{"list":"other","total":98,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2004.07219","title":"D4RL: Datasets for Deep Data-Driven Reinforcement Learning","created":"2020-04-15","cited_by_count":1427},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1707.01495","title":"Hindsight Experience Replay","created":"2017-07-05","cited_by_count":1136},{"id":"1504.00702","title":"End-to-End Training of Deep Visuomotor Policies","created":"2015-04-02","cited_by_count":875},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"1806.10293","title":"QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation","created":"2018-06-27","cited_by_count":743},{"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":"1606.01868","title":"Unifying Count-Based Exploration and Intrinsic Motivation","created":"2016-06-06","cited_by_count":639},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622},{"id":"2201.02605","title":"Detecting Twenty-thousand Classes using Image-level Supervision","created":"2022-01-07","cited_by_count":614},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"1411.4734","title":"Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture","created":"2014-11-18","cited_by_count":483},{"id":"1704.06888","title":"Time-Contrastive Networks: Self-Supervised Learning from Video","created":"2017-04-23","cited_by_count":459},{"id":"2210.00030","title":"VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training","created":"2022-09-30","cited_by_count":395},{"id":"1609.05143","title":"Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning","created":"2016-09-16","cited_by_count":366},{"id":"2010.14406","title":"Transporter Networks: Rearranging the Visual World for Robotic Manipulation","created":"2020-10-27","cited_by_count":344},{"id":"2203.01577","title":"HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction","created":"2022-03-03","cited_by_count":327},{"id":"1611.04717","title":"#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning","created":"2016-11-15","cited_by_count":309},{"id":"1710.04615","title":"Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperation","created":"2017-10-12","cited_by_count":289},{"id":"2006.06669","title":"Understanding Human Hands in Contact at Internet Scale","created":"2020-06-11","cited_by_count":281},{"id":"1703.01310","title":"Count-Based Exploration with Neural Density Models","created":"2017-03-03","cited_by_count":257},{"id":"1807.04742","title":"Visual Reinforcement Learning with Imagined Goals","created":"2018-07-12","cited_by_count":251},{"id":"2109.13396","title":"Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets","created":"2021-09-27","cited_by_count":250},{"id":"2203.06173","title":"Masked Visual Pre-training for Motor Control","created":"2022-03-11","cited_by_count":248},{"id":"2210.03109","title":"Real-World Robot Learning with Masked Visual Pre-training","created":"2022-10-06","cited_by_count":245},{"id":"1509.06825","title":"Supersizing Self-supervision: Learning to Grasp from 50K Tries and 700 Robot Hours","created":"2015-09-23","cited_by_count":209},{"id":"2108.05877","title":"DexMV: Imitation Learning for Dexterous Manipulation from Human Videos","created":"2021-08-12","cited_by_count":206},{"id":"2106.02036","title":"Anticipative Video Transformer","created":"2021-06-03","cited_by_count":200},{"id":"1810.13400","title":"Differentiable MPC for End-to-end Planning and Control","created":"2018-10-31","cited_by_count":189},{"id":"1903.03698","title":"Skew-Fit: State-Covering Self-Supervised Reinforcement Learning","created":"2019-03-08","cited_by_count":174},{"id":"1706.08033","title":"Decomposing Motion and Content for Natural Video Sequence Prediction","created":"2017-06-25","cited_by_count":169},{"id":"2108.06428","title":"FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integration","created":"2021-08-13","cited_by_count":169},{"id":"2207.09450","title":"Human-to-Robot Imitation in the Wild","created":"2022-07-19","cited_by_count":161},{"id":"2203.03580","title":"The Unsurprising Effectiveness of Pre-Trained Vision Models for Control","created":"2022-03-07","cited_by_count":155},{"id":"2112.01511","title":"The Surprising Effectiveness of Representation Learning for Visual Imitation","created":"2021-12-02","cited_by_count":154},{"id":"1802.01557","title":"One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning","created":"2018-02-05","cited_by_count":148},{"id":"2012.09856","title":"Reconstructing Hand-Object Interactions in the Wild","created":"2020-12-17","cited_by_count":144},{"id":"2209.13064","title":"EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations","created":"2022-09-26","cited_by_count":140},{"id":"1812.04558","title":"Grounded Human-Object Interaction Hotspots from Video","created":"2018-12-11","cited_by_count":129},{"id":"1803.09956","title":"Learning Synergies between Pushing and Grasping with Self-supervised Deep Reinforcement Learning","created":"2018-03-27","cited_by_count":128},{"id":"2005.02190","title":"Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video","created":"2020-05-04","cited_by_count":120},{"id":"2103.16817","title":"Learning Generalizable Robotic Reward Functions from \"In-The-Wild\" Human Videos","created":"2021-03-31","cited_by_count":119},{"id":"1804.08606","title":"Zero-Shot Visual Imitation","created":"2018-04-23","cited_by_count":117},{"id":"2001.04583","title":"EGO-TOPO: Environment Affordances from Egocentric Video","created":"2020-01-14","cited_by_count":111},{"id":"2008.04899","title":"Visual Imitation Made Easy","created":"2020-08-11","cited_by_count":111},{"id":"2204.01696","title":"Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos","created":"2022-04-04","cited_by_count":111},{"id":"1804.00892","title":"When will you do what? - Anticipating Temporal Occurrences of Activities","created":"2018-04-03","cited_by_count":107},{"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":"2212.04498","title":"VideoDex: Learning Dexterity from Internet Videos","created":"2022-12-08","cited_by_count":106},{"id":"1905.09035","title":"What Would You Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality Attention","created":"2019-05-22","cited_by_count":105},{"id":"1912.04443","title":"AVID: Learning Multi-Stage Tasks via Pixel-Level Translation of Human Videos","created":"2019-12-10","cited_by_count":105},{"id":"2012.11547","title":"Offline Reinforcement Learning from Images with Latent Space Models","created":"2020-12-21","cited_by_count":95},{"id":"2107.03380","title":"RRL: Resnet as representation for Reinforcement Learning","created":"2021-07-07","cited_by_count":91},{"id":"1703.02018","title":"Combining Self-Supervised Learning and Imitation for Vision-Based Rope Manipulation","created":"2017-03-06","cited_by_count":90},{"id":"2204.07153","title":"What's in your hands? 3D Reconstruction of Generic Objects in Hands","created":"2022-04-14","cited_by_count":90},{"id":"2202.10448","title":"Robotic Telekinesis: Learning a Robotic Hand Imitator by Watching Humans on Youtube","created":"2022-02-21","cited_by_count":82},{"id":"1707.04818","title":"RED: Reinforced Encoder-Decoder Networks for Action Anticipation","created":"2017-07-16","cited_by_count":78},{"id":"2110.03655","title":"Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Tasks","created":"2021-10-07","cited_by_count":78},{"id":"2203.13251","title":"Dexterous Imitation Made Easy: A Learning-Based Framework for Efficient Dexterous Manipulation","created":"2022-03-24","cited_by_count":78},{"id":"2204.13226","title":"Offline Visual Representation Learning for Embodied Navigation","created":"2022-04-27","cited_by_count":75},{"id":"1911.09676","title":"Third-Person Visual Imitation Learning via Decoupled Hierarchical Controller","created":"2019-11-21","cited_by_count":73},{"id":"1703.06585","title":"Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning","created":"2017-03-20","cited_by_count":71},{"id":"2109.10813","title":"A Workflow for Offline Model-Free Robotic Reinforcement Learning","created":"2021-09-22","cited_by_count":69},{"id":"2101.05181","title":"Memory-Augmented Reinforcement Learning for Image-Goal Navigation","created":"2021-01-13","cited_by_count":66},{"id":"2110.15360","title":"Accelerating Robotic Reinforcement Learning via Parameterized Action Primitives","created":"2021-10-28","cited_by_count":65},{"id":"2001.02192","title":"An Exploration of Embodied Visual Exploration","created":"2020-01-07","cited_by_count":58},{"id":"2012.02788","title":"Neural Dynamic Policies for End-to-End Sensorimotor Learning","created":"2020-12-04","cited_by_count":58},{"id":"2107.11444","title":"Cooperative Exploration for Multi-Agent Deep Reinforcement Learning","created":"2021-07-23","cited_by_count":57},{"id":"1904.05250","title":"Next-Active-Object prediction from Egocentric Videos","created":"2019-04-10","cited_by_count":55},{"id":"2007.04979","title":"A Cordial Sync: Going Beyond Marginal Policies for Multi-Agent Embodied Tasks","created":"2020-07-09","cited_by_count":52},{"id":"2112.09120","title":"Human Hands as Probes for Interactive Object Understanding","created":"2021-12-16","cited_by_count":52},{"id":"1801.02854","title":"Riemannian Motion Policies","created":"2018-01-09","cited_by_count":46},{"id":"2102.00649","title":"Forecasting Action through Contact Representations from First Person Video","created":"2021-02-01","cited_by_count":46},{"id":"1904.05879","title":"Two Body Problem: Collaborative Visual Task Completion","created":"2019-04-11","cited_by_count":45},{"id":"1509.05016","title":"Recurrent Neural Networks for Driver Activity Anticipation via Sensory-Fusion Architecture","created":"2015-09-16","cited_by_count":42},{"id":"2202.00732","title":"IFOR: Iterative Flow Minimization for Robotic Object Rearrangement","created":"2022-02-01","cited_by_count":42},{"id":"2111.13119","title":"Interesting Object, Curious Agent: Learning Task-Agnostic Exploration","created":"2021-11-25","cited_by_count":38},{"id":"1604.01347","title":"Marr Revisited: 2D-3D Alignment via Surface Normal Prediction","created":"2016-04-05","cited_by_count":34},{"id":"2207.05053","title":"Learning Continuous Grasping Function with a Dexterous Hand from Human Demonstrations","created":"2022-07-11","cited_by_count":34},{"id":"2211.11746","title":"Last-Mile Embodied Visual Navigation","created":"2022-11-21","cited_by_count":25},{"id":"2302.06604","title":"ALAN: Autonomously Exploring Robotic Agents in the Real World","created":"2023-02-13","cited_by_count":24},{"id":"2209.13583","title":"Learning State-Aware Visual Representations from Audible Interactions","created":"2022-09-27","cited_by_count":23},{"id":"2105.00931","title":"GridToPix: Training Embodied Agents with Minimal Supervision","created":"2021-04-14","cited_by_count":21},{"id":"2107.02349","title":"Physical Interaction as Communication: Learning Robot Objectives Online from Human Corrections","created":"2021-07-06","cited_by_count":19},{"id":"1603.04908","title":"First Person Action-Object Detection with EgoNet","created":"2016-03-15","cited_by_count":17},{"id":"2104.14040","title":"Pushing it out of the Way: Interactive Visual Navigation","created":"2021-04-28","cited_by_count":16},{"id":"1803.11186","title":"Two can play this Game: Visual Dialog with Discriminative Question Generation and Answering","created":"2018-03-29","cited_by_count":13},{"id":"1605.01679","title":"Learning Action Maps of Large Environments via First-Person Vision","created":"2016-05-05","cited_by_count":11},{"id":"2009.02615","title":"Learning Topological Motion Primitives for Knot Planning","created":"2020-09-05","cited_by_count":6},{"id":"1809.09558","title":"Human-Machine Interface for Remote Training of Robot Tasks","created":"2018-09-25","cited_by_count":1}],"next_cursor":null}