{"total":187,"rows":[{"id":"2406.08858","title":"OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning","created":"2024-06-13","cited_by_count":189,"area":null},{"id":"2408.03539","title":"Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes","created":"2024-08-07","cited_by_count":176,"area":"deeprl"},{"id":"2508.08241","title":"BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion","created":"2025-08-11","cited_by_count":165,"area":"diffusion"},{"id":"2402.16796","title":"Expressive Whole-Body Control for Humanoid Robots","created":"2024-02-26","cited_by_count":139,"area":null},{"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,"area":null},{"id":"2505.02833","title":"TWIST: Teleoperated Whole-Body Imitation System","created":"2025-05-05","cited_by_count":101,"area":null},{"id":"2401.16889","title":"Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control","created":"2024-01-30","cited_by_count":99,"area":"deeprl"},{"id":"2412.13196","title":"ExBody2: Advanced Expressive Humanoid Whole-Body Control","created":"2024-12-17","cited_by_count":88,"area":null},{"id":"2402.19469","title":"Humanoid Locomotion as Next Token Prediction","created":"2024-02-29","cited_by_count":69,"area":null},{"id":"2505.03729","title":"Visual Imitation Enables Contextual Humanoid Control","created":"2025-05-06","cited_by_count":68,"area":null},{"id":"2405.10315","title":"TRANSIC: Sim-to-Real Policy Transfer by Learning from Online Correction","created":"2024-05-16","cited_by_count":59,"area":null},{"id":"2406.20083","title":"PoliFormer: Scaling On-Policy RL with Transformers Results in Masterful Navigators","created":"2024-06-28","cited_by_count":58,"area":"deeprl"},{"id":"2509.19301","title":"Residual Off-Policy RL for Finetuning Behavior Cloning Policies","created":"2025-09-23","cited_by_count":55,"area":null},{"id":"2410.10803","title":"Generalizable Humanoid Manipulation with 3D Diffusion Policies","created":"2024-10-14","cited_by_count":52,"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":"2308.12517","title":"Not Only Rewards But Also Constraints: Applications on Legged Robot Locomotion","created":"2023-08-24","cited_by_count":47,"area":null},{"id":"2502.08378","title":"Learning Humanoid Standing-up Control across Diverse Postures","created":"2025-02-12","cited_by_count":46,"area":null},{"id":"2409.06366","title":"One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotion","created":"2024-09-10","cited_by_count":43,"area":"deeprl"},{"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,"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":"2412.14172","title":"Learning from Massive Human Videos for Universal Humanoid Pose Control","created":"2024-12-18","cited_by_count":29,"area":null},{"id":"2512.03422","title":"What Is The Best 3D Scene Representation for Robotics? From Geometric to Foundation Models","created":"2025-12-03","cited_by_count":29,"area":null},{"id":"2505.07294","title":"HuB: Learning Extreme Humanoid Balance","created":"2025-05-12","cited_by_count":28,"area":null},{"id":"2410.03654","title":"Learning Humanoid Locomotion over Challenging Terrain","created":"2024-10-04","cited_by_count":26,"area":null},{"id":"2502.12152","title":"Learning Getting-Up Policies for Real-World Humanoid Robots","created":"2025-02-17","cited_by_count":26,"area":null},{"id":"2510.20808","title":"The Reality Gap in Robotics: Challenges, Solutions, and Best Practices","created":"2025-10-23","cited_by_count":24,"area":null},{"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":"2404.02817","title":"A Survey of Optimization-based Task and Motion Planning: From Classical To Learning Approaches","created":"2024-04-03","cited_by_count":20,"area":null},{"id":"2412.12089","title":"Stabilizing Reinforcement Learning in Differentiable Multiphysics Simulation","created":"2024-12-16","cited_by_count":20,"area":"deeprl"},{"id":"2509.23745","title":"LocoFormer: Generalist Locomotion via Long-context Adaptation","created":"2025-09-28","cited_by_count":20,"area":null},{"id":"2303.03724","title":"Learning Bipedal Walking for Humanoids with Current Feedback","created":"2023-03-07","cited_by_count":18,"area":null},{"id":"2405.02425","title":"Learning Robot Soccer from Egocentric Vision with Deep Reinforcement Learning","created":"2024-05-03","cited_by_count":17,"area":"deeprl"},{"id":"2412.14401","title":"The One RING: a Robotic Indoor Navigation Generalist","created":"2024-12-18","cited_by_count":16,"area":null},{"id":"2505.05753","title":"Towards Embodiment Scaling Laws in Robot Locomotion","created":"2025-05-09","cited_by_count":16,"area":null},{"id":"2509.14353","title":"DreamControl: Human-Inspired Whole-Body Humanoid Control for Scene Interaction via Guided Diffusion","created":"2025-09-17","cited_by_count":15,"area":"diffusion"},{"id":"2502.10894","title":"Bridging the Sim-to-Real Gap for Athletic Loco-Manipulation","created":"2025-02-15","cited_by_count":13,"area":null},{"id":"2502.16230","title":"Learning Humanoid Locomotion with World Model Reconstruction","created":"2025-02-22","cited_by_count":13,"area":"wm"},{"id":"2509.16638","title":"KungfuBot2: Learning Versatile Motion Skills for Humanoid Whole-Body Control","created":"2025-09-20","cited_by_count":13,"area":null},{"id":"2601.07718","title":"Hiking in the Wild: A Scalable Perceptive Parkour Framework for Humanoids","created":"2026-01-12","cited_by_count":13,"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":"2503.03045","title":"ArticuBot: Learning Universal Articulated Object Manipulation Policy via Large Scale Simulation","created":"2025-03-04","cited_by_count":11,"area":null},{"id":"2503.17267","title":"Physical Plausibility-aware Trajectory Prediction via Locomotion Embodiment","created":"2025-03-21","cited_by_count":10,"area":null},{"id":"2506.08840","title":"MoRE: Mixture of Residual Experts for Humanoid Lifelike Gaits Learning on Complex Terrains","created":"2025-06-10","cited_by_count":10,"area":"deeprl"},{"id":"2604.07993","title":"HEX: Humanoid-Aligned Experts for Cross-Embodiment Whole-Body Manipulation","created":"2026-04-09","cited_by_count":10,"area":"vla"},{"id":"2305.10455","title":"Towards Generalist Robots: A Promising Paradigm via Generative Simulation","created":"2023-05-17","cited_by_count":9,"area":null},{"id":"2410.10253","title":"Feedback Favors the Generalization of Neural ODEs","created":"2024-10-14","cited_by_count":8,"area":null},{"id":"2510.14454","title":"Towards Adaptable Humanoid Control via Adaptive Motion Tracking","created":"2025-10-16","cited_by_count":8,"area":null},{"id":"2404.17070","title":"Deep Reinforcement Learning for Bipedal Locomotion: A Brief Survey","created":"2024-04-25","cited_by_count":7,"area":"deeprl"},{"id":"2406.14655","title":"HYPERmotion: Learning Hybrid Behavior Planning for Autonomous Loco-manipulation","created":"2024-06-20","cited_by_count":7,"area":null},{"id":"2507.11019","title":"Relative Entropy Pathwise Policy Optimization","created":"2025-07-15","cited_by_count":7,"area":"deeprl"},{"id":"2507.19975","title":"A roadmap for AI in robotics","created":"2025-07-26","cited_by_count":7,"area":null},{"id":"2508.12252","title":"Robot Trains Robot: Automatic Real-World Policy Adaptation and Learning for Humanoids","created":"2025-08-17","cited_by_count":7,"area":"deeprl"},{"id":"2402.06783","title":"Learn to Teach: Sample-Efficient Privileged Learning for Humanoid Locomotion over Diverse Terrains","created":"2024-02-09","cited_by_count":6,"area":null},{"id":"2409.16611","title":"Achieving Stable High-Speed Locomotion for Humanoid Robots with Deep Reinforcement Learning","created":"2024-09-25","cited_by_count":6,"area":"deeprl"},{"id":"2412.09149","title":"Student-Informed Teacher Training","created":"2024-12-12","cited_by_count":6,"area":"offlinerl"},{"id":"2505.06584","title":"JAEGER: Dual-Level Humanoid Whole-Body Controller","created":"2025-05-10","cited_by_count":6,"area":null},{"id":"2505.20619","title":"Gait-Conditioned Reinforcement Learning with Multi-Phase Curriculum for Humanoid Locomotion","created":"2025-05-27","cited_by_count":6,"area":"deeprl"},{"id":"2510.11682","title":"Ego-Vision World Model for Humanoid Contact Planning","created":"2025-10-13","cited_by_count":6,"area":"wm"},{"id":"2512.05094","title":"From Generated Human Videos to Physically Plausible Robot Trajectories","created":"2025-12-04","cited_by_count":6,"area":null},{"id":"2412.13492","title":"Efficient Language-instructed Skill Acquisition via Reward-Policy Co-Evolution","created":"2024-12-18","cited_by_count":5,"area":null},{"id":"2506.14186","title":"Differentiable Simulation of Hard Contacts with Soft Gradients for Learning and Control","created":"2025-06-17","cited_by_count":5,"area":null},{"id":"2509.00215","title":"First Order Model-Based RL through Decoupled Backpropagation","created":"2025-08-29","cited_by_count":5,"area":"deeprl"},{"id":"2512.07464","title":"Gait-Adaptive Perceptive Humanoid Locomotion with Real-Time Under-Base Terrain Reconstruction","created":"2025-12-08","cited_by_count":5,"area":"deeprl"},{"id":"2512.24321","title":"UniAct: Unified Motion Generation and Action Streaming for Humanoid Robots","created":"2025-12-30","cited_by_count":5,"area":null},{"id":"2605.22894","title":"SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-Based Humanoid Control","created":"2026-05-21","cited_by_count":5,"area":"diffusion"},{"id":"2306.17411","title":"Decentralized Motor Skill Learning for Complex Robotic Systems","created":"2023-06-30","cited_by_count":4,"area":null},{"id":"2312.03881","title":"FoMo Rewards: Can we cast foundation models as reward functions?","created":"2023-12-06","cited_by_count":4,"area":null},{"id":"2410.05406","title":"Synthesizing Interpretable Control Policies through Large Language Model Guided Search","created":"2024-10-07","cited_by_count":4,"area":null},{"id":"2411.01850","title":"ManiBox: Enhancing Embodied Spatial Generalization via Scalable Simulation Data Generations","created":"2024-11-04","cited_by_count":4,"area":null},{"id":"2501.02749","title":"Intelligent logistics management robot path planning algorithm integrating transformer and GCN network","created":"2025-01-06","cited_by_count":4,"area":null},{"id":"2503.15579","title":"Understanding the Generalization of In-Context Learning in Transformers: An Empirical Study","created":"2025-03-19","cited_by_count":4,"area":null},{"id":"2505.06218","title":"Let Humanoids Hike! Integrative Skill Development on Complex Trails","created":"2025-05-09","cited_by_count":4,"area":null},{"id":"2508.19445","title":"On Surjectivity of Neural Networks: Can you elicit any behavior from your model?","created":"2025-08-26","cited_by_count":4,"area":null},{"id":"2509.19573","title":"Chasing Stability: Humanoid Running via Control Lyapunov Function Guided Reinforcement Learning","created":"2025-09-23","cited_by_count":4,"area":"deeprl"},{"id":"2511.10635","title":"Robot Crash Course: Learning Soft and Stylized Falling","created":"2025-11-13","cited_by_count":4,"area":null},{"id":"2512.00727","title":"Beyond Topology: A Morphological Symmetry Graph Representation for Locomotion Policy Learning","created":"2025-11-30","cited_by_count":4,"area":"deeprl"},{"id":"2601.19720","title":"Improving Policy Exploitation in Online Reinforcement Learning with Instant Retrospect Action","created":"2026-01-27","cited_by_count":4,"area":"deeprl"},{"id":"2602.15060","title":"CLOT: Closed-Loop Global Motion Tracking for Whole-Body Humanoid Teleoperation","created":"2026-02-13","cited_by_count":4,"area":null},{"id":"2603.06181","title":"Towards Motion Turing Test: Evaluating Human-Likeness in Humanoid Robots","created":"2026-03-06","cited_by_count":4,"area":null},{"id":"2409.19617","title":"LiRA: Light-Robust Adversary for Model-based Reinforcement Learning in Real World","created":"2024-09-29","cited_by_count":3,"area":"deeprl"},{"id":"2411.02975","title":"Transformer-Based Fault-Tolerant Control for Fixed-Wing UAVs Using Knowledge Distillation and In-Context Adaptation","created":"2024-11-05","cited_by_count":3,"area":null},{"id":"2503.01125","title":"TACO: General Acrobatic Flight Control via Target-and-Command-Oriented Reinforcement Learning","created":"2025-03-03","cited_by_count":3,"area":"deeprl"},{"id":"2504.08246","title":"Spectral Normalization for Lipschitz-Constrained Policies on Learning Humanoid Locomotion","created":"2025-04-11","cited_by_count":3,"area":"deeprl"},{"id":"2505.20857","title":"Multi-Embodiment Robotic Retargeting via Guided Diffusion Model","created":"2025-05-27","cited_by_count":3,"area":"diffusion"},{"id":"2506.15132","title":"Booster Gym: An End-to-End Reinforcement Learning Framework for Humanoid Robot Locomotion","created":"2025-06-18","cited_by_count":3,"area":"deeprl"},{"id":"2509.12858","title":"Contrastive Representation Learning for Robust Sim-to-Real Transfer of Adaptive Humanoid Locomotion","created":"2025-09-16","cited_by_count":3,"area":"deeprl"},{"id":"2509.20717","title":"RobotDancing: Residual-Action Reinforcement Learning Enables Robust Long-Horizon Humanoid Motion Tracking","created":"2025-09-25","cited_by_count":3,"area":"deeprl"},{"id":"2510.12717","title":"Residual MPC: Blending Reinforcement Learning with GPU-Parallelized Model Predictive Control","created":"2025-10-14","cited_by_count":3,"area":"deeprl"},{"id":"2511.11218","title":"Humanoid Whole-Body Badminton via an Annealed Reinforcement Learning Curriculum","created":"2025-11-14","cited_by_count":3,"area":"deeprl"},{"id":"2511.19528","title":"Discover, Learn, and Reinforce: Scaling Vision-Language-Action Pretraining with Diverse RL-Generated Trajectories","created":"2025-11-24","cited_by_count":3,"area":"vla"},{"id":"2603.07516","title":"InterReal: A Unified Physics-Based Imitation Framework for Learning Human-Object Interaction Skills","created":"2026-03-08","cited_by_count":3,"area":null},{"id":"2604.15614","title":"Flexible Empowerment at Reasoning with Extended Best-of-N Sampling","created":"2026-04-17","cited_by_count":3,"area":null},{"id":"2311.04082","title":"Time-Efficient Reinforcement Learning with Stochastic Stateful Policies","created":"2023-11-07","cited_by_count":2,"area":null},{"id":"2409.19795","title":"The Duke Humanoid: Design and Control For Energy Efficient Bipedal Locomotion Using Passive Dynamics","created":"2024-09-29","cited_by_count":2,"area":"deeprl"},{"id":"2411.13079","title":"Neural Internal Model Control: Learning a Robust Control Policy via Predictive Error Feedback","created":"2024-11-20","cited_by_count":2,"area":null},{"id":"2502.02921","title":"Robust Reward Alignment via Hypothesis Space Batch Cutting","created":"2025-02-05","cited_by_count":2,"area":"alignment"},{"id":"2506.02507","title":"AURA: Autonomous Upskilling with Retrieval-Augmented Agents","created":"2025-06-03","cited_by_count":2,"area":"rag"},{"id":"2508.01247","title":"Coordinated Humanoid Robot Locomotion with Symmetry Equivariant Reinforcement Learning Policy","created":"2025-08-02","cited_by_count":2,"area":"deeprl"},{"id":"2509.21690","title":"PACE: Physics Augmentation for Coordinated End-to-end Reinforcement Learning toward Versatile Humanoid Table Tennis","created":"2025-09-25","cited_by_count":2,"area":"deeprl"},{"id":"2603.08619","title":"Embedding Classical Balance Control Principles in Reinforcement Learning for Humanoid Recovery","created":"2026-03-09","cited_by_count":2,"area":"deeprl"}],"next_cursor":"100"}