{"list":"other","total":56,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"2303.04137","title":"Diffusion Policy: Visuomotor Policy Learning via Action Diffusion","created":"2023-03-07","cited_by_count":2838},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"id":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"id":"2203.12601","title":"R3M: A Universal Visual Representation for Robot Manipulation","created":"2022-03-23","cited_by_count":694},{"id":"2405.05941","title":"Evaluating Real-World Robot Manipulation Policies in Simulation","created":"2024-05-09","cited_by_count":495},{"id":"1704.06888","title":"Time-Contrastive Networks: Self-Supervised Learning from Video","created":"2017-04-23","cited_by_count":459},{"id":"2305.15347","title":"A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence","created":"2023-05-24","cited_by_count":301},{"id":"2203.06173","title":"Masked Visual Pre-training for Motor Control","created":"2022-03-11","cited_by_count":248},{"id":"2306.14896","title":"RVT: Robotic View Transformer for 3D Object Manipulation","created":"2023-06-26","cited_by_count":225},{"id":"2302.11550","title":"Scaling Robot Learning with Semantically Imagined Experience","created":"2023-02-22","cited_by_count":177},{"id":"2302.12766","title":"Language-Driven Representation Learning for Robotics","created":"2023-02-24","cited_by_count":165},{"id":"1904.07846","title":"Temporal Cycle-Consistency Learning","created":"2019-04-16","cited_by_count":154},{"id":"2210.13702","title":"DeXtreme: Transfer of Agile In-hand Manipulation from Simulation to Reality","created":"2022-10-25","cited_by_count":149},{"id":"2011.13389","title":"Generalization in Reinforcement Learning by Soft Data Augmentation","created":"2020-11-26","cited_by_count":137},{"id":"2402.08191","title":"THE COLOSSEUM: A Benchmark for Evaluating Generalization for Robotic Manipulation","created":"2024-02-13","cited_by_count":133},{"id":"2007.04309","title":"Self-Supervised Policy Adaptation during Deployment","created":"2020-07-08","cited_by_count":123},{"id":"2106.03911","title":"XIRL: Cross-embodiment Inverse Reinforcement Learning","created":"2021-06-07","cited_by_count":107},{"id":"2107.00644","title":"Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation","created":"2021-07-01","cited_by_count":105},{"id":"2308.16891","title":"GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fields","created":"2023-08-31","cited_by_count":99},{"id":"2307.03659","title":"Decomposing the Generalization Gap in Imitation Learning for Visual Robotic Manipulation","created":"2023-07-07","cited_by_count":82},{"id":"2302.02408","title":"Multi-View Masked World Models for Visual Robotic Manipulation","created":"2023-02-05","cited_by_count":80},{"id":"2309.06440","title":"LEAP Hand: Low-Cost, Efficient, and Anthropomorphic Hand for Robot Learning","created":"2023-09-12","cited_by_count":79},{"id":"2401.07487","title":"Robo-ABC: Affordance Generalization Beyond Categories via Semantic Correspondence for Robot Manipulation","created":"2024-01-15","cited_by_count":71},{"id":"2212.08860","title":"Pre-Trained Image Encoder for Generalizable Visual Reinforcement Learning","created":"2022-12-17","cited_by_count":60},{"id":"2405.10315","title":"TRANSIC: Sim-to-Real Policy Transfer by Learning from Online Correction","created":"2024-05-16","cited_by_count":59},{"id":"2306.13229","title":"TACO: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning","created":"2023-06-22","cited_by_count":57},{"id":"2212.05749","title":"On Pre-Training for Visuo-Motor Control: Revisiting a Learning-from-Scratch Baseline","created":"2022-12-12","cited_by_count":56},{"id":"2306.10007","title":"Robot Learning with Sensorimotor Pre-training","created":"2023-06-16","cited_by_count":51},{"id":"2405.20321","title":"Vision-based Manipulation from Single Human Video with Open-World Object Graphs","created":"2024-05-30","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":"2309.00987","title":"Sequential Dexterity: Chaining Dexterous Policies for Long-Horizon Manipulation","created":"2023-09-02","cited_by_count":49},{"id":"2210.07241","title":"Visual Reinforcement Learning with Self-Supervised 3D Representations","created":"2022-10-13","cited_by_count":45},{"id":"2406.00439","title":"Learning Manipulation by Predicting Interaction","created":"2024-06-01","cited_by_count":37},{"id":"2309.05655","title":"Dynamic Handover: Throw and Catch with Bimanual Hands","created":"2023-09-11","cited_by_count":35},{"id":"2209.09203","title":"Look where you look! Saliency-guided Q-networks for generalization in visual Reinforcement Learning","created":"2022-09-16","cited_by_count":34},{"id":"2405.07991","title":"SPIN: Simultaneous Perception, Interaction and Navigation","created":"2024-05-13","cited_by_count":29},{"id":"2307.10224","title":"RL-ViGen: A Reinforcement Learning Benchmark for Visual Generalization","created":"2023-07-15","cited_by_count":28},{"id":"2402.14795","title":"CyberDemo: Augmenting Simulated Human Demonstration for Real-World Dexterous Manipulation","created":"2024-02-22","cited_by_count":28},{"id":"2210.04561","title":"A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learning","created":"2022-10-10","cited_by_count":25},{"id":"2304.04591","title":"For Pre-Trained Vision Models in Motor Control, Not All Policy Learning Methods are Created Equal","created":"2023-04-10","cited_by_count":22},{"id":"2202.09982","title":"Don't Touch What Matters: Task-Aware Lipschitz Data Augmentation for Visual Reinforcement Learning","created":"2022-02-21","cited_by_count":21},{"id":"2405.10020","title":"Natural Language Can Help Bridge the Sim2Real Gap","created":"2024-05-16","cited_by_count":21},{"id":"2307.00972","title":"MoVie: Visual Model-Based Policy Adaptation for View Generalization","created":"2023-07-03","cited_by_count":16},{"id":"2306.00656","title":"Normalization Enhances Generalization in Visual Reinforcement Learning","created":"2023-06-01","cited_by_count":13},{"id":"2312.17116","title":"Generalizable Visual Reinforcement Learning with Segment Anything Model","created":"2023-12-28","cited_by_count":12},{"id":"2407.07868","title":"Green Screen Augmentation Enables Scene Generalisation in Robotic Manipulation","created":"2024-07-10","cited_by_count":11},{"id":"2402.06187","title":"Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss","created":"2024-02-09","cited_by_count":10},{"id":"2406.07398","title":"Visual Representation Learning with Stochastic Frame Prediction","created":"2024-06-11","cited_by_count":10},{"id":"2405.14073","title":"PEAC: Unsupervised Pre-training for Cross-Embodiment Reinforcement Learning","created":"2024-05-23","cited_by_count":9},{"id":"2402.02701","title":"Understanding What Affects the Generalization Gap in Visual Reinforcement Learning: Theory and Empirical Evidence","created":"2024-02-05","cited_by_count":5},{"id":"2210.01379","title":"Extraneousness-Aware Imitation Learning","created":"2022-10-04","cited_by_count":3}],"next_cursor":null}