{"total":57,"rows":[{"id":"2407.06886","title":"Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI","created":"2024-07-09","cited_by_count":179,"area":null},{"id":"2405.03520","title":"Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyond","created":"2024-05-06","cited_by_count":111,"area":"wm"},{"id":"2312.08782","title":"Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis","created":"2023-12-14","cited_by_count":103,"area":null},{"id":"2403.02622","title":"World Models for Autonomous Driving: An Initial Survey","created":"2024-03-05","cited_by_count":80,"area":"wm"},{"id":"2605.12090","title":"World Action Models: The Next Frontier in Embodied AI","created":"2026-05-12","cited_by_count":50,"area":"wm"},{"id":"2409.03757","title":"Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understanding","created":"2024-09-05","cited_by_count":49,"area":null},{"id":"2509.20021","title":"Embodied AI: From LLMs to World Models","created":"2025-09-24","cited_by_count":24,"area":"wm"},{"id":"2309.16014","title":"Graph-level Representation Learning with Joint-Embedding Predictive Architectures","created":"2023-09-27","cited_by_count":22,"area":null},{"id":"2601.14354","title":"VJEPA: Variational Joint Embedding Predictive Architectures as Probabilistic World Models","created":"2026-01-20","cited_by_count":17,"area":"wm"},{"id":"2407.15447","title":"SIGMA: Sinkhorn-Guided Masked Video Modeling","created":"2024-07-22","cited_by_count":14,"area":null},{"id":"2409.15803","title":"3D-JEPA: A Joint Embedding Predictive Architecture for 3D Self-Supervised Representation Learning","created":"2024-09-24","cited_by_count":14,"area":null},{"id":"2410.03755","title":"Denoising with a Joint-Embedding Predictive Architecture","created":"2024-10-02","cited_by_count":14,"area":"diffusion"},{"id":"2409.05929","title":"M3-JEPA: Multimodal Alignment via Multi-gate MoE based on the Joint-Embedding Predictive Architecture","created":"2024-09-09","cited_by_count":13,"area":"moe"},{"id":"2406.12913","title":"T-JEPA: A Joint-Embedding Predictive Architecture for Trajectory Similarity Computation","created":"2024-06-13","cited_by_count":12,"area":null},{"id":"2606.20781","title":"World Action Models: A Survey","created":"2026-06-18","cited_by_count":12,"area":"wm"},{"id":"2408.11208","title":"PooDLe: Pooled and dense self-supervised learning from naturalistic videos","created":"2024-08-20","cited_by_count":11,"area":null},{"id":"2512.13684","title":"Recurrent Video Masked Autoencoders","created":"2025-12-15","cited_by_count":10,"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":"2312.02151","title":"Guarding Barlow Twins Against Overfitting with Mixed Samples","created":"2023-12-04","cited_by_count":8,"area":null},{"id":"2405.10093","title":"LaT-PFN: A Joint Embedding Predictive Architecture for In-context Time-series Forecasting","created":"2024-05-16","cited_by_count":8,"area":null},{"id":"2405.02288","title":"Prospective Role of Foundation Models in Advancing Autonomous Vehicles","created":"2023-12-08","cited_by_count":7,"area":null},{"id":"2502.05857","title":"EgoAgent: A Joint Predictive Agent Model in Egocentric Worlds","created":"2025-02-09","cited_by_count":7,"area":"wm"},{"id":"2606.30534","title":"Orca: The World is in Your Mind","created":"2026-06-29","cited_by_count":6,"area":null},{"id":"2403.08109","title":"VANP: Learning Where to See for Navigation with Self-Supervised Vision-Action Pre-Training","created":"2024-03-12","cited_by_count":5,"area":null},{"id":"2605.31580","title":"Giving Sensors a Voice: Multimodal JEPA for Semantic Time-Series Embeddings","created":"2026-05-29","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":"2503.19953","title":"Self-Supervised Learning of Motion Concepts by Optimizing Counterfactuals","created":"2025-03-25","cited_by_count":4,"area":null},{"id":"2606.13877","title":"ContactWorld: What Representations Matter for Vision-Tactile Latent World Models in Contact-Rich Manipulation","created":"2026-06-11","cited_by_count":4,"area":"wm"},{"id":"2602.04880","title":"Capturing Visual Environment Structure Correlates with Control Performance","created":"2026-02-04","cited_by_count":3,"area":"vla"},{"id":"2505.14543","title":"Time to Embed: Unlocking Foundation Models for Time Series with Channel Descriptions","created":"2025-05-20","cited_by_count":2,"area":null},{"id":"2506.14373","title":"Discrete JEPA: Learning Discrete Token Representations without Reconstruction","created":"2025-06-17","cited_by_count":2,"area":null},{"id":"2510.05558","title":"Midway Network: Learning Representations for Recognition and Motion from Latent Dynamics","created":"2025-10-07","cited_by_count":2,"area":null},{"id":"2603.26799","title":"Gaussian Joint Embeddings For Self-Supervised Representation Learning","created":"2026-03-26","cited_by_count":2,"area":null},{"id":"2506.23703","title":"A New Perspective On AI Safety Through Control Theory Methodologies","created":"2025-06-30","cited_by_count":1,"area":null},{"id":"2510.12931","title":"Unifying Vision-Language Latents for Zero-label Image Caption Enhancement","created":"2025-10-14","cited_by_count":1,"area":"mllm"},{"id":"2606.05173","title":"Predict and Reconstruct: Joint Objectives for Self-Supervised Language Representation Learning","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2608.04060","title":"SJEPA: Learning Elegant Latent Dynamics with Hybrid Symbolic-Neural Predictors","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2608.24044","title":"JEPA-x: Cross-Predictive Physics Grounding for Forecastable Latent Dynamics","created":"2026-08-25","cited_by_count":1,"area":"wm"},{"id":"2407.10733","title":"Joint-Embedding Predictive Architecture for Self-Supervised Learning of Mask Classification Architecture","created":"2024-07-15","cited_by_count":0,"area":null},{"id":"2410.02430","title":"Predictive Attractor Models","created":"2024-10-03","cited_by_count":0,"area":null},{"id":"2504.16140","title":"SparseJEPA: Sparse Representation Learning of Joint Embedding Predictive Architectures","created":"2025-04-22","cited_by_count":0,"area":null},{"id":"2507.03045","title":"Optimisation Is Not What You Need","created":"2025-07-03","cited_by_count":0,"area":null},{"id":"2512.04219","title":"Generalized Event Partonomy Inference with Structured Hierarchical Predictive Learning","created":"2025-12-03","cited_by_count":0,"area":null},{"id":"2602.09985","title":"Online Monitoring Framework for Automotive Time Series Data using JEPA Embeddings","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2603.21315","title":"FluidWorld: Reaction-Diffusion Dynamics as a Predictive Substrate for World Models","created":"2026-03-22","cited_by_count":0,"area":"wm"},{"id":"2606.01443","title":"UR-JEPA: Uniform Rectifiability as a Regularizer for Joint-Embedding Predictive Architectures","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2608.07214","title":"Toward a Causal Data Management Ecosystem for Decision Making and Agentic AI","created":"2026-08-07","cited_by_count":0,"area":"agents"},{"id":"2608.12050","title":"Predicting Functions, Not Features: KANs with Function-Space Joint-Embedding Predictive Learning for Medical Image Segmentation","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.13621","title":"Your Probabilistic JEPA Is Secretly a Hidden Markov Model: A State-Space Interpretation of Joint-Embedding Predictive Learning","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.21160","title":"Human-JEPA: A Human-Centric Vision Model that Perceives and Anticipates","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2608.24068","title":"Representation Learning in Diffusion and Flow-based Model: An Application Aspect","created":"2026-08-25","cited_by_count":0,"area":"diffusion"},{"id":"2608.28625","title":"Asymmetric Within-Document Predictive Learning for Scientific Document Representation","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2609.31161","title":"I Act Therefore I Am: When Is JEPA's Action-Conditioning Enough to Learn Causal Mechanisms?","created":"2026-09-25","cited_by_count":0,"area":"wm"},{"id":"2609.34375","title":"LRC-JEPA: Disentangling Dynamics and Residual Context for Efficient World Models","created":"2026-09-28","cited_by_count":0,"area":"wm"},{"id":"2609.35464","title":"W2Rep: Learning Visual Representations by Watching the World Change","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.05996","title":"EpicWorldModel: Exploration-driven Planning with Latent World Models","created":"2026-10-05","cited_by_count":0,"area":"wm"},{"id":"2610.08526","title":"WareFly-VLA: A Vision-Language-Action Framework for UAV Navigation and Human Tracking in Smart Warehouses","created":"2026-10-06","cited_by_count":0,"area":"vla"}],"next_cursor":null}