{"total":145,"rows":[{"id":"2501.09747","title":"FAST: Efficient Action Tokenization for Vision-Language-Action Models","created":"2025-01-16","cited_by_count":665,"area":"vla"},{"id":"2410.00425","title":"ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI","created":"2024-10-01","cited_by_count":229,"area":null},{"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":"2410.18647","title":"Data Scaling Laws in Imitation Learning for Robotic Manipulation","created":"2024-10-24","cited_by_count":145,"area":"offlinerl"},{"id":"2507.12440","title":"EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos","created":"2025-07-16","cited_by_count":128,"area":"vla"},{"id":"2504.13059","title":"RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins","created":"2025-04-17","cited_by_count":121,"area":null},{"id":"2410.24185","title":"DexMimicGen: Automated Data Generation for Bimanual Dexterous Manipulation via Imitation Learning","created":"2024-10-31","cited_by_count":116,"area":"offlinerl"},{"id":"2505.02833","title":"TWIST: Teleoperated Whole-Body Imitation System","created":"2025-05-05","cited_by_count":101,"area":null},{"id":"2510.07077","title":"Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications","created":"2025-10-08","cited_by_count":84,"area":"mllm"},{"id":"2503.13441","title":"Humanoid Policy ~ Human Policy","created":"2025-03-17","cited_by_count":78,"area":null},{"id":"2502.13013","title":"HOMIE: Humanoid Loco-Manipulation with Isomorphic Exoskeleton Cockpit","created":"2025-02-18","cited_by_count":76,"area":null},{"id":"2502.20390","title":"InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactions","created":"2025-02-27","cited_by_count":72,"area":null},{"id":"2409.02920","title":"RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins (early version)","created":"2024-09-04","cited_by_count":69,"area":null},{"id":"2410.11792","title":"OKAMI: Teaching Humanoid Robots Manipulation Skills through Single Video Imitation","created":"2024-10-15","cited_by_count":67,"area":null},{"id":"2503.21860","title":"ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learning","created":"2025-03-27","cited_by_count":66,"area":null},{"id":"2604.07607","title":"EgoVerse: An Egocentric Human Dataset for Robot Learning from Around the World","created":"2026-04-08","cited_by_count":57,"area":null},{"id":"2504.18904","title":"RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning","created":"2025-04-26","cited_by_count":54,"area":"offlinerl"},{"id":"2410.10803","title":"Generalizable Humanoid Manipulation with 3D Diffusion Policies","created":"2024-10-14","cited_by_count":52,"area":"diffusion"},{"id":"2412.07773","title":"Mobile-TeleVision: Predictive Motion Priors for Humanoid Whole-Body Control","created":"2024-12-10","cited_by_count":51,"area":null},{"id":"2505.03738","title":"AMO: Adaptive Motion Optimization for Hyper-Dexterous Humanoid Whole-Body Control","created":"2025-05-06","cited_by_count":51,"area":null},{"id":"2509.01819","title":"ManiFlow: A General Robot Manipulation Policy via Consistency Flow Training","created":"2025-09-01","cited_by_count":49,"area":"diffusion"},{"id":"2502.20396","title":"Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids","created":"2025-02-27","cited_by_count":48,"area":"deeprl"},{"id":"2502.08378","title":"Learning Humanoid Standing-up Control across Diverse Postures","created":"2025-02-12","cited_by_count":46,"area":null},{"id":"2503.24361","title":"Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulation","created":"2025-03-31","cited_by_count":46,"area":null},{"id":"2409.05865","title":"Robot Utility Models: General Policies for Zero-Shot Deployment in New Environments","created":"2024-09-09","cited_by_count":44,"area":null},{"id":"2511.02832","title":"TWIST2: Scalable, Portable, and Holistic Humanoid Data Collection System","created":"2025-11-04","cited_by_count":44,"area":null},{"id":"2505.07813","title":"DexWild: Dexterous Human Interactions for In-the-Wild Robot Policies","created":"2025-05-12","cited_by_count":38,"area":null},{"id":"2505.24853","title":"DexMachina: Functional Retargeting for Bimanual Dexterous Manipulation","created":"2025-05-30","cited_by_count":37,"area":null},{"id":"2410.07554","title":"ForceMimic: Force-Centric Imitation Learning with Force-Motion Capture System for Contact-Rich Manipulation","created":"2024-10-10","cited_by_count":36,"area":"offlinerl"},{"id":"2512.11047","title":"WholeBodyVLA: Towards Unified Latent VLA for Whole-Body Loco-Manipulation Control","created":"2025-12-11","cited_by_count":36,"area":null},{"id":"2408.11805","title":"ACE: A Cross-Platform Visual-Exoskeletons System for Low-Cost Dexterous Teleoperation","created":"2024-08-21","cited_by_count":34,"area":null},{"id":"2410.08464","title":"ARCap: Collecting High-quality Human Demonstrations for Robot Learning with Augmented Reality Feedback","created":"2024-10-11","cited_by_count":31,"area":"offlinerl"},{"id":"2503.05652","title":"BEHAVIOR Robot Suite: Streamlining Real-World Whole-Body Manipulation for Everyday Household Activities","created":"2025-03-07","cited_by_count":31,"area":null},{"id":"2410.11825","title":"Learning Smooth Humanoid Locomotion through Lipschitz-Constrained Policies","created":"2024-10-15","cited_by_count":30,"area":"deeprl"},{"id":"2602.03310","title":"RDT2: Exploring the Scaling Limit of UMI Data Towards Zero-Shot Cross-Embodiment Generalization","created":"2026-02-03","cited_by_count":30,"area":"vla"},{"id":"2511.15704","title":"In-N-On: Scaling Egocentric Manipulation with in-the-wild and on-task Data","created":"2025-11-19","cited_by_count":26,"area":null},{"id":"2506.10968","title":"Eye, Robot: Learning to Look to Act with a BC-RL Perception-Action Loop","created":"2025-06-12","cited_by_count":25,"area":null},{"id":"2510.08807","title":"Humanoid Everyday: A Comprehensive Robotic Dataset for Open-World Humanoid Manipulation","created":"2025-10-09","cited_by_count":25,"area":null},{"id":"2507.01961","title":"AC-DiT: Adaptive Coordination Diffusion Transformer for Mobile Manipulation","created":"2025-07-02","cited_by_count":23,"area":"diffusion"},{"id":"2412.10447","title":"TidyBot++: An Open-Source Holonomic Mobile Manipulator for Robot Learning","created":"2024-12-11","cited_by_count":22,"area":"offlinerl"},{"id":"2503.12533","title":"Being-0: A Humanoid Robotic Agent with Vision-Language Models and Modular Skills","created":"2025-03-16","cited_by_count":22,"area":"agents"},{"id":"2504.03515","title":"Dexterous Manipulation through Imitation Learning: A Survey","created":"2025-04-04","cited_by_count":21,"area":"offlinerl"},{"id":"2504.18829","title":"Dexonomy: Synthesizing All Dexterous Grasp Types in a Grasp Taxonomy","created":"2025-04-26","cited_by_count":20,"area":null},{"id":"2509.04441","title":"DEXOP: A Device for Robotic Transfer of Dexterous Human Manipulation","created":"2025-09-04","cited_by_count":19,"area":null},{"id":"2510.01607","title":"ActiveUMI: Robotic Manipulation with Active Perception from Robot-Free Human Demonstrations","created":"2025-10-02","cited_by_count":19,"area":null},{"id":"2510.20813","title":"GSWorld: Closed-Loop Photo-Realistic Simulation Suite for Robotic Manipulation","created":"2025-10-23","cited_by_count":19,"area":null},{"id":"2412.00174","title":"SOLAMI: Social Vision-Language-Action Modeling for Immersive Interaction with 3D Autonomous Characters","created":"2024-11-29","cited_by_count":18,"area":null},{"id":"2506.11948","title":"SAIL: Faster-than-Demonstration Execution of Imitation Learning Policies","created":"2025-06-13","cited_by_count":18,"area":"offlinerl"},{"id":"2412.06779","title":"AnyBimanual: Transferring Unimanual Policy for General Bimanual Manipulation","created":"2024-12-09","cited_by_count":16,"area":null},{"id":"2412.17730","title":"Mimicking-Bench: A Benchmark for Generalizable Humanoid-Scene Interaction Learning via Human Mimicking","created":"2024-12-23","cited_by_count":16,"area":null},{"id":"2505.01458","title":"A Survey of Robotic Navigation and Manipulation with Physics Simulators in the Era of Embodied AI","created":"2025-05-01","cited_by_count":16,"area":null},{"id":"2503.07541","title":"Geometric Retargeting: A Principled, Ultrafast Neural Hand Retargeting Algorithm","created":"2025-03-10","cited_by_count":14,"area":null},{"id":"2602.02473","title":"HumanX: Toward Agile and Generalizable Humanoid Interaction Skills from Human Videos","created":"2026-02-02","cited_by_count":14,"area":null},{"id":"2602.06643","title":"Humanoid Manipulation Interface: Humanoid Whole-Body Manipulation from Robot-Free Demonstrations","created":"2026-02-06","cited_by_count":12,"area":null},{"id":"2501.04169","title":"Learning to Transfer Human Hand Skills for Robot Manipulations","created":"2025-01-07","cited_by_count":11,"area":null},{"id":"2502.03206","title":"A Unified and General Humanoid Whole-Body Controller for Versatile Locomotion","created":"2025-02-05","cited_by_count":11,"area":null},{"id":"2507.15833","title":"Look, Focus, Act: Efficient and Robust Robot Learning via Human Gaze and Foveated Vision Transformers","created":"2025-07-21","cited_by_count":11,"area":null},{"id":"2509.09671","title":"Dexplore: Scalable Neural Control for Dexterous Manipulation from Reference-Scoped Exploration","created":"2025-09-11","cited_by_count":11,"area":null},{"id":"2510.14930","title":"VT-Refine: Learning Bimanual Assembly with Visuo-Tactile Feedback via Simulation Fine-Tuning","created":"2025-10-16","cited_by_count":11,"area":"offlinerl"},{"id":"2506.16475","title":"Human2LocoMan: Learning Versatile Quadrupedal Manipulation with Human Pretraining","created":"2025-06-19","cited_by_count":9,"area":null},{"id":"2510.08556","title":"DexNDM: Closing the Reality Gap for Dexterous In-Hand Rotation via Joint-Wise Neural Dynamics Model","created":"2025-10-09","cited_by_count":9,"area":null},{"id":"2511.00139","title":"End-to-End Dexterous Arm-Hand VLA Policies via Shared Autonomy: VR Teleoperation Augmented by Autonomous Hand VLA Policy for Efficient Data Collection","created":"2025-10-31","cited_by_count":9,"area":"vla"},{"id":"2410.00231","title":"Helpful DoggyBot: Open-World Object Fetching using Legged Robots and Vision-Language Models","created":"2024-09-30","cited_by_count":8,"area":null},{"id":"2508.00097","title":"XRoboToolkit: A Cross-Platform Framework for Robot Teleoperation","created":"2025-07-31","cited_by_count":8,"area":null},{"id":"2603.12193","title":"SaPaVe: Towards Active Perception and Manipulation in Vision-Language-Action Models for Robotics","created":"2026-03-12","cited_by_count":8,"area":"vla"},{"id":"2505.18793","title":"Genie Centurion: Accelerating Scalable Real-World Robot Training with Human Rewind-and-Refine Guidance","created":"2025-05-24","cited_by_count":7,"area":"vla"},{"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":"2409.20548","title":"Robi Butler: Multimodal Remote Interaction with a Household Robot Assistant","created":"2024-09-30","cited_by_count":6,"area":null},{"id":"2411.15131","title":"WildLMa: Long Horizon Loco-Manipulation in the Wild","created":"2024-11-22","cited_by_count":6,"area":"offlinerl"},{"id":"2510.08547","title":"R2RGEN: Real-to-Real 3D Data Generation for Spatially Generalized Manipulation","created":"2025-10-09","cited_by_count":6,"area":null},{"id":"2605.30338","title":"REST3D: Reconstructing Physically Stable 3D Scenes from a Single Image","created":"2026-05-28","cited_by_count":6,"area":null},{"id":"2606.06194","title":"ActiveMimic: Egocentric Video Pretraining with Active Perception","created":"2026-06-04","cited_by_count":6,"area":null},{"id":"2607.24744","title":"Data Pyramid for Embodied Manipulation: A Survey","created":"2026-07-27","cited_by_count":6,"area":null},{"id":"2505.12278","title":"Emergent Active Perception and Dexterity of Simulated Humanoids from Visual Reinforcement Learning","created":"2025-05-18","cited_by_count":5,"area":"deeprl"},{"id":"2505.18780","title":"DreamPolicy: A Unified World-model Policy for Scalable Humanoid Locomotion","created":"2025-05-24","cited_by_count":5,"area":"wm"},{"id":"2507.20217","title":"Humanoid Occupancy: Enabling A Generalized Multimodal Occupancy Perception System on Humanoid Robots","created":"2025-07-27","cited_by_count":5,"area":null},{"id":"2603.08122","title":"Towards Human-Like Manipulation through RL-Augmented Teleoperation and Mixture-of-Dexterous-Experts VLA","created":"2026-03-09","cited_by_count":5,"area":"vla"},{"id":"2502.13134","title":"RHINO: Learning Real-Time Humanoid-Human-Object Interaction from Human Demonstrations","created":"2025-02-18","cited_by_count":4,"area":null},{"id":"2503.15897","title":"Learning 3D Scene Analogies with Neural Contextual Scene Maps","created":"2025-03-20","cited_by_count":4,"area":null},{"id":"2510.05684","title":"D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI","created":"2025-10-07","cited_by_count":4,"area":null},{"id":"2510.20774","title":"FieldGen: From Teleoperated Pre-Manipulation Trajectories to Field-Guided Data Generation","created":"2025-10-23","cited_by_count":4,"area":null},{"id":"2512.25072","title":"Coordinated Humanoid Manipulation with Choice Policies","created":"2025-12-31","cited_by_count":4,"area":null},{"id":"2602.01939","title":"Towards Exploratory and Focused Manipulation with Bimanual Active Perception: A New Problem, Benchmark and Strategy","created":"2026-02-02","cited_by_count":4,"area":null},{"id":"2602.09017","title":"Contact-Anchored Policies: Contact Conditioning Creates Strong Robot Utility Models","created":"2026-02-09","cited_by_count":4,"area":null},{"id":"2603.05504","title":"RoboPocket: Improve Robot Policies Instantly with Your Phone","created":"2026-03-05","cited_by_count":4,"area":"offlinerl"},{"id":"2605.00244","title":"Lucid-XR: An Extended-Reality Data Engine for Robotic Manipulation","created":"2026-04-30","cited_by_count":4,"area":null},{"id":"2606.10244","title":"YUBI: Yielding Universal Bidigital Interface for Bimanual Dexterous Manipulation at Scale","created":"2026-06-08","cited_by_count":4,"area":null},{"id":"2607.11874","title":"A Minimalist Retargeting-Guided Reinforcement Learning Recipe for Dexterous Manipulation","created":"2026-07-13","cited_by_count":4,"area":"deeprl"},{"id":"2607.24159","title":"DeVA: Decoupled Video-Action Model with physical guidance for robot policy learning","created":"2026-07-27","cited_by_count":4,"area":null},{"id":"2608.02257","title":"Learning Panorama-Aware VLA for Mobile Manipulation with Whole-Body Teleoperation","created":"2026-08-03","cited_by_count":4,"area":"vla"},{"id":"2501.15071","title":"Gaze-Guided Task Decomposition for Imitation Learning in Robotic Manipulation","created":"2025-01-25","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":"2602.02960","title":"Embodiment-Aware Generalist Specialist Distillation for Unified Humanoid Whole-Body Control","created":"2026-02-03","cited_by_count":3,"area":"deeprl"},{"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":"2502.03297","title":"IRIS: An Immersive Robot Interaction System","created":"2025-02-05","cited_by_count":2,"area":null},{"id":"2502.18121","title":"Enhancing Reusability of Learned Skills for Robot Manipulation via Gaze Information and Motion Bottlenecks","created":"2025-02-25","cited_by_count":2,"area":null},{"id":"2505.12748","title":"TeleOpBench: A Simulator-Centric Benchmark for Dual-Arm Dexterous Teleoperation","created":"2025-05-19","cited_by_count":2,"area":null},{"id":"2505.24156","title":"Towards a Generalizable Bimanual Foundation Policy via Flow-based Video Prediction","created":"2025-05-30","cited_by_count":2,"area":"vla"},{"id":"2509.11839","title":"TrajBooster: Boosting Humanoid Whole-Body Manipulation via Trajectory-Centric Learning","created":"2025-09-15","cited_by_count":2,"area":"vla"}],"next_cursor":"100"}