{"list":"other","total":68,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"1703.06907","title":"Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World","created":"2017-03-20","cited_by_count":1498},{"id":"1911.11763","title":"SuperGlue: Learning Feature Matching with Graph Neural Networks","created":"2019-11-26","cited_by_count":1443},{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"2110.04544","title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","created":"2021-10-09","cited_by_count":1026},{"id":"2104.00680","title":"LoFTR: Detector-Free Local Feature Matching with Transformers","created":"2021-04-01","cited_by_count":984},{"id":"1912.01734","title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks","created":"2019-12-03","cited_by_count":783},{"id":"2108.03298","title":"What Matters in Learning from Offline Human Demonstrations for Robot Manipulation","created":"2021-08-06","cited_by_count":725},{"id":"2203.12601","title":"R3M: A Universal Visual Representation for Robot Manipulation","created":"2022-03-23","cited_by_count":694},{"id":"1909.12271","title":"RLBench: The Robot Learning Benchmark & Learning Environment","created":"2019-09-26","cited_by_count":689},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622},{"id":"1808.10654","title":"Gibson Env: Real-World Perception for Embodied Agents","created":"2018-08-31","cited_by_count":481},{"id":"2010.14406","title":"Transporter Networks: Rearranging the Visual World for Robotic Manipulation","created":"2020-10-27","cited_by_count":344},{"id":"1711.11543","title":"Embodied Question Answering","created":"2017-11-30","cited_by_count":336},{"id":"2203.06173","title":"Masked Visual Pre-training for Motor Control","created":"2022-03-11","cited_by_count":248},{"id":"2112.05124","title":"Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation","created":"2021-12-09","cited_by_count":209},{"id":"2004.06799","title":"RoboTHOR: An Open Simulation-to-Real Embodied AI Platform","created":"2020-04-14","cited_by_count":193},{"id":"1812.07252","title":"Sim-to-Real via Sim-to-Sim: Data-efficient Robotic Grasping via Randomized-to-Canonical Adaptation Networks","created":"2018-12-18","cited_by_count":174},{"id":"1910.07207","title":"Soft Actor-Critic for Discrete Action Settings","created":"2019-10-16","cited_by_count":174},{"id":"2011.01975","title":"Rearrangement: A Challenge for Embodied AI","created":"2020-11-03","cited_by_count":155},{"id":"1710.01330","title":"Robotic Pick-and-Place of Novel Objects in Clutter with Multi-Affordance Grasping and Cross-Domain Image Matching","created":"2017-10-03","cited_by_count":125},{"id":"2104.11213","title":"ManipulaTHOR: A Framework for Visual Object Manipulation","created":"2021-04-22","cited_by_count":102},{"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":"1604.03670","title":"Interactive Perception: Leveraging Action in Perception and Perception in Action","created":"2016-04-13","cited_by_count":78},{"id":"1707.02267","title":"Transferring End-to-End Visuomotor Control from Simulation to Real World for a Multi-Stage Task","created":"2017-07-07","cited_by_count":66},{"id":"1911.04577","title":"Online Replanning in Belief Space for Partially Observable Task and Motion Problems","created":"2019-11-11","cited_by_count":61},{"id":"2110.10189","title":"StructFormer: Learning Spatial Structure for Language-Guided Semantic Rearrangement of Novel Objects","created":"2021-10-19","cited_by_count":59},{"id":"2211.09786","title":"SE(3)-Equivariant Relational Rearrangement with Neural Descriptor Fields","created":"2022-11-17","cited_by_count":51},{"id":"2211.04604","title":"StructDiffusion: Language-Guided Creation of Physically-Valid Structures using Unseen Objects","created":"2022-11-08","cited_by_count":50},{"id":"2201.07779","title":"Look Closer: Bridging Egocentric and Third-Person Views with Transformers for Robotic Manipulation","created":"2022-01-19","cited_by_count":49},{"id":"2006.05398","title":"Deep Visual Reasoning: Learning to Predict Action Sequences for Task and Motion Planning from an Initial Scene Image","created":"2020-06-09","cited_by_count":48},{"id":"2202.00732","title":"IFOR: Iterative Flow Minimization for Robotic Object Rearrangement","created":"2022-02-01","cited_by_count":42},{"id":"2011.01968","title":"Learning 3D Dynamic Scene Representations for Robot Manipulation","created":"2020-11-03","cited_by_count":39},{"id":"2106.01352","title":"NeRP: Neural Rearrangement Planning for Unknown Objects","created":"2021-06-02","cited_by_count":34},{"id":"2302.12610","title":"A Joint Modeling of Vision-Language-Action for Target-oriented Grasping in Clutter","created":"2023-02-24","cited_by_count":34},{"id":"1903.01588","title":"Mechanical Search: Multi-Step Retrieval of a Target Object Occluded by Clutter","created":"2019-03-04","cited_by_count":30},{"id":"1811.08067","title":"Reinforcement Learning of Active Vision for Manipulating Objects under Occlusions","created":"2018-11-20","cited_by_count":25},{"id":"1904.10348","title":"Monte-Carlo Tree Search for Efficient Visually Guided Rearrangement Planning","created":"2019-04-23","cited_by_count":24},{"id":"2104.11446","title":"OCRTOC: A Cloud-Based Competition and Benchmark for Robotic Grasping and Manipulation","created":"2021-04-23","cited_by_count":24},{"id":"2108.12062","title":"Predicting Stable Configurations for Semantic Placement of Novel Objects","created":"2021-08-26","cited_by_count":24},{"id":"2111.07975","title":"Semantically Grounded Object Matching for Robust Robotic Scene Rearrangement","created":"2021-11-15","cited_by_count":21},{"id":"2302.03573","title":"Local Neural Descriptor Fields: Locally Conditioned Object Representations for Manipulation","created":"2023-02-07","cited_by_count":21},{"id":"1911.07482","title":"Object Finding in Cluttered Scenes Using Interactive Perception","created":"2019-11-18","cited_by_count":18},{"id":"1809.08564","title":"Multi-View Picking: Next-best-view Reaching for Improved Grasping in Clutter","created":"2018-09-23","cited_by_count":15},{"id":"2106.02445","title":"How to select and use tools? : Active Perception of Target Objects Using Multimodal Deep Learning","created":"2021-06-04","cited_by_count":15},{"id":"1912.07024","title":"Multi-Object Rearrangement with Monte Carlo Tree Search:A Case Study on Planar Nonprehensile Sorting","created":"2019-12-15","cited_by_count":13},{"id":"2011.03334","title":"Occlusion-Aware Search for Object Retrieval in Clutter","created":"2020-11-06","cited_by_count":12},{"id":"2103.05405","title":"Efficient learning of goal-oriented push-grasping synergy in clutter","created":"2021-03-09","cited_by_count":12},{"id":"1903.03953","title":"Domain Randomization for Active Pose Estimation","created":"2019-03-10","cited_by_count":11},{"id":"2109.08817","title":"Learning to Regrasp by Learning to Place","created":"2021-09-18","cited_by_count":11},{"id":"1711.07369","title":"Complexity Results and Fast Methods for Optimal Tabletop Rearrangement with Overhand Grasps","created":"2017-11-17","cited_by_count":10},{"id":"2202.11092","title":"ReorientBot: Learning Object Reorientation for Specific-Posed Placement","created":"2022-02-22","cited_by_count":10},{"id":"2101.12241","title":"Uniform Object Rearrangement: From Complete Monotone Primitives to Efficient Non-Monotone Informed Search","created":"2021-01-28","cited_by_count":9},{"id":"2110.12325","title":"Fast High-Quality Tabletop Rearrangement in Bounded Workspace","created":"2021-10-24","cited_by_count":9},{"id":"2211.11530","title":"Open-Set Object Detection Using Classification-free Object Proposal and Instance-level Contrastive Learning","created":"2022-11-21","cited_by_count":7},{"id":"2105.06357","title":"On Minimizing the Number of Running Buffers for Tabletop Rearrangement","created":"2021-05-13","cited_by_count":6},{"id":"2110.02814","title":"Efficient and High-quality Prehensile Rearrangement in Cluttered and Confined Spaces","created":"2021-10-06","cited_by_count":6},{"id":"1907.03956","title":"Planning for target retrieval using a robotic manipulator in cluttered and occluded environments","created":"2019-07-09","cited_by_count":4},{"id":"2304.02893","title":"Object-centric Inference for Language Conditioned Placement: A Foundation Model based Approach","created":"2023-04-06","cited_by_count":4},{"id":"2109.10583","title":"Efficient Object Manipulation to an Arbitrary Goal Pose: Learning-based Anytime Prioritized Planning","created":"2021-09-22","cited_by_count":3},{"id":"2205.11719","title":"Safe, Occlusion-Aware Manipulation for Online Object Reconstruction in Confined Spaces","created":"2022-05-24","cited_by_count":3},{"id":"2207.02347","title":"Mechanical Search on Shelves with Efficient Stacking and Destacking of Objects","created":"2022-07-05","cited_by_count":3},{"id":"2208.11079","title":"Robot Active Neural Sensing and Planning in Unknown Cluttered Environments","created":"2022-08-23","cited_by_count":1}],"next_cursor":null}