{"list":"other","total":62,"rows":[{"id":"2203.12601","title":"R3M: A Universal Visual Representation for Robot Manipulation","created":"2022-03-23","cited_by_count":694},{"id":"2511.10647","title":"Depth Anything 3: Recovering the Visual Space from Any Views","created":"2025-11-13","cited_by_count":692},{"id":"2307.07635","title":"CoTracker: It is Better to Track Together","created":"2023-07-14","cited_by_count":522},{"id":"2312.08344","title":"FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects","created":"2023-12-13","cited_by_count":429},{"id":"2210.00030","title":"VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training","created":"2022-09-30","cited_by_count":395},{"id":"1904.05767","title":"Learning joint reconstruction of hands and manipulated objects","created":"2019-04-11","cited_by_count":378},{"id":"2312.05251","title":"Reconstructing Hands in 3D with Transformers","created":"2023-12-08","cited_by_count":306},{"id":"2511.16624","title":"SAM 3D: 3Dfy Anything in Images","created":"2025-11-20","cited_by_count":247},{"id":"2304.08488","title":"Affordances from Human Videos as a Versatile Representation for Robotics","created":"2023-04-17","cited_by_count":226},{"id":"2302.12422","title":"MimicPlay: Long-Horizon Imitation Learning by Watching Human Play","created":"2023-02-24","cited_by_count":223},{"id":"2403.07788","title":"DexCap: Scalable and Portable Mocap Data Collection System for Dexterous Manipulation","created":"2024-03-12","cited_by_count":160},{"id":"2202.08227","title":"Ditto: Building Digital Twins of Articulated Objects from Interaction","created":"2022-02-16","cited_by_count":156},{"id":"2012.09856","title":"Reconstructing Hand-Object Interactions in the Wild","created":"2020-12-17","cited_by_count":144},{"id":"2410.11831","title":"CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos","created":"2024-10-15","cited_by_count":128},{"id":"2405.01527","title":"Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation","created":"2024-05-02","cited_by_count":124},{"id":"2409.12259","title":"WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild","created":"2024-09-18","cited_by_count":124},{"id":"2308.07391","title":"PARIS: Part-level Reconstruction and Motion Analysis for Articulated Objects","created":"2023-08-14","cited_by_count":118},{"id":"2410.13882","title":"Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Model","created":"2024-10-03","cited_by_count":96},{"id":"2508.00795","title":"Video Generators are Robot Policies","created":"2025-08-01","cited_by_count":92},{"id":"2507.12462","title":"SpatialTrackerV2: 3D Point Tracking Made Easy","created":"2025-07-16","cited_by_count":87},{"id":"2601.03782","title":"PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation","created":"2026-01-07","cited_by_count":82},{"id":"2311.18448","title":"HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video","created":"2023-11-30","cited_by_count":78},{"id":"2309.05663","title":"Diffusion-Guided Reconstruction of Everyday Hand-Object Interaction Clips","created":"2023-09-11","cited_by_count":74},{"id":"2008.08324","title":"FrankMocap: Fast Monocular 3D Hand and Body Motion Capture by Regression and Integration","created":"2020-08-19","cited_by_count":73},{"id":"2512.15840","title":"Large Video Planner Enables Generalizable Robot Control","created":"2025-12-17","cited_by_count":70},{"id":"2406.08474","title":"Real2Code: Reconstruct Articulated Objects via Code Generation","created":"2024-06-12","cited_by_count":69},{"id":"2501.02973","title":"HaWoR: World-Space Hand Motion Reconstruction from Egocentric Videos","created":"2025-01-06","cited_by_count":66},{"id":"2506.07310","title":"AllTracker: Efficient Dense Point Tracking at High Resolution","created":"2025-06-08","cited_by_count":58},{"id":"2409.18121","title":"Robot See Robot Do: Imitating Articulated Object Manipulation with Monocular 4D Reconstruction","created":"2024-09-26","cited_by_count":54},{"id":"2403.12943","title":"Vid2Robot: End-to-end Video-conditioned Policy Learning with Cross-Attention Transformers","created":"2024-03-19","cited_by_count":52},{"id":"2112.11347","title":"Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objects","created":"2021-12-21","cited_by_count":50},{"id":"2503.18673","title":"Any6D: Model-free 6D Pose Estimation of Novel Objects","created":"2025-03-24","cited_by_count":49},{"id":"2404.11151","title":"REACTO: Reconstructing Articulated Objects from a Single Video","created":"2024-04-17","cited_by_count":45},{"id":"2502.02590","title":"Articulate AnyMesh: Open-Vocabulary 3D Articulated Objects Modeling","created":"2025-02-04","cited_by_count":43},{"id":"1405.7705","title":"A Probabilistic Framework for Learning Kinematic Models of Articulated Objects","created":"2014-01-16","cited_by_count":40},{"id":"2510.08568","title":"NovaFlow: Zero-Shot Manipulation via Actionable Flow from Generated Videos","created":"2025-10-09","cited_by_count":40},{"id":"2312.02975","title":"Dexterous Functional Grasping","created":"2023-12-05","cited_by_count":39},{"id":"2507.00990","title":"Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations","created":"2025-07-01","cited_by_count":38},{"id":"2505.24853","title":"DexMachina: Functional Retargeting for Bimanual Dexterous Manipulation","created":"2025-05-30","cited_by_count":37},{"id":"2411.14280","title":"EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild","created":"2024-11-21","cited_by_count":36},{"id":"2512.10935","title":"Any4D: Unified Feed-Forward Metric 4D Reconstruction","created":"2025-12-11","cited_by_count":35},{"id":"2306.00979","title":"Building Rearticulable Models for Arbitrary 3D Objects from 4D Point Clouds","created":"2023-06-01","cited_by_count":34},{"id":"2503.23877","title":"ZeroMimic: Distilling Robotic Manipulation Skills from Web Videos","created":"2025-03-31","cited_by_count":32},{"id":"2511.09484","title":"SPIDER: Scalable Physics-Informed Dexterous Retargeting","created":"2025-11-12","cited_by_count":32},{"id":"2512.13644","title":"World Models for Learning Dexterous Hand-Object Interactions from Human Videos","created":"2025-12-15","cited_by_count":31},{"id":"2501.08329","title":"Predicting 4D Hand Trajectory from Monocular Videos","created":"2025-01-14","cited_by_count":21},{"id":"2506.08334","title":"iTACO: Interactable Digital Twins of Articulated Objects from Casually Captured RGBD Videos","created":"2025-06-10","cited_by_count":19},{"id":"2509.01708","title":"Articulated Object Estimation in the Wild","created":"2025-09-01","cited_by_count":19},{"id":"2511.16661","title":"Dexterity from Smart Lenses: Multi-Fingered Robot Manipulation with In-the-Wild Human Demonstrations","created":"2025-11-20","cited_by_count":19},{"id":"2606.28276","title":"SimFoundry: Modular and Automated Scene Generation for Policy Learning and Evaluation","created":"2026-06-26","cited_by_count":16},{"id":"2509.17647","title":"VideoArtGS: Building Digital Twins of Articulated Objects from Monocular Video","created":"2025-09-22","cited_by_count":15},{"id":"2508.13534","title":"MimicFunc: Imitating Tool Manipulation from a Single Human Video via Functional Correspondence","created":"2025-08-19","cited_by_count":13},{"id":"2602.09013","title":"Dexterous Manipulation Policies from RGB Human Videos via 3D Hand-Object Trajectory Reconstruction","created":"2026-02-09","cited_by_count":11},{"id":"2603.16869","title":"SegviGen: Repurposing 3D Generative Model for Part Segmentation","created":"2026-03-17","cited_by_count":10},{"id":"2512.14671","title":"ART: Articulated Reconstruction Transformer","created":"2025-12-16","cited_by_count":9},{"id":"2601.05237","title":"ObjectForesight: Predicting Future 3D Object Trajectories from Human Videos","created":"2026-01-08","cited_by_count":5},{"id":"2605.12587","title":"TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking","created":"2026-05-12","cited_by_count":5},{"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},{"id":"2603.11606","title":"Articulat3D: Reconstructing Articulated Digital Twins From Monocular Videos with Geometric and Motion Constraints","created":"2026-03-12","cited_by_count":3},{"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},{"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},{"id":"2607.16192","title":"MotionForesight: Re-purposing Video Models for Future 3D Scene-Flow Prediction","created":"2026-07-17","cited_by_count":1}],"next_cursor":null}