{"total":100,"rows":[{"id":"2505.23458","title":"Diffusion Guidance Is a Controllable Policy Improvement Operator","created":"2025-05-29","cited_by_count":58,"area":"offlinerl"},{"id":"2506.04168","title":"Horizon Reduction Makes RL Scalable","created":"2025-06-04","cited_by_count":57,"area":"offlinerl"},{"id":"2503.08558","title":"Can We Detect Failures Without Failure Data? Uncertainty-Aware Runtime Failure Detection for Imitation Learning Policies","created":"2025-03-11","cited_by_count":52,"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":"2505.15725","title":"UAV-Flow Colosseo: A Real-World Benchmark for Flying-on-a-Word UAV Imitation Learning","created":"2025-05-21","cited_by_count":31,"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":"2505.22866","title":"Scaling Offline RL via Efficient and Expressive Shortcut Models","created":"2025-05-28","cited_by_count":27,"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":"2503.09722","title":"The Pitfalls of Imitation Learning when Actions are Continuous","created":"2025-03-12","cited_by_count":26,"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":"2501.14400","title":"SKIL: Semantic Keypoint Imitation Learning for Generalizable Data-efficient Manipulation","created":"2025-01-24","cited_by_count":21,"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":"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":"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":"2510.04354","title":"Reliable and Scalable Robot Policy Evaluation with Imperfect Simulators","created":"2025-10-05","cited_by_count":14,"area":"offlinerl"},{"id":"2505.07728","title":"Guiding Data Collection via Factored Scaling Curves","created":"2025-05-12","cited_by_count":12,"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":"2510.07730","title":"DEAS: DEtached value learning with Action Sequence for Scalable Offline RL","created":"2025-10-09","cited_by_count":10,"area":"offlinerl"},{"id":"2510.20406","title":"PointMapPolicy: Structured Point Cloud Processing for Multi-Modal Imitation Learning","created":"2025-10-23","cited_by_count":10,"area":"offlinerl"},{"id":"2503.11646","title":"Adversarial Data Collection: Human-Collaborative Perturbations for Efficient and Robust Robotic Imitation Learning","created":"2025-03-14","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":"2604.16683","title":"Rewind-IL: Online Failure Detection and State Respawning for Imitation Learning","created":"2026-04-17","cited_by_count":9,"area":"offlinerl"},{"id":"2507.18809","title":"Test-time Offline Reinforcement Learning on Goal-related Experience","created":"2025-07-24","cited_by_count":8,"area":"offlinerl"},{"id":"2512.16911","title":"Posterior Behavioral Cloning: Pretraining BC Policies for Efficient RL Finetuning","created":"2025-12-18","cited_by_count":8,"area":"offlinerl"},{"id":"2509.17053","title":"FILIC: Dual-Loop Force-Guided Imitation Learning with Impedance Torque Control for Contact-Rich Manipulation Tasks","created":"2025-09-21","cited_by_count":7,"area":"offlinerl"},{"id":"2510.18316","title":"MoMaGen: Generating Demonstrations under Soft and Hard Constraints for Multi-Step Bimanual Mobile Manipulation","created":"2025-10-21","cited_by_count":7,"area":"offlinerl"},{"id":"2502.12320","title":"Towards Fusing Point Cloud and Visual Representations for Imitation Learning","created":"2025-02-17","cited_by_count":6,"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":"2505.04860","title":"D-CODA: Diffusion for Coordinated Dual-Arm Data Augmentation","created":"2025-05-08","cited_by_count":5,"area":"offlinerl"},{"id":"2508.01131","title":"COLLAGE: Adaptive Fusion-based Retrieval for Augmented Policy Learning","created":"2025-08-02","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":"2504.13618","title":"On the Importance of Tactile Sensing for Imitation Learning: A Case Study on Robotic Match Lighting","created":"2025-04-18","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":"2511.04812","title":"Multimodal Diffusion Forcing for Forceful Manipulation","created":"2025-11-06","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":"2512.07371","title":"ESPADA: Execution Speedup via Semantics Aware Demonstration Data Downsampling for Imitation Learning","created":"2025-12-08","cited_by_count":4,"area":"offlinerl"},{"id":"2605.27079","title":"Trust Region Q Adjoint Matching","created":"2026-05-26","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":"2505.10760","title":"Counterfactual Behavior Cloning: Offline Imitation Learning from Imperfect Human Demonstrations","created":"2025-05-16","cited_by_count":3,"area":"offlinerl"},{"id":"2505.17389","title":"Bootstrapping Imitation Learning for Long-horizon Manipulation via Hierarchical Data Collection Space","created":"2025-05-23","cited_by_count":3,"area":"offlinerl"},{"id":"2506.15157","title":"Robust Instant Policy: Leveraging Student's t-Regression Model for Robust In-context Imitation Learning of Robot Manipulation","created":"2025-06-18","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":"2509.17057","title":"RoboManipBaselines: A Unified Framework for Imitation Learning in Robotic Manipulation across Real and Simulation Environments","created":"2025-09-21","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":"2509.19454","title":"ROPA: Synthetic Robot Pose Generation for RGB-D Bimanual Data Augmentation","created":"2025-09-23","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":"2605.07943","title":"TAVIS: A Benchmark for Egocentric Active Vision and Anticipatory Gaze in Imitation Learning","created":"2026-05-08","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":"2605.12236","title":"TMRL: Diffusion Timestep-Modulated Pretraining Enables Exploration for Efficient Policy Finetuning","created":"2026-05-12","cited_by_count":3,"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":"2510.03706","title":"EmbodiSwap for Zero-Shot Robot Imitation Learning","created":"2025-10-04","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":"2603.08399","title":"A Recipe for Stable Offline Multi-agent Reinforcement Learning","created":"2026-03-09","cited_by_count":2,"area":"offlinerl"},{"id":"2605.11151","title":"RankQ: Offline-to-Online Reinforcement Learning via Self-Supervised Action Ranking","created":"2026-05-11","cited_by_count":2,"area":"offlinerl"},{"id":"2607.13033","title":"DenseReward: Dense Reward Learning via Failure Synthesis for Robotic Manipulation","created":"2026-07-14","cited_by_count":2,"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":"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":"2603.09056","title":"Quality over Quantity: Demonstration Curation via Influence Functions for Data-Centric Robot Learning","created":"2026-03-10","cited_by_count":1,"area":"offlinerl"},{"id":"2604.10165","title":"MoRI: Mixture of RL and IL Experts for Long-Horizon Manipulation Tasks","created":"2026-04-11","cited_by_count":1,"area":"offlinerl"},{"id":"2604.10677","title":"LIDEA: Human-to-Robot Imitation Learning via Implicit Feature Distillation and Explicit Geometry Alignment","created":"2026-04-12","cited_by_count":1,"area":"offlinerl"},{"id":"2605.01778","title":"Adversarial Imitation Learning with General Function Approximation: Theoretical Analysis and Practical Algorithms","created":"2026-05-03","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":"2605.20648","title":"Jointly Learning Predicates and Actions Enables Zero-Shot Skill Composition","created":"2026-05-20","cited_by_count":1,"area":"offlinerl"},{"id":"2605.22493","title":"Understanding Multimodal Failure in Action-Chunking Behavioral Cloning","created":"2026-05-21","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":"2608.20784","title":"Rethinking Demonstration Unlearning in Imitation Learning for Robotics","created":"2026-08-21","cited_by_count":1,"area":"offlinerl"},{"id":"2505.20350","title":"Decision Flow Policy Optimization","created":"2025-05-26","cited_by_count":0,"area":"offlinerl"},{"id":"2509.23111","title":"Liaohe-CobotMagic-PnP: an Imitation Learning Dataset of Intelligent Robot for Industrial Applications","created":"2025-09-27","cited_by_count":0,"area":"offlinerl"},{"id":"2509.26294","title":"Noise-Guided Transport for Imitation Learning","created":"2025-09-30","cited_by_count":0,"area":"offlinerl"},{"id":"2510.00726","title":"CroSTAta: Cross-State Transition Attention Transformer for Robotic Manipulation","created":"2025-10-01","cited_by_count":0,"area":"offlinerl"},{"id":"2510.11307","title":"FOSSIL: Harnessing Feedback on Suboptimal Samples for Data-Efficient Generalisation with Imitation Learning for Embodied Vision-and-Language Tasks","created":"2025-10-13","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":"2602.06512","title":"Beyond the Majority: Long-tail Imitation Learning for Robotic Manipulation","created":"2026-02-06","cited_by_count":0,"area":"offlinerl"},{"id":"2602.21684","title":"Primary-Fine Decoupling for Action Generation in Robotic Imitation","created":"2026-02-25","cited_by_count":0,"area":"offlinerl"},{"id":"2603.03960","title":"Structural Action Transformer for 3D Dexterous Manipulation","created":"2026-03-04","cited_by_count":0,"area":"offlinerl"},{"id":"2603.20538","title":"Understanding Behavior Cloning with Action Quantization","created":"2026-03-20","cited_by_count":0,"area":"offlinerl"},{"id":"2603.22713","title":"Non-Adversarial Imitation Learning Provably Free of Compounding Errors: The Value Flow Mechanism","created":"2026-03-24","cited_by_count":0,"area":"offlinerl"},{"id":"2604.03759","title":"Build on Priors: Vision--Language--Guided Neuro-Symbolic Imitation Learning for Data-Efficient Real-World Robot Manipulation","created":"2026-04-04","cited_by_count":0,"area":"offlinerl"},{"id":"2605.12162","title":"X-Imitator: Spatial-Aware Imitation Learning via Bidirectional Action-Pose Interaction","created":"2026-05-12","cited_by_count":0,"area":"offlinerl"},{"id":"2605.23847","title":"Instrumentation for Imitation Learning: Enhancing Training Datasets for Clothes Hanger Insertion","created":"2026-05-22","cited_by_count":0,"area":"offlinerl"},{"id":"2605.28736","title":"Imitation Learning for Robot Assistance in Open Surgery: A Multi-Policy Evaluation on Suture Following","created":"2026-05-27","cited_by_count":0,"area":"offlinerl"},{"id":"2606.09615","title":"DexPIE: Stable Dexterous Policy Improvement from Real-World Experience","created":"2026-06-08","cited_by_count":0,"area":"offlinerl"},{"id":"2607.09866","title":"Robo-ValueRL: Reliable Value Estimation for Offline-to-Online Reinforcement Learning","created":"2026-07-10","cited_by_count":0,"area":"offlinerl"},{"id":"2608.16058","title":"SurgVIL: Scaling Surgical Robot Imitation Learning with Open-source Surgical Videos","created":"2026-08-17","cited_by_count":0,"area":"offlinerl"},{"id":"2608.20208","title":"RoMAN-Flow: Taming Autoregressive Normalizing Flows for Offline Reinforcement Learning in Robotic Manipulation","created":"2026-08-20","cited_by_count":0,"area":"offlinerl"},{"id":"2608.22591","title":"WorldToken: Time-First Sequence Modeling for Robotic Imitation Learning","created":"2026-08-23","cited_by_count":0,"area":"offlinerl"},{"id":"2609.01453","title":"Does Imitation Learning Preserve Temporal Robustness in Dexterous Manipulation? An Expert-Learner Comparison Across Task Execution Speeds","created":"2026-09-01","cited_by_count":0,"area":"offlinerl"},{"id":"2609.09630","title":"JEPA Policy: Diffusion-Free Imitation Learning via Paired Action and Future Representation Prediction","created":"2026-09-09","cited_by_count":0,"area":"offlinerl"},{"id":"2609.21550","title":"OneBid: A Unified Auto-Bidding Foundation Model for Diverse oCPX Advertising Scenarios","created":"2026-09-18","cited_by_count":0,"area":"offlinerl"},{"id":"2609.29000","title":"Learning from Mixed-Quality Deployment Experience for Robot Manipulation","created":"2026-09-24","cited_by_count":0,"area":"offlinerl"},{"id":"2609.31207","title":"Enabling a Unified Cross-Domain Representation for Two-Finger Gripper Manipulation via Interaction-Centric Modeling","created":"2026-09-25","cited_by_count":0,"area":"offlinerl"},{"id":"2609.32762","title":"An Empirical Study on What Matters for Viewpoint-Generalizable Policies in Visual Imitation Learning","created":"2026-09-26","cited_by_count":0,"area":"offlinerl"},{"id":"2609.35375","title":"From Pixel to Poses: Object-centric Tool Manipulation Learning from Human Demonstrations","created":"2026-09-28","cited_by_count":0,"area":"offlinerl"},{"id":"2610.05882","title":"Mulligan: Performance-Guided Data Collection for Efficient On-Robot Learning","created":"2026-10-05","cited_by_count":0,"area":"offlinerl"},{"id":"2610.17748","title":"I3L: Iterative Interactive Imitation Learning for Whole-Body Mobile Manipulation","created":"2026-10-13","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}