Yikai Wang

Beijing Normal University

収録論文 17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

• 未来を保持し、ロールアウトを捨てる：ワールドアクションモデルのためのRIFT
  VLA2026/8/12

  ロボットの行動生成に使われる将来予測の反復的なビデオ生成を不要にし、学習された予測トークンで将来のキャッシュを一度に構築する手法RIFTを提案。LIBEROとRoboTwinで高い成功率と低遅延を実現した。

• Keep the Future, Drop the Rollout: RIFT for World Action Models
  2026/8/1
• EvoScene-VLA: Evolving Scene Beliefs Inside the Action Decoder for Chunked Robot Control
  2026/5/1
• HALO: Learning Human-Robot Collaboration via Heterogeneous-Agent Lyapunov Policy Optimization
  2026/3/1
• APEX: Learning Adaptive High-Platform Traversal for Humanoid Robots
  2026/2/1
• ActiveVLA: Injecting Active Perception into Vision-Language-Action Models for Precise 3D Robotic Manipulation
  2026/1/1
• Spatial-Temporal Aware Visuomotor Diffusion Policy Learning
  2025/7/1
• Human2LocoMan: Learning Versatile Quadrupedal Manipulation with Human Pretraining
  2025/6/19
• Human2LocoMan: Learning Versatile Quadrupedal Manipulation with Human Pretraining
  2025/6/1
• FlowDreamer: A RGB-D World Model with Flow-based Motion Representations for Robot Manipulation
  2025/5/1
• LocoTouch: Learning Dynamic Quadrupedal Transport with Tactile Sensing
  2025/5/1
• EMOS: Embodiment-aware Heterogeneous Multi-robot Operating System with LLM Agents
  2024/10/1
• Guardians as You Fall: Active Mode Transition for Safe Falling
  2023/10/1
• Learning Robust, Agile, Natural Legged Locomotion Skills in the Wild
  2023/4/1
• Sound Adversarial Audio-Visual Navigation
  2022/2/1
• Elastic Tactile Simulation Towards Tactile-Visual Perception
  2021/8/1
• Elastic Interaction of Particles for Robotic Tactile Simulation
  2020/11/1