Xiaolong Wang

収録論文 100本 ・ フィジカルAI/ロボット学習

※arXiv著者名で収集。同姓同名の別人の論文が含まれる場合があります。

論文

• ReForce: 力覚を考慮した器用な操作のためのリターゲティング学習
  マニピュレーション2026/8/16

  人間のデモからロボットの操作へ変換する際、運動学的なリターゲティングに加えて力の情報を考慮し、接触を再現する手法を提案。シミュレーションと実機で力追従誤差を低減し、多指接触を強化した。

• FACT: 失敗を考慮した因果的ワールドアクションモデルの訓練
  VLA2026/8/10

  ワールドアクションモデルに失敗データを組み込み、行動の結果を予測する因果的モデルを提案。シミュレーションと実機の双腕操作で既存手法を上回る性能を示した。

• FACT: Failure-Aware Causal Training for World-Action Models
  2026/8/1
• Hallucination in World Models is Predictable and Preventable
  2026/6/1
• Generating Robot Hands from Human Demonstrations
  2026/6/1
• ConTrack: Constrained Hand Motion Tracking with Adaptive Trade-off Control
  2026/6/1
• EgoPhys: Learning Generalizable Physics Models of Deformable Objects from Egocentric Video
  2026/6/1
• TactX: Learning Shared Tactile Representations Across Diverse Sensors
  2026/6/1
• Lucid-XR: An Extended-Reality Data Engine for Robotic Manipulation
  2026/5/1
• TacO: Benchmarking Tactile Sensors for Object Manipulation
  2026/5/1
• EgoVerse: An Egocentric Human Dataset for Robot Learning from Around the World
  2026/4/1
• Long-Horizon Manipulation via Trace-Conditioned VLA Planning
  2026/4/1
• Human-Robot Copilot for Data-Efficient Imitation Learning
  2026/4/1
• Cross-Hand Latent Representation for Vision-Language-Action Models
  2026/3/1
• Contact-Aware Neural Dynamics
  2026/1/1
• House of Dextra: Cross-embodied Co-design for Dexterous Hands
  2025/12/1
• Learning Massively Multitask World Models for Continuous Control
  2025/11/1
• ACE-F: A Cross Embodiment Foldable System with Force Feedback for Dexterous Teleoperation
  2025/11/1
• In-N-On: Scaling Egocentric Manipulation with in-the-wild and on-task Data
  2025/11/1
• HMC: Learning Heterogeneous Meta-Control for Contact-Rich Loco-Manipulation
  2025/11/1
• From Power to Precision: Learning Fine-grained Dexterity for Multi-fingered Robotic Hands
  2025/11/1
• GSWorld: Closed-Loop Photo-Realistic Simulation Suite for Robotic Manipulation
  2025/10/1
• VT-Refine: Learning Bimanual Assembly with Visuo-Tactile Feedback via Simulation Fine-Tuning
  2025/10/1
• Learning to Design Soft Hands using Reward Models
  2025/10/1
• Object Pose Estimation through Dexterous Touch
  2025/9/1
• ManiFlow: A General Robot Manipulation Policy via Consistency Flow Training
  2025/9/1
• EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos
  2025/7/1
• GMT: General Motion Tracking for Humanoid Whole-Body Control
  2025/6/1
• Dex1B: Learning with 1B Demonstrations for Dexterous Manipulation
  2025/6/1
• AMO: Adaptive Motion Optimization for Hyper-Dexterous Humanoid Whole-Body Control
  2025/5/1
• Co-Design of Soft Gripper with Neural Physics
  2025/5/1
• M3: 3D-Spatial MultiModal Memory
  2025/3/1
• Humanoid Policy ~ Human Policy
  2025/3/1
• Integrating LMM Planners and 3D Skill Policies for Generalizable Manipulation
  2025/1/1
• Mobile-TeleVision: Predictive Motion Priors for Humanoid Whole-Body Control
  2024/12/1
• NaVILA: Legged Robot Vision-Language-Action Model for Navigation
  2024/12/1
• ExBody2: Advanced Expressive Humanoid Whole-Body Control
  2024/12/1
• WildLMa: Long Horizon Loco-Manipulation in the Wild
  2024/11/1
• SPOT: SE(3) Pose Trajectory Diffusion for Object-Centric Manipulation
  2024/11/1
• HOVER: Versatile Neural Whole-Body Controller for Humanoid Robots
  2024/10/1
• Visual Manipulation with Legs
  2024/10/1
• Helpful DoggyBot: Open-World Object Fetching using Legged Robots and Vision-Language Models
  2024/10/1
• GraspSplats: Efficient Manipulation with 3D Feature Splatting
  2024/9/1
• ACE: A Cross-Platform Visual-Exoskeletons System for Low-Cost Dexterous Teleoperation
  2024/8/1
• Lessons from Learning to Spin "Pens"
  2024/7/1
• A Simulation Benchmark for Autonomous Racing with Large-Scale Human Data
  2024/7/1
• Open-TeleVision: Teleoperation with Immersive Active Visual Feedback
  2024/7/1
• Bunny-VisionPro: Real-Time Bimanual Dexterous Teleoperation for Imitation Learning
  2024/7/1
• Cross-Embodiment Robot Manipulation Skill Transfer using Latent Space Alignment
  2024/6/1
• Hierarchical World Models as Visual Whole-Body Humanoid Controllers
  2024/5/1
• Visual Whole-Body Control for Legged Loco-Manipulation
  2024/3/1
• Sim2Real Manipulation on Unknown Objects with Tactile-based Reinforcement Learning
  2024/3/1
• DNAct: Diffusion Guided Multi-Task 3D Policy Learning
  2024/3/1
• Learning Generalizable Feature Fields for Mobile Manipulation
  2024/3/1
• CyberDemo: Augmenting Simulated Human Demonstration for Real-World Dexterous Manipulation
  2024/2/1
• Expressive Whole-Body Control for Humanoid Robots
  2024/2/1
• DexTouch: Learning to Seek and Manipulate Objects with Tactile Dexterity
  2024/1/1
• Robot Synesthesia: In-Hand Manipulation with Visuotactile Sensing
  2023/12/1
• Harmonic Mobile Manipulation
  2023/12/1
• Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis
  2023/12/1
• Generalized Animal Imitator: Agile Locomotion with Versatile Motion Prior
  2023/10/1
• TD-MPC2: Scalable, Robust World Models for Continuous Control
  2023/10/1
• Open X-Embodiment: Robotic Learning Datasets and RT-X Models
  2023/10/1
• GenSim: Generating Robotic Simulation Tasks via Large Language Models
  2023/10/1
• Finetuning Offline World Models in the Real World
  2023/10/1
• Dynamic Handover: Throw and Catch with Bimanual Hands
  2023/9/1
• GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fields
  2023/8/1
• AnyTeleop: A General Vision-Based Dexterous Robot Arm-Hand Teleoperation System
  2023/7/1
• DexArt: Benchmarking Generalizable Dexterous Manipulation with Articulated Objects
  2023/5/1
• ContactArt: Learning 3D Interaction Priors for Category-level Articulated Object and Hand Poses Estimation
  2023/5/1
• Neural Volumetric Memory for Visual Locomotion Control
  2023/4/1
• Rotating without Seeing: Towards In-hand Dexterity through Touch
  2023/3/1
• MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrations
  2022/12/1
• Policy Adaptation from Foundation Model Feedback
  2022/12/1
• On Pre-Training for Visuo-Motor Control: Revisiting a Learning-from-Scratch Baseline
  2022/12/1
• DexPoint: Generalizable Point Cloud Reinforcement Learning for Sim-to-Real Dexterous Manipulation
  2022/11/1
• Self-Supervised Geometric Correspondence for Category-Level 6D Object Pose Estimation in the Wild
  2022/10/1
• MonoNeRF: Learning Generalizable NeRFs from Monocular Videos without Camera Pose
  2022/10/1
• Visual Reinforcement Learning with Self-Supervised 3D Representations
  2022/10/1
• Learning Continuous Grasping Function with a Dexterous Hand from Human Demonstrations
  2022/7/1
• Graph Inverse Reinforcement Learning from Diverse Videos
  2022/7/1
• Category-Level 6D Object Pose Estimation in the Wild: A Semi-Supervised Learning Approach and A New Dataset
  2022/6/1
• Coordination-free Multi-robot Path Planning for Congestion Reduction Using Topological Reasoning
  2022/5/1
• Learning Generalizable Dexterous Manipulation from Human Grasp Affordance
  2022/4/1
• From One Hand to Multiple Hands: Imitation Learning for Dexterous Manipulation from Single-Camera Teleoperation
  2022/4/1
• Temporal Difference Learning for Model Predictive Control
  2022/3/1
• Look Closer: Bridging Egocentric and Third-Person Views with Transformers for Robotic Manipulation
  2022/1/1
• Vision-Guided Quadrupedal Locomotion in the Wild with Multi-Modal Delay Randomization
  2021/9/1
• DexMV: Imitation Learning for Dexterous Manipulation from Human Videos
  2021/8/1
• Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation
  2021/7/1
• Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformers
  2021/7/1
• Single RGB-D Camera Teleoperation for General Robotic Manipulation
  2021/6/1
• DAIR: Disentangled Attention Intrinsic Regularization for Safe and Efficient Bimanual Manipulation
  2021/6/1
• Learning Cross-Domain Correspondence for Control with Dynamics Cycle-Consistency
  2020/12/1
• Fast ORB-SLAM without Keypoint Descriptors
  2020/8/1
• Self-Supervised Policy Adaptation during Deployment
  2020/7/1
• State-Only Imitation Learning for Dexterous Manipulation
  2020/4/1
• Evolutionary Population Curriculum for Scaling Multi-Agent Reinforcement Learning
  2020/3/1
• Multi-Task Reinforcement Learning with Soft Modularization
  2020/3/1
• Visual Semantic Navigation using Scene Priors
  2018/10/1