{"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":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"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":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"2103.03230","title":"Barlow Twins: Self-Supervised Learning via Redundancy Reduction","created":"2021-03-04","cited_by_count":1838},{"id":"1803.07728","title":"Unsupervised Representation Learning by Predicting Image Rotations","created":"2018-03-21","cited_by_count":1591},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2006.10029","title":"Big Self-Supervised Models are Strong Semi-Supervised Learners","created":"2020-06-17","cited_by_count":1380},{"id":"2105.04906","title":"VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning","created":"2021-05-11","cited_by_count":1057},{"id":"1604.07316","title":"End to End Learning for Self-Driving Cars","created":"2016-04-25","cited_by_count":1009},{"id":"2203.12601","title":"R3M: A Universal Visual Representation for Robot Manipulation","created":"2022-03-23","cited_by_count":694},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622},{"id":"1710.02410","title":"End-to-end Driving via Conditional Imitation Learning","created":"2017-10-06","cited_by_count":485},{"id":"2205.15997","title":"TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving","created":"2022-05-31","cited_by_count":485},{"id":"1812.03079","title":"ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worst","created":"2018-12-07","cited_by_count":397},{"id":"1912.12294","title":"Learning by Cheating","created":"2019-12-27","cited_by_count":383},{"id":"1904.08980","title":"Exploring the Limitations of Behavior Cloning for Autonomous Driving","created":"2019-04-18","cited_by_count":346},{"id":"2206.11795","title":"Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos","created":"2022-06-23","cited_by_count":345},{"id":"2304.12210","title":"A Cookbook of Self-Supervised Learning","created":"2023-04-24","cited_by_count":250},{"id":"2306.14846","title":"ViNT: A Foundation Model for Visual Navigation","created":"2023-06-26","cited_by_count":222},{"id":"2202.01771","title":"Pre-Trained Language Models for Interactive Decision-Making","created":"2022-02-03","cited_by_count":221},{"id":"2210.03370","title":"GNM: A General Navigation Model to Drive Any Robot","created":"2022-10-07","cited_by_count":171},{"id":"2308.01557","title":"Motion Planning Diffusion: Learning and Planning of Robot Motions with Diffusion Models","created":"2023-08-03","cited_by_count":161},{"id":"2210.07729","title":"Model-Based Imitation Learning for Urban Driving","created":"2022-10-14","cited_by_count":150},{"id":"2203.15041","title":"Socially Compliant Navigation Dataset (SCAND): A Large-Scale Dataset of Demonstrations for Social Navigation","created":"2022-03-28","cited_by_count":127},{"id":"2105.00636","title":"Learning to drive from a world on rails","created":"2021-05-03","cited_by_count":114},{"id":"2201.12122","title":"Can Wikipedia Help Offline Reinforcement Learning?","created":"2022-01-28","cited_by_count":77},{"id":"2011.13112","title":"Motion Planning and Control for Mobile Robot Navigation Using Machine Learning: a Survey","created":"2020-11-26","cited_by_count":58},{"id":"2307.12698","title":"MC-JEPA: A Joint-Embedding Predictive Architecture for Self-Supervised Learning of Motion and Content Features","created":"2023-07-24","cited_by_count":57},{"id":"2307.09668","title":"Towards A Unified Agent with Foundation Models","created":"2023-07-18","cited_by_count":47},{"id":"2303.14880","title":"Toward Human-Like Social Robot Navigation: A Large-Scale, Multi-Modal, Social Human Navigation Dataset","created":"2023-03-27","cited_by_count":31},{"id":"2311.12996","title":"RLIF: Interactive Imitation Learning as Reinforcement Learning","created":"2023-11-21","cited_by_count":30},{"id":"2209.10780","title":"Learning Model Predictive Controllers with Real-Time Attention for Real-World Navigation","created":"2022-09-22","cited_by_count":29},{"id":"1908.09073","title":"Situational Fusion of Visual Representation for Visual Navigation","created":"2019-08-24","cited_by_count":28},{"id":"2102.12667","title":"Learning Inverse Kinodynamics for Accurate High-Speed Off-Road Navigation on Unstructured Terrain","created":"2021-02-25","cited_by_count":25},{"id":"2110.10149","title":"Continuous Control with Action Quantization from Demonstrations","created":"2021-10-19","cited_by_count":22},{"id":"2203.15983","title":"VI-IKD: High-Speed Accurate Off-Road Navigation using Learned Visual-Inertial Inverse Kinodynamics","created":"2022-03-30","cited_by_count":21},{"id":"2105.07620","title":"APPL: Adaptive Planner Parameter Learning","created":"2021-05-17","cited_by_count":20},{"id":"2402.06838","title":"NavFormer: A Transformer Architecture for Robot Target-Driven Navigation in Unknown and Dynamic Environments","created":"2024-02-09","cited_by_count":20},{"id":"2303.00998","title":"Toward Wheeled Mobility on Vertically Challenging Terrain: Platforms, Datasets, and Algorithms","created":"2023-03-02","cited_by_count":19},{"id":"2311.04193","title":"Selective Visual Representations Improve Convergence and Generalization for Embodied AI","created":"2023-11-07","cited_by_count":19},{"id":"2311.09215","title":"ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy","created":"2023-11-15","cited_by_count":19},{"id":"2109.08968","title":"Visual Representation Learning for Preference-Aware Path Planning","created":"2021-09-18","cited_by_count":18},{"id":"2307.15801","title":"Primitive Skill-based Robot Learning from Human Evaluative Feedback","created":"2023-07-28","cited_by_count":15},{"id":"2106.12113","title":"Conflict Avoidance in Social Navigation -- a Survey","created":"2021-06-23","cited_by_count":14},{"id":"2007.14479","title":"Toward Agile Maneuvers in Highly Constrained Spaces: Learning from Hallucination","created":"2020-07-28","cited_by_count":11},{"id":"2206.08487","title":"High-Speed Accurate Robot Control using Learned Forward Kinodynamics and Non-linear Least Squares Optimization","created":"2022-06-16","cited_by_count":11},{"id":"2306.11611","title":"Learning to Model and Plan for Wheeled Mobility on Vertically Challenging Terrain","created":"2023-06-20","cited_by_count":11},{"id":"2309.15302","title":"STERLING: Self-Supervised Terrain Representation Learning from Unconstrained Robot Experience","created":"2023-09-26","cited_by_count":11},{"id":"2301.00362","title":"Goal-Guided Transformer-Enabled Reinforcement Learning for Efficient Autonomous Navigation","created":"2023-01-01","cited_by_count":10},{"id":"2311.15268","title":"Unlearning via Sparse Representations","created":"2023-11-26","cited_by_count":10},{"id":"2207.00052","title":"Visual Pre-training for Navigation: What Can We Learn from Noise?","created":"2022-06-30","cited_by_count":8},{"id":"2312.08365","title":"An Invitation to Deep Reinforcement Learning","created":"2023-12-13","cited_by_count":5},{"id":"2309.12568","title":"A Study on Learning Social Robot Navigation with Multimodal Perception","created":"2023-09-22","cited_by_count":4},{"id":"2303.02731","title":"Virtual Guidance as a Mid-level Representation for Navigation with Augmented Reality","created":"2023-03-05","cited_by_count":1}],"next_cursor":null}