{"total":78,"rows":[{"id":"2507.15597","title":"Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos","created":"2025-07-21","cited_by_count":102,"area":"vla"},{"id":"2403.19649","title":"GraspXL: Generating Grasping Motions for Diverse Objects at Scale","created":"2024-03-28","cited_by_count":60,"area":null},{"id":"2503.19199","title":"Open-Vocabulary Functional 3D Scene Graphs for Real-World Indoor Spaces","created":"2025-03-24","cited_by_count":54,"area":null},{"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,"area":null},{"id":"2403.16428","title":"Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objects","created":"2024-03-25","cited_by_count":35,"area":null},{"id":"2505.02094","title":"SkillMimic-V2: Learning Robust and Generalizable Interaction Skills from Sparse and Noisy Demonstrations","created":"2025-05-04","cited_by_count":25,"area":"deeprl"},{"id":"2406.19811","title":"EgoGaussian: Dynamic Scene Understanding from Egocentric Video with 3D Gaussian Splatting","created":"2024-06-28","cited_by_count":23,"area":null},{"id":"2408.13953","title":"InterTrack: Tracking Human Object Interaction without Object Templates","created":"2024-08-25","cited_by_count":23,"area":null},{"id":"2504.05303","title":"InteractVLM: 3D Interaction Reasoning from 2D Foundational Models","created":"2025-04-07","cited_by_count":21,"area":null},{"id":"2508.05506","title":"MagicHOI: Leveraging 3D Priors for Accurate Hand-object Reconstruction from Short Monocular Video Clips","created":"2025-08-07","cited_by_count":17,"area":"diffusion"},{"id":"2412.13187","title":"HandsOnVLM: Vision-Language Models for Hand-Object Interaction Prediction","created":"2024-12-17","cited_by_count":15,"area":"mllm"},{"id":"2512.11988","title":"CARI4D: Category Agnostic 4D Reconstruction of Human-Object Interaction","created":"2025-12-12","cited_by_count":14,"area":null},{"id":"2412.11785","title":"InterDyn: Controllable Interactive Dynamics with Video Diffusion Models","created":"2024-12-16","cited_by_count":12,"area":"diffusion"},{"id":"2503.21313","title":"HORT: Monocular Hand-held Objects Reconstruction with Transformers","created":"2025-03-27","cited_by_count":11,"area":null},{"id":"2505.05517","title":"Web2Grasp: Learning Functional Grasps from Web Images of Hand-Object Interactions","created":"2025-05-07","cited_by_count":11,"area":null},{"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,"area":null},{"id":"2312.15719","title":"Get a Grip: Reconstructing Hand-Object Stable Grasps in Egocentric Videos","created":"2023-12-25","cited_by_count":10,"area":null},{"id":"2504.09097","title":"BIGS: Bimanual Category-agnostic Interaction Reconstruction from Monocular Videos via 3D Gaussian Splatting","created":"2025-04-12","cited_by_count":10,"area":null},{"id":"2406.17988","title":"DICE: End-to-end Deformation Capture of Hand-Face Interactions from a Single Image","created":"2024-06-26","cited_by_count":9,"area":null},{"id":"2505.16602","title":"MEgoHand: Multimodal Egocentric Hand-Object Interaction Motion Generation","created":"2025-05-22","cited_by_count":9,"area":null},{"id":"2506.07886","title":"EgoM2P: Egocentric Multimodal Multitask Pretraining","created":"2025-06-09","cited_by_count":9,"area":null},{"id":"2411.09572","title":"Dynamic Reconstruction of Hand-Object Interaction with Distributed Force-aware Contact Representation","created":"2024-11-14","cited_by_count":8,"area":null},{"id":"2508.04681","title":"Perceiving and Acting in First-Person: A Dataset and Benchmark for Egocentric Human-Object-Human Interactions","created":"2025-08-06","cited_by_count":8,"area":null},{"id":"2508.18213","title":"Follow My Hold: Hand-Object Interaction Reconstruction through Geometric Guidance","created":"2025-08-25","cited_by_count":8,"area":"diffusion"},{"id":"2510.14874","title":"TOUCH: Text-guided Controllable Generation of Free-Form Hand-Object Interactions","created":"2025-10-16","cited_by_count":8,"area":null},{"id":"2602.22209","title":"WHOLE: World-Grounded Hand-Object Lifted from Egocentric Videos","created":"2026-02-25","cited_by_count":8,"area":null},{"id":"2602.06226","title":"ForeHOI: Feed-forward 3D Object Reconstruction from Daily Hand-Object Interaction Videos","created":"2026-02-05","cited_by_count":7,"area":null},{"id":"2604.03305","title":"HVG-3D: Bridging Real and Simulation Domains for 3D-Conditional Hand-Object Interaction Video Synthesis","created":"2026-03-31","cited_by_count":7,"area":null},{"id":"2408.16770","title":"3D Whole-body Grasp Synthesis with Directional Controllability","created":"2024-08-29","cited_by_count":6,"area":null},{"id":"2605.09258","title":"Monocular Biomechanical Tracking of Fingers with Inverse Kinematics to Foundation Models","created":"2026-05-10","cited_by_count":5,"area":null},{"id":"2512.09646","title":"VHOI: Controllable Video Generation of Human-Object Interactions from Sparse Trajectories via Motion Densification","created":"2025-12-10","cited_by_count":4,"area":null},{"id":"2602.04672","title":"AGILE: Hand-Object Interaction Reconstruction from Video via Agentic Generation","created":"2026-02-04","cited_by_count":4,"area":"agents"},{"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":"2607.17097","title":"HarmoHOI: Harmonizing Appearance and 3D Motion for Multi-view Hand-Object Interaction Synthesis","created":"2026-07-19","cited_by_count":4,"area":null},{"id":"2404.01402","title":"ContactHandover: Contact-Guided Robot-to-Human Object Handover","created":"2024-04-01","cited_by_count":3,"area":null},{"id":"2405.05858","title":"Free-Moving Object Reconstruction and Pose Estimation with Virtual Camera","created":"2024-05-09","cited_by_count":3,"area":null},{"id":"2409.07337","title":"Benchmarking 2D Egocentric Hand Pose Datasets","created":"2024-09-11","cited_by_count":3,"area":null},{"id":"2502.19769","title":"QORT-Former: Query-optimized Real-time Transformer for Understanding Two Hands Manipulating Objects","created":"2025-02-27","cited_by_count":3,"area":null},{"id":"2503.22869","title":"SIGHT: Synthesizing Image-Text Conditioned and Geometry-Guided 3D Hand-Object Trajectories","created":"2025-03-28","cited_by_count":3,"area":null},{"id":"2508.16465","title":"HOSt3R: Keypoint-free Hand-Object 3D Reconstruction from RGB images","created":"2025-08-22","cited_by_count":3,"area":null},{"id":"2511.05403","title":"PALM: A Dataset and Baseline for Learning Multi-subject Hand Prior","created":"2025-11-07","cited_by_count":3,"area":null},{"id":"2512.07394","title":"Reconstructing Objects along Hand Interaction Timelines in Egocentric Video","created":"2025-12-08","cited_by_count":3,"area":null},{"id":"2603.18912","title":"GHOST: Fast Category-agnostic Hand-Object Interaction Reconstruction from RGB Videos using Gaussian Splatting","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2604.12929","title":"Grasp in Gaussians: Fast Monocular Reconstruction of Dynamic Hand-Object Interactions","created":"2026-04-14","cited_by_count":3,"area":null},{"id":"2605.20992","title":"Open-CHOIR: Open-World Contact-Aware 4D Hand-Object Interaction Reconstruction","created":"2026-05-20","cited_by_count":3,"area":null},{"id":"2502.20805","title":"FunHOI: Annotation-Free 3D Hand-Object Interaction Generation via Functional Text Guidance","created":"2025-02-28","cited_by_count":2,"area":null},{"id":"2603.15612","title":"HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human-Scene Interactions","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2603.28766","title":"HandX: Scaling Bimanual Motion and Interaction Generation","created":"2026-03-30","cited_by_count":2,"area":null},{"id":"2604.20444","title":"VTouch++: A Multimodal Dataset with Vision-Based Tactile Enhancement for Bimanual Manipulation","created":"2026-04-22","cited_by_count":2,"area":null},{"id":"2606.30598","title":"Towards in-the-wild Egocentric 3D Hand-Object Pose Estimation","created":"2026-06-29","cited_by_count":2,"area":null},{"id":"2409.19215","title":"1st Place Solution to the 8th HANDS Workshop Challenge -- ARCTIC Track: 3DGS-based Bimanual Category-agnostic Interaction Reconstruction","created":"2024-09-28","cited_by_count":1,"area":null},{"id":"2501.03525","title":"TexHOI: Reconstructing Textures of 3D Unknown Objects in Monocular Hand-Object Interaction Scenes","created":"2025-01-07","cited_by_count":1,"area":null},{"id":"2508.00852","title":"Visuo-Acoustic Hand Pose and Contact Estimation","created":"2025-07-13","cited_by_count":1,"area":null},{"id":"2511.14540","title":"Interaction-Aware 4D Gaussian Splatting for Dynamic Hand-Object Interaction Reconstruction","created":"2025-11-18","cited_by_count":1,"area":null},{"id":"2604.07986","title":"DP-DeGauss: Dynamic Probabilistic Gaussian Decomposition for Egocentric 4D Scene Reconstruction","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2605.15753","title":"Hierarchical and Holistic Open-Vocabulary Functional 3D Scene Graphs for Indoor Spaces","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2607.28394","title":"Hand-Object Interaction in the Age of Large Foundation Models:Reconstruction, Generation, and Embodied Transfer","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2609.16319","title":"ConGraspXL: Controllable Constraint-Conditioned Dexterous Grasping Motion Synthesis","created":"2026-09-14","cited_by_count":1,"area":null},{"id":"2503.09640","title":"Physically Plausible Human-Object Rendering from Sparse Views via 3D Gaussian Splatting","created":"2025-03-12","cited_by_count":0,"area":null},{"id":"2505.00606","title":"Dietary Intake Estimation via Continuous 3D Reconstruction of Food","created":"2025-05-01","cited_by_count":0,"area":null},{"id":"2506.00953","title":"TIGeR: Text-Instructed Generation and Refinement for Template-Free Hand-Object Interaction","created":"2025-06-01","cited_by_count":0,"area":null},{"id":"2506.09068","title":"BG-HOP: A Bimanual Generative Hand-Object Prior","created":"2025-06-08","cited_by_count":0,"area":null},{"id":"2603.12126","title":"Hoi3DGen: Generating High-Quality Human-Object-Interactions in 3D","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2604.04016","title":"HOIGS: Human-Object Interaction Gaussian Splatting","created":"2026-04-05","cited_by_count":0,"area":null},{"id":"2605.17014","title":"RHINO: Reconstructing Human Interactions with Novel Objects from Monocular Videos","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2606.15908","title":"High-Fidelity 4D Hand-Object Capture via Multi-View Spatiotemporal Tracking and Physics-Aware Gaussians","created":"2026-06-14","cited_by_count":0,"area":null},{"id":"2606.15966","title":"VEPHand: View-Efficient Photometric Hand Performance Capture at Scale","created":"2026-06-14","cited_by_count":0,"area":null},{"id":"2606.16436","title":"V2P-Manip: Learning Dexterous Manipulation from Monocular Human Videos","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2606.19156","title":"Hand-4DGS: Feed-Forward 3D Gaussian Splatting for 4D Hand Reconstruction from Egocentric Videos","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2606.28820","title":"CoGS: Compositional Dynamic Human-Object Scenes Gaussian Splatting from Monocular Video","created":"2026-06-27","cited_by_count":0,"area":null},{"id":"2606.29924","title":"DCGrasp: Distance-aware Controllable Grasp Generation","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.09329","title":"Dynamic Inverse Rendering for Enhanced Material-Lighting Decomposition","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2608.07045","title":"C2Dex: Contact-Consistent Reconstruction and Retargeting for Dexterous Manipulation from Monocular Video","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2609.19119","title":"Track, Articulate, Act: Generating Articulation from Casual Human Videos","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.36454","title":"DynamicHOI: Coupled Dynamics for Physics-aware HOI Reconstruction","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39116","title":"GRC-Pose: Generation-Reconstruction Correspondence for Prior-Free 6D Object Pose Tracking","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.15769","title":"Hand2Robot: Object-Centric 4D Hand Reconstruction from Human Demonstrations for Robotics","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.19089","title":"DexMimic: A Generalist Dexterous Hand-Object Tracking Policy via Value-Guided Reset Allocation","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}