Li Yi

Tsinghua University

収録論文 37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

• HumanTracker: 人間の知覚に合致した包括的なモーション追跡ベンチマーク
  評価指標/ベンチマーク2026/8/13

  ヒューマノイドのモーション追跡評価を人間の知覚に合わせてスケーラブルにするため、約153時間の光学モーションデータからなるベンチマークと、選好に基づく評価指標HumanScoreを提案した。

• HumanTracker: Towards Comprehensive and Human-Aligned Motion Tracking Benchmark
  2026/8/1
• Scaling Behavior Foundation Model for Humanoid Robots
  2026/7/1
• LIMMT: Less is More for Motion Tracking
  2026/6/1
• Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking
  2026/6/1
• KPGrasp: Scalable Keypoint Flow Matching for Dexterous Grasp Generation
  2026/6/1
• Dexora: Open-source VLA for High-DoF Bimanual Dexterity
  2026/5/1
• Learning Athletic Humanoid Tennis Skills from Imperfect Human Motion Data
  2026/3/1
• LDA-1B: Scaling Latent Dynamics Action Model via Universal Embodied Data Ingestion
  2026/2/1
• Collision-Free Humanoid Traversal in Cluttered Indoor Scenes
  2026/1/1
• RF-MatID: Dataset and Benchmark for Radio Frequency Material Identification
  2026/1/1
• DexNDM: Closing the Reality Gap for Dexterous In-Hand Rotation via Joint-Wise Neural Dynamics Model
  2025/10/1
• Track Any Motions under Any Disturbances
  2025/9/1
• MotionTrans: Human VR Data Enable Motion-Level Learning for Robotic Manipulation Policies
  2025/9/1
• DexVLG: Dexterous Vision-Language-Grasp Model at Scale
  2025/7/1
• DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge
  2025/7/1
• Unleashing Humanoid Reaching Potential via Real-world-Ready Skill Space
  2025/5/1
• Learning Physics-Based Full-Body Human Reaching and Grasping from Brief Walking References
  2025/3/1
• SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation
  2025/2/1
• DexTrack: Towards Generalizable Neural Tracking Control for Dexterous Manipulation from Human References
  2025/2/1
• MobileH2R: Learning Generalizable Human to Mobile Robot Handover Exclusively from Scalable and Diverse Synthetic Data
  2025/1/1
• SyncDiff: Synchronized Motion Diffusion for Multi-Body Human-Object Interaction Synthesis
  2024/12/1
• Mimicking-Bench: A Benchmark for Generalizable Humanoid-Scene Interaction Learning via Human Mimicking
  2024/12/1
• Self-Supervised Monocular 4D Scene Reconstruction for Egocentric Videos
  2024/11/1
• QuasiSim: Parameterized Quasi-Physical Simulators for Dexterous Manipulations Transfer
  2024/4/1
• PhysReaction: Physically Plausible Real-Time Humanoid Reaction Synthesis via Forward Dynamics Guided 4D Imitation
  2024/4/1
• GenH2R: Learning Generalizable Human-to-Robot Handover via Scalable Simulation, Demonstration, and Imitation
  2024/1/1
• Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-Language Planning
  2023/11/1
• TransTouch: Learning Transparent Objects Depth Sensing Through Sparse Touches
  2023/9/1
• UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-aware Curriculum and Iterative Generalist-Specialist Learning
  2023/4/1
• UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy
  2023/3/1
• Enhancing Generalizable 6D Pose Tracking of an In-Hand Object with Tactile Sensing
  2022/10/1
• Fixing Malfunctional Objects With Learned Physical Simulation and Functional Prediction
  2022/5/1
• Multi-Robot Active Mapping via Neural Bipartite Graph Matching
  2022/3/1
• SAPIEN: A SimulAted Part-based Interactive ENvironment
  2020/3/1
• Category-Level Articulated Object Pose Estimation
  2019/12/1
• ShapeNet: An Information-Rich 3D Model Repository
  2015/12/1