{"total":531,"rows":[{"id":"2506.09985","title":"V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning","created":"2025-06-11","cited_by_count":809,"area":"wm"},{"id":"2505.06111","title":"UniVLA: Learning to Act Anywhere with Task-centric Latent Actions","created":"2025-05-09","cited_by_count":410,"area":"vla"},{"id":"2412.14164","title":"MetaMorph: Multimodal Understanding and Generation via Instruction Tuning","created":"2024-12-18","cited_by_count":206,"area":null},{"id":"2411.14499","title":"Understanding World or Predicting Future? A Comprehensive Survey of World Models","created":"2024-11-21","cited_by_count":166,"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":"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":"2412.08821","title":"Large Concept Models: Language Modeling in a Sentence Representation Space","created":"2024-12-11","cited_by_count":89,"area":null},{"id":"2601.03782","title":"PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation","created":"2026-01-07","cited_by_count":82,"area":"wm"},{"id":"2405.02771","title":"MMEarth: Exploring Multi-Modal Pretext Tasks For Geospatial Representation Learning","created":"2024-05-04","cited_by_count":77,"area":null},{"id":"2509.09676","title":"SpatialVID: A Large-Scale Video Dataset with Spatial Annotations","created":"2025-09-11","cited_by_count":77,"area":null},{"id":"2411.00785","title":"IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI","created":"2024-10-17","cited_by_count":72,"area":"wm"},{"id":"2510.16732","title":"A Comprehensive Survey on World Models for Embodied AI","created":"2025-10-19","cited_by_count":68,"area":"wm"},{"id":"2509.07996","title":"3D and 4D World Modeling: A Survey","created":"2025-09-04","cited_by_count":67,"area":"wm"},{"id":"2509.22642","title":"WoW: Towards a World omniscient World model Through Embodied Interaction","created":"2025-09-26","cited_by_count":67,"area":"wm"},{"id":"2507.19468","title":"Back to the Features: DINO as a Foundation for Video World Models","created":"2025-07-25","cited_by_count":58,"area":"wm"},{"id":"2605.15178","title":"SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer","created":"2026-05-14","cited_by_count":55,"area":"wm"},{"id":"2506.09849","title":"IntPhys 2: Benchmarking Intuitive Physics Understanding In Complex Synthetic Environments","created":"2025-06-11","cited_by_count":52,"area":null},{"id":"2507.00917","title":"A Survey: Learning Embodied Intelligence from Physical Simulators and World Models","created":"2025-07-01","cited_by_count":51,"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":"2602.22208","title":"Solaris: Building a Multiplayer Video World Model in Minecraft","created":"2026-02-25","cited_by_count":47,"area":"wm"},{"id":"2412.11673","title":"DINO-Foresight: Looking into the Future with DINO","created":"2024-12-16","cited_by_count":45,"area":null},{"id":"2409.12192","title":"DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control","created":"2024-09-18","cited_by_count":44,"area":"offlinerl"},{"id":"2512.24497","title":"What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?","created":"2025-12-30","cited_by_count":43,"area":"wm"},{"id":"2405.00740","title":"Modeling Caption Diversity in Contrastive Vision-Language Pretraining","created":"2024-04-30","cited_by_count":42,"area":"mllm"},{"id":"2411.17820","title":"CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos","created":"2024-11-26","cited_by_count":41,"area":null},{"id":"2412.15159","title":"OnlineVPO: Align Video Diffusion Model with Online Video-Centric Preference Optimization","created":"2024-12-19","cited_by_count":41,"area":"diffusion"},{"id":"2509.14252","title":"LLM-JEPA: Large Language Models Meet Joint Embedding Predictive Architectures","created":"2025-09-11","cited_by_count":38,"area":null},{"id":"2603.12231","title":"Temporal Straightening for Latent Planning","created":"2026-03-12","cited_by_count":38,"area":"wm"},{"id":"2601.10553","title":"Inference-time Physics Alignment of Video Generative Models with Latent World Models","created":"2026-01-15","cited_by_count":37,"area":"wm"},{"id":"2509.02722","title":"Planning with Reasoning using Vision Language World Model","created":"2025-09-02","cited_by_count":36,"area":"wm"},{"id":"2511.09057","title":"PAN: A World Model for General, Actionable, and Long-Horizon World Simulation","created":"2025-11-12","cited_by_count":36,"area":"wm"},{"id":"2406.02128","title":"Iteration Head: A Mechanistic Study of Chain-of-Thought","created":"2024-06-04","cited_by_count":31,"area":"lr"},{"id":"2407.03475","title":"How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks","created":"2024-07-03","cited_by_count":31,"area":"distill"},{"id":"2412.15212","title":"Scaling 4D Representations","created":"2024-12-19","cited_by_count":30,"area":null},{"id":"2601.22032","title":"Drive-JEPA: Video JEPA Meets Multimodal Trajectory Distillation for End-to-End Driving","created":"2026-01-29","cited_by_count":30,"area":"driving"},{"id":"2605.26379","title":"When Does LeJEPA Learn a World Model?","created":"2026-05-25","cited_by_count":30,"area":"wm"},{"id":"2602.11389","title":"Causal-JEPA: Learning World Models through Object-Level Latent Masking","created":"2026-02-11","cited_by_count":29,"area":"wm"},{"id":"2603.07145","title":"LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Models","created":"2026-03-07","cited_by_count":28,"area":"wm"},{"id":"2501.09436","title":"Scaling up self-supervised learning for improved surgical foundation models","created":"2025-01-16","cited_by_count":25,"area":null},{"id":"2507.05169","title":"Critique of World Model","created":"2025-07-07","cited_by_count":25,"area":"wm"},{"id":"2509.20021","title":"Embodied AI: From LLMs to World Models","created":"2025-09-24","cited_by_count":24,"area":"wm"},{"id":"2602.11832","title":"JEPA-VLA: Video Predictive Embedding is Needed for VLA Models","created":"2026-02-12","cited_by_count":24,"area":"mllm"},{"id":"2504.14151","title":"Locate 3D: Real-World Object Localization via Self-Supervised Learning in 3D","created":"2025-04-19","cited_by_count":23,"area":null},{"id":"2410.05203","title":"Beyond FVD: Enhanced Evaluation Metrics for Video Generation Quality","created":"2024-10-07","cited_by_count":22,"area":null},{"id":"2512.10950","title":"E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training","created":"2025-12-11","cited_by_count":22,"area":null},{"id":"2504.19475","title":"Prisma: An Open Source Toolkit for Mechanistic Interpretability in Vision and Video","created":"2025-04-28","cited_by_count":21,"area":"mechinterp"},{"id":"2601.00844","title":"Value-guided action planning with JEPA world models","created":"2025-12-28","cited_by_count":21,"area":"wm"},{"id":"2410.19560","title":"Connecting Joint-Embedding Predictive Architecture with Contrastive Self-supervised Learning","created":"2024-10-25","cited_by_count":20,"area":null},{"id":"2501.13329","title":"Sparse identification of nonlinear dynamics and Koopman operators with Shallow Recurrent Decoder Networks","created":"2025-01-23","cited_by_count":20,"area":null},{"id":"2506.04363","title":"WorldPrediction: A Benchmark for High-level World Modeling and Long-horizon Procedural Planning","created":"2025-06-04","cited_by_count":20,"area":"wm"},{"id":"2410.08559","title":"Learning General Representation of 12-Lead Electrocardiogram with a Joint-Embedding Predictive Architecture","created":"2024-10-11","cited_by_count":19,"area":null},{"id":"2411.17385","title":"DepthCues: Evaluating Monocular Depth Perception in Large Vision Models","created":"2024-11-26","cited_by_count":19,"area":null},{"id":"2507.02608","title":"Lost in Latent Space: An Empirical Study of Latent Diffusion Models for Physics Emulation","created":"2025-07-03","cited_by_count":19,"area":"diffusion"},{"id":"2601.19834","title":"Visual Generation Unlocks Human-Like Reasoning through Multimodal World Models","created":"2026-01-27","cited_by_count":19,"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":"2512.14014","title":"MobileWorldBench: Towards Semantic World Modeling For Mobile Agents","created":"2025-12-16","cited_by_count":18,"area":"wm"},{"id":"2410.10394","title":"PIVOT-R: Primitive-Driven Waypoint-Aware World Model for Robotic Manipulation","created":"2024-10-14","cited_by_count":17,"area":"wm"},{"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":"2601.14354","title":"VJEPA: Variational Joint Embedding Predictive Architectures as Probabilistic World Models","created":"2026-01-20","cited_by_count":17,"area":"wm"},{"id":"2403.11772","title":"S-JEPA: towards seamless cross-dataset transfer through dynamic spatial attention","created":"2024-03-18","cited_by_count":16,"area":null},{"id":"2602.24012","title":"InfoNCE Induces Gaussian Distribution","created":"2026-02-27","cited_by_count":16,"area":null},{"id":"2605.09241","title":"Sub-JEPA: Subspace Gaussian Regularization for Stable End-to-End World Models","created":"2026-05-10","cited_by_count":16,"area":"wm"},{"id":"2607.13017","title":"FlowWAM: Optical Flow as a Unified Action Representation for World Action Models","created":"2026-07-14","cited_by_count":16,"area":"wm"},{"id":"2501.00226","title":"Generative Emergent Communication: Large Language Model is a Collective World Model","created":"2024-12-31","cited_by_count":15,"area":"wm"},{"id":"2502.07001","title":"From Image to Video: An Empirical Study of Diffusion Representations","created":"2025-02-10","cited_by_count":15,"area":"diffusion"},{"id":"2502.17100","title":"Generative Models in Decision Making: A Survey","created":"2025-02-24","cited_by_count":15,"area":null},{"id":"2511.02097","title":"A Step Toward World Models: A Survey on Robotic Manipulation","created":"2025-10-31","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":"2410.03755","title":"Denoising with a Joint-Embedding Predictive Architecture","created":"2024-10-02","cited_by_count":14,"area":"diffusion"},{"id":"2410.05016","title":"T-JEPA: Augmentation-Free Self-Supervised Learning for Tabular Data","created":"2024-10-07","cited_by_count":14,"area":null},{"id":"2410.13867","title":"Self-Supervised Pre-Training with Joint-Embedding Predictive Architecture Boosts ECG Classification Performance","created":"2024-10-02","cited_by_count":14,"area":null},{"id":"2411.02914","title":"Exploring the Interplay Between Video Generation and World Models in Autonomous Driving: A Survey","created":"2024-11-05","cited_by_count":14,"area":"wm"},{"id":"2510.08713","title":"Towards Unified World Models for Visual Navigation via Memory-Augmented Planning and Foresight","created":"2025-10-09","cited_by_count":14,"area":"wm"},{"id":"2604.22748","title":"Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond","created":"2026-04-24","cited_by_count":14,"area":"wm"},{"id":"2607.09024","title":"Video Generation Models are General-Purpose Vision Learners","created":"2026-07-10","cited_by_count":14,"area":null},{"id":"2410.03936","title":"Learning Truncated Causal History Model for Video Restoration","created":"2024-10-04","cited_by_count":13,"area":null},{"id":"2504.01928","title":"Is the Reversal Curse a Binding Problem? Uncovering Limitations of Transformers from a Basic Generalization Failure","created":"2025-04-02","cited_by_count":13,"area":null},{"id":"2601.07823","title":"Robotic Video World Models: A Survey of Applications, Research Challenges, Future Directions","created":"2026-01-12","cited_by_count":13,"area":"wm"},{"id":"2602.02603","title":"EchoJEPA: A Latent Predictive Foundation Model for Echocardiography","created":"2026-02-02","cited_by_count":13,"area":null},{"id":"2407.06491","title":"VideoEval: Comprehensive Benchmark Suite for Low-Cost Evaluation of Video Foundation Model","created":"2024-07-09","cited_by_count":12,"area":null},{"id":"2509.24317","title":"Rethinking JEPA: Compute-Efficient Video SSL with Frozen Teachers","created":"2025-09-29","cited_by_count":12,"area":null},{"id":"2602.10102","title":"VideoWorld 2: Learning Transferable Knowledge from Real-world Videos","created":"2026-02-10","cited_by_count":12,"area":null},{"id":"2605.10426","title":"CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Driving","created":"2026-05-11","cited_by_count":12,"area":"wm"},{"id":"2606.05979","title":"World-Language-Action Model for Unified World Modeling, Language Reasoning, and Action Synthesis","created":"2026-06-04","cited_by_count":12,"area":"wm"},{"id":"2606.20781","title":"World Action Models: A Survey","created":"2026-06-18","cited_by_count":12,"area":"wm"},{"id":"2503.15485","title":"TULIP: Towards Unified Language-Image Pretraining","created":"2025-03-19","cited_by_count":11,"area":null},{"id":"2506.10178","title":"Attention, Please! Revisiting Attentive Probing Through the Lens of Efficiency","created":"2025-06-11","cited_by_count":11,"area":null},{"id":"2509.08502","title":"Chirality in Action: Time-Aware Video Representation Learning by Latent Straightening","created":"2025-09-10","cited_by_count":11,"area":null},{"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":"2602.08984","title":"Next Concept Prediction in Discrete Latent Space Leads to Stronger Language Models","created":"2026-02-09","cited_by_count":11,"area":null},{"id":"2603.13227","title":"Representation Learning for Spatiotemporal Physical Systems","created":"2026-03-13","cited_by_count":11,"area":null},{"id":"2603.15381","title":"Why AI systems don't learn and what to do about it: Lessons on autonomous learning from cognitive science","created":"2026-03-16","cited_by_count":11,"area":null},{"id":"2605.07514","title":"Is the Future Compatible? Diagnosing Dynamic Consistency in World Action Models","created":"2026-05-08","cited_by_count":11,"area":"wm"},{"id":"2606.23085","title":"Foresight: Failure Detection for Long-Horizon Robotic Manipulation with Action-Conditioned World Model Latents","created":"2026-06-22","cited_by_count":11,"area":"wm"},{"id":"2501.01426","title":"Unifying Specialized Visual Encoders for Video Language Models","created":"2025-01-02","cited_by_count":10,"area":"lr"},{"id":"2511.23428","title":"DisMo: Disentangled Motion Representations for Open-World Motion Transfer","created":"2025-11-28","cited_by_count":10,"area":null},{"id":"2512.13684","title":"Recurrent Video Masked Autoencoders","created":"2025-12-15","cited_by_count":10,"area":null},{"id":"2603.26741","title":"Language-Conditioned World Modeling for Visual Navigation","created":"2026-03-23","cited_by_count":10,"area":"wm"},{"id":"2604.04913","title":"A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens","created":"2026-04-06","cited_by_count":10,"area":"wm"}],"next_cursor":"100"}