{"list":"other","total":52,"rows":[{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2504.16054","title":"$\\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization","created":"2025-04-22","cited_by_count":1761},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2203.12601","title":"R3M: A Universal Visual Representation for Robot Manipulation","created":"2022-03-23","cited_by_count":694},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490},{"id":"2602.15922","title":"World Action Models are Zero-shot Policies","created":"2026-02-17","cited_by_count":465},{"id":"2505.06111","title":"UniVLA: Learning to Act Anywhere with Task-centric Latent Actions","created":"2025-05-09","cited_by_count":410},{"id":"2210.00030","title":"VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training","created":"2022-09-30","cited_by_count":395},{"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":"2312.13139","title":"Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation","created":"2023-12-20","cited_by_count":364},{"id":"2410.11758","title":"Latent Action Pretraining from Videos","created":"2024-10-15","cited_by_count":321},{"id":"2505.11709","title":"EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video","created":"2025-05-16","cited_by_count":211},{"id":"2406.08858","title":"OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning","created":"2024-06-13","cited_by_count":189},{"id":"2406.10454","title":"HumanPlus: Humanoid Shadowing and Imitation from Humans","created":"2024-06-15","cited_by_count":185},{"id":"2410.24221","title":"EgoMimic: Scaling Imitation Learning via Egocentric Video","created":"2024-10-31","cited_by_count":175},{"id":"2403.04436","title":"Learning Human-to-Humanoid Real-Time Whole-Body Teleoperation","created":"2024-03-07","cited_by_count":130},{"id":"2502.01143","title":"ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills","created":"2025-02-03","cited_by_count":130},{"id":"2505.02833","title":"TWIST: Teleoperated Whole-Body Imitation System","created":"2025-05-05","cited_by_count":101},{"id":"2511.07820","title":"SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control","created":"2025-11-11","cited_by_count":101},{"id":"2602.16710","title":"EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data","created":"2026-02-18","cited_by_count":94},{"id":"2412.13196","title":"ExBody2: Advanced Expressive Humanoid Whole-Body Control","created":"2024-12-17","cited_by_count":88},{"id":"2506.14770","title":"GMT: General Motion Tracking for Humanoid Whole-Body Control","created":"2025-06-17","cited_by_count":83},{"id":"2503.13441","title":"Humanoid Policy ~ Human Policy","created":"2025-03-17","cited_by_count":78},{"id":"2502.13013","title":"HOMIE: Humanoid Loco-Manipulation with Isomorphic Exoskeleton Cockpit","created":"2025-02-18","cited_by_count":76},{"id":"2510.02252","title":"Retargeting Matters: General Motion Retargeting for Humanoid Motion Tracking","created":"2025-10-02","cited_by_count":75},{"id":"2501.10018","title":"DiffuEraser: A Diffusion Model for Video Inpainting","created":"2025-01-17","cited_by_count":72},{"id":"2509.26633","title":"OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipulation and Scene Interaction","created":"2025-09-30","cited_by_count":71},{"id":"2505.03729","title":"Visual Imitation Enables Contextual Humanoid Control","created":"2025-05-06","cited_by_count":68},{"id":"2505.21864","title":"DexUMI: Using Human Hand as the Universal Manipulation Interface for Dexterous Manipulation","created":"2025-05-28","cited_by_count":66},{"id":"2505.03738","title":"AMO: Adaptive Motion Optimization for Hyper-Dexterous Humanoid Whole-Body Control","created":"2025-05-06","cited_by_count":51},{"id":"2409.03403","title":"RoVi-Aug: Robot and Viewpoint Augmentation for Cross-Embodiment Robot Learning","created":"2024-09-05","cited_by_count":46},{"id":"2512.22414","title":"Emergence of Human to Robot Transfer in Vision-Language-Action Models","created":"2025-12-27","cited_by_count":42},{"id":"2510.05070","title":"ResMimic: From General Motion Tracking to Humanoid Whole-body Loco-Manipulation via Residual Learning","created":"2025-10-06","cited_by_count":41},{"id":"2409.19499","title":"FastUMI: A Scalable and Hardware-Independent Universal Manipulation Interface with Dataset","created":"2024-09-29","cited_by_count":40},{"id":"2505.07813","title":"DexWild: Dexterous Human Interactions for In-the-Wild Robot Policies","created":"2025-05-12","cited_by_count":38},{"id":"2406.00439","title":"Learning Manipulation by Predicting Interaction","created":"2024-06-01","cited_by_count":37},{"id":"2402.19249","title":"Mirage: Cross-Embodiment Zero-Shot Policy Transfer with Cross-Painting","created":"2024-02-29","cited_by_count":36},{"id":"2512.11047","title":"WholeBodyVLA: Towards Unified Latent VLA for Whole-Body Loco-Manipulation Control","created":"2025-12-11","cited_by_count":36},{"id":"2511.09484","title":"SPIDER: Scalable Physics-Informed Dexterous Retargeting","created":"2025-11-12","cited_by_count":32},{"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},{"id":"2509.19626","title":"EgoBridge: Domain Adaptation for Generalizable Imitation from Egocentric Human Data","created":"2025-09-23","cited_by_count":29},{"id":"2603.12263","title":"$\\Psi_0$: An Open Foundation Model Towards Universal Humanoid Loco-Manipulation","created":"2026-03-12","cited_by_count":27},{"id":"2509.17759","title":"MotionTrans: Human VR Data Enable Motion-Level Learning for Robotic Manipulation Policies","created":"2025-09-22","cited_by_count":23},{"id":"2602.01067","title":"A Systematic Study of Data Modalities and Strategies for Co-training Large Behavior Models for Robot Manipulation","created":"2026-02-01","cited_by_count":22},{"id":"2602.10106","title":"EgoHumanoid: Unlocking In-the-Wild Loco-Manipulation with Robot-Free Egocentric Demonstration","created":"2026-02-10","cited_by_count":21},{"id":"2603.03243","title":"HoMMI: Learning Whole-Body Mobile Manipulation from Human Demonstrations","created":"2026-03-03","cited_by_count":16},{"id":"2602.06643","title":"Humanoid Manipulation Interface: Humanoid Whole-Body Manipulation from Robot-Free Demonstrations","created":"2026-02-06","cited_by_count":12},{"id":"2511.17373","title":"Agility Meets Stability: Versatile Humanoid Control with Heterogeneous Data","created":"2025-11-21","cited_by_count":11},{"id":"2603.09170","title":"ZeroWBC: Learning Natural Whole-Body Humanoid Interaction from Human Egocentric Data","created":"2026-03-10","cited_by_count":8},{"id":"2510.03022","title":"HumanoidExo: Scalable Whole-Body Humanoid Manipulation via Wearable Exoskeleton","created":"2025-10-03","cited_by_count":4},{"id":"2605.03452","title":"BifrostUMI: Bridging Robot-Free Demonstrations and Humanoid Whole-Body Manipulation","created":"2026-05-05","cited_by_count":3},{"id":"2609.05994","title":"GLoRI: Closed-Loop Whole-Body Tracking with Global-Local Reference Interaction for Humanoid Loco-Manipulation","created":"2026-09-05","cited_by_count":1}],"next_cursor":null}