Zhongyuan Wang

収録論文 32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

• PRM-as-a-Judge 1.5: ロボットプロセス評価のためのツールキット
  評価指標2026/8/14

  ロボットの動作動画から詳細な進捗曲線を生成し、失敗側の進捗や回復能力、成功側の実行品質など複数の細かい指標を導出する評価ツールキットを提案した。

• FORCE: Efficient VLA Reinforcement Fine-Tuning via Value-Calibrated Warm-up and Self-Distillation
  2026/6/1
• OmniUMI: Towards Physically Grounded Robot Learning via Human-Aligned Multimodal Interaction
  2026/4/1
• SaPaVe: Towards Active Perception and Manipulation in Vision-Language-Action Models for Robotics
  2026/3/1
• PRM-as-a-Judge: A Dense Evaluation Paradigm for Fine-Grained Robotic Auditing
  2026/3/1
• Scaling World Model for Hierarchical Manipulation Policies
  2026/2/1
• Latent Reasoning VLA: Latent Thinking and Prediction for Vision-Language-Action Models
  2026/2/1
• Reshaping Action Error Distributions for Reliable Vision-Language-Action Models
  2026/2/1
• Action-Sketcher: From Reasoning to Action via Visual Sketches for Long-Horizon Robotic Manipulation
  2026/1/1
• RoboBrain 2.5: Depth in Sight, Time in Mind
  2026/1/1
• Robo-Dopamine: General Process Reward Modeling for High-Precision Robotic Manipulation
  2025/12/1
• Towards Spatial Trace with Reasoning in Vision-Language Models for Robotics
  2025/12/1
• Do You Have Freestyle? Expressive Humanoid Locomotion via Audio Control
  2025/12/1
• RoboMirror: Understand Before You Imitate for Video to Humanoid Locomotion
  2025/12/1
• METIS: Multi-Source Egocentric Training for Integrated Dexterous Vision-Language-Action Model
  2025/11/1
• PIGEON: VLM-Driven Object Navigation via Points of Interest Selection
  2025/11/1
• RoboCOIN: An Open-Sourced Bimanual Robotic Data Collection for Integrated Manipulation
  2025/11/1
• TIGeR: Tool-Integrated Geometric Reasoning in Vision-Language Models for Robotics
  2025/10/1
• From Language to Locomotion: Retargeting-free Humanoid Control via Motion Latent Guidance
  2025/10/1
• Robobench: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models as Embodied Brain
  2025/10/1
• Thor: Towards Human-Level Whole-Body Reactions for Intense Contact-Rich Environments
  2025/10/1
• RoboOS-NeXT: A Unified Memory-based Framework for Lifelong, Scalable, and Robust Multi-Robot Collaboration
  2025/10/1
• $NavA^3$: Understanding Any Instruction, Navigating Anywhere, Finding Anything
  2025/8/1
• AC-DiT: Adaptive Coordination Diffusion Transformer for Mobile Manipulation
  2025/7/1
• RoboBrain 2.0 Technical Report
  2025/7/1
• RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics
  2025/6/1
• RoboOS: A Hierarchical Embodied Framework for Cross-Embodiment and Multi-Agent Collaboration
  2025/5/1
• AffordGrasp: In-Context Affordance Reasoning for Open-Vocabulary Task-Oriented Grasping in Clutter
  2025/3/1
• MapNav: A Novel Memory Representation via Annotated Semantic Maps for Vision-and-Language Navigation
  2025/2/1
• RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete
  2025/2/1
• Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection
  2024/12/1
• Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks
  2024/12/1