Haoyi Niu

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

• Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models
  2026/7/1
• ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow
  2026/7/1
• A Recipe for Efficient Sim-to-Real Transfer in Manipulation with Online Imitation-Pretrained World Models
  2025/10/1
• PhysiAgent: An Embodied Agent Framework in Physical World
  2025/9/1
• Efficient Robotic Policy Learning via Latent Space Backward Planning
  2025/5/1
• Skill Expansion and Composition in Parameter Space
  2025/2/1
• xTED: Cross-Domain Adaptation via Diffusion-Based Trajectory Editing
  2024/9/1
• Multi-Objective Trajectory Planning with Dual-Encoder
  2024/3/1
• DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning
  2024/2/1
• A Comprehensive Survey of Cross-Domain Policy Transfer for Embodied Agents
  2024/2/1
• H2O+: An Improved Framework for Hybrid Offline-and-Online RL with Dynamics Gaps
  2023/9/1
• Continual Driving Policy Optimization with Closed-Loop Individualized Curricula
  2023/9/1
• Stackelberg Driver Model for Continual Policy Improvement in Scenario-Based Closed-Loop Autonomous Driving
  2023/9/1
• A Versatile and Efficient Reinforcement Learning Framework for Autonomous Driving
  2021/10/1
• DR2L: Surfacing Corner Cases to Robustify Autonomous Driving via Domain Randomization Reinforcement Learning
  2021/7/1