{"total":207,"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":"2502.20110","title":"UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler","created":"2025-02-27","cited_by_count":173,"area":null},{"id":"2508.10934","title":"ViPE: Video Pose Engine for 3D Geometric Perception","created":"2025-08-12","cited_by_count":170,"area":null},{"id":"2507.12462","title":"SpatialTrackerV2: 3D Point Tracking Made Easy","created":"2025-07-16","cited_by_count":87,"area":null},{"id":"2510.15742","title":"Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset","created":"2025-10-17","cited_by_count":79,"area":null},{"id":"2604.26694","title":"Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising","created":"2026-04-29","cited_by_count":71,"area":"wm"},{"id":"2511.19861","title":"GigaWorld-0: World Models as Data Engine to Empower Embodied AI","created":"2025-11-25","cited_by_count":62,"area":"wm"},{"id":"2512.07826","title":"OpenVE-3M: A Large-Scale High-Quality Dataset for Instruction-Guided Video Editing","created":"2025-12-08","cited_by_count":53,"area":null},{"id":"2510.07316","title":"Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers","created":"2025-10-08","cited_by_count":51,"area":"diffusion"},{"id":"2510.19430","title":"GigaBrain-0: A World Model-Powered Vision-Language-Action Model","created":"2025-10-22","cited_by_count":44,"area":"wm"},{"id":"2508.10898","title":"Puppeteer: Rig and Animate Your 3D Models","created":"2025-08-14","cited_by_count":43,"area":null},{"id":"2506.23135","title":"RoboScape: Physics-informed Embodied World Model","created":"2025-06-29","cited_by_count":40,"area":"wm"},{"id":"2509.21657","title":"FantasyWorld: Geometry-Consistent World Modeling via Unified Video and 3D Prediction","created":"2025-09-25","cited_by_count":38,"area":"wm"},{"id":"2507.10065","title":"MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second","created":"2025-07-14","cited_by_count":35,"area":null},{"id":"2512.10935","title":"Any4D: Unified Feed-Forward Metric 4D Reconstruction","created":"2025-12-11","cited_by_count":35,"area":null},{"id":"2506.01943","title":"Learning Video Generation for Robotic Manipulation with Collaborative Trajectory Control","created":"2025-06-02","cited_by_count":34,"area":"diffusion"},{"id":"2512.01989","title":"PAI-Bench: A Comprehensive Benchmark For Physical AI","created":"2025-12-01","cited_by_count":34,"area":"mllm"},{"id":"2601.15282","title":"Rethinking Video Generation Model for the Embodied World","created":"2026-01-21","cited_by_count":33,"area":null},{"id":"2510.13678","title":"FlashWorld: High-quality 3D Scene Generation within Seconds","created":"2025-10-15","cited_by_count":32,"area":"diffusion"},{"id":"2506.01799","title":"WorldExplorer: Towards Generating Fully Navigable 3D Scenes","created":"2025-06-02","cited_by_count":26,"area":null},{"id":"2504.05692","title":"POMATO: Marrying Pointmap Matching with Temporal Motion for Dynamic 3D Reconstruction","created":"2025-04-08","cited_by_count":25,"area":null},{"id":"2504.10825","title":"OmniVDiff: Omni Controllable Video Diffusion for Generation and Understanding","created":"2025-04-15","cited_by_count":22,"area":"diffusion"},{"id":"2508.03694","title":"LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation","created":"2025-08-05","cited_by_count":22,"area":null},{"id":"2510.14836","title":"QDepth-VLA: Quantized Depth Prediction as Auxiliary Supervision for Vision-Language-Action Models","created":"2025-10-16","cited_by_count":21,"area":"vla"},{"id":"2512.18741","title":"Memorize-and-Generate: Towards Long-Term Consistency in Real-Time Video Generation","created":"2025-12-21","cited_by_count":20,"area":"wm"},{"id":"2512.03453","title":"GeoVideo: Introducing Geometric Regularization into Video Generation Model","created":"2025-12-03","cited_by_count":19,"area":"diffusion"},{"id":"2604.19092","title":"RoboWM-Bench: A Benchmark for Evaluating World Models in Robotic Manipulation","created":"2026-04-21","cited_by_count":19,"area":"wm"},{"id":"2505.24867","title":"Time Blindness: Why Video-Language Models Can't See What Humans Can?","created":"2025-05-30","cited_by_count":18,"area":"mllm"},{"id":"2604.21915","title":"Vista4D: Video Reshooting with 4D Point Clouds","created":"2026-04-23","cited_by_count":18,"area":null},{"id":"2505.10075","title":"FlowDreamer: A RGB-D World Model with Flow-based Motion Representations for Robot Manipulation","created":"2025-05-15","cited_by_count":17,"area":"wm"},{"id":"2506.23361","title":"OmniVCus: Feedforward Subject-driven Video Customization with Multimodal Control Conditions","created":"2025-06-29","cited_by_count":17,"area":null},{"id":"2504.03198","title":"Endo3R: Unified Online Reconstruction from Dynamic Monocular Endoscopic Video","created":"2025-04-04","cited_by_count":16,"area":null},{"id":"2504.07093","title":"FlashDepth: Real-time Streaming Video Depth Estimation at 2K Resolution","created":"2025-04-09","cited_by_count":14,"area":null},{"id":"2507.08344","title":"MM-Gesture: Towards Precise Micro-Gesture Recognition through Multimodal Fusion","created":"2025-07-11","cited_by_count":14,"area":null},{"id":"2507.21045","title":"Reconstructing 4D Spatial Intelligence: A Survey","created":"2025-07-28","cited_by_count":14,"area":null},{"id":"2512.11988","title":"CARI4D: Category Agnostic 4D Reconstruction of Human-Object Interaction","created":"2025-12-12","cited_by_count":14,"area":null},{"id":"2602.15828","title":"Dex4D: Task-Agnostic Point Track Policy for Zero-Shot Dexterous Manipulation","created":"2026-02-17","cited_by_count":14,"area":null},{"id":"2509.22407","title":"EMMA: Generalizing Real-World Robot Manipulation via Generative Visual Transfer","created":"2025-09-26","cited_by_count":12,"area":"vla"},{"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":"2511.19827","title":"ReDirector: Creating Any-Length Video Retakes with Rotary Camera Encoding","created":"2025-11-25","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":"2511.18416","title":"4D-VGGT: A General Foundation Model with SpatioTemporal Awareness for Dynamic Scene Geometry Estimation","created":"2025-11-23","cited_by_count":10,"area":null},{"id":"2604.02329","title":"Generative World Renderer","created":"2026-04-02","cited_by_count":10,"area":null},{"id":"2606.28128","title":"PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation","created":"2026-06-26","cited_by_count":10,"area":null},{"id":"2505.24521","title":"UniGeo: Taming Video Diffusion for Unified Consistent Geometry Estimation","created":"2025-05-30","cited_by_count":9,"area":"diffusion"},{"id":"2508.14811","title":"Tinker: Diffusion's Gift to 3D--Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization","created":"2025-08-20","cited_by_count":9,"area":"diffusion"},{"id":"2512.13604","title":"LongVie 2: Multimodal Controllable Ultra-Long Video World Model","created":"2025-12-15","cited_by_count":9,"area":"wm"},{"id":"2602.01661","title":"From Frames to Sequences: Temporally Consistent Human-Centric Dense Prediction","created":"2026-02-02","cited_by_count":9,"area":null},{"id":"2503.05549","title":"Stereo Any Video: Temporally Consistent Stereo Matching","created":"2025-03-07","cited_by_count":8,"area":null},{"id":"2504.17787","title":"The Fourth Monocular Depth Estimation Challenge","created":"2025-04-24","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":"2602.09609","title":"Tele-Omni: a Unified Multimodal Framework for Video Generation and Editing","created":"2026-02-10","cited_by_count":8,"area":"diffusion"},{"id":"2502.03465","title":"Seeing World Dynamics in a Nutshell","created":"2025-02-05","cited_by_count":7,"area":null},{"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":"2506.01933","title":"E3D-Bench: A Benchmark for End-to-End 3D Geometric Foundation Models","created":"2025-06-02","cited_by_count":7,"area":null},{"id":"2506.03150","title":"IllumiCraft: Unified Geometry and Illumination Diffusion for Controllable Video Generation","created":"2025-06-03","cited_by_count":7,"area":null},{"id":"2508.04147","title":"IDCNet: Guided Video Diffusion for Metric-Consistent RGBD Scene Generation with Precise Camera Control","created":"2025-08-06","cited_by_count":7,"area":"diffusion"},{"id":"2511.00503","title":"Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models","created":"2025-11-01","cited_by_count":7,"area":"diffusion"},{"id":"2512.01342","title":"InternVideo-Next: Towards General Video Foundation Models without Video-Text Supervision","created":"2025-12-01","cited_by_count":7,"area":"wm"},{"id":"2512.22808","title":"EgoReAct: Egocentric Video-Driven 3D Human Reaction Generation","created":"2025-12-28","cited_by_count":7,"area":null},{"id":"2504.10001","title":"GaussVideoDreamer: 3D Scene Generation with Video Diffusion and Inconsistency-Aware Gaussian Splatting","created":"2025-04-14","cited_by_count":6,"area":"diffusion"},{"id":"2510.01686","title":"FreeViS: Training-free Video Stylization with Inconsistent References","created":"2025-10-02","cited_by_count":6,"area":null},{"id":"2511.21129","title":"CtrlVDiff: Controllable Video Generation via Unified Multimodal Video Diffusion","created":"2025-11-26","cited_by_count":6,"area":"diffusion"},{"id":"2512.19629","title":"LoGoPlanner: Localization Grounded Navigation Policy with Metric-aware Visual Geometry","created":"2025-12-22","cited_by_count":6,"area":null},{"id":"2512.01677","title":"Open-world Hand-Object Interaction Video Generation Based on Structure and Contact-aware Representation","created":"2025-12-01","cited_by_count":5,"area":null},{"id":"2603.24793","title":"AVControl: Efficient Framework for Training Audio-Visual Controls","created":"2026-03-25","cited_by_count":5,"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":"2512.07371","title":"ESPADA: Execution Speedup via Semantics Aware Demonstration Data Downsampling for Imitation Learning","created":"2025-12-08","cited_by_count":4,"area":"offlinerl"},{"id":"2512.15635","title":"IC-Effect: Precise and Efficient Video Effects Editing via In-Context Learning","created":"2025-12-17","cited_by_count":4,"area":null},{"id":"2603.12250","title":"DVD: Deterministic Video Depth Estimation with Generative Priors","created":"2026-03-12","cited_by_count":4,"area":null},{"id":"2603.25791","title":"ArtHOI: Taming Foundation Models for Monocular 4D Reconstruction of Hand-Articulated-Object Interactions","created":"2026-03-26","cited_by_count":4,"area":null},{"id":"2605.21431","title":"iTryOn: Mastering Interactive Video Virtual Try-On with Spatial-Semantic Guidance","created":"2026-05-20","cited_by_count":4,"area":null},{"id":"2606.15162","title":"GeoStream: Toward Precise Camera Controlled Streaming Video Generation","created":"2026-06-13","cited_by_count":4,"area":"wm"},{"id":"2607.24159","title":"DeVA: Decoupled Video-Action Model with physical guidance for robot policy learning","created":"2026-07-27","cited_by_count":4,"area":null},{"id":"2608.15555","title":"RigidBench: Evaluating Rigid-Body Physics in Video Generation Models","created":"2026-08-16","cited_by_count":4,"area":null},{"id":"2511.12921","title":"Generative Photographic Control for Scene-Consistent Video Cinematic Editing","created":"2025-11-17","cited_by_count":3,"area":null},{"id":"2511.16993","title":"DepthFocus: Controllable Depth Estimation for See-Through Scenes","created":"2025-11-21","cited_by_count":3,"area":null},{"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":"2512.03040","title":"Video4Spatial: Towards Visuospatial Intelligence with Context-Guided Video Generation","created":"2025-12-02","cited_by_count":3,"area":null},{"id":"2512.09363","title":"StereoWorld: Geometry-Aware Monocular-to-Stereo Video Generation","created":"2025-12-10","cited_by_count":3,"area":null},{"id":"2512.10725","title":"Video Depth Propagation","created":"2025-12-11","cited_by_count":3,"area":null},{"id":"2602.14751","title":"Depth Completion as Parameter-Efficient Test-Time Adaptation","created":"2026-02-16","cited_by_count":3,"area":null},{"id":"2603.01765","title":"StreamTTO: Efficient Online Test-Time Optimization for Video Depth Completion","created":"2026-03-02","cited_by_count":3,"area":null},{"id":"2603.03744","title":"DAGE: Dual-Stream Architecture for Efficient and Fine-Grained Geometry Estimation","created":"2026-03-04","cited_by_count":3,"area":null},{"id":"2603.09668","title":"DiffWind: Physics-Informed Differentiable Modeling of Wind-Driven Object Dynamics","created":"2026-03-10","cited_by_count":3,"area":null},{"id":"2605.00658","title":"UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors","created":"2026-05-01","cited_by_count":3,"area":"diffusion"},{"id":"2605.23903","title":"Geo-Align: Video Generation Alignment via Metric Geometry Reward","created":"2026-05-22","cited_by_count":3,"area":null},{"id":"2605.25308","title":"Stabilizing Streaming Video Geometry via Dynamic Feature Normalization","created":"2026-05-25","cited_by_count":3,"area":null},{"id":"2605.30060","title":"Towards Consistent Video Geometry Estimation","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2607.12993","title":"X-Lens: Real-Time Metric Depth Estimation with Heterogeneous Cameras","created":"2026-07-14","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":"2610.03715","title":"4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes","created":"2026-10-02","cited_by_count":3,"area":null},{"id":"2506.15560","title":"RaCalNet: Radar Calibration Network for Sparse-Supervised Metric Depth Estimation","created":"2025-06-18","cited_by_count":2,"area":null},{"id":"2507.11540","title":"Towards Depth Foundation Model: Recent Trends in Vision-Based Depth Estimation","created":"2025-07-15","cited_by_count":2,"area":null},{"id":"2509.17323","title":"DepTR-MOT: Unveiling the Potential of Depth-Informed Trajectory Refinement for Multi-Object Tracking","created":"2025-09-22","cited_by_count":2,"area":null},{"id":"2510.11107","title":"MoMaps: Semantics-Aware Scene Motion Generation with Motion Maps","created":"2025-10-13","cited_by_count":2,"area":null},{"id":"2512.08282","title":"PAVAS: Physics-Aware Video-to-Audio Synthesis","created":"2025-12-09","cited_by_count":2,"area":null},{"id":"2512.13597","title":"Lighting in Motion: Spatiotemporal HDR Lighting Estimation","created":"2025-12-15","cited_by_count":2,"area":"diffusion"},{"id":"2512.14217","title":"DRAW2ACT: Turning Depth-Encoded Trajectories into Robotic Demonstration Videos","created":"2025-12-16","cited_by_count":2,"area":"diffusion"}],"next_cursor":"100"}