Mingqi Yuan

The University of Hong Kong

収録論文 10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

• 統一条件・行動モデリングによる高精度ワンステップ行動生成
  マニピュレーション2026/8/17

  条件と行動を共有トークン空間で統一的にモデリングするUCA-Flowを提案し、推論速度を大幅に向上させつつ成功率を9.3ポイント改善した。

• GEM-Occ: From Visual Geometry Evidence to Embodied Semantic Occupancy Memory
  2026/7/1
• HiMem-WAM: Hierarchical Memory-Gated World Action Models for Robotic Manipulation
  2026/6/1
• Can Vision-Language-Action Models Learn from Real-World Data Continually without Forgetting?
  2026/5/1
• AIM: Intent-Aware Unified world action Modeling with Spatial Value Maps
  2026/4/1
• AtomVLA: Scalable Post-Training for Robotic Manipulation via Predictive Latent World Models
  2026/3/1
• PvP: Data-Efficient Humanoid Robot Learning with Proprioceptive-Privileged Contrastive Representations
  2025/12/1
• Gait-Adaptive Perceptive Humanoid Locomotion with Real-Time Under-Base Terrain Reconstruction
  2025/12/1
• A Survey of Behavior Foundation Model: Next-Generation Whole-Body Control System of Humanoid Robots
  2025/6/1
• Hierarchical Procedural Framework for Low-latency Robot-Assisted Hand-Object Interaction
  2024/5/1