{"list":"other","total":53,"rows":[{"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"2405.12213","title":"Octo: An Open-Source Generalist Robot Policy","created":"2024-05-20","cited_by_count":1484},{"id":"2004.07219","title":"D4RL: Datasets for Deep Data-Driven Reinforcement Learning","created":"2020-04-15","cited_by_count":1427},{"id":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"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":"1609.09106","title":"HyperNetworks","created":"2016-09-27","cited_by_count":1027},{"id":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"id":"2108.03298","title":"What Matters in Learning from Offline Human Demonstrations for Robot Manipulation","created":"2021-08-06","cited_by_count":725},{"id":"1709.10087","title":"Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations","created":"2017-09-28","cited_by_count":715},{"id":"2209.05451","title":"Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation","created":"2022-09-12","cited_by_count":551},{"id":"2109.00137","title":"Implicit Behavioral Cloning","created":"2021-09-01","cited_by_count":452},{"id":"2206.14176","title":"DayDreamer: World Models for Physical Robot Learning","created":"2022-06-28","cited_by_count":400},{"id":"2209.00588","title":"Transformers are Sample-Efficient World Models","created":"2022-09-01","cited_by_count":328},{"id":"1605.09673","title":"Dynamic Filter Networks","created":"2016-05-31","cited_by_count":319},{"id":"1506.07365","title":"Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images","created":"2015-06-24","cited_by_count":274},{"id":"1906.00695","title":"Continual learning with hypernetworks","created":"2019-06-03","cited_by_count":273},{"id":"2004.00784","title":"Learning Agile Robotic Locomotion Skills by Imitating Animals","created":"2020-04-02","cited_by_count":251},{"id":"2304.02532","title":"Goal-Conditioned Imitation Learning using Score-based Diffusion Policies","created":"2023-04-05","cited_by_count":236},{"id":"1907.00953","title":"Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model","created":"2019-07-01","cited_by_count":231},{"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":"1602.02867","title":"Value Iteration Networks","created":"2016-02-09","cited_by_count":160},{"id":"2210.07729","title":"Model-Based Imitation Learning for Urban Driving","created":"2022-10-14","cited_by_count":150},{"id":"2209.03855","title":"SE(3)-DiffusionFields: Learning smooth cost functions for joint grasp and motion optimization through diffusion","created":"2022-09-08","cited_by_count":127},{"id":"2212.09462","title":"Latent Diffusion for Language Generation","created":"2022-12-19","cited_by_count":115},{"id":"1606.05233","title":"Learning feed-forward one-shot learners","created":"2016-06-16","cited_by_count":93},{"id":"2401.03360","title":"Generative Skill Chaining: Long-Horizon Skill Planning with Diffusion Models","created":"2023-10-13","cited_by_count":91},{"id":"2310.09615","title":"STORM: Efficient Stochastic Transformer based World Models for Reinforcement Learning","created":"2023-10-14","cited_by_count":89},{"id":"2209.12892","title":"Learning to Learn with Generative Models of Neural Network Checkpoints","created":"2022-09-26","cited_by_count":86},{"id":"2406.09455","title":"Pandora: Towards General World Model with Natural Language Actions and Video States","created":"2024-06-12","cited_by_count":86},{"id":"2312.11598","title":"SkillDiffuser: Interpretable Hierarchical Planning via Skill Abstractions in Diffusion-Based Task Execution","created":"2023-12-18","cited_by_count":70},{"id":"2307.07176","title":"SafeDreamer: Safe Reinforcement Learning with World Models","created":"2023-07-14","cited_by_count":54},{"id":"2404.19264","title":"DiffuseLoco: Real-Time Legged Locomotion Control with Diffusion from Offline Datasets","created":"2024-04-30","cited_by_count":49},{"id":"2402.13144","title":"Neural Network Diffusion","created":"2024-02-20","cited_by_count":42},{"id":"2407.06169","title":"Potential Based Diffusion Motion Planning","created":"2024-07-08","cited_by_count":41},{"id":"2302.13335","title":"Diffusion Model-Augmented Behavioral Cloning","created":"2023-02-26","cited_by_count":38},{"id":"2409.16663","title":"Mitigating Covariate Shift in Imitation Learning for Autonomous Vehicles Using Latent Space Generative World Models","created":"2024-09-25","cited_by_count":22},{"id":"2205.06333","title":"Visuomotor Control in Multi-Object Scenes Using Object-Aware Representations","created":"2022-05-12","cited_by_count":21},{"id":"2402.10450","title":"PRISE: LLM-Style Sequence Compression for Learning Temporal Action Abstractions in Control","created":"2024-02-16","cited_by_count":21},{"id":"2305.13795","title":"Proximal Policy Gradient Arborescence for Quality Diversity Reinforcement Learning","created":"2023-05-23","cited_by_count":20},{"id":"2305.18738","title":"Generating Behaviorally Diverse Policies with Latent Diffusion Models","created":"2023-05-30","cited_by_count":19},{"id":"2402.04647","title":"Latent Plan Transformer for Trajectory Abstraction: Planning as Latent Space Inference","created":"2024-02-07","cited_by_count":14},{"id":"2407.10973","title":"Make-An-Agent: A Generalizable Policy Network Generator with Behavior-Prompted Diffusion","created":"2024-07-15","cited_by_count":14},{"id":"2406.10667","title":"UniZero: Generalized and Efficient Planning with Scalable Latent World Models","created":"2024-06-15","cited_by_count":12},{"id":"2309.16663","title":"HyperPPO: A scalable method for finding small policies for robotic control","created":"2023-09-28","cited_by_count":4}],"next_cursor":null}