{"list":"other","total":55,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1706.02413","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","created":"2017-06-07","cited_by_count":4401},{"id":"1812.03828","title":"Occupancy Networks: Learning 3D Reconstruction in Function Space","created":"2018-12-10","cited_by_count":2041},{"id":"2304.13705","title":"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware","created":"2023-04-23","cited_by_count":1568},{"id":"2405.12213","title":"Octo: An Open-Source Generalist Robot Policy","created":"2024-05-20","cited_by_count":1484},{"id":"2205.09991","title":"Planning with Diffusion for Flexible Behavior Synthesis","created":"2022-05-20","cited_by_count":1061},{"id":"2310.08864","title":"Open X-Embodiment: Robotic Learning Datasets and RT-X Models","created":"2023-10-13","cited_by_count":862},{"id":"2003.08515","title":"SAPIEN: A SimulAted Part-based Interactive ENvironment","created":"2020-03-19","cited_by_count":595},{"id":"2303.09553","title":"LERF: Language Embedded Radiance Fields","created":"2023-03-16","cited_by_count":543},{"id":"2202.02005","title":"BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning","created":"2022-02-04","cited_by_count":523},{"id":"2210.03094","title":"VIMA: General Robot Manipulation with Multimodal Prompts","created":"2022-10-06","cited_by_count":407},{"id":"2309.16650","title":"ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning","created":"2023-09-28","cited_by_count":365},{"id":"2312.03203","title":"Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields","created":"2023-12-06","cited_by_count":364},{"id":"2206.11251","title":"Behavior Transformers: Cloning $k$ modes with one stone","created":"2022-06-22","cited_by_count":304},{"id":"1905.10520","title":"6-DOF GraspNet: Variational Grasp Generation for Object Manipulation","created":"2019-05-25","cited_by_count":242},{"id":"2306.14896","title":"RVT: Robotic View Transformer for 3D Object Manipulation","created":"2023-06-26","cited_by_count":225},{"id":"1810.01566","title":"Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids","created":"2018-10-03","cited_by_count":220},{"id":"2112.05124","title":"Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation","created":"2021-12-09","cited_by_count":209},{"id":"1806.08756","title":"Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulation","created":"2018-06-22","cited_by_count":142},{"id":"2306.17817","title":"Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulation","created":"2023-06-30","cited_by_count":138},{"id":"2308.07931","title":"Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation","created":"2023-07-27","cited_by_count":130},{"id":"2106.12534","title":"Coarse-to-Fine Q-attention: Efficient Learning for Visual Robotic Manipulation via Discretisation","created":"2021-06-23","cited_by_count":122},{"id":"2211.11744","title":"Visual Dexterity: In-Hand Reorientation of Novel and Complex Object Shapes","created":"2022-11-21","cited_by_count":101},{"id":"2308.16891","title":"GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fields","created":"2023-08-31","cited_by_count":99},{"id":"1906.07889","title":"Unsupervised Learning of Object Structure and Dynamics from Videos","created":"2019-06-19","cited_by_count":92},{"id":"2309.07970","title":"Language Embedded Radiance Fields for Zero-Shot Task-Oriented Grasping","created":"2023-09-14","cited_by_count":91},{"id":"2211.09423","title":"DexPoint: Generalizable Point Cloud Reinforcement Learning for Sim-to-Real Dexterous Manipulation","created":"2022-11-17","cited_by_count":84},{"id":"2201.12716","title":"You Only Demonstrate Once: Category-Level Manipulation from Single Visual Demonstration","created":"2022-01-30","cited_by_count":81},{"id":"2106.14440","title":"VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D ARTiculated Objects","created":"2021-06-28","cited_by_count":80},{"id":"2306.14447","title":"RoboCook: Long-Horizon Elasto-Plastic Object Manipulation with Diverse Tools","created":"2023-06-26","cited_by_count":76},{"id":"2003.05436","title":"Learning Predictive Representations for Deformable Objects Using Contrastive Estimation","created":"2020-03-11","cited_by_count":72},{"id":"2205.02909","title":"RoboCraft: Learning to See, Simulate, and Shape Elasto-Plastic Objects with Graph Networks","created":"2022-05-05","cited_by_count":72},{"id":"2009.05085","title":"Keypoints into the Future: Self-Supervised Correspondence in Model-Based Reinforcement Learning","created":"2020-09-10","cited_by_count":70},{"id":"2310.14386","title":"Learning Generalizable Manipulation Policies with Object-Centric 3D Representations","created":"2023-10-22","cited_by_count":61},{"id":"2112.00246","title":"AdaAfford: Learning to Adapt Manipulation Affordance for 3D Articulated Objects via Few-shot Interactions","created":"2021-12-01","cited_by_count":57},{"id":"2312.01853","title":"Robot Synesthesia: In-Hand Manipulation with Visuotactile Sensing","created":"2023-12-04","cited_by_count":56},{"id":"2306.10007","title":"Robot Learning with Sensorimotor Pre-training","created":"2023-06-16","cited_by_count":51},{"id":"2109.03891","title":"SORNet: Spatial Object-Centric Representations for Sequential Manipulation","created":"2021-09-08","cited_by_count":48},{"id":"2303.12786","title":"FeatureNeRF: Learning Generalizable NeRFs by Distilling Foundation Models","created":"2023-03-22","cited_by_count":47},{"id":"2402.13181","title":"DINOBot: Robot Manipulation via Retrieval and Alignment with Vision Foundation Models","created":"2024-02-20","cited_by_count":44},{"id":"2011.01968","title":"Learning 3D Dynamic Scene Representations for Robot Manipulation","created":"2020-11-03","cited_by_count":39},{"id":"2403.07563","title":"Learning Generalizable Feature Fields for Mobile Manipulation","created":"2024-03-12","cited_by_count":31},{"id":"1902.01537","title":"Functional Object-Oriented Network for Manipulation Learning","created":"2019-02-05","cited_by_count":27},{"id":"2212.06088","title":"MIRA: Mental Imagery for Robotic Affordances","created":"2022-12-12","cited_by_count":26},{"id":"2303.11057","title":"Learning Foresightful Dense Visual Affordance for Deformable Object Manipulation","created":"2023-03-20","cited_by_count":25},{"id":"2103.15231","title":"ReAgent: Point Cloud Registration using Imitation and Reinforcement Learning","created":"2021-03-28","cited_by_count":23},{"id":"2306.16700","title":"Dynamic-Resolution Model Learning for Object Pile Manipulation","created":"2023-06-29","cited_by_count":22},{"id":"2207.01971","title":"DualAfford: Learning Collaborative Visual Affordance for Dual-gripper Manipulation","created":"2022-07-05","cited_by_count":18},{"id":"2312.12345","title":"On the Effectiveness of Retrieval, Alignment, and Replay in Manipulation","created":"2023-12-19","cited_by_count":15},{"id":"2309.16873","title":"Predicting Object Interactions with Behavior Primitives: An Application in Stowing Tasks","created":"2023-09-28","cited_by_count":13},{"id":"2310.13914","title":"Cold Diffusion on the Replay Buffer: Learning to Plan from Known Good States","created":"2023-10-21","cited_by_count":10},{"id":"2010.08202","title":"Manipulation-Oriented Object Perception in Clutter through Affordance Coordinate Frames","created":"2020-10-16","cited_by_count":4},{"id":"2310.09943","title":"Evaluating Robustness of Visual Representations for Object Assembly Task Requiring Spatio-Geometrical Reasoning","created":"2023-10-15","cited_by_count":3}],"next_cursor":null}