{"total":67,"rows":[{"id":"2508.13009","title":"Matrix-game 2.0: An open-source real-time and streaming interactive world model","created":"2025-08-18","cited_by_count":186,"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":"2510.26583","title":"Emu3.5: Native Multimodal Models are World Learners","created":"2025-10-30","cited_by_count":132,"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":"2507.17744","title":"Yume: An Interactive World Generation Model","created":"2025-07-23","cited_by_count":81,"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":"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":"2602.06028","title":"Context Forcing: Consistent Autoregressive Video Generation with Long Context","created":"2026-02-05","cited_by_count":59,"area":null},{"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":"2602.02393","title":"Infinite-World: Scaling Interactive World Models to 1000-Frame Horizons via Pose-Free Hierarchical Memory","created":"2026-02-02","cited_by_count":40,"area":"wm"},{"id":"2606.16993","title":"DreamX-World 1.0: A General-Purpose Interactive World Model","created":"2026-06-15","cited_by_count":40,"area":"wm"},{"id":"2512.08931","title":"Astra: General Interactive World Model with Autoregressive Denoising","created":"2025-12-09","cited_by_count":33,"area":"wm"},{"id":"2510.01784","title":"Pack and Force Your Memory: Long-form and Consistent Video Generation","created":"2025-10-02","cited_by_count":29,"area":null},{"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":"2603.17117","title":"MosaicMem: Hybrid Spatial Memory for Controllable Video World Models","created":"2026-03-17","cited_by_count":27,"area":"wm"},{"id":"2603.25716","title":"Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models","created":"2026-03-26","cited_by_count":26,"area":"wm"},{"id":"2605.15195","title":"VGGT-$\\Omega$","created":"2026-05-14","cited_by_count":26,"area":null},{"id":"2603.22212","title":"Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models","created":"2026-03-23","cited_by_count":18,"area":"wm"},{"id":"2603.23497","title":"WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG","created":"2026-03-24","cited_by_count":13,"area":"wm"},{"id":"2602.24289","title":"Mode Seeking meets Mean Seeking for Fast Long Video Generation","created":"2026-02-27","cited_by_count":12,"area":"diffusion"},{"id":"2603.16871","title":"WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation","created":"2026-03-17","cited_by_count":12,"area":"wm"},{"id":"2609.02886","title":"SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models","created":"2026-09-02","cited_by_count":12,"area":"wm"},{"id":"2607.18367","title":"AlayaWorld: Interactive Long-Horizon World Modeling -- Full Technical Report","created":"2026-07-20","cited_by_count":11,"area":"wm"},{"id":"2608.23565","title":"ReWorld: An Interactive World Model with Long-Horizon Memory","created":"2026-08-24","cited_by_count":10,"area":"wm"},{"id":"2606.31734","title":"MemLearner: Learning to Query Context memory for Video World Models","created":"2026-06-30","cited_by_count":9,"area":"wm"},{"id":"2512.21003","title":"MVInverse: Feed-forward Multi-view Inverse Rendering in Seconds","created":"2025-12-24","cited_by_count":6,"area":null},{"id":"2606.10135","title":"BiWM: Advancing Open-Source Interactive Video World Models with Bidirectional Autoregression","created":"2026-06-08","cited_by_count":6,"area":"wm"},{"id":"2604.24762","title":"OmniShotCut: Holistic Relational Shot Boundary Detection with Shot-Query Transformer","created":"2026-04-27","cited_by_count":5,"area":null},{"id":"2607.03964","title":"Worldscape-MoE: A Unified Mixture-of-Experts World Model for Scalable Heterogeneous Action Control","created":"2026-07-04","cited_by_count":5,"area":"wm"},{"id":"2602.04439","title":"TrajVG: 3D Trajectory-Coupled Visual Geometry Learning","created":"2026-02-04","cited_by_count":4,"area":null},{"id":"2607.14076","title":"From Pixels to States: Rethinking Interactive World Models as Game Engines","created":"2026-07-15","cited_by_count":4,"area":"wm"},{"id":"2510.23576","title":"UrbanVLA: A Vision-Language-Action Model for Urban Micromobility","created":"2025-10-27","cited_by_count":3,"area":"vla"},{"id":"2511.18886","title":"MagicWorld: Towards Long-Horizon Stability for Interactive Video World Exploration","created":"2025-11-24","cited_by_count":3,"area":"wm"},{"id":"2602.04441","title":"SynthVerse: A Large-Scale Diverse Synthetic Dataset for Point Tracking","created":"2026-02-04","cited_by_count":3,"area":"synth"},{"id":"2605.23903","title":"Geo-Align: Video Generation Alignment via Metric Geometry Reward","created":"2026-05-22","cited_by_count":3,"area":null},{"id":"2606.20083","title":"Holo-World: Unified Camera, Object and Weather Control for Video World Model","created":"2026-06-18","cited_by_count":3,"area":"wm"},{"id":"2606.20521","title":"HumanScale: Egocentric Human Video Can Outperform Real-Robot Data for Embodied Pretraining","created":"2026-06-18","cited_by_count":3,"area":null},{"id":"2608.09449","title":"Sekai2: From World Exploration to Interactive World Modeling","created":"2026-08-10","cited_by_count":3,"area":"wm"},{"id":"2511.17792","title":"Target-Bench: Can Video World Models Achieve Mapless Path Planning with Semantic Targets?","created":"2025-11-21","cited_by_count":2,"area":"wm"},{"id":"2606.07967","title":"DisCo: World Models with Discrete Camera Motion Control","created":"2026-06-06","cited_by_count":2,"area":"wm"},{"id":"2606.26694","title":"PhysEditWorld: A Large-Scale Dataset Toward Physics-Editable World Models","created":"2026-06-25","cited_by_count":2,"area":"wm"},{"id":"2607.28624","title":"PhiZero: A World Model Built Around Physical Language","created":"2026-07-30","cited_by_count":2,"area":"wm"},{"id":"2608.03979","title":"Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent","created":"2026-08-04","cited_by_count":2,"area":"agents"},{"id":"2608.15659","title":"WorldRover: A Scalable Synthetic Video Data Engine for World Exploration with Rich Annotations","created":"2026-08-16","cited_by_count":2,"area":null},{"id":"2609.09123","title":"Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rollout","created":"2026-09-08","cited_by_count":2,"area":"diffusion"},{"id":"2512.12209","title":"CineLOG: A Training Free Approach for Cinematic Long Video Generation","created":"2025-12-13","cited_by_count":1,"area":null},{"id":"2604.07990","title":"SceneScribe-1M: A Large-Scale Video Dataset with Comprehensive Geometric and Semantic Annotations","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2604.07991","title":"MotionScape: A Motion-Stratified UAV Video Benchmark for World Modeling and Future Video Generation","created":"2026-04-09","cited_by_count":1,"area":"wm"},{"id":"2608.05070","title":"HelloWorld: Enabling Socially Interactive Characters in Video World Models","created":"2026-08-05","cited_by_count":1,"area":"wm"},{"id":"2609.34470","title":"Precise Editing and Flexible Referencing for Interactable Worlds","created":"2026-09-28","cited_by_count":1,"area":"wm"},{"id":"2610.01614","title":"Oneira: From Open-Ended Generation to Open-World Interaction in Video World Models","created":"2026-10-01","cited_by_count":1,"area":"wm"},{"id":"2603.22249","title":"EgoGroups: A Benchmark For Detecting Social Groups of People in the Wild","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2603.29036","title":"Generating Humanless Environment Walkthroughs from Egocentric Walking Tour Videos","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2606.15629","title":"XPASS-Vis: A Dataset for Cross-Domain Personalized Image Aesthetic Assessment","created":"2026-06-14","cited_by_count":0,"area":null},{"id":"2606.16449","title":"PermaVid: Consistent Video Generation Across Edits via Disentangled Context Memory","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2607.12000","title":"MetaView: Monocular Novel View Synthesis with Scale-Aware Implicit Geometry Priors","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2607.16560","title":"From Modalities to Propositions: A Language-Centric Framework for Multimodal Intelligence","created":"2026-07-18","cited_by_count":0,"area":null},{"id":"2608.14043","title":"Beyond Text Conditioning: A Systematic Study of MLLM-DiT Fusion for Video Generation","created":"2026-08-14","cited_by_count":0,"area":"diffusion"},{"id":"2608.25559","title":"AdaVDR: Adaptive Tool Use and Reflection for Video Deep Research","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.06652","title":"VidaForge: Open Research Infrastructure for Video Pretraining Data Recipes","created":"2026-09-06","cited_by_count":0,"area":null},{"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":"2609.38077","title":"MUGEN: Interactive Panoramic World Exploration via Camera Control","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38146","title":"LIFT: Layout-In-Future Video Generation under Large Viewpoint Change via On-Policy Self-Distillation","created":"2026-09-29","cited_by_count":0,"area":"distill"},{"id":"2609.39047","title":"BadAction: Backdoor Attacks on Interactive Video Generation via Action-Guided Triggers","created":"2026-09-30","cited_by_count":0,"area":"safety"},{"id":"2610.16302","title":"RAR: Rate-Adaptive Rollout for Time-Consistent Interactive World Models","created":"2026-10-12","cited_by_count":0,"area":"wm"},{"id":"2610.19726","title":"Generative World Simulation with DAO and JING","created":"2026-10-14","cited_by_count":0,"area":null},{"id":"2610.20160","title":"OneLA: Learning Many Worlds from Latent Actions","created":"2026-10-14","cited_by_count":0,"area":"wm"}],"next_cursor":null}