Zhenghao Peng

収録論文 21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

• DiSCo: Diffusion Sequence Copilots for Shared Autonomy
  2026/3/1
• Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail
  2025/11/1
• Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail
  2025/10/30
• Predictive Preference Learning from Human Interventions
  2025/10/1
• SceneStreamer: Continuous Scenario Generation as Next Token Group Prediction
  2025/6/1
• Adv-BMT: Bidirectional Motion Transformer for Safety-Critical Traffic Scenario Generation
  2025/6/1
• Robot-Gated Interactive Imitation Learning with Adaptive Intervention Mechanism
  2025/6/1
• Data-Efficient Learning from Human Interventions for Mobile Robots
  2025/3/1
• Learning from Active Human Involvement through Proxy Value Propagation
  2025/2/1
• Vid2Sim: Realistic and Interactive Simulation from Video for Urban Navigation
  2025/1/1
• Embodied Scene Understanding for Vision Language Models via MetaVQA
  2025/1/1
• Shared Autonomy with IDA: Interventional Diffusion Assistance
  2024/9/1
• ScenarioNet: Open-Source Platform for Large-Scale Traffic Scenario Simulation and Modeling
  2023/6/1
• Guarded Policy Optimization with Imperfect Online Demonstrations
  2023/3/1
• TrafficGen: Learning to Generate Diverse and Realistic Traffic Scenarios
  2022/10/1
• Human-AI Shared Control via Policy Dissection
  2022/6/1
• Learning to Drive by Watching YouTube Videos: Action-Conditioned Contrastive Policy Pretraining
  2022/4/1
• Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimization
  2022/2/1
• Safe Driving via Expert Guided Policy Optimization
  2021/10/1
• MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning
  2021/9/1
• Improving the Generalization of End-to-End Driving through Procedural Generation
  2020/12/1