{"list":"other","total":89,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2201.05989","title":"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding","created":"2022-01-16","cited_by_count":3723},{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2112.05131","title":"Plenoxels: Radiance Fields without Neural Networks","created":"2021-12-09","cited_by_count":1613},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"2010.03768","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","created":"2020-10-08","cited_by_count":1205},{"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":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"2201.07207","title":"Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents","created":"2022-01-18","cited_by_count":1035},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"1504.00702","title":"End-to-End Training of Deep Visuomotor Policies","created":"2015-04-02","cited_by_count":875},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"2009.06732","title":"Efficient Transformers: A Survey","created":"2020-09-14","cited_by_count":790},{"id":"1711.00199","title":"PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes","created":"2017-11-01","cited_by_count":775},{"id":"1806.10293","title":"QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation","created":"2018-06-27","cited_by_count":743},{"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":"1904.00962","title":"Large Batch Optimization for Deep Learning: Training BERT in 76 minutes","created":"2019-04-01","cited_by_count":674},{"id":"2106.02039","title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","created":"2021-06-03","cited_by_count":644},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622},{"id":"2112.03227","title":"CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks","created":"2021-12-06","cited_by_count":584},{"id":"2202.02005","title":"BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning","created":"2022-02-04","cited_by_count":523},{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513},{"id":"2109.00137","title":"Implicit Behavioral Cloning","created":"2021-09-01","cited_by_count":452},{"id":"1812.01024","title":"DeepVoxels: Learning Persistent 3D Feature Embeddings","created":"2018-12-03","cited_by_count":405},{"id":"2109.10852","title":"Pix2seq: A Language Modeling Framework for Object Detection","created":"2021-09-22","cited_by_count":349},{"id":"2010.14406","title":"Transporter Networks: Rearranging the Visual World for Robotic Manipulation","created":"2020-10-27","cited_by_count":344},{"id":"2110.01963","title":"Multimodal datasets: misogyny, pornography, and malignant stereotypes","created":"2021-10-05","cited_by_count":327},{"id":"2010.01083","title":"Integrated Task and Motion Planning","created":"2020-10-02","cited_by_count":290},{"id":"1610.00696","title":"Deep Visual Foresight for Planning Robot Motion","created":"2016-10-03","cited_by_count":285},{"id":"2109.02497","title":"Voxel Transformer for 3D Object Detection","created":"2021-09-06","cited_by_count":247},{"id":"1905.10520","title":"6-DOF GraspNet: Variational Grasp Generation for Object Manipulation","created":"2019-05-25","cited_by_count":242},{"id":"2004.10151","title":"Experience Grounds Language","created":"2020-04-21","cited_by_count":242},{"id":"2205.15241","title":"Multi-Game Decision Transformers","created":"2022-05-30","cited_by_count":214},{"id":"2112.05124","title":"Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation","created":"2021-12-09","cited_by_count":209},{"id":"2102.06177","title":"Multi-Task Reinforcement Learning with Context-based Representations","created":"2021-02-11","cited_by_count":174},{"id":"2204.06252","title":"What Matters in Language Conditioned Robotic Imitation Learning over Unstructured Data","created":"2022-04-13","cited_by_count":138},{"id":"1903.11239","title":"TossingBot: Learning to Throw Arbitrary Objects with Residual Physics","created":"2019-03-27","cited_by_count":137},{"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":"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":"2109.01115","title":"Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotation","created":"2021-09-02","cited_by_count":118},{"id":"1912.04344","title":"Grasping in the Wild:Learning 6DoF Closed-Loop Grasping from Low-Cost Demonstrations","created":"2019-12-09","cited_by_count":107},{"id":"2203.10314","title":"Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Clouds","created":"2022-03-19","cited_by_count":102},{"id":"1809.00786","title":"Mapping Instructions to Actions in 3D Environments with Visual Goal Prediction","created":"2018-09-04","cited_by_count":101},{"id":"1909.10159","title":"Self-supervised 6D Object Pose Estimation for Robot Manipulation","created":"2019-09-23","cited_by_count":101},{"id":"2105.06411","title":"Coarse-to-Fine Imitation Learning: Robot Manipulation from a Single Demonstration","created":"2021-05-13","cited_by_count":93},{"id":"2107.05612","title":"A Persistent Spatial Semantic Representation for High-level Natural Language Instruction Execution","created":"2021-07-12","cited_by_count":91},{"id":"2203.11931","title":"MetaMorph: Learning Universal Controllers with Transformers","created":"2022-03-22","cited_by_count":89},{"id":"2103.01197","title":"Coordination Among Neural Modules Through a Shared Global Workspace","created":"2021-03-01","cited_by_count":85},{"id":"2105.14829","title":"Q-attention: Enabling Efficient Learning for Vision-based Robotic Manipulation","created":"2021-05-31","cited_by_count":85},{"id":"2107.03996","title":"Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformers","created":"2021-07-08","cited_by_count":79},{"id":"2011.05970","title":"Transformers for One-Shot Visual Imitation","created":"2020-11-11","cited_by_count":78},{"id":"1910.13439","title":"Learning to Manipulate Deformable Objects without Demonstrations","created":"2019-10-29","cited_by_count":77},{"id":"2202.03091","title":"Auto-Lambda: Disentangling Dynamic Task Relationships","created":"2022-02-07","cited_by_count":73},{"id":"1609.09475","title":"Multi-view Self-supervised Deep Learning for 6D Pose Estimation in the Amazon Picking Challenge","created":"2016-09-29","cited_by_count":70},{"id":"1912.03628","title":"6-DOF Grasping for Target-driven Object Manipulation in Clutter","created":"2019-12-08","cited_by_count":70},{"id":"2109.05668","title":"UMPNet: Universal Manipulation Policy Network for Articulated Objects","created":"2021-09-13","cited_by_count":65},{"id":"1710.06280","title":"Interactively Picking Real-World Objects with Unconstrained Spoken Language Instructions","created":"2017-10-17","cited_by_count":62},{"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":"1806.03831","title":"Interactive Visual Grounding of Referring Expressions for Human-Robot Interaction","created":"2018-06-11","cited_by_count":56},{"id":"2109.03891","title":"SORNet: Spatial Object-Centric Representations for Sequential Manipulation","created":"2021-09-08","cited_by_count":48},{"id":"1906.11176","title":"PyRep: Bringing V-REP to Deep Robot Learning","created":"2019-06-26","cited_by_count":44},{"id":"1907.13236","title":"The Best of Both Modes: Separately Leveraging RGB and Depth for Unseen Object Instance Segmentation","created":"2019-07-30","cited_by_count":39},{"id":"2108.00385","title":"Transformer-based deep imitation learning for dual-arm robot manipulation","created":"2021-08-01","cited_by_count":32},{"id":"2006.13253","title":"Robot Object Retrieval with Contextual Natural Language Queries","created":"2020-06-23","cited_by_count":26},{"id":"2112.01010","title":"Differentiable Spatial Planning using Transformers","created":"2021-12-02","cited_by_count":25},{"id":"2104.00492","title":"A Joint Network for Grasp Detection Conditioned on Natural Language Commands","created":"2021-04-01","cited_by_count":23},{"id":"1903.08309","title":"Prospection: Interpretable Plans From Language By Predicting the Future","created":"2019-03-20","cited_by_count":21},{"id":"2011.06464","title":"3D-OES: Viewpoint-Invariant Object-Factorized Environment Simulators","created":"2020-11-12","cited_by_count":21},{"id":"2104.03851","title":"CoCoNets: Continuous Contrastive 3D Scene Representations","created":"2021-04-08","cited_by_count":19},{"id":"2110.09991","title":"Towards Optimal Correlational Object Search","created":"2021-10-19","cited_by_count":14},{"id":"2204.01571","title":"Coarse-to-Fine Q-attention with Learned Path Ranking","created":"2022-04-04","cited_by_count":13},{"id":"2112.05129","title":"Assistive Tele-op: Leveraging Transformers to Collect Robotic Task Demonstrations","created":"2021-12-09","cited_by_count":11},{"id":"2205.09710","title":"Voxel-informed Language Grounding","created":"2022-05-19","cited_by_count":11},{"id":"2110.04450","title":"Scene Editing as Teleoperation: A Case Study in 6DoF Kit Assembly","created":"2021-10-09","cited_by_count":6}],"next_cursor":null}