{"list":"other","total":53,"rows":[{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"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":"2303.04137","title":"Diffusion Policy: Visuomotor Policy Learning via Action Diffusion","created":"2023-03-07","cited_by_count":2838},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"2211.17192","title":"Fast Inference from Transformers via Speculative Decoding","created":"2022-11-30","cited_by_count":1653},{"id":"2304.13705","title":"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware","created":"2023-04-23","cited_by_count":1568},{"id":"2405.12213","title":"Octo: An Open-Source Generalist Robot Policy","created":"2024-05-20","cited_by_count":1484},{"id":"1805.04833","title":"Hierarchical Neural Story Generation","created":"2018-05-13","cited_by_count":1193},{"id":"2205.09991","title":"Planning with Diffusion for Flexible Behavior Synthesis","created":"2022-05-20","cited_by_count":1061},{"id":"2108.03298","title":"What Matters in Learning from Offline Human Demonstrations for Robot Manipulation","created":"2021-08-06","cited_by_count":725},{"id":"2210.15097","title":"Contrastive Decoding: Open-ended Text Generation as Optimization","created":"2022-10-27","cited_by_count":609},{"id":"2202.02005","title":"BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning","created":"2022-02-04","cited_by_count":523},{"id":"1908.04319","title":"Neural Text Generation with Unlikelihood Training","created":"2019-08-12","cited_by_count":503},{"id":"2109.00137","title":"Implicit Behavioral Cloning","created":"2021-09-01","cited_by_count":452},{"id":"2402.10329","title":"Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots","created":"2024-02-15","cited_by_count":394},{"id":"2401.02117","title":"Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation","created":"2024-01-04","cited_by_count":391},{"id":"1910.11956","title":"Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning","created":"2019-10-25","cited_by_count":384},{"id":"2304.10573","title":"IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies","created":"2023-04-20","cited_by_count":325},{"id":"2206.11251","title":"Behavior Transformers: Cloning $k$ modes with one stone","created":"2022-06-22","cited_by_count":304},{"id":"2402.02057","title":"Break the Sequential Dependency of LLM Inference Using Lookahead Decoding","created":"2024-02-03","cited_by_count":298},{"id":"1905.11979","title":"Causal Confusion in Imitation Learning","created":"2019-05-28","cited_by_count":288},{"id":"1810.02890","title":"HG-DAgger: Interactive Imitation Learning with Human Experts","created":"2018-10-05","cited_by_count":266},{"id":"1702.01806","title":"Beam Search Strategies for Neural Machine Translation","created":"2017-02-06","cited_by_count":232},{"id":"1703.09327","title":"DART: Noise Injection for Robust Imitation Learning","created":"2017-03-27","cited_by_count":191},{"id":"2309.13037","title":"GELLO: A General, Low-Cost, and Intuitive Teleoperation Framework for Robot Manipulators","created":"2023-09-22","cited_by_count":189},{"id":"2309.01918","title":"RoboAgent: Generalization and Efficiency in Robot Manipulation via Semantic Augmentations and Action Chunking","created":"2023-09-05","cited_by_count":169},{"id":"2405.07503","title":"Consistency Policy: Accelerated Visuomotor Policies via Consistency Distillation","created":"2024-05-13","cited_by_count":166},{"id":"2403.03181","title":"Behavior Generation with Latent Actions","created":"2024-03-05","cited_by_count":160},{"id":"2210.15191","title":"Truncation Sampling as Language Model Desmoothing","created":"2022-10-27","cited_by_count":123},{"id":"2202.00666","title":"Locally Typical Sampling","created":"2022-02-01","cited_by_count":111},{"id":"2109.08273","title":"ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learning","created":"2021-09-17","cited_by_count":108},{"id":"1807.08364","title":"EnsembleDAgger: A Bayesian Approach to Safe Imitation Learning","created":"2018-07-22","cited_by_count":100},{"id":"2011.06619","title":"Learning Latent Representations to Influence Multi-Agent Interaction","created":"2020-11-12","cited_by_count":93},{"id":"2403.03890","title":"Hierarchical Diffusion Policy for Kinematics-Aware Multi-Task Robotic Manipulation","created":"2024-03-06","cited_by_count":93},{"id":"1911.05321","title":"IRIS: Implicit Reinforcement without Interaction at Scale for Learning Control from Offline Robot Manipulation Data","created":"2019-11-13","cited_by_count":86},{"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":"2306.02437","title":"Data Quality in Imitation Learning","created":"2023-06-04","cited_by_count":75},{"id":"2010.14876","title":"Fighting Copycat Agents in Behavioral Cloning from Observation Histories","created":"2020-10-28","cited_by_count":71},{"id":"2303.00855","title":"Grounded Decoding: Guiding Text Generation with Grounded Models for Embodied Agents","created":"2023-03-01","cited_by_count":67},{"id":"2307.14326","title":"Waypoint-Based Imitation Learning for Robotic Manipulation","created":"2023-07-26","cited_by_count":61},{"id":"2105.08504","title":"Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translation","created":"2021-05-18","cited_by_count":56},{"id":"2104.00053","title":"LazyDAgger: Reducing Context Switching in Interactive Imitation Learning","created":"2021-03-31","cited_by_count":51},{"id":"2011.06719","title":"Grasping with Chopsticks: Combating Covariate Shift in Model-free Imitation Learning for Fine Manipulation","created":"2020-11-13","cited_by_count":38},{"id":"2202.01312","title":"Causal Imitation Learning under Temporally Correlated Noise","created":"2022-02-02","cited_by_count":28},{"id":"2210.08073","title":"Eliciting Compatible Demonstrations for Multi-Human Imitation Learning","created":"2022-10-14","cited_by_count":23},{"id":"2212.04590","title":"Learning Options via Compression","created":"2022-12-08","cited_by_count":22},{"id":"2309.10175","title":"One ACT Play: Single Demonstration Behavior Cloning with Action Chunking Transformers","created":"2023-09-18","cited_by_count":17},{"id":"2210.02343","title":"Visual Backtracking Teleoperation: A Data Collection Protocol for Offline Image-Based Reinforcement Learning","created":"2022-10-05","cited_by_count":11},{"id":"1710.05090","title":"Burn-In Demonstrations for Multi-Modal Imitation Learning","created":"2017-10-13","cited_by_count":9},{"id":"1803.02208","title":"Discovering Underlying Plans Based on Shallow Models","created":"2018-03-04","cited_by_count":9},{"id":"2306.07919","title":"Skill Disentanglement for Imitation Learning from Suboptimal Demonstrations","created":"2023-06-13","cited_by_count":5}],"next_cursor":null}