{"total":85,"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":"2509.26645","title":"TTT3R: 3D Reconstruction as Test-Time Training","created":"2025-09-30","cited_by_count":129,"area":null},{"id":"2509.09676","title":"SpatialVID: A Large-Scale Video Dataset with Spatial Annotations","created":"2025-09-11","cited_by_count":77,"area":null},{"id":"2604.13036","title":"Lyra 2.0: Explorable Generative 3D Worlds","created":"2026-04-14","cited_by_count":44,"area":null},{"id":"2604.14141","title":"LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction","created":"2026-04-15","cited_by_count":37,"area":null},{"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":"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":"2604.01001","title":"EgoSim: Egocentric World Simulator for Embodied Interaction Generation","created":"2026-04-01","cited_by_count":14,"area":null},{"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":"2601.16982","title":"AnyView: Synthesizing Any Novel View in Dynamic Scenes","created":"2026-01-23","cited_by_count":12,"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":"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":"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":"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":"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":"2605.22819","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":"2511.21681","title":"Seeing without Pixels: Perception from Camera Trajectories","created":"2025-11-26","cited_by_count":4,"area":null},{"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":"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":"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":"2605.23903","title":"Geo-Align: Video Generation Alignment via Metric Geometry Reward","created":"2026-05-22","cited_by_count":3,"area":null},{"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":"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":"2605.26316","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":"2607.27194","title":"VidMap: Exploiting Temporal Structure for Video-Based Structure-from-Motion","created":"2026-07-29","cited_by_count":2,"area":null},{"id":"2609.05416","title":"WorldSculpt: Generating Compositional Worlds from Grounded Videos","created":"2026-09-04","cited_by_count":2,"area":null},{"id":"2512.01889","title":"KM-ViPE: Online Tightly Coupled Vision-Language-Geometry Fusion for Open-Vocabulary Semantic SLAM","created":"2025-12-01","cited_by_count":1,"area":null},{"id":"2512.16564","title":"4D Primitive-M\\^ach\\'e: Glueing Primitives for Persistent 4D Scene Reconstruction","created":"2025-12-18","cited_by_count":1,"area":null},{"id":"2601.09665","title":"SCE-SLAM: Scale-Consistent Monocular SLAM via Scene Coordinate Embeddings","created":"2026-01-14","cited_by_count":1,"area":null},{"id":"2603.12064","title":"Dense Dynamic Scene Reconstruction and Camera Pose Estimation from Multi-View Videos","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2603.24770","title":"DRoPS: Dynamic 3D Reconstruction of Pre-Scanned Objects","created":"2026-03-25","cited_by_count":1,"area":null},{"id":"2604.11038","title":"EgoFun3D: Modeling Interactive Objects from Egocentric Videos using Function Templates","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2604.13793","title":"From Synchrony to Sequence: Exo-to-Ego Generation via Interpolation","created":"2026-04-15","cited_by_count":1,"area":null},{"id":"2604.26067","title":"RADIO-ViPE: Online Tightly Coupled Multi-Modal Fusion for Open-Vocabulary Semantic SLAM in Dynamic Environments","created":"2026-04-28","cited_by_count":1,"area":null},{"id":"2605.12774","title":"WildPose: A Unified Framework for Robust Pose Estimation in the Wild","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2605.18645","title":"Articulation in Prime: Primitive-Based Articulated Object Understanding from a Single Casual Video","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2607.01962","title":"NeoMap: Training-free Novel-View Synthesis from Single Images and Videos","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2607.03043","title":"Natural Language Camera Movement Understanding","created":"2026-07-03","cited_by_count":1,"area":null},{"id":"2607.17790","title":"ReViV: Reconstructing the Viewer and the View in 4D from Monocular Egocentric Video","created":"2026-07-20","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":"2608.28288","title":"GeoFF3D: Coordinate-Anchored Feed-Forward Reconstruction for Large-Scale UAV Mapping","created":"2026-08-28","cited_by_count":1,"area":null},{"id":"2512.05398","title":"The Dynamic Prior: Understanding 3D Structures for Casual Dynamic Videos","created":"2025-12-05","cited_by_count":0,"area":null},{"id":"2602.19035","title":"OpenVO: Open-World Visual Odometry with Temporal Dynamics Awareness","created":"2026-02-22","cited_by_count":0,"area":null},{"id":"2603.29734","title":"GRVS: a Generalizable and Recurrent Approach to Monocular Dynamic View Synthesis","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2605.23672","title":"RiGS: Rigid-aware 4D Gaussian Splatting from a Single Monocular Video","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2605.27367","title":"SpatialBench: Is Your Spatial Foundation Model an All-Round Player?","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2606.06761","title":"AxisGuide: Grounding Robot Action Coordinate System in RGB Observations for Robust Visuomotor Manipulation","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2607.01202","title":"World from Motion: Generative Dynamic Gaussian Reconstruction from Monocular Video","created":"2026-07-01","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":"2607.19880","title":"EA-Nav: Learning Safe Visual Navigation Policies with Embodiment Awareness","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2608.12442","title":"MV2: Multi-View Multi-Vehicle Driving Dataset for Novel View Synthesis","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.21008","title":"Triangulation-Free Bundle Adjustment with Graduated Non-Convexity for Camera Pose Refinement from Coarse Priors","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.03563","title":"FlashRender: Few-Step Generative Rendering via Camera-Controlled Video MeanFlow","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.04201","title":"Scal3R: Learning Efficient Multi-Relative Pose Query for Scalable Online 3D Reconstruction","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.05210","title":"BLASt3R: Bundle Adjustment of Any Image Set with Multi-View Matching and Monocular Priors","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.19518","title":"AMB3R-SLAM: Kilometer-scale SLAM with Hierarchical Backend","created":"2026-09-17","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":"2609.34722","title":"Geometry as Address: Routing Attention to Visual Memory for Long-Horizon Camera-Controlled Video Generation","created":"2026-09-28","cited_by_count":0,"area":null},{"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":"2609.35368","title":"Ego-Forge: Text and Geometric-Attention Free Exo-to-Egocentric Video Generation","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35704","title":"DynaTokens: Teaching Dynamics to Camera-Controlled Video Models at Test Time","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.37030","title":"MotionInsight: Diagnosing Object Motion Deficiencies in Generated Videos","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38077","title":"MUGEN: Interactive Panoramic World Exploration via Camera Control","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38683","title":"Unveiling the Value of Motion for Cinematic Camera Trajectories","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.02180","title":"Generative Cinematographer: Composing Camera and Object Motion in 3D","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.12374","title":"AgentGarten: Code Worlds for Evolving Agents","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.12421","title":"Beyond Spatio-Temporal Priors: A Generalizable Approach for Dense Correspondence Matching","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.14445","title":"FreeCHROMA: Generative Chroma Keying from Unaligned Background References","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.14698","title":"PURE: Refining Feed-forward 3D Reconstruction with Unlabeled Post-training","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.19726","title":"Generative World Simulation with DAO and JING","created":"2026-10-14","cited_by_count":0,"area":null},{"id":"2610.19729","title":"A Diagnostic Study of World-Space Human Recovery Under High Camera Dynamics","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}