{"total":98,"rows":[{"id":"2506.05284","title":"Video World Models with Long-term Spatial Memory","created":"2025-06-05","cited_by_count":136,"area":"wm"},{"id":"2506.17201","title":"Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition","created":"2025-06-20","cited_by_count":98,"area":null},{"id":"2507.16869","title":"Controllable Video Generation: A Survey","created":"2025-07-22","cited_by_count":98,"area":null},{"id":"2507.21809","title":"HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels","created":"2025-07-29","cited_by_count":94,"area":null},{"id":"2506.09350","title":"Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation","created":"2025-06-11","cited_by_count":90,"area":null},{"id":"2504.08685","title":"Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model","created":"2025-04-11","cited_by_count":82,"area":null},{"id":"2504.14899","title":"Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generation","created":"2025-04-21","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":"2607.07534","title":"Infinite Worlds with Versatile Interactions","created":"2026-07-08","cited_by_count":48,"area":null},{"id":"2510.18135","title":"World-in-World: World Models in a Closed-Loop World","created":"2025-10-20","cited_by_count":47,"area":"wm"},{"id":"2509.19296","title":"Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation","created":"2025-09-23","cited_by_count":41,"area":"diffusion"},{"id":"2512.15716","title":"Spatia: Video Generation with Updatable Spatial Memory","created":"2025-12-17","cited_by_count":40,"area":null},{"id":"2512.07237","title":"Unified Camera Positional Encoding for Controlled Video Generation","created":"2025-12-08","cited_by_count":37,"area":"wm"},{"id":"2510.18313","title":"OmniNWM: Omniscient Driving Navigation World Models","created":"2025-10-21","cited_by_count":33,"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":"2507.14501","title":"Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey","created":"2025-07-19","cited_by_count":27,"area":null},{"id":"2603.17117","title":"MosaicMem: Hybrid Spatial Memory for Controllable Video World Models","created":"2026-03-17","cited_by_count":27,"area":"wm"},{"id":"2510.21615","title":"Epipolar Geometry Improves Video Generation Models","created":"2025-10-24","cited_by_count":26,"area":"diffusion"},{"id":"2602.09022","title":"WorldCompass: Reinforcement Learning for Long-Horizon World Models","created":"2026-02-09","cited_by_count":24,"area":"wm"},{"id":"2505.22016","title":"PanoWan: Lifting Diffusion Video Generation Models to 360{\\deg} with Latitude/Longitude-aware Mechanisms","created":"2025-05-28","cited_by_count":23,"area":null},{"id":"2505.21876","title":"EPiC: Efficient Video Camera Control Learning with Precise Anchor-Video Guidance","created":"2025-05-28","cited_by_count":21,"area":"diffusion"},{"id":"2604.07209","title":"INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling","created":"2026-04-08","cited_by_count":21,"area":"wm"},{"id":"2506.03107","title":"ByteMorph: Benchmarking Instruction-Guided Image Editing with Non-Rigid Motions","created":"2025-06-03","cited_by_count":19,"area":null},{"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":"2603.25730","title":"PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference","created":"2026-03-26","cited_by_count":17,"area":"diffusion"},{"id":"2606.09828","title":"Latent Spatial Memory for Video World Models","created":"2026-06-08","cited_by_count":17,"area":"wm"},{"id":"2505.11992","title":"SpatialCrafter: Unleashing the Imagination of Video Diffusion Models for Scene Reconstruction from Limited Observations","created":"2025-05-17","cited_by_count":16,"area":"diffusion"},{"id":"2602.14941","title":"AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories","created":"2026-02-16","cited_by_count":15,"area":null},{"id":"2512.05076","title":"BulletTime: Decoupled Control of Time and Camera Pose for Video Generation","created":"2025-12-04","cited_by_count":14,"area":"diffusion"},{"id":"2510.14945","title":"3D Scene Prompting for Scene-Consistent Camera-Controllable Video Generation","created":"2025-10-16","cited_by_count":13,"area":null},{"id":"2504.11092","title":"Vivid4D: Improving 4D Reconstruction from Monocular Video by Video Inpainting","created":"2025-04-15","cited_by_count":11,"area":null},{"id":"2511.23127","title":"DualCamCtrl: Dual-Branch Diffusion Model for Geometry-Aware Camera-Controlled Video Generation","created":"2025-11-28","cited_by_count":11,"area":"diffusion"},{"id":"2512.19949","title":"How Much 3D Do Video Foundation Models Encode?","created":"2025-12-23","cited_by_count":11,"area":null},{"id":"2512.25075","title":"SpaceTimePilot: Generative Rendering of Dynamic Scenes Across Space and Time","created":"2025-12-31","cited_by_count":11,"area":"diffusion"},{"id":"2607.18367","title":"AlayaWorld: Interactive Long-Horizon World Modeling -- Full Technical Report","created":"2026-07-20","cited_by_count":11,"area":"wm"},{"id":"2504.19614","title":"DiVE: Efficient Multi-View Driving Scenes Generation Based on Video Diffusion Transformer","created":"2025-04-28","cited_by_count":10,"area":"diffusion"},{"id":"2512.02870","title":"Taming Camera-Controlled Video Generation with Verifiable Geometry Reward","created":"2025-12-02","cited_by_count":10,"area":"diffusion"},{"id":"2604.03723","title":"SymphoMotion: Joint Control of Camera Motion and Object Dynamics for Coherent Video Generation","created":"2026-04-04","cited_by_count":10,"area":null},{"id":"2510.04236","title":"Scaling Sequence-to-Sequence Generative Neural Rendering","created":"2025-10-05","cited_by_count":8,"area":null},{"id":"2511.06271","title":"RelightMaster: Precise Video Relighting with Multi-plane Light Images","created":"2025-11-09","cited_by_count":8,"area":"diffusion"},{"id":"2505.23171","title":"RoboTransfer: Controllable Geometry-Consistent Video Diffusion for Manipulation Policy Transfer","created":"2025-05-29","cited_by_count":7,"area":"diffusion"},{"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":"2603.11421","title":"ShotVerse: Advancing Cinematic Camera Control for Text-Driven Multi-Shot Video Creation","created":"2026-03-12","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":"2603.16271","title":"VIGOR: VIdeo Geometry-Oriented Reward for Temporal Generative Alignment","created":"2026-03-17","cited_by_count":7,"area":"diffusion"},{"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":"2511.17185","title":"PostCam: Camera-Controllable Novel-View Video Generation with Query-Shared Cross-Attention","created":"2025-11-21","cited_by_count":6,"area":null},{"id":"2512.10286","title":"ShotDirector: Directorially Controllable Multi-Shot Video Generation with Cinematographic Transitions","created":"2025-12-11","cited_by_count":6,"area":null},{"id":"2606.27964","title":"Directing the World: Fast Autoregressive Video Generation with Compositional Human-Camera Control","created":"2026-06-26","cited_by_count":6,"area":"wm"},{"id":"2607.06291","title":"AlayaWorld: Long-Horizon and Playable Video World Generation","created":"2026-07-07","cited_by_count":6,"area":"wm"},{"id":"2604.09429","title":"Rays as Pixels: Learning A Joint Distribution of Videos and Camera Trajectories","created":"2026-04-10","cited_by_count":5,"area":null},{"id":"2606.24101","title":"NavWM: A Unified Navigation World Model for Foresight-Driven Planning","created":"2026-06-23","cited_by_count":5,"area":"wm"},{"id":"2606.27345","title":"SCoPE: Sightline-Coordinate Positional Encoding for Video Diffusion Transformers","created":"2026-06-25","cited_by_count":5,"area":"diffusion"},{"id":"2608.13391","title":"Context-Matched Distillation: Teacher Causality for Autoregressive Video Distillation","created":"2026-08-13","cited_by_count":5,"area":"distill"},{"id":"2505.21205","title":"EF-VI: Enhancing End-Frame Injection for Video Inbetweening","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2510.24718","title":"Generative View Stitching","created":"2025-10-28","cited_by_count":4,"area":"diffusion"},{"id":"2512.03619","title":"LAMP: Language-Assisted Motion Planning for Controllable Video Generation","created":"2025-12-03","cited_by_count":4,"area":null},{"id":"2601.16214","title":"CamPilot: Improving Camera Control in Video Diffusion Model with Efficient Camera Reward Feedback","created":"2026-01-22","cited_by_count":4,"area":"diffusion"},{"id":"2605.25449","title":"Pantheon360: Taming Digital Twin Generation via 3D-Aware 360{\\deg} Video Diffusion","created":"2026-05-25","cited_by_count":4,"area":"diffusion"},{"id":"2605.30774","title":"CameraNoise: Enabling Faithful Camera Control in Video Diffusion through Geometry-Flow-Guided Noise Warping","created":"2026-05-29","cited_by_count":4,"area":"diffusion"},{"id":"2512.16915","title":"StereoPilot: Learning Unified and Efficient Stereo Conversion via Generative Priors","created":"2025-12-18","cited_by_count":3,"area":null},{"id":"2603.13119","title":"Geometry-Guided Camera Motion Understanding in VideoLLMs","created":"2026-03-13","cited_by_count":3,"area":"mllm"},{"id":"2603.14965","title":"GeoNVS: Geometry Grounded Video Diffusion for Novel View Synthesis","created":"2026-03-16","cited_by_count":3,"area":"diffusion"},{"id":"2608.09449","title":"Sekai2: From World Exploration to Interactive World Modeling","created":"2026-08-10","cited_by_count":3,"area":"wm"},{"id":"2512.01481","title":"ChronosObserver: Taming 4D World with Hyperspace Diffusion Sampling","created":"2025-12-01","cited_by_count":2,"area":"diffusion"},{"id":"2512.09112","title":"GimbalDiffusion: Gravity-Aware Camera Control for Video Generation","created":"2025-12-09","cited_by_count":2,"area":null},{"id":"2603.22972","title":"WorldMesh: Generating Navigable Multi-Room 3D Scenes via Mesh-Conditioned Image Diffusion","created":"2026-03-24","cited_by_count":2,"area":null},{"id":"2603.24835","title":"DCARL: A Divide-and-Conquer Framework for Autoregressive Long-Trajectory Video Generation","created":"2026-03-25","cited_by_count":2,"area":"wm"},{"id":"2606.20774","title":"TriMotion: Modality-Agnostic Camera Control for Video Generation","created":"2026-06-18","cited_by_count":2,"area":null},{"id":"2609.04911","title":"TourPhysics: Bringing Physics to World Models for Exploration and Manipulation from a Single Image","created":"2026-09-04","cited_by_count":2,"area":"wm"},{"id":"2512.17796","title":"CustomX: Unified Character, Action, and Scene Customization in Video World Models","created":"2025-12-18","cited_by_count":1,"area":"wm"},{"id":"2603.09104","title":"Training-free Motion Factorization for Compositional Video Generation","created":"2026-03-10","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":"2604.09201","title":"CT-1: Vision-Language-Camera Models Transfer Spatial Reasoning Knowledge to Camera-Controllable Video Generation","created":"2026-04-10","cited_by_count":1,"area":"lr"},{"id":"2605.11871","title":"$h$-control: Training-Free Camera Control via Block-Conditional Gibbs Refinement","created":"2026-05-12","cited_by_count":1,"area":"diffusion"},{"id":"2605.14815","title":"Probing into Camera Control of Video Models","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2606.01900","title":"Auteur: Language-Driven Cinematographic Framing for Human-Centric Video Generation","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2607.24591","title":"CameraAnything: Refilming Videos with Arbitrary Camera Control","created":"2026-07-27","cited_by_count":1,"area":null},{"id":"2510.24904","title":"VividCam: Learning Unconventional Camera Motions from Virtual Synthetic Videos","created":"2025-10-28","cited_by_count":0,"area":null},{"id":"2602.15539","title":"Dynamic Training-Free Fusion of Subject and Style LoRAs","created":"2026-02-17","cited_by_count":0,"area":null},{"id":"2603.25420","title":"VideoWeaver: Multimodal Multi-View Video-to-Video Transfer for Embodied Agents","created":"2026-03-26","cited_by_count":0,"area":"agents"},{"id":"2604.06010","title":"OmniCamera: A Unified Framework for Multi-task Video Generation with Arbitrary Camera Control","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2606.01590","title":"Effective Multi-sensor Conditioning for Street-view Novel-view Synthesis","created":"2026-06-01","cited_by_count":0,"area":"diffusion"},{"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":"2606.31258","title":"WarpHammer: Densifying Scene Warps with 3D Object Priors for Extreme View Synthesis","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.01663","title":"Unified Panoramic-Gaussian Representation for Monocular 4D Scene Synthesis","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2609.02847","title":"RoGe: Novel View Synthesis via End-to-End Implicit Reconstruction and Generation","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.03952","title":"WorldReward: Reward Modeling for Camera-Conditioned World Models","created":"2026-09-03","cited_by_count":0,"area":"wm"},{"id":"2609.06099","title":"PASTEL: Panoramic Alignment for Monocular 4D Scene Reconstruction","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.20819","title":"Can 4D Foundation Models Remember?","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.30595","title":"Action Forcing: Training World Models on Unsupervised Video by Recovering Underlying Egomotion Bases","created":"2026-09-24","cited_by_count":0,"area":"wm"},{"id":"2609.35023","title":"Proxy2World: Learning to Generate Worlds From Lightweight Proxies without Seeing Them","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.37690","title":"Honeycomb: Constant-Size Scene Memory Representation for Video World Models","created":"2026-09-29","cited_by_count":0,"area":"wm"},{"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":"2610.02160","title":"4Director: Controlling Video World Models with Rigid 3D Geometry","created":"2026-10-01","cited_by_count":0,"area":"wm"},{"id":"2610.02180","title":"Generative Cinematographer: Composing Camera and Object Motion in 3D","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.19257","title":"Long-horizon Video Generation with Slot Memory Addressed By Region Tokens","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}