{"list":"other","total":65,"rows":[{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"2302.04264","title":"Nerfstudio: A Modular Framework for Neural Radiance Field Development","created":"2023-02-08","cited_by_count":600},{"id":"1805.01954","title":"Behavioral Cloning from Observation","created":"2018-05-04","cited_by_count":492},{"id":"2312.08344","title":"FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects","created":"2023-12-13","cited_by_count":429},{"id":"2312.16084","title":"LangSplat: 3D Language Gaussian Splatting","created":"2023-12-26","cited_by_count":415},{"id":"2205.15585","title":"Decomposing NeRF for Editing via Feature Field Distillation","created":"2022-05-31","cited_by_count":371},{"id":"2109.07547","title":"RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching","created":"2021-09-15","cited_by_count":353},{"id":"2312.05251","title":"Reconstructing Hands in 3D with Transformers","created":"2023-12-08","cited_by_count":306},{"id":"2409.06765","title":"gsplat: An Open-Source Library for Gaussian Splatting","created":"2024-09-10","cited_by_count":285},{"id":"1703.09312","title":"Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics","created":"2017-03-27","cited_by_count":264},{"id":"2303.16196","title":"SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesis","created":"2023-03-28","cited_by_count":247},{"id":"1809.10790","title":"Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objects","created":"2018-09-27","cited_by_count":241},{"id":"1701.03077","title":"A General and Adaptive Robust Loss Function","created":"2017-01-11","cited_by_count":236},{"id":"1703.07326","title":"One-Shot Imitation Learning","created":"2017-03-21","cited_by_count":233},{"id":"1709.04905","title":"One-Shot Visual Imitation Learning via Meta-Learning","created":"2017-09-14","cited_by_count":228},{"id":"2303.12153","title":"Text2Motion: From Natural Language Instructions to Feasible Plans","created":"2023-03-21","cited_by_count":224},{"id":"2401.00025","title":"Any-point Trajectory Modeling for Policy Learning","created":"2023-12-28","cited_by_count":215},{"id":"2207.09450","title":"Human-to-Robot Imitation in the Wild","created":"2022-07-19","cited_by_count":161},{"id":"1912.11913","title":"Category-Level Articulated Object Pose Estimation","created":"2019-12-26","cited_by_count":159},{"id":"2110.00168","title":"Vision-Only Robot Navigation in a Neural Radiance World","created":"2021-10-01","cited_by_count":155},{"id":"1802.01557","title":"One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning","created":"2018-02-05","cited_by_count":148},{"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":"2211.05272","title":"GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Parts","created":"2022-11-10","cited_by_count":139},{"id":"2210.11339","title":"VIOLA: Imitation Learning for Vision-Based Manipulation with Object Proposal Priors","created":"2022-10-20","cited_by_count":136},{"id":"2308.07931","title":"Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation","created":"2023-07-27","cited_by_count":130},{"id":"1903.03911","title":"Shape2Motion: Joint Analysis of Motion Parts and Attributes from 3D Shapes","created":"2019-03-10","cited_by_count":119},{"id":"2110.14217","title":"Dex-NeRF: Using a Neural Radiance Field to Grasp Transparent Objects","created":"2021-10-27","cited_by_count":119},{"id":"2308.07391","title":"PARIS: Part-level Reconstruction and Motion Analysis for Articulated Objects","created":"2023-08-14","cited_by_count":118},{"id":"2309.07970","title":"Language Embedded Radiance Fields for Zero-Shot Task-Oriented Grasping","created":"2023-09-14","cited_by_count":91},{"id":"2012.07277","title":"Hierarchical Planning for Long-Horizon Manipulation with Geometric and Symbolic Scene Graphs","created":"2020-12-14","cited_by_count":83},{"id":"2403.09637","title":"GaussianGrasper: 3D Language Gaussian Splatting for Open-vocabulary Robotic Grasping","created":"2024-03-14","cited_by_count":78},{"id":"1806.01830","title":"Relational Deep Reinforcement Learning","created":"2018-06-05","cited_by_count":73},{"id":"2008.10518","title":"ScrewNet: Category-Independent Articulation Model Estimation From Depth Images Using Screw Theory","created":"2020-08-24","cited_by_count":70},{"id":"2406.08474","title":"Real2Code: Reconstruct Articulated Objects via Code Generation","created":"2024-06-12","cited_by_count":69},{"id":"2202.11855","title":"Learning Multi-Object Dynamics with Compositional Neural Radiance Fields","created":"2022-02-24","cited_by_count":63},{"id":"2310.14386","title":"Learning Generalizable Manipulation Policies with Object-Centric 3D Representations","created":"2023-10-22","cited_by_count":61},{"id":"1912.11032","title":"Towards Practical Multi-Object Manipulation using Relational Reinforcement Learning","created":"2019-12-23","cited_by_count":55},{"id":"1812.10972","title":"Reasoning About Physical Interactions with Object-Oriented Prediction and Planning","created":"2018-12-28","cited_by_count":51},{"id":"2205.08525","title":"Self-supervised Neural Articulated Shape and Appearance Models","created":"2022-05-17","cited_by_count":51},{"id":"1708.04225","title":"Deep Object-Centric Representations for Generalizable Robot Learning","created":"2017-08-14","cited_by_count":50},{"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":"2109.03891","title":"SORNet: Spatial Object-Centric Representations for Sequential Manipulation","created":"2021-09-08","cited_by_count":48},{"id":"1907.05518","title":"Graph-Structured Visual Imitation","created":"2019-07-11","cited_by_count":43},{"id":"2204.02863","title":"Demonstrate Once, Imitate Immediately (DOME): Learning Visual Servoing for One-Shot Imitation Learning","created":"2022-04-06","cited_by_count":38},{"id":"1911.04679","title":"Object-Centric Task and Motion Planning in Dynamic Environments","created":"2019-11-12","cited_by_count":35},{"id":"2309.16118","title":"D$^3$Fields: Dynamic 3D Descriptor Fields for Zero-Shot Generalizable Rearrangement","created":"2023-09-28","cited_by_count":35},{"id":"1911.01103","title":"Learning One-Shot Imitation from Humans without Humans","created":"2019-11-04","cited_by_count":33},{"id":"2209.07147","title":"One-Shot Transfer of Affordance Regions? AffCorrs!","created":"2022-09-15","cited_by_count":31},{"id":"2010.13021","title":"Multimodal Sensor Fusion with Differentiable Filters","created":"2020-10-25","cited_by_count":29},{"id":"2302.14268","title":"Self-Supervised Category-Level Articulated Object Pose Estimation with Part-Level SE(3) Equivariance","created":"2023-02-28","cited_by_count":26},{"id":"2005.10872","title":"Guided Uncertainty-Aware Policy Optimization: Combining Learning and Model-Based Strategies for Sample-Efficient Policy Learning","created":"2020-05-21","cited_by_count":25},{"id":"2108.12062","title":"Predicting Stable Configurations for Semantic Placement of Novel Objects","created":"2021-08-26","cited_by_count":24},{"id":"2205.03721","title":"Category-Independent Articulated Object Tracking with Factor Graphs","created":"2022-05-07","cited_by_count":24},{"id":"2111.07447","title":"Learning Multi-Stage Tasks with One Demonstration via Self-Replay","created":"2021-11-14","cited_by_count":21},{"id":"2305.16314","title":"Banana: Banach Fixed-Point Network for Pointcloud Segmentation with Inter-Part Equivariance","created":"2023-05-25","cited_by_count":19},{"id":"2010.11735","title":"Self-Supervised Learning of Part Mobility from Point Cloud Sequence","created":"2020-10-20","cited_by_count":18},{"id":"2103.16352","title":"Learning monocular 3D reconstruction of articulated categories from motion","created":"2021-03-30","cited_by_count":18},{"id":"2105.08257","title":"Differentiable Factor Graph Optimization for Learning Smoothers","created":"2021-05-18","cited_by_count":17},{"id":"2405.05876","title":"Composable Part-Based Manipulation","created":"2024-05-09","cited_by_count":17},{"id":"1812.03647","title":"Factored Pose Estimation of Articulated Objects using Efficient Nonparametric Belief Propagation","created":"2018-12-10","cited_by_count":16},{"id":"2109.14078","title":"Learning Periodic Tasks from Human Demonstrations","created":"2021-09-28","cited_by_count":10}],"next_cursor":null}