{"total":94,"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":"2512.14614","title":"WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling","created":"2025-12-16","cited_by_count":170,"area":"wm"},{"id":"2604.08995","title":"Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory","created":"2026-04-10","cited_by_count":100,"area":"wm"},{"id":"2512.04040","title":"RELIC: Interactive Video World Model with Long-Horizon Memory","created":"2025-12-03","cited_by_count":96,"area":"wm"},{"id":"2509.09676","title":"SpatialVID: A Large-Scale Video Dataset with Spatial Annotations","created":"2025-09-11","cited_by_count":77,"area":null},{"id":"2510.10726","title":"WorldMirror: Universal 3D World Reconstruction with Any-Prior Prompting","created":"2025-10-12","cited_by_count":67,"area":null},{"id":"2603.04379","title":"Helios: Real Real-Time Long Video Generation Model","created":"2026-03-04","cited_by_count":65,"area":null},{"id":"2509.12201","title":"OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling","created":"2025-09-15","cited_by_count":62,"area":"wm"},{"id":"2604.14268","title":"HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds","created":"2026-04-15","cited_by_count":44,"area":"wm"},{"id":"2512.07237","title":"Unified Camera Positional Encoding for Controlled Video Generation","created":"2025-12-08","cited_by_count":37,"area":"wm"},{"id":"2510.13678","title":"FlashWorld: High-quality 3D Scene Generation within Seconds","created":"2025-10-15","cited_by_count":32,"area":"diffusion"},{"id":"2512.13644","title":"World Models for Learning Dexterous Hand-Object Interactions from Human Videos","created":"2025-12-15","cited_by_count":31,"area":"wm"},{"id":"2601.05138","title":"VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Control","created":"2026-01-08","cited_by_count":28,"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":"2604.21686","title":"WorldMark: A Unified Benchmark Suite for Interactive Video World Models","created":"2026-04-23","cited_by_count":26,"area":"wm"},{"id":"2509.26618","title":"DA$^{2}$: Depth Anything in Any Direction","created":"2025-09-30","cited_by_count":25,"area":null},{"id":"2510.11712","title":"DiT360: High-Fidelity Panoramic Image Generation via Hybrid Training","created":"2025-10-13","cited_by_count":24,"area":null},{"id":"2602.09022","title":"WorldCompass: Reinforcement Learning for Long-Horizon World Models","created":"2026-02-09","cited_by_count":24,"area":"wm"},{"id":"2509.09595","title":"Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis","created":"2025-09-11","cited_by_count":21,"area":null},{"id":"2510.01183","title":"EvoWorld: Evolving Panoramic World Generation with Explicit 3D Memory","created":"2025-10-01","cited_by_count":20,"area":"wm"},{"id":"2509.21574","title":"X-Streamer: Unified Human World Modeling with Audiovisual Interaction","created":"2025-09-25","cited_by_count":18,"area":"wm"},{"id":"2602.01801","title":"Fast Autoregressive Video Diffusion and World Models with Temporal Cache Compression and Sparse Attention","created":"2026-02-02","cited_by_count":18,"area":"wm"},{"id":"2603.02049","title":"WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memories","created":"2026-03-02","cited_by_count":18,"area":"diffusion"},{"id":"2511.07222","title":"Omni-View: Unlocking How Generation Facilitates Understanding in Unified 3D Model based on Multiview images","created":"2025-11-10","cited_by_count":17,"area":null},{"id":"2607.26037","title":"Wonder: Video World Model Done Better","created":"2026-07-28","cited_by_count":15,"area":"wm"},{"id":"2606.17730","title":"ActWorld: From Explorable to Interactive World Model via Action-Aware Memory","created":"2026-06-16","cited_by_count":14,"area":"wm"},{"id":"2608.25927","title":"Code World Model: Coding Agent as World Brain","created":"2026-08-26","cited_by_count":14,"area":"wm"},{"id":"2509.23958","title":"Reinforcement Learning with Inverse Rewards for World Model Post-training","created":"2025-09-28","cited_by_count":13,"area":"wm"},{"id":"2512.13313","title":"KlingAvatar 2.0 Technical Report","created":"2025-12-15","cited_by_count":13,"area":null},{"id":"2601.04137","title":"Wow, wo, val! A Comprehensive Embodied World Model Evaluation Turing Test","created":"2026-01-07","cited_by_count":13,"area":"wm"},{"id":"2601.21282","title":"WorldBench: Benchmarking Physical Understanding of World Models by Isolating Physics Concepts","created":"2026-01-29","cited_by_count":12,"area":"wm"},{"id":"2512.12751","title":"GenieDrive: Towards Physics-Aware Driving World Model with 4D Occupancy Guided Video Generation","created":"2025-12-14","cited_by_count":11,"area":"wm"},{"id":"2602.19766","title":"One2Scene: Geometric Consistent Explorable 3D Scene Generation from a Single Image","created":"2026-02-23","cited_by_count":11,"area":null},{"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":"2603.08982","title":"SVG-EAR: Parameter-Free Linear Compensation for Sparse Video Generation via Error-aware Routing","created":"2026-03-09","cited_by_count":10,"area":"diffusion"},{"id":"2608.23565","title":"ReWorld: An Interactive World Model with Long-Horizon Memory","created":"2026-08-24","cited_by_count":10,"area":"wm"},{"id":"2602.04876","title":"PerpetualWonder: Long-Horizon Action-Conditioned 4D Scene Generation","created":"2026-02-04","cited_by_count":9,"area":null},{"id":"2510.23880","title":"TRELLISWorld: Training-Free World Generation from Object Generators","created":"2025-10-27","cited_by_count":8,"area":null},{"id":"2606.01164","title":"Towards Interactive Video World Modeling: Frontiers, Challenges, Benchmarks, and Future Trends","created":"2026-05-31","cited_by_count":8,"area":"wm"},{"id":"2606.21775","title":"Beyond the Next Step: Variable-Length Latent World Models for Long-Horizon Planning","created":"2026-06-19","cited_by_count":8,"area":"wm"},{"id":"2608.05248","title":"WorldClaw: Agentic 3D Open-World Generation at Scale","created":"2026-08-05","cited_by_count":8,"area":"agents"},{"id":"2512.16924","title":"The World is Your Canvas: Painting Promptable Events with Reference Images, Trajectories, and Text","created":"2025-12-18","cited_by_count":7,"area":null},{"id":"2601.16192","title":"360Anything: Geometry-Free Lifting of Images and Videos to 360{\\deg}","created":"2026-01-22","cited_by_count":7,"area":null},{"id":"2603.11911","title":"InSpatio-WorldFM: An Open-Source Real-Time Generative Frame Model","created":"2026-03-12","cited_by_count":7,"area":"wm"},{"id":"2604.18215","title":"Memorize When Needed: Decoupled Memory Control for Spatially Consistent Long-Horizon Video Generation","created":"2026-04-20","cited_by_count":7,"area":null},{"id":"2606.23105","title":"Compression and Retrieval: Implicit Memory Retrieval for Video World Models","created":"2026-06-22","cited_by_count":6,"area":"wm"},{"id":"2512.07527","title":"From Orbit to Ground: Generative City Photogrammetry from Extreme Off-Nadir Satellite Images","created":"2025-12-08","cited_by_count":5,"area":null},{"id":"2602.05362","title":"Imagine a City: CityGenAgent for Procedural 3D City Generation","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2606.18180","title":"EgoCS-400K: An Egocentric Gameplay Dataset for World Models","created":"2026-06-16","cited_by_count":5,"area":"wm"},{"id":"2607.06401","title":"A Definition and Roadmap for World Models","created":"2026-07-07","cited_by_count":5,"area":"wm"},{"id":"2510.26800","title":"OmniX: From Unified Panoramic Generation and Perception to Graphics-Ready 3D Scenes","created":"2025-10-30","cited_by_count":4,"area":null},{"id":"2511.18991","title":"View-Consistent Diffusion Representations for 3D-Consistent Video Generation","created":"2025-11-24","cited_by_count":4,"area":"diffusion"},{"id":"2512.12430","title":"Endless World: Real-Time 3D-Aware Long Video Generation","created":"2025-12-13","cited_by_count":4,"area":null},{"id":"2602.05321","title":"Wid3R: Wide Field-of-View 3D Reconstruction via Camera Model Conditioning","created":"2026-02-05","cited_by_count":4,"area":null},{"id":"2605.12938","title":"CRePE: Curved Ray Expectation Positional Encoding for Unified-Camera-Controlled Video Generation","created":"2026-05-13","cited_by_count":4,"area":"wm"},{"id":"2606.13376","title":"MoVerse: Real-Time Video World Modeling with Panoramic Gaussian Scaffold","created":"2026-06-11","cited_by_count":4,"area":"wm"},{"id":"2512.05103","title":"TV2TV: A Unified Framework for Interleaved Language and Video Generation","created":"2025-12-04","cited_by_count":3,"area":null},{"id":"2601.16296","title":"Memory-V2V: Memory-Augmented Video-to-Video Diffusion for Consistent Multi-Turn Editing","created":"2026-01-22","cited_by_count":3,"area":"diffusion"},{"id":"2602.01630","title":"Research on World Models Is Not Merely Injecting World Knowledge into Specific Tasks","created":"2026-02-02","cited_by_count":3,"area":"wm"},{"id":"2603.28757","title":"SonoWorld: From One Image to a 3D Audio-Visual Scene","created":"2026-03-30","cited_by_count":3,"area":null},{"id":"2604.04707","title":"OpenWorldLib: A Unified Codebase and Definition of Advanced World Models","created":"2026-04-06","cited_by_count":3,"area":"wm"},{"id":"2604.09535","title":"EgoTL: Egocentric Think-Aloud Chains for Long-Horizon Tasks","created":"2026-04-10","cited_by_count":3,"area":"wm"},{"id":"2607.12592","title":"WanToFight: Real-Time Generative Game Engine for Multi-Player Combat Interaction","created":"2026-07-14","cited_by_count":3,"area":null},{"id":"2512.22819","title":"Depth Anything in $360^\\circ$: Towards Scale Invariance in the Wild","created":"2025-12-28","cited_by_count":2,"area":null},{"id":"2603.06445","title":"What if? Emulative Simulation with World Models for Situated Reasoning","created":"2026-03-06","cited_by_count":2,"area":"wm"},{"id":"2603.24866","title":"How Far Are Vision-Language Models from Constructing the Real World? A Benchmark for Physical Generative Reasoning","created":"2026-03-25","cited_by_count":2,"area":"lr"},{"id":"2605.31336","title":"DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory","created":"2026-05-29","cited_by_count":2,"area":"wm"},{"id":"2606.00499","title":"OptiWorld: Optimal Control for Video World Generation under Physical Constraints","created":"2026-05-30","cited_by_count":2,"area":"wm"},{"id":"2606.08402","title":"SceneConductor: 3D Scene Generation from a Single Image with Multi-Agent Orchestration","created":"2026-06-07","cited_by_count":2,"area":null},{"id":"2509.24758","title":"ExGS: Extreme 3D Gaussian Compression with Diffusion Priors","created":"2025-09-29","cited_by_count":1,"area":"diffusion"},{"id":"2511.19319","title":"SyncMV4D: Synchronized Multi-view Joint Diffusion of Appearance and Motion for Hand-Object Interaction Synthesis","created":"2025-11-24","cited_by_count":1,"area":null},{"id":"2512.09164","title":"WonderZoom: Multi-Scale 3D World Generation","created":"2025-12-09","cited_by_count":1,"area":null},{"id":"2602.00785","title":"World Models as an Intermediary between Agents and the Real World","created":"2026-01-31","cited_by_count":1,"area":"wm"},{"id":"2607.24591","title":"CameraAnything: Refilming Videos with Arbitrary Camera Control","created":"2026-07-27","cited_by_count":1,"area":null},{"id":"2607.27201","title":"Mental World Modeling","created":"2026-07-29","cited_by_count":1,"area":"wm"},{"id":"2512.06885","title":"JoPano: Unified Panorama Generation via Joint Modeling","created":"2025-12-07","cited_by_count":0,"area":null},{"id":"2603.12759","title":"SAP: Segment Any 4K Panorama","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2603.13910","title":"Scene Generation at Absolute Scale: Utilizing Semantic and Geometric Guidance From Text for Accurate and Interpretable 3D Indoor Scene Generation","created":"2026-03-14","cited_by_count":0,"area":"diffusion"},{"id":"2603.23179","title":"Gimbal360: Canonicalizing Planar Diffusion for Spherical Panorama Completion","created":"2026-03-24","cited_by_count":0,"area":"diffusion"},{"id":"2605.11115","title":"LatentHDR: Decoupling Exposure from Diffusion via Conditional Latent-to-Latent Mapping for Text/Image-to-Panoramic HDR","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.24630","title":"DexSIM: Real-time Dexterous Simulation with Unified Causal Video Diffusion","created":"2026-05-23","cited_by_count":0,"area":"diffusion"},{"id":"2606.12213","title":"SHERPA: Seam-aware Harmonized ERP Adaptation for Open-Domain 360$^\\circ$ Panorama Generation","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2606.13655","title":"Flex4DHuman: Flexible Multi-view Video Diffusion for 4D Human Reconstruction","created":"2026-06-11","cited_by_count":0,"area":"diffusion"},{"id":"2607.03461","title":"WorldBagel: Uncovering the Power of Unified Multimodal Models for Vision-Language-Action-World Modeling","created":"2026-07-03","cited_by_count":0,"area":"wm"},{"id":"2607.08765","title":"Enhancing In-context Panoramic Generation via Geometric-aware Pretraining","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2609.24308","title":"HappyWorld-Bench","created":"2026-09-21","cited_by_count":0,"area":"wm"},{"id":"2609.32921","title":"Adaptive Latent Capacity for World Models","created":"2026-09-26","cited_by_count":0,"area":"wm"},{"id":"2609.35560","title":"WorldPlay2: Extending Real-Time Interactive World Models in Control and Horizon","created":"2026-09-28","cited_by_count":0,"area":"wm"},{"id":"2609.38444","title":"Audible World Models: Spatially Aware Sound Generation for 3D Worlds","created":"2026-09-29","cited_by_count":0,"area":"wm"},{"id":"2610.02160","title":"4Director: Controlling Video World Models with Rigid 3D Geometry","created":"2026-10-01","cited_by_count":0,"area":"wm"},{"id":"2610.03522","title":"Feedforward Novel View Synthesis for Heterogeneous Cameras","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.12461","title":"OuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphs","created":"2026-10-08","cited_by_count":0,"area":"wm"},{"id":"2610.13832","title":"SpatialASM: Internalizing Active Mentalization for Spatial Reasoning","created":"2026-10-09","cited_by_count":0,"area":"lr"},{"id":"2610.20240","title":"PAWA: Panoramic Action-conditioned World Modeling for Multiple Agents","created":"2026-10-14","cited_by_count":0,"area":"wm"}],"next_cursor":null}