{"total":153,"rows":[{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622,"area":null},{"id":"2409.01652","title":"ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation","created":"2024-09-03","cited_by_count":315,"area":"lr"},{"id":"2211.03726","title":"TAP-Vid: A Benchmark for Tracking Any Point in a Video","created":"2022-11-07","cited_by_count":263,"area":null},{"id":"2406.10721","title":"RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Robotics","created":"2024-06-15","cited_by_count":251,"area":"mllm"},{"id":"2103.14127","title":"Contact-GraspNet: Efficient 6-DoF Grasp Generation in Cluttered Scenes","created":"2021-03-25","cited_by_count":218,"area":null},{"id":"2112.05124","title":"Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation","created":"2021-12-09","cited_by_count":209,"area":null},{"id":"2212.06870","title":"MegaPose: 6D Pose Estimation of Novel Objects via Render & Compare","created":"2022-12-13","cited_by_count":201,"area":null},{"id":"2310.08576","title":"Learning to Act from Actionless Videos through Dense Correspondences","created":"2023-10-12","cited_by_count":164,"area":null},{"id":"2210.11339","title":"VIOLA: Imitation Learning for Vision-Based Manipulation with Object Proposal Priors","created":"2022-10-20","cited_by_count":136,"area":"offlinerl"},{"id":"2403.03174","title":"MOKA: Open-World Robotic Manipulation through Mark-Based Visual Prompting","created":"2024-03-05","cited_by_count":129,"area":null},{"id":"2311.14155","title":"GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence","created":"2023-11-23","cited_by_count":114,"area":null},{"id":"2107.04004","title":"3D Neural Scene Representations for Visuomotor Control","created":"2021-07-08","cited_by_count":111,"area":null},{"id":"2308.15975","title":"RoboTAP: Tracking Arbitrary Points for Few-Shot Visual Imitation","created":"2023-08-30","cited_by_count":90,"area":null},{"id":"2203.01913","title":"NeRF-Supervision: Learning Dense Object Descriptors from Neural Radiance Fields","created":"2022-03-03","cited_by_count":86,"area":null},{"id":"2401.11439","title":"General Flow as Foundation Affordance for Scalable Robot Learning","created":"2024-01-21","cited_by_count":85,"area":null},{"id":"2201.12716","title":"You Only Demonstrate Once: Category-Level Manipulation from Single Visual Demonstration","created":"2022-01-30","cited_by_count":81,"area":null},{"id":"2206.15477","title":"Denoised MDPs: Learning World Models Better Than the World Itself","created":"2022-06-30","cited_by_count":68,"area":"wm"},{"id":"2204.03635","title":"Zero-Shot Category-Level Object Pose Estimation","created":"2022-04-07","cited_by_count":57,"area":null},{"id":"2101.00443","title":"Semantics for Robotic Mapping, Perception and Interaction: A Survey","created":"2021-01-02","cited_by_count":56,"area":null},{"id":"2409.01083","title":"Affordance-based Robot Manipulation with Flow Matching","created":"2024-09-02","cited_by_count":54,"area":"diffusion"},{"id":"2106.14193","title":"SAR-Net: Shape Alignment and Recovery Network for Category-level 6D Object Pose and Size Estimation","created":"2021-06-27","cited_by_count":53,"area":null},{"id":"2212.10428","title":"HouseCat6D -- A Large-Scale Multi-Modal Category Level 6D Object Perception Dataset with Household Objects in Realistic Scenarios","created":"2022-12-20","cited_by_count":53,"area":null},{"id":"2010.09034","title":"Model-Based Inverse Reinforcement Learning from Visual Demonstrations","created":"2020-10-18","cited_by_count":52,"area":"offlinerl"},{"id":"2410.03645","title":"GenSim2: Scaling Robot Data Generation with Multi-modal and Reasoning LLMs","created":"2024-10-04","cited_by_count":52,"area":"wm"},{"id":"2104.11224","title":"KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Control","created":"2021-04-22","cited_by_count":51,"area":null},{"id":"2211.09786","title":"SE(3)-Equivariant Relational Rearrangement with Neural Descriptor Fields","created":"2022-11-17","cited_by_count":51,"area":null},{"id":"2109.09163","title":"CaTGrasp: Learning Category-Level Task-Relevant Grasping in Clutter from Simulation","created":"2021-09-19","cited_by_count":49,"area":null},{"id":"2211.09325","title":"TAX-Pose: Task-Specific Cross-Pose Estimation for Robot Manipulation","created":"2022-11-17","cited_by_count":47,"area":null},{"id":"2205.08811","title":"PhoCaL: A Multi-Modal Dataset for Category-Level Object Pose Estimation with Photometrically Challenging Objects","created":"2022-05-18","cited_by_count":45,"area":null},{"id":"2402.13181","title":"DINOBot: Robot Manipulation via Retrieval and Alignment with Vision Foundation Models","created":"2024-02-20","cited_by_count":44,"area":"offlinerl"},{"id":"2206.01634","title":"Reinforcement Learning with Neural Radiance Fields","created":"2022-06-03","cited_by_count":43,"area":null},{"id":"2109.06161","title":"Single-Stage Keypoint-Based Category-Level Object Pose Estimation from an RGB Image","created":"2021-09-13","cited_by_count":42,"area":null},{"id":"2403.02709","title":"RT-Sketch: Goal-Conditioned Imitation Learning from Hand-Drawn Sketches","created":"2024-03-05","cited_by_count":41,"area":"offlinerl"},{"id":"2409.02084","title":"GraspSplats: Efficient Manipulation with 3D Feature Splatting","created":"2024-09-03","cited_by_count":41,"area":"mllm"},{"id":"2109.10115","title":"StereOBJ-1M: Large-scale Stereo Image Dataset for 6D Object Pose Estimation","created":"2021-09-21","cited_by_count":40,"area":null},{"id":"2405.07801","title":"Deep Learning-Based Object Pose Estimation: A Comprehensive Survey","created":"2024-05-13","cited_by_count":40,"area":null},{"id":"2306.16605","title":"KITE: Keypoint-Conditioned Policies for Semantic Manipulation","created":"2023-06-29","cited_by_count":39,"area":null},{"id":"2412.03142","title":"AffordDP: Generalizable Diffusion Policy with Transferable Affordance","created":"2024-12-04","cited_by_count":37,"area":"diffusion"},{"id":"2408.04380","title":"Deep Generative Models in Robotics: A Survey on Learning from Multimodal Demonstrations","created":"2024-08-08","cited_by_count":35,"area":"offlinerl"},{"id":"2303.12246","title":"Object Pose Estimation with Statistical Guarantees: Conformal Keypoint Detection and Geometric Uncertainty Propagation","created":"2023-03-22","cited_by_count":33,"area":null},{"id":"2106.07643","title":"Unsupervised Learning of Visual 3D Keypoints for Control","created":"2021-06-14","cited_by_count":30,"area":null},{"id":"2304.14391","title":"Energy-based Models are Zero-Shot Planners for Compositional Scene Rearrangement","created":"2023-04-27","cited_by_count":30,"area":null},{"id":"2307.04751","title":"Shelving, Stacking, Hanging: Relational Pose Diffusion for Multi-modal Rearrangement","created":"2023-07-10","cited_by_count":29,"area":null},{"id":"2209.13864","title":"USEEK: Unsupervised SE(3)-Equivariant 3D Keypoints for Generalizable Manipulation","created":"2022-09-28","cited_by_count":27,"area":null},{"id":"2104.13526","title":"ZePHyR: Zero-shot Pose Hypothesis Rating","created":"2021-04-28","cited_by_count":26,"area":null},{"id":"2103.00375","title":"Generalization Through Hand-Eye Coordination: An Action Space for Learning Spatially-Invariant Visuomotor Control","created":"2021-02-28","cited_by_count":24,"area":"offlinerl"},{"id":"2506.09284","title":"UAD: Unsupervised Affordance Distillation for Generalization in Robotic Manipulation","created":"2025-06-10","cited_by_count":23,"area":null},{"id":"2310.16838","title":"SparseDFF: Sparse-View Feature Distillation for One-Shot Dexterous Manipulation","created":"2023-10-25","cited_by_count":22,"area":"distill"},{"id":"2205.06333","title":"Visuomotor Control in Multi-Object Scenes Using Object-Aware Representations","created":"2022-05-12","cited_by_count":21,"area":null},{"id":"2302.03573","title":"Local Neural Descriptor Fields: Locally Conditioned Object Representations for Manipulation","created":"2023-02-07","cited_by_count":21,"area":null},{"id":"2501.14400","title":"SKIL: Semantic Keypoint Imitation Learning for Generalizable Data-efficient Manipulation","created":"2025-01-24","cited_by_count":21,"area":"offlinerl"},{"id":"2601.07060","title":"PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation","created":"2026-01-11","cited_by_count":21,"area":"vla"},{"id":"2309.05098","title":"3D Implicit Transporter for Temporally Consistent Keypoint Discovery","created":"2023-09-10","cited_by_count":20,"area":null},{"id":"2410.23254","title":"Keypoint Abstraction using Large Models for Object-Relative Imitation Learning","created":"2024-10-30","cited_by_count":20,"area":"offlinerl"},{"id":"2304.14329","title":"Learning to Extrapolate: A Transductive Approach","created":"2023-04-27","cited_by_count":19,"area":null},{"id":"2308.07948","title":"Leveraging Symmetries in Pick and Place","created":"2023-08-15","cited_by_count":19,"area":null},{"id":"2106.16118","title":"SimNet: Enabling Robust Unknown Object Manipulation from Pure Synthetic Data via Stereo","created":"2021-06-30","cited_by_count":18,"area":null},{"id":"2405.13178","title":"One-Shot Imitation Learning with Invariance Matching for Robotic Manipulation","created":"2024-05-21","cited_by_count":18,"area":"offlinerl"},{"id":"2506.14198","title":"AMPLIFY: Actionless Motion Priors for Robot Learning from Videos","created":"2025-06-17","cited_by_count":18,"area":"wm"},{"id":"2203.08472","title":"Fusing Local Similarities for Retrieval-based 3D Orientation Estimation of Unseen Objects","created":"2022-03-16","cited_by_count":17,"area":null},{"id":"2304.01716","title":"Decoupling Dynamic Monocular Videos for Dynamic View Synthesis","created":"2023-04-04","cited_by_count":17,"area":null},{"id":"2405.05876","title":"Composable Part-Based Manipulation","created":"2024-05-09","cited_by_count":17,"area":"diffusion"},{"id":"2306.10474","title":"A Universal Semantic-Geometric Representation for Robotic Manipulation","created":"2023-06-18","cited_by_count":16,"area":null},{"id":"2306.12392","title":"One-shot Imitation Learning via Interaction Warping","created":"2023-06-21","cited_by_count":16,"area":"offlinerl"},{"id":"2104.08383","title":"Optimal Pose and Shape Estimation for Category-level 3D Object Perception","created":"2021-04-16","cited_by_count":15,"area":null},{"id":"2409.14066","title":"KALIE: Fine-Tuning Vision-Language Models for Open-World Manipulation without Robot Data","created":"2024-09-21","cited_by_count":15,"area":"mllm"},{"id":"2202.00368","title":"Filtered-CoPhy: Unsupervised Learning of Counterfactual Physics in Pixel Space","created":"2022-02-01","cited_by_count":14,"area":null},{"id":"2310.12238","title":"Few-Shot In-Context Imitation Learning via Implicit Graph Alignment","created":"2023-10-18","cited_by_count":14,"area":"offlinerl"},{"id":"2312.08240","title":"CenterGrasp: Object-Aware Implicit Representation Learning for Simultaneous Shape Reconstruction and 6-DoF Grasp Estimation","created":"2023-12-13","cited_by_count":13,"area":null},{"id":"2508.13534","title":"MimicFunc: Imitating Tool Manipulation from a Single Human Video via Functional Correspondence","created":"2025-08-19","cited_by_count":13,"area":null},{"id":"2207.09978","title":"NeuralBF: Neural Bilateral Filtering for Top-down Instance Segmentation on Point Clouds","created":"2022-07-20","cited_by_count":12,"area":null},{"id":"2403.19460","title":"RiEMann: Near Real-Time SE(3)-Equivariant Robot Manipulation without Point Cloud Segmentation","created":"2024-03-28","cited_by_count":12,"area":"offlinerl"},{"id":"2112.05068","title":"A Bayesian Treatment of Real-to-Sim for Deformable Object Manipulation","created":"2021-12-09","cited_by_count":11,"area":null},{"id":"2310.01362","title":"Robot Fleet Learning via Policy Merging","created":"2023-10-02","cited_by_count":11,"area":null},{"id":"2202.11092","title":"ReorientBot: Learning Object Reorientation for Specific-Posed Placement","created":"2022-02-22","cited_by_count":10,"area":null},{"id":"2303.05344","title":"Recent Advances of Deep Robotic Affordance Learning: A Reinforcement Learning Perspective","created":"2023-03-09","cited_by_count":10,"area":null},{"id":"2410.12124","title":"Learning from 10 Demos: Generalisable and Sample-Efficient Policy Learning with Oriented Affordance Frames","created":"2024-10-15","cited_by_count":10,"area":"offlinerl"},{"id":"2502.11744","title":"FUNCTO: Function-Centric One-Shot Imitation Learning for Tool Manipulation","created":"2025-02-17","cited_by_count":10,"area":"offlinerl"},{"id":"2103.14283","title":"OmniHang: Learning to Hang Arbitrary Objects using Contact Point Correspondences and Neural Collision Estimation","created":"2021-03-26","cited_by_count":9,"area":null},{"id":"2306.08748","title":"Multi-Object Manipulation via Object-Centric Neural Scattering Functions","created":"2023-06-14","cited_by_count":9,"area":null},{"id":"2405.11928","title":"\"Set It Up!\": Functional Object Arrangement with Compositional Generative Models","created":"2024-05-20","cited_by_count":9,"area":null},{"id":"2508.18268","title":"SafeBimanual: Diffusion-based Trajectory Optimization for Safe Bimanual Manipulation","created":"2025-08-25","cited_by_count":9,"area":null},{"id":"2210.01166","title":"NARF22: Neural Articulated Radiance Fields for Configuration-Aware Rendering","created":"2022-10-03","cited_by_count":8,"area":null},{"id":"2305.12626","title":"You Only Look at One: Category-Level Object Representations for Pose Estimation From a Single Example","created":"2023-05-22","cited_by_count":8,"area":null},{"id":"2309.12312","title":"ForceSight: Text-Guided Mobile Manipulation with Visual-Force Goals","created":"2023-09-21","cited_by_count":8,"area":null},{"id":"2411.09627","title":"One-Shot Manipulation Strategy Learning by Making Contact Analogies","created":"2024-11-14","cited_by_count":8,"area":null},{"id":"2204.05864","title":"Semantic keypoint-based pose estimation from single RGB frames","created":"2022-04-12","cited_by_count":7,"area":null},{"id":"2206.12498","title":"Optimal and Robust Category-level Perception: Object Pose and Shape Estimation from 2D and 3D Semantic Keypoints","created":"2022-06-24","cited_by_count":7,"area":null},{"id":"2304.12405","title":"Synthesizing Stable Reduced-Order Visuomotor Policies for Nonlinear Systems via Sums-of-Squares Optimization","created":"2023-04-24","cited_by_count":7,"area":null},{"id":"2503.22462","title":"SemAlign3D: Semantic Correspondence between RGB-Images through Aligning 3D Object-Class Representations","created":"2025-03-28","cited_by_count":7,"area":null},{"id":"2103.06182","title":"Dynamical Pose Estimation","created":"2021-03-10","cited_by_count":6,"area":null},{"id":"2209.05013","title":"Learning A Locally Unified 3D Point Cloud for View Synthesis","created":"2022-09-12","cited_by_count":6,"area":null},{"id":"2310.00156","title":"Learning Generalizable Tool-use Skills through Trajectory Generation","created":"2023-09-29","cited_by_count":6,"area":null},{"id":"2402.05644","title":"FuncGrasp: Learning Object-Centric Neural Grasp Functions from Single Annotated Example Object","created":"2024-02-08","cited_by_count":6,"area":null},{"id":"2508.03944","title":"Constraint-Preserving Data Generation for Visuomotor Policy Learning","created":"2025-08-05","cited_by_count":6,"area":null},{"id":"2202.13604","title":"Generalizable task representation learning from human demonstration videos: a geometric approach","created":"2022-02-28","cited_by_count":5,"area":null},{"id":"2403.12682","title":"IFFNeRF: Initialisation Free and Fast 6DoF pose estimation from a single image and a NeRF model","created":"2024-03-19","cited_by_count":5,"area":null},{"id":"2410.02237","title":"Key-Grid: Unsupervised 3D Keypoints Detection using Grid Heatmap Features","created":"2024-10-03","cited_by_count":5,"area":null},{"id":"2410.23039","title":"Neural Attention Field: Emerging Point Relevance in 3D Scenes for One-Shot Dexterous Grasping","created":"2024-10-30","cited_by_count":5,"area":null},{"id":"2207.08925","title":"Image to Icosahedral Projection for $\\mathrm{SO}(3)$ Object Reasoning from Single-View Images","created":"2022-07-18","cited_by_count":4,"area":null}],"next_cursor":"100"}