for Time Series","created":"2026-05-11","cited_by_count":2,"area":null},{"id":"2605.13013","title":"JEDI: Joint Embedding Diffusion World Model for Online Model-Based Reinforcement Learning","created":"2026-05-13","cited_by_count":2,"area":"wm"},{"id":"2605.21075","title":"SpectralEarth-FM: Bringing Hyperspectral Imagery into Multimodal Earth Observation Pretraining","created":"2026-05-20","cited_by_count":2,"area":null},{"id":"2606.07770","title":"Contrast encodes inductive bias: separating slow noise from dynamics in predictive representation learning","created":"2026-06-05","cited_by_count":2,"area":null},{"id":"2606.20627","title":"Latent Goal Prediction from Language for Model-Based Planning","created":"2026-05-26","cited_by_count":2,"area":"wm"},{"id":"2607.00784","title":"LeVLJEPA: End-to-End Vision-Language Pretraining Without Negatives","created":"2026-07-01","cited_by_count":2,"area":"mllm"},{"id":"2607.13612","title":"The SIGReg Objective as Variational Free Energy: A Theoretical Active-Inference Account of JEPA World Models","created":"2026-07-15","cited_by_count":2,"area":"wm"},{"id":"2607.22000","title":"Music-JEPA: Learning a World Model of Sound from Action","created":"2026-07-24","cited_by_count":2,"area":"wm"},{"id":"2607.24235","title":"Minimax Lower Bounds of Kernel Discrepancy Estimation: MMD, HSIC, KSD","created":"2026-07-27","cited_by_count":2,"area":null},{"id":"2608.06706","title":"Dueling World Models: Advantage-Style Action Channels for Common-Mode Distractor Rejection","created":"2026-08-07","cited_by_count":2,"area":"wm"},{"id":"2608.22642","title":"Mol-JEPA: A multimodal Joint Embedding Predictive Architecture for Molecules","created":"2026-08-23","cited_by_count":2,"area":null},{"id":"2609.03565","title":"Toward Physically Grounded JEPA World Models for Goal-Conditioned Robotic Planning","created":"2026-09-03","cited_by_count":2,"area":"wm"},{"id":"2511.20844","title":"Pre-train to Gain: Robust Learning Without Clean Labels","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2602.04583","title":"PEPR: Privileged Event-based Predictive Regularization for Domain Generalization","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2603.12916","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","created":"2026-03-13","cited_by_count":1,"area":null},{"id":"2603.15263","title":"IConE: Batch Independent Collapse Prevention for Self-Supervised Representation Learning","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2603.24181","title":"Unlocking Few-Shot Capabilities in LVLMs via Prompt Conditioning and Head Selection","created":"2026-03-25","cited_by_count":1,"area":"mllm"},{"id":"2603.24327","title":"Le MuMo JEPA: Multi-Modal Self-Supervised Representation Learning with Learnable Fusion Tokens","created":"2026-03-25","cited_by_count":1,"area":null},{"id":"2604.00383","title":"Mine-JEPA: In-Domain Self-Supervised Learning for Mine-Like Object Classification in Side-Scan Sonar","created":"2026-04-01","cited_by_count":1,"area":null},{"id":"2604.17651","title":"Infrastructure-Centric World Models: Bridging Temporal Depth and Spatial Breadth for Roadside Perception","created":"2026-04-19","cited_by_count":1,"area":"wm"},{"id":"2604.24662","title":"Information bottleneck for learning the phase space of dynamics from high-dimensional experimental data","created":"2026-04-27","cited_by_count":1,"area":null},{"id":"2605.15394","title":"Representation Without Reward: A JEPA Audit for LLM Fine-Tuning","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2605.20581","title":"TriForces: Augmenting Atomistic GNNs for Transferable Representations","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2605.21973","title":"Foresee-to-Ground: From Predictive Temporal Perception to Evidence-Driven Reasoning for Video Temporal Grounding","created":"2026-05-21","cited_by_count":1,"area":"lr"},{"id":"2606.09653","title":"A Unifying Framework for Concept-Based Representational Similarity","created":"2026-06-08","cited_by_count":1,"area":null}],"next_cursor":"100"}