{"total":53,"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":"2403.02622","title":"World Models for Autonomous Driving: An Initial Survey","created":"2024-03-05","cited_by_count":80,"area":"wm"},{"id":"2504.02436","title":"SkyReels-A2: Compose Anything in Video Diffusion Transformers","created":"2025-04-03","cited_by_count":73,"area":"diffusion"},{"id":"2512.10942","title":"VL-JEPA: Joint Embedding Predictive Architecture for Vision-language","created":"2025-12-11","cited_by_count":68,"area":"mllm"},{"id":"2605.12090","title":"World Action Models: The Next Frontier in Embodied AI","created":"2026-05-12","cited_by_count":50,"area":"wm"},{"id":"2408.14340","title":"Foundation Models for Music: A Survey","created":"2024-08-26","cited_by_count":37,"area":"diffusion"},{"id":"2509.20021","title":"Embodied AI: From LLMs to World Models","created":"2025-09-24","cited_by_count":24,"area":"wm"},{"id":"2409.00587","title":"FLUX that Plays Music","created":"2024-09-01","cited_by_count":18,"area":"diffusion"},{"id":"2507.02915","title":"Audio-JEPA: Joint-Embedding Predictive Architecture for Audio Representation Learning","created":"2025-06-25","cited_by_count":17,"area":null},{"id":"2506.12222","title":"SSLAM: Enhancing Self-Supervised Models with Audio Mixtures for Polyphonic Soundscapes","created":"2025-06-13","cited_by_count":16,"area":"mllm"},{"id":"2501.01790","title":"Ingredients: Blending Custom Photos with Video Diffusion Transformers","created":"2025-01-03","cited_by_count":13,"area":"diffusion"},{"id":"2412.10783","title":"Video Diffusion Transformers are In-Context Learners","created":"2024-12-14","cited_by_count":12,"area":"diffusion"},{"id":"2606.20781","title":"World Action Models: A Survey","created":"2026-06-18","cited_by_count":12,"area":"wm"},{"id":"2512.13684","title":"Recurrent Video Masked Autoencoders","created":"2025-12-15","cited_by_count":10,"area":null},{"id":"2406.04853","title":"Time-Series JEPA for Predictive Remote Control under Capacity-Limited Networks","created":"2024-06-07","cited_by_count":9,"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":"2501.14622","title":"ACT-JEPA: Novel Joint-Embedding Predictive Architecture for Efficient Policy Representation Learning","created":"2025-01-24","cited_by_count":8,"area":"wm"},{"id":"2404.13358","title":"Music Consistency Models","created":"2024-04-20","cited_by_count":7,"area":"diffusion"},{"id":"2405.02288","title":"Prospective Role of Foundation Models in Advancing Autonomous Vehicles","created":"2023-12-08","cited_by_count":7,"area":null},{"id":"2409.10045","title":"Learning Latent Wireless Dynamics from Channel State Information","created":"2024-09-16","cited_by_count":7,"area":null},{"id":"2511.18424","title":"CrossJEPA: Cross-Modal Joint-Embedding Predictive Architecture for Efficient 3D Representation Learning from 2D Images","created":"2025-11-23","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":"2603.15553","title":"Self-Distillation of Hidden Layers for Self-Supervised Representation Learning","created":"2026-03-16","cited_by_count":3,"area":"distill"},{"id":"2506.14373","title":"Discrete JEPA: Learning Discrete Token Representations without Reconstruction","created":"2025-06-17","cited_by_count":2,"area":null},{"id":"2601.05911","title":"Pantagruel: Unified Self-Supervised Encoders for French Text and Speech","created":"2026-01-09","cited_by_count":2,"area":null},{"id":"2604.13518","title":"From Alignment to Prediction: A Study of Self-Supervised Learning and Predictive Representation Learning","created":"2026-04-15","cited_by_count":2,"area":null},{"id":"2606.25225","title":"MJEPA: A Simple and Scalable Joint-Embedding Predictive Architecture for Audio-Visual Learning","created":"2026-06-23","cited_by_count":2,"area":null},{"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":"2503.22713","title":"Chirp Localization via Fine-Tuned Transformer Model: A Proof-of-Concept Study","created":"2025-03-24","cited_by_count":1,"area":null},{"id":"2602.20344","title":"Hierarchical Molecular Representation Learning via Fragment-Based Self-Supervised Embedding Prediction","created":"2026-02-23","cited_by_count":1,"area":null},{"id":"2605.14231","title":"AudioMosaic: Contrastive Masked Audio Representation Learning","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2607.16350","title":"Joint-Embedding Predictive Architecture for Sensor-based Activity Recognition","created":"2026-07-17","cited_by_count":1,"area":null},{"id":"2607.18412","title":"Scalable and Efficient Joint Spiking Embedding Predictive Architecture for Large-Scale Dynamic Graphs","created":"2026-07-20","cited_by_count":1,"area":null},{"id":"2502.01684","title":"Predict, Cluster, Refine: A Joint Embedding Predictive Self-Supervised Framework for Graph Representation Learning","created":"2025-02-02","cited_by_count":0,"area":null},{"id":"2502.04899","title":"Towards Unified Approaches in Self-Supervised Event Stream Modeling: Progress and Prospects","created":"2025-02-07","cited_by_count":0,"area":null},{"id":"2509.15430","title":"BiRQ: Bi-Level Self-Labeling Random Quantization for Self-Supervised Speech Recognition","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2510.03606","title":"Unsupervised Transformer Pre-Training for Images: Self-Distillation, Mean Teachers, and Random Crops","created":"2025-10-04","cited_by_count":0,"area":"distill"},{"id":"2601.21612","title":"Representation-Regularized Convolutional Audio Transformer for Audio Understanding","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2604.16086","title":"Stylistic-STORM (ST-STORM) : Perceiving the Semantic Nature of Appearance","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2605.06582","title":"PairAlign: A Framework for Autoregressive Tokenization via Self-Alignment with Applications to Audio Tokenization","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2606.30700","title":"BEST-RQ-2: Contextualize-Then-Predict, a Two-Step Approach for Self-Supervised Audio Representations","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.00052","title":"AGE: Adaptive-masking for Graph Embedding in Graph Retrieval-Augmented Generation","created":"2026-06-30","cited_by_count":0,"area":"rag"},{"id":"2607.09205","title":"Joint-Embedding Predictive Architecture for Solar PV Panel Fault Classification","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2608.06062","title":"Bar-JEPA: Extracting Values from Bar Chart with Joint-Embedding Predictive Architecture","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.19863","title":"Listening Forward: Next Patch Embedding Prediction Enables Scalable Audio Learners","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2609.17029","title":"Distributed JEPA: A Self-Supervised Framework for Energy Forecasting","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.22674","title":"Mask-Aware Execution for Efficient JEPA Training","created":"2026-09-19","cited_by_count":0,"area":"wm"},{"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":"2609.32481","title":"JEPA Learns What the Mask Leaves Unrecoverable","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.34085","title":"AD-E2E-JEPA: A Joint-Embedding Predictive Architecture For End-to-End Autonomous Driving","created":"2026-09-28","cited_by_count":0,"area":"wm"},{"id":"2609.37798","title":"GLaS-JEPA: Gaussian-Regularized Speech SSL without Engineered Prediction Targets","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.08192","title":"MacJEPA: Missingness-Robust Audio-Visual Recognition from Untrimmed Egocentric Videos","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}