{"total":170,"rows":[{"id":"2511.00062","title":"World Simulation with Video Foundation Models for Physical AI","created":"2025-10-28","cited_by_count":200,"area":null},{"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":"2606.02800","title":"Cosmos 3: Omnimodal World Models for Physical AI","created":"2026-06-01","cited_by_count":165,"area":"wm"},{"id":"2509.26645","title":"TTT3R: 3D Reconstruction as Test-Time Training","created":"2025-09-30","cited_by_count":129,"area":null},{"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":"2511.23429","title":"Hunyuan-GameCraft-2: Instruction-following Interactive Game World Model","created":"2025-11-28","cited_by_count":61,"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":"2604.13036","title":"Lyra 2.0: Explorable Generative 3D Worlds","created":"2026-04-14","cited_by_count":44,"area":null},{"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":"2512.07237","title":"Unified Camera Positional Encoding for Controlled Video Generation","created":"2025-12-08","cited_by_count":37,"area":"wm"},{"id":"2604.14141","title":"LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction","created":"2026-04-15","cited_by_count":37,"area":null},{"id":"2602.08025","title":"MIND: Benchmarking Memory Consistency and Action Control in World Models","created":"2026-02-08","cited_by_count":35,"area":"wm"},{"id":"2508.13154","title":"4DNeX: Feed-Forward 4D Generative Modeling Made Easy","created":"2025-08-18","cited_by_count":34,"area":"diffusion"},{"id":"2510.13678","title":"FlashWorld: High-quality 3D Scene Generation within Seconds","created":"2025-10-15","cited_by_count":32,"area":"diffusion"},{"id":"2510.04290","title":"ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation","created":"2025-10-05","cited_by_count":29,"area":"lr"},{"id":"2512.03422","title":"What Is The Best 3D Scene Representation for Robotics? From Geometric to Foundation Models","created":"2025-12-03","cited_by_count":29,"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":"2604.21686","title":"WorldMark: A Unified Benchmark Suite for Interactive Video World Models","created":"2026-04-23","cited_by_count":26,"area":"wm"},{"id":"2605.15195","title":"VGGT-$\\Omega$","created":"2026-05-14","cited_by_count":26,"area":null},{"id":"2512.02015","title":"Generative Video Motion Editing with 3D Point Tracks","created":"2025-12-01","cited_by_count":23,"area":null},{"id":"2511.20343","title":"AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backend","created":"2025-11-25","cited_by_count":20,"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":"2606.09828","title":"Latent Spatial Memory for Video World Models","created":"2026-06-08","cited_by_count":17,"area":"wm"},{"id":"2512.10226","title":"Latent Chain-of-Thought World Modeling for End-to-End Driving","created":"2025-12-11","cited_by_count":15,"area":"wm"},{"id":"2607.26037","title":"Wonder: Video World Model Done Better","created":"2026-07-28","cited_by_count":15,"area":"wm"},{"id":"2510.02268","title":"Do You Know Where Your Camera Is? View-Invariant Policy Learning with Camera Conditioning","created":"2025-10-02","cited_by_count":14,"area":"offlinerl"},{"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":"2603.06408","title":"Physical Simulator In-the-Loop Video Generation","created":"2026-03-06","cited_by_count":14,"area":"diffusion"},{"id":"2604.01001","title":"EgoSim: Egocentric World Simulator for Embodied Interaction Generation","created":"2026-04-01","cited_by_count":14,"area":null},{"id":"2605.03941","title":"iWorld-Bench: A Benchmark for Interactive World Models with a Unified Action Generation Framework","created":"2026-05-05","cited_by_count":14,"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":"2509.23958","title":"Reinforcement Learning with Inverse Rewards for World Model Post-training","created":"2025-09-28","cited_by_count":13,"area":"wm"},{"id":"2602.08068","title":"ReRoPE: Repurposing RoPE for Relative Camera Control","created":"2026-02-08","cited_by_count":13,"area":"diffusion"},{"id":"2603.02573","title":"Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels","created":"2026-03-03","cited_by_count":13,"area":null},{"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":"2606.02436","title":"Geometry-Aware Implicit Memory for Video World Models","created":"2026-06-01","cited_by_count":13,"area":"wm"},{"id":"2608.23189","title":"EchoWM: Open and Enterable Omnimodal World Models","created":"2026-08-24","cited_by_count":13,"area":"wm"},{"id":"2601.16982","title":"AnyView: Synthesizing Any Novel View in Dynamic Scenes","created":"2026-01-23","cited_by_count":12,"area":null},{"id":"2603.12746","title":"Thinking in Dynamics: How Multimodal Large Language Models Perceive, Track, and Reason Dynamics in Physical 4D World","created":"2026-03-13","cited_by_count":12,"area":"lr"},{"id":"2603.16669","title":"Kinema4D: Kinematic 4D World Modeling for Spatiotemporal Embodied Simulation","created":"2026-03-17","cited_by_count":12,"area":"wm"},{"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":"2511.19827","title":"ReDirector: Creating Any-Length Video Retakes with Rotary Camera Encoding","created":"2025-11-25","cited_by_count":11,"area":null},{"id":"2607.18367","title":"AlayaWorld: Interactive Long-Horizon World Modeling -- Full Technical Report","created":"2026-07-20","cited_by_count":11,"area":"wm"},{"id":"2512.02870","title":"Taming Camera-Controlled Video Generation with Verifiable Geometry Reward","created":"2025-12-02","cited_by_count":10,"area":"diffusion"},{"id":"2602.10104","title":"Olaf-World: Orienting Latent Actions for Video World Modeling","created":"2026-02-10","cited_by_count":10,"area":"wm"},{"id":"2606.17200","title":"ACE-Ego-0: Unifying Egocentric Human and Robotic Data for VLA Pretraining","created":"2026-06-15","cited_by_count":10,"area":"vla"},{"id":"2606.31672","title":"WorldRoamBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models","created":"2026-06-30","cited_by_count":10,"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":"2609.10540","title":"Programmable World Model","created":"2026-09-09","cited_by_count":10,"area":"wm"},{"id":"2601.05239","title":"Plenoptic Video Generation","created":"2026-01-08","cited_by_count":9,"area":null},{"id":"2602.20157","title":"Flow3r: Factored Flow Prediction for Scalable Visual Geometry Learning","created":"2026-02-23","cited_by_count":9,"area":null},{"id":"2606.18478","title":"Data-Forcing Distillation: Restoring Diversity and Fidelity in Few-Step Video Generation","created":"2026-06-16","cited_by_count":9,"area":"diffusion"},{"id":"2511.18173","title":"EgoControl: Controllable Egocentric Video Generation via 3D Full-Body Poses","created":"2025-11-22","cited_by_count":8,"area":null},{"id":"2512.08269","title":"EgoX: Egocentric Video Generation from a Single Exocentric Video","created":"2025-12-09","cited_by_count":8,"area":null},{"id":"2601.18993","title":"FreeOrbit4D: Training-Free Arbitrary Camera Redirection for Monocular Videos via Foreground-Complete 4D Reconstruction","created":"2026-01-26","cited_by_count":6,"area":"diffusion"},{"id":"2605.30215","title":"D\\'ej\\`a View: Looping Transformers for Multi-View 3D Reconstruction","created":"2026-05-28","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":"2607.00033","title":"Learning Dexterous Manipulation Using Contact Wrench Guidance From Human Demonstration","created":"2026-06-22","cited_by_count":6,"area":"deeprl"},{"id":"2510.13310","title":"InstantSfM: Towards GPU-Native SfM for the Deep Learning Era","created":"2025-10-15","cited_by_count":5,"area":null},{"id":"2512.07821","title":"WorldReel: 4D Video Generation with Consistent Geometry and Motion Modeling","created":"2025-12-08","cited_by_count":5,"area":null},{"id":"2512.19020","title":"CETCAM: Camera-Controllable Video Generation via Consistent and Extensible Tokenization","created":"2025-12-22","cited_by_count":5,"area":null},{"id":"2605.12587","title":"TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking","created":"2026-05-12","cited_by_count":5,"area":"diffusion"},{"id":"2605.22819","title":"Cambrian-P: Pose-Grounded Video Understanding","created":"2026-05-21","cited_by_count":5,"area":null},{"id":"2606.11628","title":"LUCID: Learning Embodiment-Agnostic Intent Models from Unstructured Human Videos for Scalable Dexterous Robot Skill Acquisition","created":"2026-06-10","cited_by_count":5,"area":null},{"id":"2606.18558","title":"MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction","created":"2026-06-17","cited_by_count":5,"area":null},{"id":"2606.27345","title":"SCoPE: Sightline-Coordinate Positional Encoding for Video Diffusion Transformers","created":"2026-06-25","cited_by_count":5,"area":"diffusion"},{"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":"2607.09661","title":"PanoWorld: Real-World Panoramic Generation","created":"2026-07-10","cited_by_count":5,"area":"wm"},{"id":"2511.21681","title":"Seeing without Pixels: Perception from Camera Trajectories","created":"2025-11-26","cited_by_count":4,"area":null},{"id":"2603.24506","title":"Toward Physically Consistent Driving Video World Models under Challenging Trajectories","created":"2026-03-25","cited_by_count":4,"area":"wm"},{"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":"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":"2608.23383","title":"Long-Horizon Audio-Visual Generation for Persistent Stories and Interactive Worlds","created":"2026-08-24","cited_by_count":4,"area":"wm"},{"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":"2512.06368","title":"HuPrior3R: Incorporating Human Priors for Better 3D Dynamic Reconstruction from Monocular Videos","created":"2025-12-06","cited_by_count":3,"area":null},{"id":"2512.15160","title":"EagleVision: A Dual-Stage Framework with BEV-grounding-based Chain-of-Thought for Spatial Intelligence","created":"2025-12-17","cited_by_count":3,"area":"lr"},{"id":"2602.21778","title":"From Statics to Dynamics: Physics-Aware Image Editing with Latent Transition Priors","created":"2026-02-25","cited_by_count":3,"area":null},{"id":"2603.14965","title":"GeoNVS: Geometry Grounded Video Diffusion for Novel View Synthesis","created":"2026-03-16","cited_by_count":3,"area":"diffusion"},{"id":"2605.06051","title":"RealCam: Real-Time Novel-View Video Generation with Interactive Camera Control","created":"2026-05-07","cited_by_count":3,"area":null},{"id":"2605.15477","title":"EgoExo-WM: Unlocking Exo Video for Ego World Models","created":"2026-05-14","cited_by_count":3,"area":"wm"},{"id":"2605.23903","title":"Geo-Align: Video Generation Alignment via Metric Geometry Reward","created":"2026-05-22","cited_by_count":3,"area":null},{"id":"2608.04701","title":"UniWorld-View: Large-Baseline View Synthesis via Video Diffusion Models","created":"2026-08-05","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":"2608.27073","title":"SpatialCrafter: Single Image World Modeling with Generative 3D Proxies","created":"2026-08-27","cited_by_count":3,"area":"wm"},{"id":"2609.14462","title":"AlayaVista: Streaming World Modeling from Panoramic States to Perspective Video","created":"2026-09-13","cited_by_count":3,"area":"wm"},{"id":"2509.22222","title":"Rigidity-Aware 3D Gaussian Deformation from a Single Image","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2511.17364","title":"SVRecon: Sparse Voxel Rasterization for Surface Reconstruction","created":"2025-11-21","cited_by_count":2,"area":null},{"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":"2512.07698","title":"sim2art: Accurate Articulated Object Modeling from a Single Video using Synthetic Training Data Only","created":"2025-12-08","cited_by_count":2,"area":null},{"id":"2512.09112","title":"GimbalDiffusion: Gravity-Aware Camera Control for Video Generation","created":"2025-12-09","cited_by_count":2,"area":null},{"id":"2604.07348","title":"MoRight: Motion Control Done Right","created":"2026-04-08","cited_by_count":2,"area":null},{"id":"2604.21776","title":"Reshoot-Anything: A Self-Supervised Model for In-the-Wild Video Reshooting","created":"2026-04-23","cited_by_count":2,"area":null},{"id":"2605.12119","title":"MoCam: Unified Novel View Synthesis via Structured Denoising Dynamics","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2605.14615","title":"CalibAnyView: Beyond Single-View Camera Calibration in the Wild","created":"2026-05-14","cited_by_count":2,"area":null},{"id":"2605.25077","title":"WorldCraft: From Camera Navigation to Object Manipulation in Interactive Video World Models","created":"2026-05-24","cited_by_count":2,"area":"wm"},{"id":"2605.26316","title":"E$^3$C: Video Generation with 3D Environmental Memory and Ego-Exo Human Pose Control","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2606.07967","title":"DisCo: World Models with Discrete Camera Motion Control","created":"2026-06-06","cited_by_count":2,"area":"wm"},{"id":"2607.09655","title":"OpenLongTail: Generative Scaling of Long-Tail Driving Data","created":"2026-07-10","cited_by_count":2,"area":"wm"}],"next_cursor":"100"}