Lixin Yang

Shanghai Jiao Tong University

収録論文 14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

• Track4Action: 世界中心の3Dトラッカーを視覚言語行動ポリシーに蒸留する
  VLA2026/8/4

  デモ動画のフレーム遷移から得られる3Dトラッカー特徴を教師信号としてVLAポリシーに蒸留し、推論時はトラッカー不要で高い成功率を達成するフレームワークを提案。

• Track4Action: Distilling World-Centric 3D Tracker into Vision-Language-Action Policies
  2026/8/1
• AnyDexRT: Calibration-Free Dexterous Hand Retargeting with Few-Shot Human Guidance
  2026/7/1
• ChronoFlow-Policy: Unifying Past-Current-Future Interaction Flow in Visuomotor Policy Learning
  2026/6/1
• Revisiting Articulated Parts Perception in Robot Manipulation
  2026/6/1
• X-Imitator: Spatial-Aware Imitation Learning via Bidirectional Action-Pose Interaction
  2026/5/1
• LIDEA: Human-to-Robot Imitation Learning via Implicit Feature Distillation and Explicit Geometry Alignment
  2026/4/1
• LaMP: Learning Vision-Language-Action Policy with 3D Scene Flow as Latent Motion Prior
  2026/3/1
• AG-MPBS: a Mobility-Aware Prediction and Behavior-Based Scheduling Framework for Air-Ground Unmanned Systems
  2025/12/1
• L1 Sample Flow for Efficient Visuomotor Learning
  2025/11/1
• TrajBooster: Boosting Humanoid Whole-Body Manipulation via Trajectory-Centric Learning
  2025/9/1
• AirExo-2: Scaling up Generalizable Robotic Imitation Learning with Low-Cost Exoskeletons
  2025/3/1
• Dense Policy: Bidirectional Autoregressive Learning of Actions
  2025/3/1
• Motion Before Action: Diffusing Object Motion as Manipulation Condition
  2024/11/1