{"total":119,"rows":[{"id":"2401.02117","title":"Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation","created":"2024-01-04","cited_by_count":391,"area":"offlinerl"},{"id":"2410.24221","title":"EgoMimic: Scaling Imitation Learning via Egocentric Video","created":"2024-10-31","cited_by_count":175,"area":"offlinerl"},{"id":"2412.13877","title":"RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation","created":"2024-12-18","cited_by_count":175,"area":"offlinerl"},{"id":"2407.01512","title":"Open-TeleVision: Teleoperation with Immersive Active Visual Feedback","created":"2024-07-01","cited_by_count":145,"area":"offlinerl"},{"id":"2410.18647","title":"Data Scaling Laws in Imitation Learning for Robotic Manipulation","created":"2024-10-24","cited_by_count":145,"area":"offlinerl"},{"id":"2412.06685","title":"Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone","created":"2024-12-09","cited_by_count":79,"area":"offlinerl"},{"id":"2407.03162","title":"Bunny-VisionPro: Real-Time Bimanual Dexterous Teleoperation for Imitation Learning","created":"2024-07-03","cited_by_count":77,"area":"offlinerl"},{"id":"2403.19578","title":"Keypoint Action Tokens Enable In-Context Imitation Learning in Robotics","created":"2024-03-28","cited_by_count":74,"area":"offlinerl"},{"id":"2408.15980","title":"In-Context Imitation Learning via Next-Token Prediction","created":"2024-08-28","cited_by_count":70,"area":"offlinerl"},{"id":"2412.13630","title":"Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model","created":"2024-12-18","cited_by_count":70,"area":"offlinerl"},{"id":"2310.05905","title":"TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models","created":"2023-10-09","cited_by_count":53,"area":"offlinerl"},{"id":"2409.14674","title":"RACER: Rich Language-Guided Failure Recovery Policies for Imitation Learning","created":"2024-09-23","cited_by_count":49,"area":"offlinerl"},{"id":"2312.02976","title":"SPOC: Imitating Shortest Paths in Simulation Enables Effective Navigation and Manipulation in the Real World","created":"2023-12-05","cited_by_count":48,"area":"offlinerl"},{"id":"2408.14037","title":"Re-Mix: Optimizing Data Mixtures for Large Scale Imitation Learning","created":"2024-08-26","cited_by_count":47,"area":"offlinerl"},{"id":"2403.02709","title":"RT-Sketch: Goal-Conditioned Imitation Learning from Hand-Drawn Sketches","created":"2024-03-05","cited_by_count":41,"area":"offlinerl"},{"id":"2407.12998","title":"Surgical Robot Transformer (SRT): Imitation Learning for Surgical Tasks","created":"2024-07-17","cited_by_count":40,"area":"offlinerl"},{"id":"2404.03729","title":"JUICER: Data-Efficient Imitation Learning for Robotic Assembly","created":"2024-04-04","cited_by_count":38,"area":"offlinerl"},{"id":"2408.04380","title":"Deep Generative Models in Robotics: A Survey on Learning from Multimodal Demonstrations","created":"2024-08-08","cited_by_count":35,"area":"offlinerl"},{"id":"2503.23877","title":"ZeroMimic: Distilling Robotic Manipulation Skills from Web Videos","created":"2025-03-31","cited_by_count":32,"area":"offlinerl"},{"id":"2309.11359","title":"Prompt, Plan, Perform: LLM-based Humanoid Control via Quantized Imitation Learning","created":"2023-09-20","cited_by_count":31,"area":"offlinerl"},{"id":"2402.05546","title":"Offline Actor-Critic Reinforcement Learning Scales to Large Models","created":"2024-02-08","cited_by_count":30,"area":"offlinerl"},{"id":"2509.19626","title":"EgoBridge: Domain Adaptation for Generalizable Imitation from Egocentric Human Data","created":"2025-09-23","cited_by_count":29,"area":"offlinerl"},{"id":"2505.09603","title":"DataMIL: Selecting Data for Robot Imitation Learning with Datamodels","created":"2025-05-14","cited_by_count":28,"area":"offlinerl"},{"id":"2506.06072","title":"BEAST: Efficient Tokenization of B-Splines Encoded Action Sequences for Imitation Learning","created":"2025-06-06","cited_by_count":27,"area":"offlinerl"},{"id":"2503.07771","title":"RoboCopilot: Human-in-the-loop Interactive Imitation Learning for Robot Manipulation","created":"2025-03-10","cited_by_count":26,"area":"offlinerl"},{"id":"2505.10251","title":"SRT-H: A Hierarchical Framework for Autonomous Surgery via Language Conditioned Imitation Learning","created":"2025-05-15","cited_by_count":26,"area":"offlinerl"},{"id":"2310.20587","title":"Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning","created":"2023-10-31","cited_by_count":24,"area":"offlinerl"},{"id":"2506.19121","title":"CUPID: Curating Data your Robot Loves with Influence Functions","created":"2025-06-23","cited_by_count":23,"area":"offlinerl"},{"id":"2503.03081","title":"AirExo-2: Scaling up Generalizable Robotic Imitation Learning with Low-Cost Exoskeletons","created":"2025-03-05","cited_by_count":18,"area":"offlinerl"},{"id":"2602.15010","title":"BPP: Long-Context Robot Imitation Learning by Focusing on Key History Frames","created":"2026-02-16","cited_by_count":18,"area":"offlinerl"},{"id":"2503.04877","title":"Adapt3R: Adaptive 3D Scene Representation for Domain Transfer in Imitation Learning","created":"2025-03-06","cited_by_count":17,"area":"offlinerl"},{"id":"2405.05439","title":"How Generalizable Is My Behavior Cloning Policy? A Statistical Approach to Trustworthy Performance Evaluation","created":"2024-05-08","cited_by_count":15,"area":"offlinerl"},{"id":"2406.09738","title":"Contrastive Imitation Learning for Language-guided Multi-Task Robotic Manipulation","created":"2024-06-14","cited_by_count":15,"area":"offlinerl"},{"id":"2407.15403","title":"Offline Imitation Learning Through Graph Search and Retrieval","created":"2024-07-22","cited_by_count":14,"area":"offlinerl"},{"id":"2503.10966","title":"Is Your Imitation Learning Policy Better than Mine? Policy Comparison with Near-Optimal Stopping","created":"2025-03-14","cited_by_count":14,"area":"offlinerl"},{"id":"2506.13498","title":"A Survey on Imitation Learning for Contact-Rich Tasks in Robotics","created":"2025-06-16","cited_by_count":14,"area":"offlinerl"},{"id":"2506.13762","title":"Touch begins where vision ends: Generalizable policies for contact-rich manipulation","created":"2025-06-16","cited_by_count":14,"area":"offlinerl"},{"id":"2510.02268","title":"Do You Know Where Your Camera Is? View-Invariant Policy Learning with Camera Conditioning","created":"2025-10-02","cited_by_count":14,"area":"offlinerl"},{"id":"2411.16959","title":"RoCoDA: Counterfactual Data Augmentation for Data-Efficient Robot Learning from Demonstrations","created":"2024-11-25","cited_by_count":13,"area":"offlinerl"},{"id":"2505.07728","title":"Guiding Data Collection via Factored Scaling Curves","created":"2025-05-12","cited_by_count":12,"area":"offlinerl"},{"id":"2410.00064","title":"M2Distill: Multi-Modal Distillation for Lifelong Imitation Learning","created":"2024-09-30","cited_by_count":11,"area":"offlinerl"},{"id":"2507.06224","title":"EC-Flow: Enabling Versatile Robotic Manipulation from Action-Unlabeled Videos via Embodiment-Centric Flow","created":"2025-07-08","cited_by_count":11,"area":"offlinerl"},{"id":"2509.18778","title":"VGGT-DP: Generalizable Robot Control via Vision Foundation Models","created":"2025-09-23","cited_by_count":11,"area":"offlinerl"},{"id":"2411.05193","title":"Q-SFT: Q-Learning for Language Models via Supervised Fine-Tuning","created":"2024-11-07","cited_by_count":10,"area":"offlinerl"},{"id":"2502.02853","title":"Rethinking Latent Redundancy in Behavior Cloning: An Information Bottleneck Approach for Robot Manipulation","created":"2025-02-05","cited_by_count":10,"area":"offlinerl"},{"id":"2407.20164","title":"Language-Conditioned Offline RL for Multi-Robot Navigation","created":"2024-07-29","cited_by_count":9,"area":"offlinerl"},{"id":"2504.15561","title":"SPECI: Skill Prompts based Hierarchical Continual Imitation Learning for Robot Manipulation","created":"2025-04-22","cited_by_count":9,"area":"offlinerl"},{"id":"2505.22626","title":"SCIZOR: A Self-Supervised Approach to Data Curation for Large-Scale Imitation Learning","created":"2025-05-28","cited_by_count":9,"area":"offlinerl"},{"id":"2410.24108","title":"Reinforcement Learning Gradients as Vitamin for Online Finetuning Decision Transformers","created":"2024-10-31","cited_by_count":8,"area":"offlinerl"},{"id":"2312.12036","title":"LHManip: A Dataset for Long-Horizon Language-Grounded Manipulation Tasks in Cluttered Tabletop Environments","created":"2023-12-19","cited_by_count":7,"area":"offlinerl"},{"id":"2411.00610","title":"Provably and Practically Efficient Adversarial Imitation Learning with General Function Approximation","created":"2024-11-01","cited_by_count":6,"area":"offlinerl"},{"id":"2604.00557","title":"Multi-Camera View Scaling for Data-Efficient Robot Imitation Learning","created":"2026-04-01","cited_by_count":6,"area":"offlinerl"},{"id":"2401.07603","title":"Multi-task real-robot data with gaze attention for dual-arm fine manipulation","created":"2024-01-15","cited_by_count":5,"area":"offlinerl"},{"id":"2404.02407","title":"Decision Transformer as a Foundation Model for Partially Observable Continuous Control","created":"2024-04-03","cited_by_count":5,"area":"offlinerl"},{"id":"2503.05231","title":"Kaiwu: A Multimodal Manipulation Dataset and Framework for Robot Learning and Human-Robot Interaction","created":"2025-03-07","cited_by_count":5,"area":"offlinerl"},{"id":"2504.15046","title":"Text-to-Decision Agent: Offline Meta-Reinforcement Learning from Natural Language Supervision","created":"2025-04-21","cited_by_count":5,"area":"offlinerl"},{"id":"2510.19495","title":"Using Non-Expert Data to Robustify Imitation Learning via Offline Reinforcement Learning","created":"2025-10-22","cited_by_count":5,"area":"offlinerl"},{"id":"2601.11421","title":"The Great March 100: 100 Detail-oriented Tasks for Evaluating Embodied AI Agents","created":"2026-01-16","cited_by_count":5,"area":"offlinerl"},{"id":"2408.11048","title":"RP1M: A Large-Scale Motion Dataset for Piano Playing with Bi-Manual Dexterous Robot Hands","created":"2024-08-20","cited_by_count":4,"area":"offlinerl"},{"id":"2504.04395","title":"Human-Level Competitive Pok\\'emon via Scalable Offline Reinforcement Learning with Transformers","created":"2025-04-06","cited_by_count":4,"area":"offlinerl"},{"id":"2506.00098","title":"Interactive Imitation Learning for Dexterous Robotic Manipulation: Challenges and Perspectives -- A Survey","created":"2025-05-30","cited_by_count":4,"area":"offlinerl"},{"id":"2507.22380","title":"Improving Generalization Ability of Robotic Imitation Learning by Resolving Causal Confusion in Observations","created":"2025-07-30","cited_by_count":4,"area":"offlinerl"},{"id":"2511.18617","title":"AutoFocus-IL: VLM-based Saliency Maps for Data-Efficient Visual Imitation Learning without Extra Human Annotations","created":"2025-11-23","cited_by_count":4,"area":"offlinerl"},{"id":"2605.27724","title":"HumanoidMimicGen: Data Generation for Loco-Manipulation via Whole-Body Planning","created":"2026-05-26","cited_by_count":4,"area":"offlinerl"},{"id":"2404.16483","title":"Leveraging Pretrained Latent Representations for Few-Shot Imitation Learning on a Dexterous Robotic Hand","created":"2024-04-25","cited_by_count":3,"area":"offlinerl"},{"id":"2410.01273","title":"CANVAS: Commonsense-Aware Navigation System for Intuitive Human-Robot Interaction","created":"2024-10-02","cited_by_count":3,"area":"offlinerl"},{"id":"2503.22886","title":"Task Tokens: A Flexible Approach to Adapting Behavior Foundation Models","created":"2025-03-28","cited_by_count":3,"area":"offlinerl"},{"id":"2504.17959","title":"CIVIL: Causal and Intuitive Visual Imitation Learning","created":"2025-04-24","cited_by_count":3,"area":"offlinerl"},{"id":"2506.12815","title":"TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models","created":"2025-06-15","cited_by_count":3,"area":"offlinerl"},{"id":"2508.17449","title":"Robotic Manipulation via Imitation Learning: Taxonomy, Evolution, Benchmark, and Challenges","created":"2025-08-24","cited_by_count":3,"area":"offlinerl"},{"id":"2509.18043","title":"Prepare Before You Act: Learning From Humans to Rearrange Initial States","created":"2025-09-22","cited_by_count":3,"area":"offlinerl"},{"id":"2604.00055","title":"Generalizable Dense Reward for Long-Horizon Robotic Tasks","created":"2026-03-31","cited_by_count":3,"area":"offlinerl"},{"id":"2605.09989","title":"StereoPolicy: Improving Robotic Manipulation Policies via Stereo Perception","created":"2026-05-11","cited_by_count":3,"area":"offlinerl"},{"id":"2403.18222","title":"Uncertainty-Aware Deployment of Pre-trained Language-Conditioned Imitation Learning Policies","created":"2024-03-27","cited_by_count":2,"area":"offlinerl"},{"id":"2410.01292","title":"Robust Imitation Learning for Mobile Manipulator Focusing on Task-Related Viewpoints and Regions","created":"2024-10-02","cited_by_count":2,"area":"offlinerl"},{"id":"2506.21057","title":"Knowledge-Driven Imitation Learning: Enabling Generalization Across Diverse Conditions","created":"2025-06-26","cited_by_count":2,"area":"offlinerl"},{"id":"2602.11464","title":"EasyMimic: A Low-Cost Framework for Robot Imitation Learning from Human Videos","created":"2026-02-12","cited_by_count":2,"area":"offlinerl"},{"id":"2401.09691","title":"Imitation Learning Inputting Image Feature to Each Layer of Neural Network","created":"2024-01-18","cited_by_count":1,"area":"offlinerl"},{"id":"2410.07787","title":"Mastering Contact-rich Tasks by Combining Soft and Rigid Robotics with Imitation Learning","created":"2024-10-10","cited_by_count":1,"area":"offlinerl"},{"id":"2505.05701","title":"Pretraining a Shared Q-Network for Data-Efficient Offline Reinforcement Learning","created":"2025-05-09","cited_by_count":1,"area":"offlinerl"},{"id":"2507.06404","title":"Learning to Evaluate Autonomous Behaviour in Human-Robot Interaction","created":"2025-07-08","cited_by_count":1,"area":"offlinerl"},{"id":"2507.10899","title":"Object-Centric Mobile Manipulation through SAM2-Guided Perception and Imitation Learning","created":"2025-07-15","cited_by_count":1,"area":"offlinerl"},{"id":"2508.00491","title":"HannesImitation: Grasping with the Hannes Prosthetic Hand via Imitation Learning","created":"2025-08-01","cited_by_count":1,"area":"offlinerl"},{"id":"2509.05368","title":"Long-Horizon Visual Imitation Learning via Plan and Code Reflection","created":"2025-09-04","cited_by_count":1,"area":"offlinerl"},{"id":"2511.07942","title":"Balance Equation-based Distributionally Robust Offline Imitation Learning","created":"2025-11-11","cited_by_count":1,"area":"offlinerl"},{"id":"2512.02609","title":"SAM2Grasp: Resolve Multi-modal Grasping via Prompt-conditioned Temporal Action Prediction","created":"2025-12-02","cited_by_count":1,"area":"offlinerl"},{"id":"2512.05953","title":"Correspondence-Oriented Imitation Learning: Flexible Visuomotor Control with 3D Conditioning","created":"2025-12-05","cited_by_count":1,"area":"offlinerl"},{"id":"2602.01018","title":"Offline Discovery of Interpretable Skills from Multi-Task Trajectories","created":"2026-02-01","cited_by_count":1,"area":"offlinerl"},{"id":"2603.08476","title":"LAR-MoE: Latent-Aligned Routing for Mixture of Experts in Robotic Imitation Learning","created":"2026-03-09","cited_by_count":1,"area":"offlinerl"},{"id":"2604.03613","title":"Human-Robot Copilot for Data-Efficient Imitation Learning","created":"2026-04-04","cited_by_count":1,"area":"offlinerl"},{"id":"2605.06470","title":"Hitting Time Isomorphism for Multi-Stage Planning with Foundation Policies","created":"2026-05-07","cited_by_count":1,"area":"offlinerl"},{"id":"2606.04825","title":"HapTile: A Haptic-Informed Vision-Tactile-Language-Action Dataset for Contact-Rich Imitation Learning","created":"2026-06-03","cited_by_count":1,"area":"offlinerl"},{"id":"2607.27549","title":"Cross-Embodiment Transfer via Behavior-Aligned Representations","created":"2026-07-30","cited_by_count":1,"area":"offlinerl"},{"id":"2609.30404","title":"POIL: Point-based One-Shot Imitation Learning with Stable Dynamical Systems","created":"2026-09-24","cited_by_count":1,"area":"offlinerl"},{"id":"2405.20351","title":"Imitating from auxiliary imperfect demonstrations via Adversarial Density Weighted Regression","created":"2024-05-28","cited_by_count":0,"area":"offlinerl"},{"id":"2503.05114","title":"Look Before You Leap: Using Serialized State Machine for Language Conditioned Robotic Manipulation","created":"2025-03-07","cited_by_count":0,"area":"offlinerl"},{"id":"2508.05077","title":"Analyzing the Impact of Multimodal Perception on Sample Complexity and Optimization Landscapes in Imitation Learning","created":"2025-08-07","cited_by_count":0,"area":"offlinerl"},{"id":"2509.23220","title":"GLUE: Global-Local Unified Encoding for Imitation Learning via Key-Patch Tracking","created":"2025-09-27","cited_by_count":0,"area":"offlinerl"},{"id":"2510.15189","title":"RM-RL: Role-Model Reinforcement Learning for Precise Robot Manipulation","created":"2025-10-16","cited_by_count":0,"area":"offlinerl"},{"id":"2601.04441","title":"Improving and Accelerating Offline RL in Large Discrete Action Spaces with Structured Policy Initialization","created":"2026-01-07","cited_by_count":0,"area":"offlinerl"}],"next_cursor":"100"}