Zekun Qi

Tsinghua University

収録論文 15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
• DeformGen: Dynamics-Based Topology Augmentation for Deformable Manipulation Policy Learning
  2026/6/1
• ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?
  2026/6/1
• LIMMT: Less is More for Motion Tracking
  2026/6/1
• Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking
  2026/6/1
• Disentangled Robot Learning via Separate Forward and Inverse Dynamics Pretraining
  2026/4/1
• Learning Athletic Humanoid Tennis Skills from Imperfect Human Motion Data
  2026/3/1
• VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model
  2026/2/1
• ReWorld: Multi-Dimensional Reward Modeling for Embodied World Models
  2026/1/1
• Switch-JustDance: Benchmarking Whole Body Motion Tracking Controllers Using a Commercial Console Game
  2025/11/1
• MM-Nav: Multi-View VLA Model for Robust Visual Navigation via Multi-Expert Learning
  2025/10/1
• DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge
  2025/7/1
• DexVLG: Dexterous Vision-Language-Grasp Model at Scale
  2025/7/1
• SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation
  2025/2/1