[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-72539":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":25,"hasPages":23,"topics":26,"createdAt":10,"pushedAt":10,"updatedAt":27,"readmeContent":28,"aiSummary":29,"trendingCount":16,"starSnapshotCount":16,"syncStatus":30,"lastSyncTime":31,"discoverSource":32},72539,"awesome-humanoid-robot-learning","YanjieZe\u002Fawesome-humanoid-robot-learning","YanjieZe","A Paper List for Humanoid Robot Learning.","",null,"Python",2437,143,72,1,0,25,60,186,75,108.48,"MIT License",false,"main",true,[],"2026-06-12 04:01:06","# Awesome-Humanoid-Robot-Learning  [![Awesome](https:\u002F\u002Fcdn.rawgit.com\u002Fsindresorhus\u002Fawesome\u002Fd7305f38d29fed78fa85652e3a63e154dd8e8829\u002Fmedia\u002Fbadge.svg)](https:\u002F\u002Fgithub.com\u002Fsindresorhus\u002Fawesome) [![Maintenance](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FMaintained%3F-yes-green.svg)](https:\u002F\u002FGitHub.com\u002FNaereen\u002FStrapDown.js\u002Fgraphs\u002Fcommit-activity) [![PR's Welcome](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPRs-welcome-brightgreen.svg?style=flat)](http:\u002F\u002Fmakeapullrequest.com)\n\n**Basic Info.** This repo collects academic papers about **humanoid robot learning**.  They are mainly categorized by the tasks they focus on. The papers with **real robot experiments** are preferred in this list. The papers with **open-sourced code** are added with a star🌟.\n\nFeel free to pull a request for new papers\u002Fcodes about humanoid robot learning.\n\n![Word Cloud](assets\u002Fwordcloud.png)\n\n- [Awesome-Humanoid-Robot-Learning    ](#awesome-humanoid-robot-learning----)\n  - [Loco-Manipulation and Whole-Body-Control](#loco-manipulation-and-whole-body-control)\n  - [Manipulation](#manipulation)\n  - [Teleoperation](#teleoperation)\n  - [Locomotion](#locomotion)\n  - [Navigation](#navigation)\n  - [State Estimation](#state-estimation)\n  - [Sim-to-Real](#sim-to-real)\n  - [Hardware Design](#hardware-design)\n  - [Simulation Benchmark](#simulation-benchmark)\n  - [Physics-Based Character Animation](#physics-based-character-animation)\n  - [Human Motion Analysis and Synthesis](#human-motion-analysis-and-synthesis)\n- [Contact](#contact)\n\n---\n\n## Loco-Manipulation and Whole-Body-Control\n- [arXiv 2026.05](https:\u002F\u002Farxiv.org\u002Fabs\u002F2605.06593), ReActor: Reinforcement Learning for Physics-Aware Motion Retargeting\n- [arXiv 2026.03](https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.27756), Heracles: Bridging Precise Tracking and Generative Synthesis for General Humanoid Control\n- [arXiv 2026.03](https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.23983), SafeFlow: Real-Time Text-Driven Humanoid Whole-Body Control via Physics-Guided Rectified Flow and Selective Safety Gating, [website](https:\u002F\u002Fhanbyelcho.info\u002Fsafeflow\u002F)\n- 🌟[website 2026.03](https:\u002F\u002Fzzk273.github.io\u002FLATENT\u002F), LATENT: Learning Athletic Humanoid Tennis Skills from Imperfect Human Motion Data\n- [arXiv 2026.03](https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.12263), Ψ₀: An Open Foundation Model Towards Universal Humanoid Loco-Manipulation\n- [arXiv 2026.03](https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.10306), SteadyTray: Learning Object Balancing Tasks in Humanoid Tray Transport via Residual Reinforcement Learning, [website](https:\u002F\u002Fsteadytray.github.io\u002F)\n- [arXiv 2026.03](https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.09170), ZeroWBC: Learning Natural Visuomotor Humanoid Control Directly from Human Egocentric Video, [website](https:\u002F\u002Fzerowbc.github.io\u002F)\n- [arXiv 2026.03](https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.08619), Embedding Classical Balance Control Principles in Reinforcement Learning for Humanoid Recovery\n- [arXiv 2026.03](https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.03279), ULTRA: Unified Multimodal Control for Autonomous Humanoid Whole-Body Loco-Manipulation, [website](https:\u002F\u002Fultra-humanoid.github.io\u002F)\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.23843), OmniXtreme: Breaking the Generality Barrier in High-Dynamic Humanoid Control\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.21723), LessMimic: Long-Horizon Humanoid Interaction with Unified Distance Field Representations, [website](https:\u002F\u002Fyzhu.io\u002Fpreprint\u002Fhumanoid2026lessmimic\u002F)\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.16705), Learning Humanoid End-Effector Control for Open-Vocabulary Visual Loco-Manipulation\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.16511), VIGOR: Visual Goal-In-Context Inference for Unified Humanoid Fall Safety\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.15827), Perceptive Humanoid Parkour: Chaining Dynamic Human Skills via Motion Matching, [website](https:\u002F\u002Fphp-parkour.github.io\u002F)\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.15733), MeshMimic: Geometry-Aware Humanoid Motion Learning through 3D Scene Reconstruction\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.13850), Humanoid Hanoi: Investigating Shared Whole-Body Control for Skill-Based Box Rearrangement\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.11929), General Humanoid Whole-Body Control via Pretraining and Fast Adaptation\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.11758), HAIC: Humanoid Agile Object Interaction Control via Dynamics-Aware World Model, [website](https:\u002F\u002Fhaic-humanoid.github.io\u002F)\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.10106), EgoHumanoid: Unlocking In-the-Wild Loco-Manipulation with Robot-Free Egocentric Demonstration, [website](https:\u002F\u002Fopendrivelab.com\u002FEgoHumanoid\u002F)\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.08594), MOSAIC: Bridging the Sim-to-Real Gap in Generalist Humanoid Motion Tracking and Teleoperation with Rapid Residual Adaptation\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.08370), Learning Human-Like Badminton Skills for Humanoid Robots\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.07439), TextOp: Real-time Interactive Text-Driven Humanoid Robot Motion Generation and Control\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.06827), DynaRetarget: Dynamically-Feasible Retargeting using Sampling-Based Trajectory Optimization\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.06643), Humanoid Manipulation Interface: Humanoid Whole-Body Manipulation from Robot-Free Demonstrations, [website](https:\u002F\u002Fhumanoid-manipulation-interface.github.io)\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.06341), HiWET: Hierarchical World-Frame End-Effector Tracking for Long-Horizon Humanoid Loco-Manipulation\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.05310), Learning Soccer Skills for Humanoid Robots:   A Progressive Perception-Action Framework\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.04851), PDF-HR: Pose Distance Fields for Humanoid Robots\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.03205), HUSKY: Humanoid Skateboarding System via Physics-Aware Whole-Body Control\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.02960), Embodiment-Aware Generalist Specialist Distillation for Unified Humanoid Whole-Body Control\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.02473), HumanX: Toward Agile and Generalizable Humanoid Interaction Skills from Human Videos, [website](https:\u002F\u002Fwyhuai.github.io\u002Fhuman-x\u002F)\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.02331), TTT-Parkour: Rapid Test-Time Training for Perceptive Robot Parkour\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.00401), ZEST: Zero-shot Embodied Skill Transfer for Athletic Robot Control\n- [arXiv 2026.01](https:\u002F\u002Farxiv.org\u002Fabs\u002F2601.23080), Robust and Generalized Humanoid Motion Tracking\n- [arXiv 2026.01](https:\u002F\u002Farxiv.org\u002Fabs\u002F2601.22517), RoboStriker: Hierarchical Decision-Making for Autonomous Humanoid Boxing\n- [arXiv 2026.01](https:\u002F\u002Farxiv.org\u002Fabs\u002F2601.17440), PILOT: A Perceptive Integrated Low-level Controller for Loco-manipulation over Unstructured Scenes\n- [arXiv 2026.01](https:\u002F\u002Farxiv.org\u002Fabs\u002F2601.16035), Collision-Free Humanoid Traversal in Cluttered Indoor Scenes\n- [arXiv 2026.01](https:\u002F\u002Farxiv.org\u002Fabs\u002F2601.12799), FRoM-W1: Towards General Humanoid Whole-Body Control with Language Instructions\n- [arXiv 2026.01](https:\u002F\u002Farxiv.org\u002Fabs\u002F2601.09518), Learning Whole-Body Human-Humanoid Interaction from Human-Human Demonstrations\n- [arXiv 2026.01](https:\u002F\u002Farxiv.org\u002Fabs\u002F2601.07718), Hiking in the Wild: A Scalable Perceptive Parkour Framework for Humanoids\n- [arXiv 2026.01](https:\u002F\u002Farxiv.org\u002Fabs\u002F2601.07701), Deep Whole-body Parkour\n- [arXiv 2025.12](https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.25072), Coordinated Humanoid Manipulation with Choice Policies\n- [arXiv 2025.12](https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.24321), UniAct: Unified Motion Generation and Action Streaming for Humanoid Robots\n- [arXiv 2025.12](https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.19043), EGM: Efficiently Learning General Motion Tracking Policy for High Dynamic Humanoid Whole-Body Control\n- [arXiv 2025.12](https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.17183), Semantic Co-Speech Gesture Synthesis and Real-Time Control for Humanoid Robots\n- [arXiv 2025.12](https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.14689), CHIP: Adaptive Compliance for Humanoid Control through Hindsight Perturbation\n- [arXiv 2025.12](https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.13093), PvP: Data-Efficient Humanoid Robot Learning with Proprioceptive-Privileged Contrastive Representations\n- [arXiv 2025.12](https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.06571), Learning Agile Striker Skills for Humanoid Soccer Robots from Noisy Sensory Input\n- [arXiv 2025.12](https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.01336), Discovering Self-Protective Falling Policy for Humanoid Robot via Deep Reinforcement Learning\n- [arXiv 2025.12](https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.01061), Opening the Sim-to-Real Door for Humanoid Pixel-to-Action Policy Transfer\n- [arXiv 2025.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.22963), Commanding Humanoid by Free-form Language: A Large Language Action Model with Unified Motion Vocabulary\n- [arXiv 2025.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.21169), Kinematics-Aware Multi-Policy Reinforcement Learning for Force-Capable Humanoid Loco-Manipulation\n- [arXiv 2025.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.20275), HAFO: A Force-Adaptive Control Framework for Humanoid Robots in Intense Interaction Environments\n- [arXiv 2025.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.19236), SENTINEL: A Fully End-to-End Language-Action Model for Humanoid Whole Body Control\n- [arXiv 2025.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.18509), SafeFall: Learning Protective Control for Humanoid Robots\n- [arXiv 2025.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.17373), Agility Meets Stability: Versatile Humanoid Control with Heterogeneous Data\n- [arXiv 2025.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.15200), VIRAL: Visual Sim-to-Real at Scale for Humanoid Loco-Manipulation\n- [arXiv 2025.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.14756), HMC: Learning Heterogeneous Meta-Control for Contact-Rich Loco-Manipulation\n- [arXiv 2025.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.11218), Humanoid Whole-Body Badminton via Multi-Stage Reinforcement Learning\n- [arXiv 2025.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.10635), Robot Crash Course: Learning Soft and Stylized Falling\n- [arXiv 2025.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.09241), Unveiling the Impact of Data and Model Scaling on High-Level Control for Humanoid Robots\n- [arXiv 2025.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.07820), SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control\n- [arXiv 2025.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.07407), Unified Humanoid Fall-Safety Policy from a Few Demonstrations\n- [arXiv 2025.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.06371), Towards Adaptive Humanoid Control via Multi-Behavior Distillation and Reinforced Fine-Tuning\n- [arXiv 2025.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.04679), GentleHumanoid: Learning Upper-body Compliance for Contact-rich Human and Object Interaction\n- [arXiv 2025.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.04131), BFM-Zero: A Promptable Behavioral Foundation Model for Humanoid Control Using Unsupervised Reinforcement Learning\n- [arXiv 2025.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.03996), Learning Vision-Driven Reactive Soccer Skills for Humanoid Robots\n- [arXiv 2025.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.02832), TWIST2: Scalable, Portable, and Holistic Humanoid Data Collection System\n- [arXiv 2025.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.26280), Thor: Towards Human-Level Whole-Body Reactions for Intense Contact-Rich Environments\n- [arXiv 2025.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.25241), One-shot Humanoid Whole-body Motion Learning\n- [arXiv 2025.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.18002), Humanoid Goalkeeper: Learning from Position Conditioned Task-Motion Constraints\n- [arXiv 2025.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.17792), SoftMimic: Learning Compliant Whole-body Control from Examples\n- [arXiv 2025.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.14952), From Language to Locomotion: Retargeting-free Humanoid Control via Motion Latent Guidance\n- [arXiv 2025.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.14454), Towards Adaptable Humanoid Control via Adaptive Motion Tracking\n- [arXiv 2025.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.14293), Learning Human-Humanoid Coordination for Collaborative Object Carrying\n- [arXiv 2025.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.11682), Ego-Vision World Model for Humanoid Contact Planning, [website](https:\u002F\u002Fego-vcp.github.io\u002F)\n- [arXiv 2025.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.11258), DemoHLM: From One Demonstration to Generalizable Humanoid Loco-Manipulation\n- [arXiv 2025.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.11072), PhysHSI: Towards a Real-World Generalizable and Natural Humanoid-Scene Interaction System\n- [arXiv 2025.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.10206), It Takes Two: Learning Interactive Whole-Body Control Between Humanoid Robots\n- [arXiv 2025.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.05070), ResMimic: From General Motion Tracking to Humanoid Whole-body Loco-Manipulation via Residual Learning\n- [arXiv 2025.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.03022), HumanoidExo: Scalable Whole-Body Humanoid Manipulation via Wearable Exoskeleton\n- [arXiv 2025.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.02252), Retargeting Matters: General Motion Retargeting for Humanoid Motion Tracking\n- [arXiv 2025.09](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.26633), OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipulation and Scene Interaction\n- [arXiv 2025.09](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.21690), Towards Versatile Humanoid Table Tennis: Unified Reinforcement Learning with Prediction Augmentation\n- [arXiv 2025.09](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.21231), SEEC: Stable End-Effector Control with Model-Enhanced Residual Learning for Humanoid Loco-Manipulation\n- [arXiv 2025.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.20322), VisualMimic: Visual Humanoid Loco-Manipulation via Motion Tracking and Generation\n- [arXiv 2025.09](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.16757), HDMI: Learning Interactive Humanoid Whole-Body Control from Human Videos\n- [arXiv 2025.09](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.16638), KungfuBot 2: Learning Versatile Motion Skills for Humanoid Whole-Body Control\n- [arXiv 2025.09](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.15443), Implicit Kinodynamic Motion Retargeting for Human-to-humanoid Imitation Learning\n- [arXiv 2025.09](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.14353), DreamControl: Human-Inspired Whole-Body Humanoid Control for Scene Interaction via Guided Diffusion\n- [arXiv 2025.09](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.13833), Track Any Motions under Any Disturbances, [website](https:\u002F\u002Fzzk273.github.io\u002FAny2Track\u002F)\n- [arXiv 2025.09](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.13780), Behavior Foundation Model for Humanoid Robots, [website](https:\u002F\u002Fbfm4humanoid.github.io\u002F)\n- [arXiv 2025.09](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.13534), Embracing Bulky Objects with Humanoid Robots: Whole-Body Manipulation with Reinforcement Learning\n- [arXiv 2025.09](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.13200), StageACT: Stage-Conditioned Imitation for Robust Humanoid Door Opening\n- [arXiv 2025.09](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.11839), TrajBooster: Boosting Humanoid Whole-Body Manipulation via Trajectory-Centric Learning, [website](https:\u002F\u002Fjiachengliu3.github.io\u002FTrajBooster\u002F)\n- [arXiv 2025.08](https:\u002F\u002Farxiv.org\u002Fabs\u002F2508.21043), HITTER: A HumanoId Table TEnnis Robot via Hierarchical Planning and Learning, [website](https:\u002F\u002Fhumanoid-table-tennis.github.io\u002F)\n- [arXiv 2025.08](https:\u002F\u002Farxiv.org\u002Fabs\u002F2508.19002), HuBE: Cross-Embodiment Human-like Behavior Execution for Humanoid Robots\n- [arXiv 2025.08](https:\u002F\u002Farxiv.org\u002Fabs\u002F2508.16943), HumanoidVerse: A Versatile Humanoid for Vision-Language Guided Multi-Object Rearrangement\n- [arXiv 2025.08](https:\u002F\u002Farxiv.org\u002Fabs\u002F2508.14099), Task and Motion Planning for Humanoid Loco-manipulation\n- [arXiv 2025.08](https:\u002F\u002Farxiv.org\u002Fabs\u002F2508.11275), Learning Differentiable Reachability Maps for Optimization-based Humanoid Motion Generation\n- [arXiv 2025.08](https:\u002F\u002Farxiv.org\u002Fabs\u002F2508.09960), GBC: Generalized Behavior-Cloning Framework for Whole-Body Humanoid Imitation\n- [arXiv 2025.08](https:\u002F\u002Farxiv.org\u002Fabs\u002F2508.08241), BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion\n- [arXiv 2025.08](https:\u002F\u002Farxiv.org\u002Fabs\u002F2508.00362), A Whole-Body Motion Imitation Framework from Human Data for Full-Size Humanoid Robot\n- [arXiv 2025.07](https:\u002F\u002Farxiv.org\u002Fabs\u002F2507.15649), EMP: Executable Motion Prior for Humanoid Robot Standing Upper-body Motion Imitation\n- [arXiv 2025.07](https:\u002F\u002Farxiv.org\u002Fabs\u002F2507.08303), Keep on Going: Learning Robust Humanoid Motion Skills via Selective Adversarial Training\n- [arXiv 2025.07](https:\u002F\u002Farxiv.org\u002Fabs\u002F2507.07356), UniTracker: Learning Universal Whole-Body Motion Tracker for Humanoid Robots\n- [arXiv 2025.07](https:\u002F\u002Farxiv.org\u002Fabs\u002F2507.06905), ULC: A Unified and Fine-Grained Controller for Humanoid Loco-Manipulation\n- [arXiv 2025.06](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.23125), Learning Motion Skills with Adaptive Assistive Curriculum Force in Humanoid Robots\n- [arXiv 2025.06](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.20487), A Survey of Behavior Foundation Model: Next-Generation Whole-Body Control System of Humanoid Robots\n- [arXiv 2025.06](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.15146), TACT: Humanoid Whole-body Contact Manipulation through Deep Imitation Learning with Tactile Modality\n- [arXiv 2025.06](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.14770), GMT: General Motion Tracking for Humanoid Whole-Body Control\n- [arXiv 2025.06](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.13751), LeVERB: Humanoid Whole-Body Control with Latent Vision-Language Instruction\n- [arXiv 2025.06](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.12851), KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills\n- [arXiv 2025.06](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.12779), From Experts to a Generalist: Toward General Whole-Body Control for Humanoid Robots, [website](https:\u002F\u002Fbeingbeyond.github.io\u002FBumbleBee\u002F)\n- [arXiv 2025.06](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.09366), SkillBlender: Towards Versatile Humanoid Whole-Body Loco-Manipulation via Skill Blending\n- 🌟 [arXiv 2025.06](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.04147), SLAC: Simulation-Pretrained Latent Action Space for Whole-Body Real-World Reinforcement Learning, [websie](https:\u002F\u002Frobo-rl.github.io\u002F)\n- [arXiv 2025.06](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.01563), Hierarchical Intention-Aware Expressive Motion Generation for Humanoid Robots\n- [arXiv 2025.06](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.00043), From Motion to Behavior: Hierarchical Modeling of Humanoid Generative Behavior Control\n- [arXiv 2025.05](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.24266), SignBot: Learning Human-to-Humanoid Sign Language Interaction\n- [arXiv 2025.05](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.24198), Learning Gentle Humanoid Locomotion and End-Effector Stabilization Control\n- [arXiv 2025.05](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.23692), Mobi-π: Mobilizing Your Robot Learning Policy, [website](https:\u002F\u002Fmobipi.github.io\u002F)\n- [arXiv 2025.05](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.19580), Whole-body Multi-contact Motion Control for Humanoid Robots Based on Distributed Tactile Sensors\n- [arXiv 2025.05](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.19463), SMAP: Self-supervised Motion Adaptation for Physically Plausible Humanoid Whole-body Control\n- [arXiv 2025.05](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2505.17627),H2-COMPACT: Human-Humanoid Co-Manipulation via Adaptive Contact Trajectory Policies,[website](https:\u002F\u002Fh2compact.github.io\u002Fh2compact\u002F)\n- [arXiv 2025.05](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.10918), Unleashing Humanoid Reaching Potential via Real-world-Ready Skill Space\n- [arXiv 2025.05](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.07294), HuB: Learning Extreme Humanoid Balance, [website](https:\u002F\u002Fhub-robot.github.io\u002F),\n- [arXiv 2025.05](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.06776), FALCON: Learning Force-Adaptive Humanoid Loco-Manipulation, [website](https:\u002F\u002Flecar-lab.github.io\u002Ffalcon-humanoid\u002F)\n- 🌟 [arXiv 2026.03](https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.08961v1), FAME: Force-Adaptive RL for Expanding the Manipulation Envelope of a Full-Scale Humanoid, [website](https:\u002F\u002Ffame10.github.io\u002FFame\u002F)\n- [arXiv 2025.05](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.06584), JAEGER: Dual-Level Humanoid Whole-Body Controller\n- [arXiv 2025.05](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.03738), AMO: Adaptive Motion Optimization for Hyper-Dexterous Humanoid Whole-Body Control, [website](https:\u002F\u002Famo-humanoid.github.io\u002F)\n- [arXiv 2025.05](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.03728), PyRoki: A Modular Toolkit for Robot Kinematic Optimization, [website](https:\u002F\u002Fpyroki-toolkit.github.io\u002F)\n- [arXiv 2025.05](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.02833), **TWIST: Teleoperated Whole-Body Imitation System**\n- [arXiv 2025.04](https:\u002F\u002Farxiv.org\u002Fabs\u002F2504.21738), LangWBC: Language-directed Humanoid Whole-Body Control via End-to-end Learning\n- [arXiv 2025.04](https:\u002F\u002Farxiv.org\u002Fabs\u002F2504.16843v1), Physically Consistent Humanoid Loco-Manipulation using Latent Diffusion Models\n- [arXiv 2025.04](https:\u002F\u002Farxiv.org\u002Fabs\u002F2504.14305), Adversarial Locomotion and Motion Imitation for Humanoid Policy Learning, [website](https:\u002F\u002Falmi-humanoid.github.io\u002F)\n- [arXiv 2025.04](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2504.09532), [website],Embodied Chain of Action Reasoning with Multi-Modal Foundation Model for Humanoid Loco-manipulation,[website](https:\u002F\u002Fhumanoid-coa.github.io\u002F)\n- [arXiv 2025.03](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.22249), FLAM: Foundation Model-Based Body Stabilization for Humanoid Locomotion and Manipulation\n- [arXiv 2025.03](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.12533), Being-0: A Humanoid Robotic Agent with Vision-Language Models and Modular Skills, [website](https:\u002F\u002Fbeingbeyond.github.io\u002Fbeing-0\u002F)\n- [arXiv 2025.03](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.08338), Trinity: A Modular Humanoid Robot AI System\n- 🌟 [arXiv 2025.03](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.05652), BEHAVIOR Robot Suite: Streamlining Real-World Whole-Body Manipulation for Everyday Household Activities, [websie](https:\u002F\u002Fbehavior-robot-suite.github.io\u002F)\n- [arXiv 2025.03](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.04613), Whole-Body Model-Predictive Control of Legged Robots with MuJoCo\n- [arXiv 2025.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.20061), HiFAR: Multi-Stage Curriculum Learning for High-Dynamics Humanoid Fall Recovery\n- 🌟 [arXiv 2025.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.13013), **HOMIE**: Humanoid Loco-Manipulation with Isomorphic Exoskeleton Cockpit, [website](https:\u002F\u002Fhomietele.github.io\u002F) \u002F [github](https:\u002F\u002Fgithub.com\u002FOpenRobotLab\u002FOpenHomie)\n- [arXiv 2025.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.12152), Learning Getting-Up Policies for Real-World Humanoid Robots, [website](https:\u002F\u002Fhumanoid-getup.github.io\u002F)\n- [arXiv 2025.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.08378), Learning Humanoid Standing-up Control across Diverse Postures\n- [arXiv 2025.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.03206), **HugWBC**: A Unified and General Humanoid Whole-Body Controller\n- [arXiv 2025.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.03132), **SPARK**: A Toolbox for Safe Humanoid Autonomy and Teleoperation, [website](https:\u002F\u002Fintelligent-control-lab.github.io\u002Fspark\u002F)\n- [arXiv 2025.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.01465), **Embrace Collisions**: Humanoid Shadowing for Deployable Contact-Agnostics Motions, [website](https:\u002F\u002Fproject-instinct.github.io\u002F)\n- [arXiv 2024.12](https:\u002F\u002Farxiv.org\u002Fabs\u002F2412.15166), Human-Humanoid Robots Cross-Embodiment Behavior-Skill Transfer Using Decomposed Adversarial Learning from Demonstration\n- [arXiv 2024.12](https:\u002F\u002Farxiv.org\u002Fabs\u002F2412.14172), Learning from Massive Human Videos for Universal Humanoid Pose Control, [website](https:\u002F\u002Fusc-gvl.github.io\u002FUH-1\u002F)\n- [arXiv 2024.12](https:\u002F\u002Farxiv.org\u002Fabs\u002F2412.13196), **ExBody2**: Advanced Expressive Humanoid Whole-Body Control, [website](https:\u002F\u002Fexbody2.github.io\u002F)\n- [arXiv 2024.12](https:\u002F\u002Farxiv.org\u002Fabs\u002F2412.07773), **Mobile-TeleVision**: Predictive Motion Priors for Humanoid Whole-Body Control, [website](https:\u002F\u002Fmobile-tv.github.io\u002F)\n- [arXiv 2024.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2411.03532), A Behavior Architecture for Fast Humanoid Robot Door Traversals, [video](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLXuyT8w3JVgMPaB5nWNRNHtqzRK8i68dy)\n- [arXiv 2024.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2411.01349), The Role of Domain Randomization in Training Diffusion Policies for Whole-Body Humanoid Control\n- [arXiv 2024.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.23234), EMOTION: Expressive Motion Sequence Generation for Humanoid Robots with In-Context Learning\n- [arXiv 2024.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.21229), HOVER: Versatile Neural Whole-Body Controller for Humanoid Robots, [website](https:\u002F\u002Fhover-versatile-humanoid.github.io\u002F)\n- [arXiv 2024.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.12773), Harmon: Whole-Body Motion Generation of Humanoid Robots from Language Descriptions, [website](https:\u002F\u002Fut-austin-rpl.github.io\u002FHarmon\u002F)\n- [arXiv 2024.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.05681), Whole-Body Dynamic Throwing with Legged Manipulators\n- [arXiv 2024.09](https:\u002F\u002Farxiv.org\u002Fabs\u002F2409.20514), Opt2Skill: Imitating Dynamically-feasible Whole-Body Trajectories for Versatile Humanoid Loco-Manipulation, [Website](https:\u002F\u002Fopt2skill.github.io\u002F)\n- [arXiv 2024.09](https:\u002F\u002Farxiv.org\u002Fabs\u002F2409.15610), Full-Order Sampling-Based MPC for Torque-Level Locomotion Control via Diffusion-Style Annealing\n- [arXiv 2024.07](https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.12381), Flow Multi-Support: Flow Matching Imitation Learning for Multi-Support Manipulation, [video](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=OyXojqRasHU) \u002F [website](https:\u002F\u002Fhucebot.github.io\u002Fflow_multisupport_website\u002F)\n- [arXiv 2024.06](https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.14655v1), HYPERmotion: Learning Hybrid Behavior Planning for Autonomous Loco-manipulation, [website](https:\u002F\u002Fhy-motion.github.io\u002F)\n- 🌟 [arXiv 2024.06](https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.10454), HumanPlus: Humanoid Shadowing and Imitation from Humans, [website](https:\u002F\u002Fhumanoid-ai.github.io\u002F) \u002F [code](https:\u002F\u002Fgithub.com\u002FMarkFzp\u002Fhumanplus)\n- 🌟 [arXiv 2024.06](https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.08858), OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning, [website](https:\u002F\u002Fomni.human2humanoid.com\u002F) \u002F [code](https:\u002F\u002Fgithub.com\u002FLeCAR-Lab\u002Fhuman2humanoid)\n- [arXiv 2024.06](https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.06005), WoCoCo: Learning Whole-Body Humanoid Control with Sequential Contacts, [website](https:\u002F\u002Flecar-lab.github.io\u002Fwococo\u002F)\n- 🌟 [arXiv 2024.03](https:\u002F\u002Farxiv.org\u002Fabs\u002F2403.04436), Learning Human-to-Humanoid Real-Time Whole-Body Teleoperation, [website](https:\u002F\u002Fhuman2humanoid.com\u002F) \u002F [code](https:\u002F\u002Fgithub.com\u002FLeCAR-Lab\u002Fhuman2humanoid)\n- 🌟 [arXiv 2024.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.16796), Expressive Whole-Body Control for Humanoid Robots, [website](https:\u002F\u002Fexpressive-humanoid.github.io\u002F) \u002F [code](https:\u002F\u002Fgithub.com\u002Fchengxuxin\u002Fexpressive-humanoid)\n- [arXiv 2023.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.03191), Sim-to-Real Learning for Humanoid Box Loco-Manipulation\n- [arXiv 2022.12](https:\u002F\u002Farxiv.org\u002Fabs\u002F2212.00541), Predictive Sampling: Real-time Behaviour Synthesis with MuJoCo\n- [arXiv 2025.12](https:\u002F\u002Fopendrivelab.com\u002FWholeBodyVLA\u002Fstatic\u002Fpdf\u002FWholeBodyVLA.pdf), WholeBodyVLA: Towards Unified Latent VLA for Whole-body Loco-manipulation Control\n- [website 2025.11](https:\u002F\u002Fjc-bao.github.io\u002Fspider-project\u002F), SPIDER: Scalable Physics-Informed DExterous Retargeting\n- [website 2025.11](https:\u002F\u002Fnvlabs.github.io\u002FSONIC\u002F), SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control\n- [arXiv 2025.10](https:\u002F\u002Ftaohuang13.github.io\u002Fadamimic.github.io\u002F), AdaMimic: Towards Adaptable Humanoid Control via Adaptive Motion Tracking\n- [arXiv 2025.10](https:\u002F\u002Fhumanoid-exo.github.io\u002F), HumanoidExo: Scalable Whole-Body Humanoid Manipulation via Wearable Exoskeleton\n- [arXiv 2025.10](https:\u002F\u002Fomniretarget.github.io\u002F), OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipulation and Scene Interaction\n- arXiv 2025.07, ULC: A Unified and Fine-Grained Controller for Humanoid Loco-Manipulation, [website](https:\u002F\u002Fulc-humanoid.github.io)\n- arXiv 2025.06, LeVERB: Humanoid Whole-Body Control with Latent Vision-Language Instruction, [website](https:\u002F\u002Fember-lab-berkeley.github.io\u002FLeVERB-Website\u002F)\n- arXiv 2025.06, General Motion Tracking for Humanoid Whole-Body Control, [website](https:\u002F\u002Fgmt-humanoid.github.io\u002F)\n- arXiv 2025.06, KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills, [website](https:\u002F\u002Fkungfu-bot.github.io\u002F)\n- arXiv 2025.06, CLONE: Holistic Closed-Loop Whole-Body Teleoperation for Long-Horizon Humanoid Control, [website](https:\u002F\u002Fhumanoidclone.github.io\u002FCLONE.github.io\u002F)\n- [arXiv 2025.02](https:\u002F\u002Fagile.human2humanoid.com\u002F), **ASAP**: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills, [website](https:\u002F\u002Fagile.human2humanoid.com\u002F)\n- [2024.08](https:\u002F\u002Fla.disneyresearch.com\u002Fpublication\u002Fvmp-versatile-motion-priors-for-robustly-tracking-motion-on-physical-characters\u002F), VMP: Versatile Motion Priors for Robustly Tracking Motion on Physical Characters, [website](https:\u002F\u002Fla.disneyresearch.com\u002Fpublication\u002Fvmp-versatile-motion-priors-for-robustly-tracking-motion-on-physical-characters\u002F)\n- [2024.07](https:\u002F\u002Fla.disneyresearch.com\u002Fpublication\u002Frobot-motion-diffusion-model-motion-generation-for-robotic-characters\u002F), Robot Motion Diffusion Model: Motion Generation for Robotic Characters,\n\n## Manipulation\n- 🌟[arXiv 2026.03](https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.12260), HumDex: Humanoid Dexterous Manipulation Made Easy\n- [arXiv 2026.03](https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.05493), cuRoboV2: Dynamics-Aware Motion Generation with Depth-Fused Distance Fields for High-DoF Robots\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.06949), DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos, [website](https:\u002F\u002Fdreamdojo-world.github.io\u002F)\n- [arXiv 2026.01](https:\u002F\u002Farxiv.org\u002Fabs\u002F2601.14874), HumanoidVLM: Vision-Language-Guided Impedance Control for Contact-Rich Humanoid Manipulation\n- [arXiv 2026.01](https:\u002F\u002Farxiv.org\u002Fabs\u002F2601.09031), Generalizable Geometric Prior and Recurrent Spiking Feature Learning for Humanoid Robot Manipulation\n- [arXiv 2026.01](https:\u002F\u002Farxiv.org\u002Fabs\u002F2601.05844), DexterCap: An Affordable and Automated System for Capturing Dexterous Hand-Object Manipulation\n- [arXiv 2026.01](https:\u002F\u002Farxiv.org\u002Fabs\u002F2601.02078), Genie Sim 3.0 : A High-Fidelity Comprehensive Simulation Platform for Humanoid Robot\n- [arXiv 2025.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.23300), SafeHumanoid: VLM-RAG-driven Control of Upper Body Impedance for Humanoid Robot\n- [arXiv 2025.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.16661), Dexterity from Smart Lenses: Multi-Fingered Robot Manipulation with In-the-Wild Human Demonstrations\n- [arXiv 2025.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.15704), In-N-On: Scaling Egocentric Manipulation with in-the-wild and on-task Data\n- [arXiv 2025.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.09141), RGMP: Recurrent Geometric-prior Multimodal Policy for Generalizable Humanoid Robot Manipulation\n- [arXiv 2025.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.07418), Lightning Grasp: High Performance Procedural Grasp Synthesis with Contact Fields\n- [arXiv 2025.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.00153), EgoMI: Learning Active Vision and Whole-Body Manipulation from Egocentric Human Demonstrations\n- [arXiv 2025.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.00041), Endowing GPT-4 with a Humanoid Body: Building the Bridge Between Off-the-Shelf VLMs and the Physical World\n- [arXiv 2025.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.25725), A Humanoid Visual-Tactile-Action Dataset for Contact-Rich Manipulation\n- [arXiv 2025.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.07882), Towards Proprioception-Aware Embodied Planning for Dual-Arm Humanoid Robots\n- [arXiv 2025.09](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.22578), EgoDemoGen: Novel Egocentric Demonstration Generation Enables Viewpoint-Robust Manipulation\n- [arXiv 2025.09](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.19301), Residual Off-Policy RL for Finetuning Behavior Cloning Policies\n- [arXiv 2025.09](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.09769), MimicDroid: In-Context Learning for Humanoid Robot Manipulation from Human Play Videos\n- [arXiv 2025.08](https:\u002F\u002Farxiv.org\u002Fabs\u002F2508.09976), Masquerade: Learning from In-the-wild Human Videos using Data-Editing\n- [arXiv 2025.08](https:\u002F\u002Farxiv.org\u002Fabs\u002F2508.00355), TOP: Time Optimization Policy for Stable and Accurate Standing Manipulation with Humanoid Robots\n- [arXiv 2025.07](https:\u002F\u002Farxiv.org\u002Fabs\u002F2507.23523), H-RDT: Human Manipulation Enhanced Bimanual Robotic Manipulation\n- [arXiv 2025.07](https:\u002F\u002Farxiv.org\u002Fabs\u002F2507.15597), Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos, [website](https:\u002F\u002Fbeingbeyond.github.io\u002FBeing-H0\u002F) \u002F [code](https:\u002F\u002Fgithub.com\u002FBeingBeyond\u002FBeing-H0) \u002F [model](https:\u002F\u002Fhuggingface.co\u002Fcollections\u002FBeingBeyond\u002Fbeing-h0-688dcc58cbd6b452f16bd7ec)\n- [arXiv 2025.07](https:\u002F\u002Farxiv.org\u002Fabs\u002F2507.12440), EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos, [website](https:\u002F\u002Frchalyang.github.io\u002FEgoVLA\u002F)\n- [arXiv 2025.07](https:\u002F\u002Farxiv.org\u002Fabs\u002F2507.11498), Robot Drummer: Learning Rhythmic Skills for Humanoid Drumming\n- [arXiv 2025.06](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.22827), Hierarchical Vision-Language Planning for Multi-Step Humanoid Manipulation\n- [arXiv 2025.06](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.15666), Vision in Action: Learning Active Perception from Human Demonstrations\n- [arXiv 2025.05](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.12705), DreamGen: Unlocking Generalization in Robot Learning through Neural Trajectories\n- [arXiv 2025.05](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.11709), EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video\n- [arXiv 2025.03](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.24361), Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulation, [website](https:\u002F\u002Fco-training.github.io\u002F)\n- [arXiv 2025.03](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.14734), GR00T N1: An Open Foundation Model for Generalist Humanoid Robots\n- [arXiv 2025.03](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.13441), Humanoid Policy ~ Human Policy, [website](https:\u002F\u002Fhuman-as-robot.github.io\u002F)\n- [arXiv 2025.03](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.12725), Humanoids in Hospitals: A Technical Study of Humanoid Surrogates for Dexterous Medical Interventions\n- [arXiv 2025.03](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.00200), Unified Video Action Model, [website](https:\u002F\u002Funified-video-action-model.github.io\u002F)\n- [arXiv 2025.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.02858), **Dexterous Safe Control** for Humanoids in Cluttered Environments via Projected Safe Set Algorithm\n- [arXiv 2025.01](https:\u002F\u002Farxiv.org\u002Fabs\u002F2501.04595), MobileH2R: Learning Generalizable Human to Mobile Robot Handover Exclusively from Scalable and Diverse Synthetic Data\n- [arXiv 2024.12](https:\u002F\u002Farxiv.org\u002Fabs\u002F2412.10631), ARMADA: Augmented Reality for Robot Manipulation and Robot-Free Data Acquisition, [website](https:\u002F\u002Fnataliya.dev\u002Farmada)\n- [arXiv 2024.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2411.04005), Object-Centric Dexterous Manipulation from Human Motion Data, [website](https:\u002F\u002Fcypypccpy.github.io\u002Fobj-dex.github.io\u002F)\n- [arXiv 2024.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2411.02214), DexHub and DART: Towards Internet-Scale Robot Data Collection, [website](https:\u002F\u002Fdexhub.ai\u002Fproject)\n- [arXiv 2024.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2411.00704), Learning to Look Around: Enhancing Teleoperation and Learning with a Human-like Actuated Neck\n- 🌟 [arXiv 2024.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.24221), EgoMimic: Scaling Imitation Learning via Egocentric Video, [website](https:\u002F\u002Fegomimic.github.io\u002F) \u002F [code](https:\u002F\u002Fgithub.com\u002FSimarKareer\u002FEgoMimic)\n- [arXiv 2024.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.18964), Learning to Look: Seeking Information for Decision Making via Policy Factorization, [website](https:\u002F\u002Frobin-lab.cs.utexas.edu\u002Flearning2look\u002F)\n- [arXiv 2024.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.11792), OKAMI: Teaching Humanoid Robots Manipulation Skills through Single Video Imitation, [website](https:\u002F\u002Fut-austin-rpl.github.io\u002FOKAMI\u002F)\n- 🌟 [arXiv 2024.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.10803), Generalizable Humanoid Manipulation with Improved 3D Diffusion Policies, [website](https:\u002F\u002Fhumanoid-manipulation.github.io\u002F) \u002F [code](https:\u002F\u002Fgithub.com\u002FYanjieZe\u002FImproved-3D-Diffusion-Policy)\n- 🌟 [arXiv 2024.08](https:\u002F\u002Farxiv.org\u002Fabs\u002F2408.11805), ACE: A Cross-Platform Visual-Exoskeletons System for Low-Cost Dexterous Teleoperation, [website](https:\u002F\u002Face-teleop.github.io\u002F) \u002F [code](https:\u002F\u002Fgithub.com\u002FACETeleop\u002FACETeleop)\n- 🌟 [arXiv 2024.07](https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.03162), Bunny-VisionPro: Real-Time Bimanual Dexterous Teleoperation for Imitation Learning, [website](https:\u002F\u002Fdingry.github.io\u002Fprojects\u002Fbunny_visionpro.html) \u002F [code](https:\u002F\u002Fgithub.com\u002FDingry\u002FBunnyVisionPro)\n- 🌟 [arXiv 2024.07](https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.01512), Open-TeleVision: Teleoperation with Immersive Active Visual Feedback, [website](https:\u002F\u002Frobot-tv.github.io\u002F) \u002F [code](https:\u002F\u002Fgithub.com\u002FOpenTeleVision\u002FTeleVision)\n- 🌟 [arXiv 2024.04](https:\u002F\u002Farxiv.org\u002Fabs\u002F2404.16823), Learning Visuotactile Skills with Two Multifingered Hands, [website](https:\u002F\u002Ftoruowo.github.io\u002Fhato\u002F) \u002F [code](https:\u002F\u002Fgithub.com\u002Ftoruowo\u002Fhato)\n- 🌟 [arXiv 2024.03](https:\u002F\u002Farxiv.org\u002Fabs\u002F2403.07788), DexCap: Scalable and Portable Mocap Data Collection System for Dexterous Manipulation, [website](https:\u002F\u002Fdex-cap.github.io\u002F) \u002F [code](https:\u002F\u002Fgithub.com\u002Fj96w\u002FDexCap)\n- [website](https:\u002F\u002Fdreamzero0.github.io\u002F), DreamZero: World Action Models are Zero-shot Policies\n- [website](https:\u002F\u002Fco-training-lbm.github.io\u002F), A Systematic Study of Data Modalities and Strategies for Co-training Large Behavior Models for Robot Manipulation\n- [Science Robotics 2026.01](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fscirobotics.ady2869), Visual-tactile pretraining and online multitask learning for humanlike manipulation dexterity\n- [pdf](https:\u002F\u002Fopenreview.net\u002Fattachment?id=JoK1hJg0Td&name=pdf), IN-N-ON: SCALING EGOCENTRIC MANIPULATION WITH IN-THE-WILD AND ON-TASK DATA\n- [website](https:\u002F\u002Flego-grasp.github.io\u002F), Learning to Grasp Anything by Playing with Random Toys\n  - provide some intuition on imitation learning data collection: learn generalizable grasping from toy objects with different primitives to real-world objects\n- [arXiv 2025.10](https:\u002F\u002Fhumanoideveryday.github.io\u002F), Humanoid Everyday: A Comprehensive Robotic Dataset for Open-World Humanoid Manipulation\n- [arXiv 2025.10](https:\u002F\u002Factiveumi.github.io\u002F), ActiveUMI: Robotic Manipulation with Active Perception from Robot‑Free Human Demonstrations\n- arXiv 2025.05, DexUMI: Using Human Hand as the Universal Manipulation Interface for Dexterous Manipulation, [website](https:\u002F\u002Fdex-umi.github.io\u002F)\n- arXiv 2025.02, Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids, [website](https:\u002F\u002Ftoruowo.github.io\u002Frecipe\u002F)\n- [2024.09](https:\u002F\u002Fopenreview.net\u002Fforum?id=55tYfHvanf), Bimanual Dexterity for Complex Tasks, [website](https:\u002F\u002Fbidex-teleop.github.io\u002F)\n- [1999](https:\u002F\u002Fwww.cell.com\u002Ftrends\u002Fcognitive-sciences\u002Fabstract\u002FS1364-6613(99)01327-3), Is imitation learning the route to humanoid robots?\n\n## Teleoperation\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.15060), CLOT: Closed-Loop Global Motion Tracking for Whole-Body Humanoid Teleoperation\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.11321), ExtremControl: Low-Latency Humanoid Teleoperation with Direct Extremity Control\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.09628), TeleGate: Whole-Body Humanoid Teleoperation via Gated Expert Selection with Motion Prior\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.01632), A Closed-Form Geometric Retargeting Solver for Upper Body Humanoid Robot Teleoperation\n- [arXiv 2025.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.12390), Learning Adaptive Neural Teleoperation for Humanoid Robots\n- [arXiv 2025.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.02832), TWIST2: Scalable, Portable, and Holistic Humanoid Data Collection System\n- [arXiv 2025.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.13594), Development of an Intuitive GUI for Non-Expert Teleoperation of Humanoid Robots\n- [arXiv 2025.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.04353), Stability-Aware Retargeting for Humanoid Multi-Contact Teleoperation\n- [arXiv 2025.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.03529), LapSurgie: Humanoid Robots Performing Surgery via Teleoperated Handheld Laparoscopy\n- [arXiv 2025.08](https:\u002F\u002Farxiv.org\u002Fabs\u002F2508.09846), Whole-Body Bilateral Teleoperation with Multi-Stage Object Parameter Estimation for Wheeled Humanoid Locomanipulation\n- [arXiv 2025.08](https:\u002F\u002Farxiv.org\u002Fabs\u002F2508.00162), CHILD: a Whole-Body Humanoid Teleoperation System\n- [arXiv 2025.06](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.08931), CLONE: Closed-Loop Whole-Body Humanoid Teleoperation for Long-Horizon Tasks\n- [arXiv 2025.05](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.19530), Heavy lifting tasks via haptic teleoperation of a wheeled humanoid\n- [arXiv 2025.05](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.12748), TeleOpBench: A Simulator-Centric Benchmark for Dual-Arm Dexterous Teleoperation, [website](https:\u002F\u002Fgorgeous2002.github.io\u002FTeleOpBench\u002F)\n- [arXiv 2025.05](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.05773), Human-Robot Collaboration for the Remote Control of Mobile Humanoid Robots\n- [arXiv 2025.05](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.02833), TWIST: Teleoperated Whole-Body Imitation System\n- [arXiv 2025.03](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.10554), NuExo: A Wearable Exoskeleton Covering all Upper Limb ROM for Outdoor Data Collection and Teleoperation of Humanoid Robots\n- 🌟 [arXiv 2025.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.13013), HOMIE: Humanoid Loco-Manipulation with Isomorphic Exoskeleton Cockpit, [code](https:\u002F\u002Fgithub.com\u002FOpenRobotLab\u002FOpenHomie)\n- [arXiv 2024.12](https:\u002F\u002Farxiv.org\u002Fabs\u002F2412.07773), Mobile-TeleVision: Predictive Motion Priors for Humanoid Whole-Body Control\n- 🌟 [arXiv 2024.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.10803), Generalizable Humanoid Manipulation with 3D Diffusion Policies, [website](https:\u002F\u002Fhumanoid-manipulation.github.io\u002F) \u002F [code](https:\u002F\u002Fgithub.com\u002FYanjieZe\u002FImproved-3D-Diffusion-Policy)\n- [arXiv 2024.09](https:\u002F\u002Farxiv.org\u002Fabs\u002F2409.04639v1), High-Speed and Impact Resilient Teleoperation of Humanoid Robots\n- 🌟 [arXiv 2024.08](https:\u002F\u002Farxiv.org\u002Fabs\u002F2408.11805), ACE: A Cross-Platform Visual-Exoskeletons System for Low-Cost Dexterous Teleoperation, [website](https:\u002F\u002Face-teleop.github.io\u002F) \u002F [code](https:\u002F\u002Fgithub.com\u002FACETeleop\u002FACETeleop)\n- 🌟 [arXiv 2024.07](https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.03162), Bunny-VisionPro: Real-Time Bimanual Dexterous Teleoperation for Imitation Learning, [website](https:\u002F\u002Fdingry.github.io\u002Fprojects\u002Fbunny_visionpro.html) \u002F [code](https:\u002F\u002Fgithub.com\u002FDingry\u002FBunnyVisionPro)\n- 🌟 [arXiv 2024.07](https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.01512), Open-TeleVision: Teleoperation with Immersive Active Visual Feedback, [website](https:\u002F\u002Frobot-tv.github.io\u002F) \u002F [code](https:\u002F\u002Fgithub.com\u002FOpenTeleVision\u002FTeleVision)\n- 🌟 [arXiv 2024.06](https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.10454), HumanPlus: Humanoid Shadowing and Imitation from Humans, [website](https:\u002F\u002Fhumanoid-ai.github.io\u002F) \u002F [code](https:\u002F\u002Fgithub.com\u002FMarkFzp\u002Fhumanplus)\n- 🌟 [arXiv 2024.06](https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.08858), OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning, [website](https:\u002F\u002Fomni.human2humanoid.com\u002F) \u002F [code](https:\u002F\u002Fgithub.com\u002FLeCAR-Lab\u002Fhuman2humanoid)\n- [arXiv 2024.03](https:\u002F\u002Farxiv.org\u002Fabs\u002F2403.04436), Learning Human-to-Humanoid Real-Time Whole-Body Teleoperation, [website](https:\u002F\u002Fhuman2humanoid.com\u002F)\n- 🌟 [arXiv 2023.09](https:\u002F\u002Farxiv.org\u002Fabs\u002F2309.01952), Deep Imitation Learning for Humanoid Loco-manipulation through Human Teleoperation, [website](https:\u002F\u002Fut-austin-rpl.github.io\u002FTRILL\u002F) \u002F [code](https:\u002F\u002Fgithub.com\u002FUT-Austin-RPL\u002FTRILL)\n- [arXiv 2023.01](https:\u002F\u002Farxiv.org\u002Fabs\u002F2301.04317), Teleoperation of Humanoid Robots: A Survey, [webpage](https:\u002F\u002Fhumanoid-teleoperation.github.io\u002F)\n- [arXiv 2022.03](https:\u002F\u002Farxiv.org\u002Fabs\u002F2203.06972), iCub3 Avatar System: Enabling Remote Fully-Immersive Embodiment of Humanoid Robots, [Science Robotics](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fscirobotics.adh3834) \u002F [github](https:\u002F\u002Fgithub.com\u002Fami-iit\u002Fpaper_dafarra_2024_science-robotics_icub3-avatar-system)\n- arXiv 2025.08, CHILD: Controller for Humanoid Imitation and Live Demonstration a Whole-Body Humanoid Teleoperation System, [website](https:\u002F\u002Fuiuckimlab.github.io\u002FCHILD-pages\u002F)\n\n\n## Locomotion\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.21666), Biomechanical Comparisons Reveal Divergence of Human and Humanoid Gaits\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.11143), APEX: Learning Adaptive High-Platform Traversal for Humanoid Robots, [website](https:\u002F\u002Fapex-humanoid.github.io\u002F)\n- 🌟 [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.06445), ECO: Energy-Constrained Optimization with Reinforcement Learning for Humanoid Walking, [website](https:\u002F\u002Fsites.google.com\u002Fview\u002Feco-humanoid) \u002F [code](https:\u002F\u002Fgithub.com\u002Fbigai-ai\u002FECO-humanoid)\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.06382), Now You See That: Learning End-to-End Humanoid Locomotion from Raw Pixels\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.05855), A Hybrid Autoencoder for Robust Heightmap Generation from Fused Lidar and Depth Data for Humanoid Robot Locomotion\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.05791), Scalable and General Whole-Body Control for Cross-Humanoid Locomotion\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.04412), HoRD: Robust Humanoid Control via History-Conditioned Reinforcement Learning and Online Distillation\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.03511), CMR: Contractive Mapping Embeddings for Robust Humanoid Locomotion on Unstructured Terrains\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.03002), RPL: Learning Robust Humanoid Perceptive Locomotion on Challenging Terrains\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.00678), Toward Reliable Sim-to-Real Predictability for MoE-based Robust Quadrupedal Locomotion\n- [arXiv 2026.01](https:\u002F\u002Farxiv.org\u002Fabs\u002F2601.10365), FastStair: Learning to Run Up Stairs with Humanoid Robots\n- [arXiv 2026.01](https:\u002F\u002Farxiv.org\u002Fabs\u002F2601.08485), AME-2: Agile and Generalized Legged Locomotion via Attention-Based Neural Map Encoding\n- [arXiv 2026.01](https:\u002F\u002Farxiv.org\u002Fabs\u002F2601.06286), Walk the PLANC: Physics-Guided RL for Agile Humanoid Locomotion on Constrained Footholds\n- [arXiv 2026.01](https:\u002F\u002Farxiv.org\u002Fabs\u002F2601.04948), SKATER: Synthesized Kinematics for Advanced Traversing Efficiency on a Humanoid Robot via Roller Skate Swizzles\n- [arXiv 2025.12](https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.23650), Do You Have Freestyle? Expressive Humanoid Locomotion via Audio Control\n- [arXiv 2025.12](https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.23649), RoboMirror: Understand Before You Imitate for Video to Humanoid Locomotion\n- [arXiv 2025.12](https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.16446), E-SDS: Environment-aware See it, Do it, Sorted - Automated Environment-Aware Reinforcement Learning for Humanoid Locomotion\n- [arXiv 2025.12](https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.12230), Learning to Get Up Across Morphologies: Zero-Shot Recovery with a Unified Humanoid Policy\n- [arXiv 2025.12](https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.10477), Symphony: A Heuristic Normalized Calibrated Advantage Actor and Critic Algorithm in application for Humanoid Robots\n- [arXiv 2025.12](https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.09431), A Hierarchical, Model-Based System for High-Performance Humanoid Soccer\n- [arXiv 2025.12](https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.07464), Gait-Adaptive Perceptive Humanoid Locomotion with Real-Time Under-Base Terrain Reconstruction\n- [arXiv 2025.12](https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.01996), Learning Sim-to-Real Humanoid Locomotion in 15 Minutes\n- [arXiv 2025.12](https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.00971), H-Zero: Cross-Humanoid Locomotion Pretraining Enables Few-shot Novel Embodiment Transfer\n- [arXiv 2025.12](https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.00077), A Hierarchical Framework for Humanoid Locomotion with Supernumerary Limbs\n- [arXiv 2025.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.19204), Reference-Free Sampling-Based Model Predictive Control\n- [arXiv 2025.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.12215), Learning a Vision-Based Footstep Planner for Hierarchical Walking Control\n- [arXiv 2025.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.26236), PHUMA: Physically-Grounded Humanoid Locomotion Dataset\n- [arXiv 2025.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.15352), GaussGym: An open-source real-to-sim framework for learning locomotion from pixels\n- [arXiv 2025.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.14947), Architecture Is All You Need: Diversity-Enabled Sweet Spots for Robust Humanoid Locomotion\n- [arXiv 2025.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.12346), PolygMap: A Perceptive Locomotion Framework for Humanoid Robot Stair Climbing\n- [arXiv 2025.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.10851), Preference-Conditioned Multi-Objective RL for Integrated Command Tracking and Force Compliance in Humanoid Locomotion\n- [arXiv 2025.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.07152), DPL: Depth-only Perceptive Humanoid Locomotion via Realistic Depth Synthesis and Cross-Attention Terrain Reconstruction\n- [arXiv 2025.09](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.24697), Stabilizing Humanoid Robot Trajectory Generation via Physics-Informed Learning\n- [arXiv 2025.09](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.20696), RuN: Residual Policy for Natural Humanoid Locomotion\n- [arXiv 2025.09](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.19573), Chasing Stability: Humanoid Running via Control Lyapunov Function Guided RL\n- [arXiv 2025.09](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.19023), Reduced-Order Model-Guided RL for Demonstration-Free Humanoid Locomotion\n- [arXiv 2025.09](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.18046), HuMam: Humanoid Motion Control via End-to-End Deep RL with Mamba\n- [arXiv 2025.09](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.05581), Learning to Walk in Costume: Adversarial Motion Priors for Aesthetically Constrained Humanoids\n- [arXiv 2025.08](https:\u002F\u002Farxiv.org\u002Fabs\u002F2508.20661), Traversing Narrow Paths: A Two-Stage RL Framework for Robust and Safe Humanoid Walking\n- [arXiv 2025.08](https:\u002F\u002Farxiv.org\u002Fabs\u002F2508.14098), No More Marching: Learning Humanoid Locomotion for Short-Range SE(2) Targets\n- [arXiv 2025.08](https:\u002F\u002Farxiv.org\u002Fabs\u002F2508.11129), Geometry-Aware Predictive Safety Filters on Humanoids\n- [arXiv 2025.08](https:\u002F\u002Farxiv.org\u002Fabs\u002F2508.10423), MASH: Cooperative-Heterogeneous Multi-Agent RL for Single Humanoid Robot Locomotion\n- [arXiv 2025.08](https:\u002F\u002Farxiv.org\u002Fabs\u002F2508.07611), End-to-End Humanoid Robot Safe and Comfortable Locomotion Policy\n- [arXiv 2025.08](https:\u002F\u002Farxiv.org\u002Fabs\u002F2508.03070), Optimizing Bipedal Locomotion for The 100m Dash With Comparison to Human Running\n- [arXiv 2025.08](https:\u002F\u002Farxiv.org\u002Fabs\u002F2508.01247), Coordinated Humanoid Robot Locomotion with Symmetry Equivariant Reinforcement Learning Policy\n- [arXiv 2025.07](https:\u002F\u002Farxiv.org\u002Fabs\u002F2507.18883), Success in Humanoid Reinforcement Learning under Partial Observation\n- [arXiv 2025.07](https:\u002F\u002Fwww.arxiv.org\u002Fabs\u002F2507.04140), Learning Humanoid Arm Motion via Centroidal Momentum Regularized Multi-Agent Reinforcement Learning\n- [arXiv 2025.07](https:\u002F\u002Farxiv.org\u002Fabs\u002F2507.00273), Mechanical Intelligence-Aware Curriculum RL for Humanoids with Parallel Actuation\n- [arXiv 2025.06](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.15132), Booster Gym: An End-to-End RL Framework for Humanoid Robot Locomotion\n- [arXiv 2025.06](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.12095), DoublyAware: Dual Planning and Policy Awareness for Temporal Difference Learning in Humanoid Locomotion\n- [arXiv 2025.06](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.08840), MoRE: Mixture of Residual Experts for Humanoid Lifelike Gaits Learning on Complex Terrains, [website](https:\u002F\u002Fmore-humanoid.github.io\u002F)\n- [arXiv 2025.06](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.08416), A Gait Driven RL Framework for Humanoid Robots\n- [arXiv 2025.06](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.00305), Learning Aerodynamics for the Control of Flying Humanoid Robots\n- [arXiv 2025.05](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.22642), FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid Control, [website](https:\u002F\u002Fyounggyo.me\u002Ffast_td3\u002F)\n- [arXiv 2025.05](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.20619), Gait-Conditioned RL with Multi-Phase Curriculum for Humanoid Locomotion\n- [arXiv 2025.05](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.19214), Omni-Perception: Omnidirectional Collision Avoidance for Legged Locomotion in Dynamic Environments\n- [arXiv 2025.05](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.18780), One Policy but Many Worlds: A Scalable Unified Policy for Versatile Humanoid Locomotion\n- [arXiv 2025.05](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.13549), TD-GRPC: Temporal Difference Learning with Group Relative Policy Constraint for Humanoid Locomotion\n- [arXiv 2025.05](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.12679), Dribble Master: Learning Agile Humanoid Dribbling Through Legged Locomotion\n- [arXiv 2025.05](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.11494), SHIELD: Safety on Humanoids via CBFs In Expectation on Learned Dynamics\n- [arXiv 2025.05](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.06218), Let Humanoids Hike! Integrative Skill Development on Complex Trails\n- [arXiv 2025.05](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.03729), VideoMimic: Visual imitation enables contextual humanoid control, [website](https:\u002F\u002Fwww.videomimic.net\u002F)\n- [arXiv 2025.04](https:\u002F\u002Farxiv.org\u002Fabs\u002F2504.20808), SoccerDiffusion: Toward Learning End-to-End Humanoid Robot Soccer from Gameplay Recordings\n- [arXiv 2025.04](https:\u002F\u002Farxiv.org\u002Fabs\u002F2504.13619), Robust Humanoid Walking on Compliant and Uneven Terrain with Deep RL\n- [arXiv 2025.04](https:\u002F\u002Farxiv.org\u002Fabs\u002F2504.09833), PPF: Pre-training and Preservative Fine-tuning of Humanoid Locomotion\n- [arXiv 2025.04](https:\u002F\u002Farxiv.org\u002Fabs\u002F2504.08246), Spectral Normalization for Lipschitz-Constrained Policies on Learning Humanoid Locomotion\n- [arXiv 2025.04](https:\u002F\u002Farxiv.org\u002Fabs\u002F2504.00614), Learning Bipedal Locomotion on Gear-Driven Humanoid Robot Using Foot-Mounted IMUs\n- [arXiv 2025.03](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.15082), StyleLoco: Generative Adversarial Distillation for Natural Humanoid Robot Locomotion\n- [arXiv 2025.03](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.09015), Natural Humanoid Robot Locomotion with Generative Motion Prior\n- [arXiv 2025.03](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.08349), LiPS: Large-Scale Humanoid Robot RL with Parallel-Series Structures\n- [arXiv 2025.03](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.08299), Distillation-PPO: A Novel Two-Stage RL Framework for Humanoid Robot Perceptive Locomotion\n- [arXiv 2025.03](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.00923), HWC-Loco: A Hierarchical Whole-Body Control Approach to Robust Humanoid Locomotion, [website](https:\u002F\u002Fsimonlinsx.github.io\u002FHWC_Loco\u002F)\n- [arXiv 2025.03](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.00692), Learning Perceptive Humanoid Locomotion over Challenging Terrain\n- [arXiv 2025.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.17219), Humanoid Whole-Body Locomotion on Narrow Terrain via Dynamic Balance and Reinforcement Learning\n- [arXiv 2025.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.16230), Learning Humanoid Locomotion with World Model Reconstruction\n- [arXiv 2025.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.14814), **VB-Com**: Learning Vision-Blind Composite Humanoid Locomotion Against Deficient Perception, [website](https:\u002F\u002Frenjunli99.github.io\u002Fvbcom.github.io\u002F)\n- [arXiv 2025.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.10363), BeamDojo: Learning Agile Humanoid Locomotion on Sparse Footholds, [website](https:\u002F\u002Fwhy618188.github.io\u002Fbeamdojo\u002F)\n- [arXiv 2024.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2411.14386), Learning Humanoid Locomotion with Perceptive Internal Model\n- 🌟 [arXiv 2024.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2411.01919), Real-Time Polygonal Semantic Mapping for Humanoid Robot Stair Climbing, [code](https:\u002F\u002Fgithub.com\u002FBTFrontier\u002Fpolygon_mapping)\n- 🌟 [arXiv 2024.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.11825), Learning Smooth Humanoid Locomotion through Lipschitz-Constrained Policies, [website](https:\u002F\u002Flipschitz-constrained-policy.github.io\u002F) \u002F [code](https:\u002F\u002Fgithub.com\u002Fzixuan417\u002Fsmooth-humanoid-locomotion)\n- [arXiv 2024.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.03654), Learning Humanoid Locomotion over Challenging Terrain, [website](https:\u002F\u002Fhumanoid-challenging-terrain.github.io\u002F)\n- [arXiv 2024.08](https:\u002F\u002Farxiv.org\u002Fabs\u002F2408.14472), Advancing Humanoid Locomotion: Mastering Challenging Terrains with Denoising World Model Learning\n- [arXiv 2024.06](https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.10759), Humanoid Parkour Learning, [website](https:\u002F\u002Fhumanoid4parkour.github.io\u002F)\n- [arXiv 2024.04](https:\u002F\u002Farxiv.org\u002Fabs\u002F2404.17070), Deep Reinforcement Learning for Bipedal Locomotion: A Brief Survey\n- [arXiv 2024.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.19469), Humanoid Locomotion as Next Token Prediction, [website](https:\u002F\u002Fhumanoid-next-token-prediction.github.io\u002F)\n- [arXiv 2024.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.18294), Whole-body Humanoid Robot Locomotion with Human Reference, [website](https:\u002F\u002Fgreatsjk.github.io\u002FAdam-PNDbotics\u002F)\n- [arXiv 2024.01](https:\u002F\u002Farxiv.org\u002Fabs\u002F2401.16889), Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control\n- [arXiv 2023.09](https:\u002F\u002Farxiv.org\u002Fabs\u002F2309.12784), Learning to Walk and Fly with Adversarial Motion Priors\n- [arXiv 2023.07](https:\u002F\u002Farxiv.org\u002Fabs\u002F2307.10142), Benchmarking **Potential Based Rewards** for Learning Humanoid Locomotion,\n- [arXiv 2023.03](https:\u002F\u002Farxiv.org\u002Fabs\u002F2303.03381), Real-World Humanoid Locomotion with Reinforcement Learning, [website](https:\u002F\u002Flearning-humanoid-locomotion.github.io\u002F)\n- [arXiv 2023.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2302.09450), Robust and Versatile Bipedal Jumping Control through Reinforcement Learning\n- [website 2026.01](https:\u002F\u002Fcaltech-amber.github.io\u002Fplanc\u002F), Walk the PLANC: Physics‑Guided RL for Agile Humanoid LocomotioN on Constrained Footholds\n- [arXiv 2025.09](https:\u002F\u002Fgeneralist-locomotion.github.io\u002F), LocoFormer: Generalist Locomotion via Long-Context Adaptation\n- [2024.10](https:\u002F\u002Fopenreview.net\u002Fforum?id=O0oK2bVist), Adapting Humanoid Locomotion over Challenging Terrain via Two-Phase Training, [website](https:\u002F\u002Fsites.google.com\u002Fview\u002Fadapting-humanoid-locomotion\u002Ftwo-phase-training)\n- [2024.10](https:\u002F\u002Fopenreview.net\u002Fforum?id=wH7Wv0nAm8), Bi-Level Motion Imitation for Humanoid Robots, [website](https:\u002F\u002Fsites.google.com\u002Fview\u002Fbmi-corl2024)\n\n## Navigation\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.04515), EgoActor: Grounding Task Planning into Spatial-aware Egocentric Actions for Humanoid Robots via Visual-Language Models\n- [arXiv 2026.01](https:\u002F\u002Farxiv.org\u002Fabs\u002F2601.12790), FocusNav: Spatial Selective Attention with Waypoint Guidance for Humanoid Local Navigation\n- 🌟[arXiv 2025.12](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.01046), STATE-NAV: Stability-Aware Traversability Estimation for Bipedal Navigation on Rough Terrain \u002F [code](https:\u002F\u002Fgithub.com\u002Fyzwfromk\u002FSTATE-NAV)\n- [arXiv 2025.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.20351), Thinking in 360: Humanoid Visual Search in the Wild\n- [arXiv 2025.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.14625), Gallant: Voxel Grid-based Humanoid Locomotion and Local-navigation across 3D Constrained Terrains\n- [arXiv 2025.09](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.11388), Quantum deep reinforcement learning for humanoid robot navigation task\n- [arXiv 2025.08](https:\u002F\u002Farxiv.org\u002Fabs\u002F2508.06779), Learning Social Navigation from Positive and Negative Demonstrations and Rule-Based Specifications\n- [arXiv 2025.08](https:\u002F\u002Farxiv.org\u002Fabs\u002F2508.14466), LookOut: Real-World Humanoid Egocentric Navigation\n- [arXiv 2025.08](https:\u002F\u002Farxiv.org\u002Fabs\u002F2508.04931), INTENTION: Inferring Tendencies of Humanoid Robot Motion Through Interactive Intuition and Grounded VLM\n- [arXiv 2025.08](https:\u002F\u002Farxiv.org\u002Fabs\u002F2508.03068), Hand-Eye Autonomous Delivery: Learning Humanoid Navigation, Locomotion and Reaching\n- [arXiv 2025.07](https:\u002F\u002Fwww.arxiv.org\u002Fabs\u002F2507.20217), Humanoid Occupancy: Enabling A Generalized Multimodal Occupancy Perception System on Humanoid Robots\n- [arXiv 2025.06](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.02206), RL with Data Bootstrapping for Dynamic Subgoal Pursuit in Humanoid Robot Navigation\n- [arXiv 2025.05](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.08712), NavDP: Learning Sim-to-Real Navigation Diffusion Policy with Privileged Information Guidance\n- [arXiv 2025.03](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.09010), HumanoidPano: Hybrid Spherical Panoramic-LiDAR Cross-Modal Perception for Humanoid Robots\n- [arXiv 2024.12](https:\u002F\u002Farxiv.org\u002Fabs\u002F2412.04453), **NaVILA**: Legged Robot Vision-Language-Action Model for Navigation, [website](https:\u002F\u002Fnavila-bot.github.io\u002F)\n- [arXiv 2024.12](https:\u002F\u002Farxiv.org\u002Fabs\u002F2412.00396), ARMOR: Egocentric Perception for Humanoid Robot Collision Avoidance and Motion Planning\n- [arXiv 2023.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.07896), NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration\n- arXiv 2025.07, LOVON: Legged Open-Vocabulary Object Navigator, [website](https:\u002F\u002Fdaojiepeng.github.io\u002FLOVON\u002F)\n\n## State Estimation\n- [arXiv 2025.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.18857), AutoOdom: Learning Auto-regressive Proprioceptive Odometry for Legged Locomotion\n- [arXiv 2025.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.16306), InEKFormer: A Hybrid State Estimator for Humanoid Robots\n- [arXiv 2025.07](https:\u002F\u002Farxiv.org\u002Fabs\u002F2507.10105), Physics-Informed Neural Networks with Unscented Kalman Filter for Sensorless Joint Torque Estimation\n- [arXiv 2022.07](https:\u002F\u002Farxiv.org\u002Fabs\u002F2207.06780), An Empirical Evaluation of Four Off-the-Shelf Proprietary Visual-Inertial Odometry Systems\n- [arXiv 2019.04](https:\u002F\u002Farxiv.org\u002Fabs\u002F1904.09251), Contact-Aided Invariant Extended Kalman Filtering for Robot State Estimation\n- [arXiv 2017.05](https:\u002F\u002Farxiv.org\u002Fabs\u002F1712.05873), Legged Robot State-Estimation Through Combined Forward Kinematic and Preintegrated Contact Factors\n- [arXiv 2014.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F1410.1465), The invariant extended Kalman filter as a stable observer\n- [website](https:\u002F\u002Fgtsam.org\u002F), GTSAM: Factor graphs for Sensor Fusion in Robotics\n- [github](https:\u002F\u002Fgithub.com\u002FMIT-SPARK\u002FKimera), Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and Mapping\n- [github](https:\u002F\u002Fgithub.com\u002FHKUST-Aerial-Robotics\u002FVINS-Fusion), VINS-Fusion: An optimization-based multi-sensor state estimator\n- [github](https:\u002F\u002Fgithub.com\u002FUZ-SLAMLab\u002FORB_SLAM3), ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM\n\n\n## Sim-to-Real\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.08594), MOSAIC: Bridging the Sim-to-Real Gap in Generalist Humanoid Motion Tracking and Teleoperation with Rapid Residual Adaptation\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.01515), RAPT: Model-Predictive Out-of-Distribution Detection and Failure Diagnosis for Sim-to-Real Humanoid Robots\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.00401), ZEST: Zero-shot Embodied Skill Transfer for Athletic Robot Control\n- 🌟 [arXiv 2026.01](https:\u002F\u002Farxiv.org\u002Fabs\u002F2601.21363), Towards Bridging the Gap between Large-Scale Pretraining and Efficient Finetuning for Humanoid Control, [website](https:\u002F\u002Flift-humanoid.github.io\u002F) \u002F [code](https:\u002F\u002Fgithub.com\u002Fbigai-ai\u002FLIFT-humanoid)\n- [arXiv 2025.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.01708), PolySim: Bridging the Sim-to-Real Gap for Humanoid Control via Multi-Simulator Dynamics Randomization\n- [arXiv 2025.09](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.12858), Contrastive Representation Learning for Robust Sim-to-Real Transfer of Adaptive Humanoid Locomotion\n- [arXiv 2025.09](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.06342), Towards bridging the gap: Systematic sim-to-real transfer for diverse legged robots\n- [arXiv 2025.08](https:\u002F\u002Farxiv.org\u002Fabs\u002F2508.12252), Robot Trains Robot: Automatic Real-World Policy Adaptation and Learning for Humanoids\n- [arXiv 2025.05](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.24068), DiffCoTune: Differentiable Co-Tuning for Cross-domain Robot Control\n- [arXiv 2025.05](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.14266), Sampling-Based System Identification with Active Exploration for Legged Robot Sim2Real Learning\n- [arXiv 2025.04](https:\u002F\u002Farxiv.org\u002Fabs\u002F2504.06585), Sim-to-Real of Humanoid Locomotion Policies via Joint Torque Space Perturbation Injection\n- [arXiv 2025.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.10894), Bridging the Sim-to-Real Gap for Athletic Loco-Manipulation\n- [arXiv 2019.01](https:\u002F\u002Farxiv.org\u002Fabs\u002F1901.08652), Learning Agile and Dynamic Motor Skills for Legged Robots\n\n## Hardware Design\n- [arXiv 2026.02](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.08518), Characteristics, Management, and Utilization of Muscles in Musculoskeletal Humanoids\n- [arXiv 2026.01](https:\u002F\u002Farxiv.org\u002Fabs\u002F2601.18963), Fauna Sprout: A lightweight, approachable, developer-ready humanoid robot\n- [arXiv 2025.12](https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.24657), Antagonistic Bowden-Cable Actuation of a Lightweight Robotic Hand: Toward Dexterous Manipulation for Payload Constrained Humanoids\n- [arXiv 2025.12](https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.16705), Olaf: Bringing an Animated Character to Life in the Physical World\n- [arXiv 2025.12](https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.08920), OSMO: Open-Source Tactile Glove for Human-to-Robot Skill Transfer\n- [arXiv 2025.12](https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.07998), DIJIT: A Robotic Head for an Active Observer\n- [arXiv 2025.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.10021), DecARt Leg: Design and Evaluation of a Novel Humanoid Robot Leg with Decoupled Actuation for Agile Locomotion\n- [arXiv 2025.11](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.06796), Human-Level Actuation for Humanoids\n- [arXiv 2025.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.22336), Toward Humanoid Brain-Body Co-design: Joint Optimization of Control and Morphology for Fall Recovery\n- [arXiv 2025.10](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.03081), Embracing Evolution: A Call for Body-Control Co-Design in Embodied Humanoid Robot\n- [arXiv 2025.09](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.26082), Evolutionary Continuous Adaptive RL-Powered Co-Design for Humanoid Chin-Up Performance\n- [arXiv 2025.09](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.16469), A Framework for Optimal Ankle Design of Humanoid Robots\n- [arXiv 2025.09](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.14935), CAD-Driven Co-Design for Flight-Ready Jet-Powered Humanoids\n- [arXiv 2025.09](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.09364), AGILOped: Agile Open-Source Humanoid Robot for Research\n- [arXiv 2025.07](https:\u002F\u002Farxiv.org\u002Fabs\u002F2507.14538), A 21-DOF Humanoid Dexterous Hand with Hybrid SMA-Motor Actuation: CYJ Hand-0\n- [arXiv 2025.07](https:\u002F\u002Farxiv.org\u002Fabs\u002F2507.03227), Dexterous Teleoperation of 20-DoF ByteDexter Hand via Human Motion Retargeting\n- [arXiv 2025.06](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.20343), PIMBS: Efficient Body Schema Learning for Musculoskeletal Humanoids\n- [arXiv 2025.06](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.12314), Explosive Output to Enhance Jumping Ability: A Variable Reduction Ratio Design Paradigm for Humanoid Robots Knee Joint\n- [arXiv 2025.06](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.07490), RAPID Hand: A Robust, Affordable, Perception-Integrated, Dexterous Manipulation Platform for Generalist Robot Autonomy\n- [arXiv 2025.06](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.01125), iRonCub 3: The Jet-Powered Flying Humanoid Robot\n- [arXiv 2025.04](https:\u002F\u002Farxiv.org\u002Fabs\u002F2504.17249), Berke","该项目是一个关于人形机器人学习的学术论文列表，主要收集了涉及人形机器人学习任务的相关研究。其核心功能是将这些论文按照研究重点进行分类，如全身控制、操作、远程操作等，并特别标注了包含真实机器人实验和开源代码的论文。项目采用Python语言编写，并在GitHub上获得了2251颗星和131次分叉，遵循MIT许可证。它适合于从事人形机器人研究与开发的专业人士、学者以及对相关领域感兴趣的读者使用，为他们提供了一个全面了解当前研究进展和技术趋势的平台。",2,"2026-06-11 03:42:29","high_star"]