Haoqi Yuan

Alibaba Inc.

収録論文 27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

• Ego2Robot: 自己中心視点の人間データからのスケーラブルなロボットデータ合成
  データ生成/VLA2026/8/3

  自己中心視点の人間の操作動画を、行動リターゲティングとロボットアームの視覚合成、品質キュレーションを経てロボット訓練データに変換するスケーラブルなパイプラインを提案し、大規模データでVLAモデルの汎化性能を向上させた。

• Ego2Robot: Scalable Robot Data Synthesis from Egocentric Human Data
  2026/8/1
• Human-Centric Transferable Tactile Pre-Training for Dexterous Robotic Manipulation
  2026/7/1
• Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models
  2026/6/16
• RealDexUMI: A Wearable Universal Manipulation Interface for Dexterous Robot Learning
  2026/6/1
• Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models
  2026/6/1
• Qwen-RobotNav Technical Report: A Scalable Navigation Model Designed for an Agentic Navigation System
  2026/6/1
• Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments
  2026/5/1
• X-DiffVLA: X-Embodied Diffusion Action Heads for Vision-Language-Action Models
  2026/5/1
• Conservative Offline Robot Policy Learning via Posterior-Transition Reweighting
  2026/3/1
• Joint-Aligned Latent Action: Towards Scalable VLA Pretraining in the Wild
  2026/2/1
• Rethinking Visual-Language-Action Model Scaling: Alignment, Mixture, and Regularization
  2026/2/1
• Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization
  2026/1/1
• UniTacHand: Unified Spatio-Tactile Representation for Human to Robotic Hand Skill Transfer
  2025/12/1
• Spatial-Aware VLA Pretraining through Visual-Physical Alignment from Human Videos
  2025/12/1
• Universal Dexterous Functional Grasping via Demonstration-Editing Reinforcement Learning
  2025/12/1
• Transport Discrepancy as a Reliability Signal for Vision-Language-Action Models
  2025/12/1
• DemoHLM: From One Demonstration to Generalizable Humanoid Loco-Manipulation
  2025/10/1
• Towards Proprioception-Aware Embodied Planning for Dual-Arm Humanoid Robots
  2025/10/1
• DemoGrasp: Universal Dexterous Grasping from a Single Demonstration
  2025/9/1
• Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos
  2025/7/1
• DualTHOR: A Dual-Arm Humanoid Simulation Platform for Contingency-Aware Planning
  2025/6/1
• Being-0: A Humanoid Robotic Agent with Vision-Language Models and Modular Skills
  2025/3/1
• Efficient Residual Learning with Mixture-of-Experts for Universal Dexterous Grasping
  2024/10/1
• Learning Diverse Bimanual Dexterous Manipulation Skills from Human Demonstrations
  2024/10/1
• Cross-Embodiment Dexterous Grasping with Reinforcement Learning
  2024/10/1
• DMotion: Robotic Visuomotor Control with Unsupervised Forward Model Learned from Videos
  2021/3/1