Zhenyu Wu

Tsinghua University

収録論文 36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

• SkillMemo: 専門家ガイドによるスキル記憶フレームワークを用いた構成可能な身体操作
  操作2026/8/6

  長期的なデモンストレーションを潜在的な原子スキルに分解し、動的エピソード記憶バンクに統合することで、構成可能な操作タスクの汎化を向上させるフレームワークを提案した。

• SkillMemo: Expert-guided Skill Memory Framework for Compositional Embodied Manipulation
  2026/8/1
• WorldSample: Closed-loop Real-robot RL with World Modelling
  2026/7/1
• GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearch
  2026/7/1
• GigaWorld-1: A Roadmap to Build World Models for Robot Policy Evaluation
  2026/7/1
• R2RDreamer: 3D-aware Data Augmentation for Spatially-generalized 2D Manipulation Policies
  2026/6/1
• DVG-WM: Disentangled Video Generation Enables Efficient Embodied World Model for Robotic Manipulation
  2026/6/1
• MIL-LC: A Robust Magnetometer-Inertial-LiDAR Fusion Multimodal Localization Framework
  2026/6/1
• iMaC: Translating Actions into Motion and Contact Images for Embodied World Models
  2026/6/1
• UniIntervene: Agentic Intervention for Efficient Real-World Reinforcement Learning
  2026/6/1
• DockAnywhere: Data-Efficient Visuomotor Policy Learning for Mobile Manipulation via Novel Demonstration Generation
  2026/4/1
• RoSLAC: Robust Simultaneous Localization and Calibration of Multiple Magnetometers
  2026/4/1
• RoCo Challenge at AAAI 2026: Benchmarking Robotic Collaborative Manipulation for Assembly Towards Industrial Automation
  2026/3/1
• SteadyTray: Learning Object Balancing Tasks in Humanoid Tray Transport via Residual Reinforcement Learning
  2026/3/1
• E2HiL: Entropy-Guided Sample Selection for Efficient Real-World Human-in-the-Loop Reinforcement Learning
  2026/1/1
• L2M-Calib: One-key Calibration Method for LiDAR and Multiple Magnetic Sensors
  2025/12/1
• MAP-VLA: Memory-Augmented Prompting for Vision-Language-Action Model in Robotic Manipulation
  2025/11/1
• RESample: A Robust Data Augmentation Framework via Exploratory Sampling for Robotic Manipulation
  2025/10/20
• RESample: A Robust Data Augmentation Framework via Exploratory Sampling for Robotic Manipulation
  2025/10/1
• VLA-Reasoner: Empowering Vision-Language-Action Models with Reasoning via Online Monte Carlo Tree Search
  2025/9/1
• MoTo: A Zero-shot Plug-in Interaction-aware Navigation for General Mobile Manipulation
  2025/9/1
• SafeBimanual: Diffusion-based Trajectory Optimization for Safe Bimanual Manipulation
  2025/8/1
• UniLGL: Learning Uniform Place Recognition for FOV-limited/Panoramic LiDAR Global Localization
  2025/7/1
• MCN-SLAM: Multi-Agent Collaborative Neural SLAM with Hybrid Implicit Neural Scene Representation
  2025/6/1
• MoManipVLA: Transferring Vision-language-action Models for General Mobile Manipulation
  2025/3/1
• IDF-MFL: Infrastructure-free and Drift-free Magnetic Field Localization for Mobile Robot
  2024/11/1
• SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation
  2024/10/1
• CTE-MLO: Continuous-time and Efficient Multi-LiDAR Odometry with Localizability-aware Point Cloud Sampling
  2024/8/1
• Embodied Instruction Following in Unknown Environments
  2024/6/1
• Anyview: Generalizable Indoor 3D Object Detection with Variable Frames
  2023/10/1
• NTU4DRadLM: 4D Radar-centric Multi-Modal Dataset for Localization and Mapping
  2023/9/1
• Embodied Task Planning with Large Language Models
  2023/7/1
• Category-level Shape Estimation for Densely Cluttered Objects
  2023/2/1
• Smart Explorer: Recognizing Objects in Dense Clutter via Interactive Exploration
  2022/8/1
• Semantic Reinforced Attention Learning for Visual Place Recognition
  2021/8/1
• Magnetic-Assisted Initialization for Infrastructure-free Mobile Robot Localization
  2019/11/1