Awesome-Humanoid-Robot-Learning

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🌟.

Feel free to pull a request for new papers/codes about humanoid robot learning.

• Awesome-Humanoid-Robot-Learning
  • Loco-Manipulation and Whole-Body-Control
  • Manipulation
  • Teleoperation
  • Locomotion
  • Navigation
  • State Estimation
  • Sim-to-Real
  • Hardware Design
  • Simulation Benchmark
  • Physics-Based Character Animation
  • Human Motion Analysis and Synthesis
• Contact

---

Loco-Manipulation and Whole-Body-Control

• arXiv 2026.10, METATRON: A Promptable Whole-Body Execution Layer for Humanoids, website
• arXiv 2026.10, Mimetic Embodiment Transfer of Human-Humanoid Interaction from In-the-Wild Videos
• arXiv 2026.10, GRAFT: Geometry-Aware Residual Adaptation for Foundation Trackers, website
• Humanoids 2026, Whole-Body Humanoid Control via Stochastic Motion Tokenization
• arXiv 2026.10, Learning Multi-Phase Robot Loco-Manipulation via Phase-Conditioned Policy Optimization
• arXiv 2026.10, Learning Force-Reactive Humanoid Loco-Manipulation, website
• arXiv 2026.10, Zero-HLM: Generalizable Humanoid Loco-Manipulation without Real Robot Data, website
• arXiv 2026.10, HuGe: Scaling Humanoid Generalist Vision-Language-Action Models with Egocentric Experience
• CoRL 2026, HumanoidNDM: Closing the Training-Deployment Gap of Motion Tracking via Humanoid Neural Dynamics Model
• arXiv 2026.10, MimicAll: Structured Embodiment Conditioning for Cross-Humanoid Whole-Body Motion Tracking
• arXiv 2026.10, MOTIO: Agentic Skill Engineering for Reality-Grounded Humanoid Loco-Manipulation,

Manipulation

• arXiv 2026.10, EmbodyHOI: Embodiment-Aware Generation of Hand-Object Interactions for Humanoid Dexterous Manipulation
• arXiv 2026.10, Data-Efficient Learning from Demonstration for Humanoid Robots via Feature-Level Perception and Prompt-Based Object Detection
• arXiv 2026.10, Compositional Humanoid Manipulation through Isomorphic Teleoperation and Independent Skill Routing
• arXiv 2026.10, Spark-0: Scaling Spatially Aligned Tactile Pretraining for Robot Dexterous Manipulation, website
• arXiv 2026.10, Immiscible Diffusion Policy: Preserving Multimodal Robot Actions through Label-Free Noise Assignment
• arXiv 2026.10, AutodidactWAM: Cross-Modal Self-Distillation from Generated Video to Robot Actions
• arXiv 2026.10, MobileVISTA: Generative Data Augmentation for Pose Generalization in Mobile Manipulation, website
• arXiv 2026.09, IronMind: Scaling Humanoid Dexterous Manipulation via Camera-Space Ego-Centric Pretraining, website
• arXiv 2026.09, Principal Steering Subspaces for Online Adaptation of Frozen Generative Robot Policies
• arXiv 2026.09, XPACE: Joint World and Action Modeling from Heterogeneous Experience
• arXiv 2026.09, How to Better Train VLAs: Lessons Learned From the REAL-I Challenge at ICRA 2026

Teleoperation

• arXiv 2026.10, HuMiT: Low-Latency Whole-Body Humanoid Teleoperation via Compact Reference Tracking, website
• arXiv 2026.10, Evaluating Lightweight Contact Feedback in Dual-Operator Collaborative Humanoid Teleoperation, website
• arXiv 2026.10, Beyond Retargeting: Low-Latency and Robust Humanoid Whole-Body Teleoperation with Learned Atomic Motion Primitives
• IROS 2026 Workshop, Toward Humanoid Robots in Construction: A Teleoperation Feasibility Study
• arXiv 2026.09, NEXUS: Perceptive Whole-Body Control for Terrain-Adaptive Teleoperation, website
• arXiv 2026.09, GAE: General Action Expert for Real-Time Humanoid Teleoperation, website
• arXiv 2026.09, MATE: Multi-Agent Virtual Teleoperation Platform for Humanoid Collaboration Data Collection, website
• arXiv 2026.09, Gated Residual Body-Hand Coordination for Whole-Body Humanoid Teleoperation
• arXiv 2026.09, SPOT: Spatial Perception-Oriented Long-Horizon Humanoid Teleoperation
• arXiv 2026.08, Teleopit: A Full-Embodiment Humanoid Teleoperation System,

Locomotion

• Humanoids 2026, FORGE: Feasible Online Reduced-Order Reference Generation and Whole-Body Execution for Agile Humanoid Locomotion
• arXiv 2026.10, HC2Robot: Hyper-Connection Transformers with Predicted Foresight for Multi-Terrain Humanoid Parkour
• 🌟Humanoids 2026, REACH: An RL-based Hierarchical Humanoid Crawling Framework for Adaptable Confined Space Traversal, website
• arXiv 2026.10, Active Reachability Learning for Humanoid Recoverability Monitoring
• arXiv 2026.10, Humanoid Mobility via Attention-based Contacts
• arXiv 2026.10, MPBRS: Multi-Potential-Based Reward Shaping for Unified Reward Configuration in Humanoid Locomotion
• arXiv 2026.10, Do Earth-Trained Humanoid Controllers Walk on the Moon? Gravity, Terrain, and Soil Transfer
• arXiv 2026.10, Test-Time Motion Steering for Perceptive Humanoid Fall Recovery, website
• arXiv 2026.10, Watch Your Step: Anticipated Perception for Humanoid Locomotion, website
• arXiv 2026.10, Validation of Human Motor Development Scales with Humanoid Robots
• CoRL 2026, Push the Limit: Learning High-Speed Sprinting and Aggressive Cornering on a Full-Scale Humanoid

Navigation

• 🌟arXiv 2026.10, Adaptive Traversal Tubes for Posture-Aware Navigation of Bipedal Humanoids
• arXiv 2026.10, TAPNAV: Humanoid Navigation through Tactile Active Perception
• arXiv 2026.10, What the Elevation Map Cannot See: Semantic-Aware Locomotion and Execution-Aware Navigation for Humanoid Robot
• arXiv 2026.09, DODGER: Safety-Guided Reinforcement Learning for Robot Navigation Among Dynamic Obstacles, website
• arXiv 2026.09, Learning Safe Humanoid Navigation from Reduced Order Models, website
• arXiv 2026.09, TANGO: Humanoid Navigation in Cluttered Environments with a Whole-Body Vision-Language-Action Model
• arXiv 2026.08, EgoNav: Bridging Learned Waypoints and Geometry-Aware Local Control for Robust Indoor Navigation
• arXiv 2026.08, HumanoidVLN: A Physics-Grounded Simulator and Benchmark for Vision-Language Navigation Across Diverse Humanoid Embodiments, website
• arXiv 2026.07, RAVEN: Reinforcement-Adaptive Visibility-Graph Planning for Robust Humanoid Navigation with Collision-Free MPC
• arXiv 2026.06, LP-NavOA: Integrated Local Navigation and Obstacle Avoidance for Humanoid Robots under Limited Perception
• arXiv 2026.06, GuideWalk: Learning Unified Autonomous Navigation and Locomotion for Humanoid Robots across Versatile Terrains,

State Estimation

• 🌟arXiv 2026.10, Vision as Proprioception: Estimating Humanoid Robot Pose from Video
• 🌟arXiv 2026.09, PRIMO: Prior-Informed Odometry from Human-Motion Tracking for Humanoid Robots
• arXiv 2026.09, A Multimodal Label Forecasting Method for Aperiodic Visuo-Motor Time Series
• arXiv 2026.09, FOCUS: Foot Observation Confidence for Robust Humanoid Proprioceptive Odometry
• TMECH 2026, KILVO: Kinematic-Inertial-LiDAR-Visual Odometry with Robust Multimodal Adaptation for Humanoid Robots
• arXiv 2026.06, Proprioceptive Invariant State Estimation for Humanoid Robots on Non-Inertial Ground
• arXiv 2026.06, Proprioceptive-visual correspondence enables self-other distinction in humanoid robots, website
• RSS 2026, PRIME: Physically-consistent Robotic Inertial and Motion Estimation for Legged and Humanoid Robots
• RSS 2026, CoCo-InEKF: State Estimation with Learned Contact Covariances in Dynamic, Contact-Rich Scenarios
• arXiv 2026.05, SixthSense: Task-Agnostic Proprioception-Only Whole-Body Wrench Estimation for Humanoids
• arXiv 2025.11, AutoOdom: Learning Auto-regressive Proprioceptive Odometry for Legged Locomotion
• arXiv 2025.11, InEKFormer: A Hybrid State Estimator for Humanoid Robots

Sim-to-Real

• arXiv 2026.10, Delay Randomization Widens the Delay Margin of Learned Humanoid Motion Trackers
• arXiv 2026.10, Contact-UAN: Unsupervised Actuator Networks as a Residual World Model for Humanoid Control, website
• arXiv 2026.10, Informationally Decoupled Trajectory Design for Sim-to-Real System Identification
• arXiv 2026.09, Bundled Contact Gradients: Stabilizing Differentiable Simulation for Deployable Dynamic Tasks, website
• arXiv 2026.09, Online Sim-to-Real Adaptation via Closed-Loop System Modeling, website
• arXiv 2026.06, FADA: Few-Shot Domain Adaptation via Dynamics Alignment for Humanoid Control, website
• RSS 2026, asRoBallet: Closing the Sim2Real Gap via Friction-Aware Reinforcement Learning for Underactuated Spherical Dynamics, website
• arXiv 2026.03, AGILE: A Comprehensive Workflow for Humanoid Loco-Manipulation Learning
• arXiv 2026.03, HALO:Closing Sim-to-Real Gap for Heavy-loaded Humanoid Agile Motion Skills via Differentiable Simulation, website

Hardware Design

• arXiv 2026.10, A fully articulated humanoid dexterous hand with human-level joint structure enabled by linkage-based actuation
• Humanoids 2026, PHD-Hand: A Printable Humanoid Dexterous Hand with Linkage-Driven 3-DOA Digits
• arXiv 2026.10, Design and Analysis of a Nonlinear Parallel Mechanism Coupling for Dynamic Humanoid Legs
• arXiv 2026.10, PhoneBot: A Low-Cost Open Humanoid Robot Platform Reusing Smartphones, website
• arXiv 2026.09, GlowTact: Simple and Compact Vision-Based Tactile Sensing with High Sensitivity and Spatial Resolution, website
• IROS 2026 Workshop, Tactile Sensing Array for Multi-Phalanx Sensing in Humanoid Hands
• arXiv 2026.09, Visible-Reachable Workspace for Perception-Aware Humanoid Design, website
• arXiv 2026.09, BRIDGE: An Open-Source Humanoid Platform via Morphology-Control Co-Design for Physical AI, website
• AIM 2026, A Dual-Cam Parallel Elastic Actuator with Shared Gas-Spring Compensation for Humanoid Ankles
• IROS 2026, Design of a Biomimetic Joint-Covering Skin with Tissue-Like Structure to Enhance Proprioception in a Musculoskeletal Humanoid,

Simulation Benchmark

• arXiv 2026.10, LocoManiLab: A Unified Testbed for Data, Policies, Controllers, and Deployment in Humanoid Loco-Manipulation
• 🌟arXiv 2026.10, RoboQuest: Generalist Physical Agents that Search, Inspect and Test, website
• arXiv 2026.10, Benchmarking Behavioral Steerability in Behavior Foundation Models
• 🌟arXiv 2026.10, BiGym 2.0: Benchmarking Learned and Agent-Developed Policies for Humanoid Household Manipulation
• 🌟arXiv 2026.10, R2RI: A Multi-View Event and RGB Dataset for Robot-to-Robot Interaction
• arXiv 2026.10, HumanoidToolBench: Benchmarking Humanoid Tool Use from Selection to Mobile Execution, website
• arXiv 2026.09, Fiatlux: A Long-Horizon Benchmark for Humanoid Ladder Climbing and Light-Bulb Replacement, website
• arXiv 2026.09, CoHuB: A Simulation Benchmark for Multi-Humanoid Collaboration, website
• arXiv 2026.09, Traceable Human-to-Humanoid Sign Language Benchmarking
• arXiv 2026.09, MSK-Bench: Benchmarking Full-Body Musculoskeletal Motor Control Across Tasks, Control Paradigms, and Physiological Metrics,

Physics-Based Character Animation

• SIGGRAPH 2010, Spatial relationship preserving character motion adaptation
• CoRL 2026, Walk Like This: Stylized Locomotion for Physics-Based Characters through Example-Driven Diffusion
• 🌟arXiv 2026.10, Scalable Multi-Human Cooperative Manipulation via Commander-Executor Coordination
• arXiv 2026.10, From Digital Human Interactions to Physics-Based Humanoid Skills: Physics-Grounded Post-Training of Interaction Generators
• arXiv 2026.10, Co²Skill: Whole-Body Control via Skill Composition for Long-Horizon Human-Environment Interaction
• arXiv 2026.09, LYRIC: Language-Driven Physics-Based Character Control for Contact-Rich Whole-Body Object Interaction, website
• arXiv 2026.09, DSD: Learning Diverse and Reusable Motor Skills via Diffusion Skill Discovery
• SIGGRAPH Asia 2026, InstantMimic: A High Performance System for Learning Physics-based Skills in Seconds, website
• SIGGRAPH Asia 2026, Unifying Physics-Based Humanoid Interaction with a Context-Conditioned Interaction Prior, website
• arXiv 2026.08, Progressively Learning Heterogeneous Skills in a Unified Latent Space

Human Motion Analysis and Synthesis

• arXiv 2026.10, PhysibleMDM: Enforcing Inference-Time Physical Feasibility Constraints on Motion Diffusion Models via Noise Optimization
• arXiv 2026.10, TRACE: Typed Reference-Aware Conversational Editing for Humanoid Motion Diffusion
• arXiv 2026.10, PartiGen: Part-Aware Representations for Language-Conditioned Humanoid Motion Generation
• arXiv 2026.10, Streaming Multi-Track Timeline Control for 3D Human Motion Generation, website
• SIGGRAPH Asia 2026, ReCHOIR: Contact-guided Human Object Interaction Retargeting to Diverse Characters, website
• ECCV 2026, RoboGesture: Real-Time Semantic-aligned Co-Speech Gestures Generation for Humanoid Interaction, website
• arXiv 2026.08, PAMoR: Parameterized Affective Motion Generation in Real Time for Humanoid Robots
• CoRL 2026, HiPHI: A Large-Scale Benchmark for High-Precision Human Motion and Object-Interaction, website
• arXiv 2026.08, GenTrack: Physical Alignment for Robot-Native Motion Generation and Zero-Shot Humanoid Tracking
• arXiv 2026.07, EgoHTR: Egocentric 4D Demonstrations of Human Terrain Traversal,

---

Contact

If you have questions/suggestions, feel free to email Yanjie Ze.