Hang Zhao

収録論文 68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

• G0.5: ロボットの推論と行動のための単一自己回帰ストリーム
  VLA2026/8/12

  事前学習済みのVLMと別の行動エキスパートを組み合わせる従来のVLAモデルに対し、単一のトランスフォーマーデコーダが推論トークンと行動トークンを単一の目的で生成する自己回帰VLAモデルG0.5を提案。クロスエンボディメント行動トークナイザー、ネイティブな思考連鎖ストリーム、視覚メモリモジュールにより、基礎モデル規模での学習を可能にし、複数のベンチマークで最先端を達成。

• SLAMFormer-$\infty$: Infinite SLAM Transformer for Unbounded Frontend and Backend Processing
  2026/8/1
• G0.5: One Autoregressive Stream for Robot Reasoning and Action
  2026/8/1
• Agent-driven Long-tail Simulation for Autonomous Driving
  2026/7/1
• Automated Synthesis of Facial Mechanisms for Conversational Animatronic Robots
  2026/7/1
• Is Your Trajectory Displacement Safe in Long-tail?
  2026/6/1
• OMG: Omni-Modal Motion Generation for Generalist Humanoid Control
  2026/6/1
• PAIWorld: A 3D-Consistent World Foundation Model for Robotic Manipulation
  2026/6/1
• TopoRetarget: Interaction-Preserving Retargeting for Dexterous Manipulation
  2026/6/1
• Coarse-to-Control: Action-Token Planning for Vision-Language-Action Models
  2026/6/1
• Dexora: Open-source VLA for High-DoF Bimanual Dexterity
  2026/5/1
• UniDex: A Robot Foundation Suite for Universal Dexterous Hand Control from Egocentric Human Videos
  2026/3/1
• VolumeDP: Modeling Volumetric Representation for Manipulation Policy Learning
  2026/3/1
• Generative Control as Optimization: Time Unconditional Flow Matching for Adaptive and Robust Robotic Control
  2026/3/1
• TTT-Parkour: Rapid Test-Time Training for Perceptive Robot Parkour
  2026/2/1
• Embodied Intelligence for Flexible Manufacturing: A Survey
  2026/2/1
• ActionCodec: What Makes for Good Action Tokenizers
  2026/2/1
• Hiking in the Wild: A Scalable Perceptive Parkour Framework for Humanoids
  2026/1/1
• Deep Whole-body Parkour
  2026/1/1
• FASTer: Toward Efficient Autoregressive Vision Language Action Modeling via Neural Action Tokenization
  2025/12/1
• RoboBPP: Benchmarking Robotic Online Bin Packing with Physics-based Simulation
  2025/12/1
• RoboCOIN: An Open-Sourced Bimanual Robotic Data Collection for Integrated Manipulation
  2025/11/1
• Galaxea Open-World Dataset and G0 Dual-System VLA Model
  2025/9/1
• SLAM-Former: Putting SLAM into One Transformer
  2025/9/1
• Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Driving
  2025/9/1
• SAMP: Spatial Anchor-based Motion Policy for Collision-Aware Robotic Manipulators
  2025/9/1
• OccVLA: Vision-Language-Action Model with Implicit 3D Occupancy Supervision
  2025/9/1
• Morpheus: A Neural-driven Animatronic Face with Hybrid Actuation and Diverse Emotion Control
  2025/7/1
• Conditioning Matters: Training Diffusion Policies is Faster Than You Think
  2025/5/1
• Designing Pin-pression Gripper and Learning its Dexterous Grasping with Online In-hand Adjustment
  2025/5/1
• Deliberate Planning of 3D Bin Packing on Packing Configuration Trees
  2025/4/1
• PIN-WM: Learning Physics-INformed World Models for Non-Prehensile Manipulation
  2025/4/1
• Learning Personalized Driving Styles via Reinforcement Learning from Human Feedback
  2025/3/1
• RoboEngine: Plug-and-Play Robot Data Augmentation with Semantic Robot Segmentation and Background Generation
  2025/3/1
• MoE-Loco: Mixture of Experts for Multitask Locomotion
  2025/3/1
• Physics-informed Neural Network Predictive Control for Quadruped Locomotion
  2025/3/1
• Embrace Collisions: Humanoid Shadowing for Deployable Contact-Agnostics Motions
  2025/2/1
• VR-Robo: A Real-to-Sim-to-Real Framework for Visual Robot Navigation and Locomotion
  2025/2/1
• Generalizing Motion Planners with Mixture of Experts for Autonomous Driving
  2024/10/1
• Robust Robot Walker: Learning Agile Locomotion over Tiny Traps
  2024/9/1
• Playful DoggyBot: Learning Agile and Precise Quadrupedal Locomotion
  2024/9/1
• SARO: Space-Aware Robot System for Terrain Crossing via Vision-Language Model
  2024/7/1
• Humanoid Parkour Learning
  2024/6/1
• LiDAR-based 4D Occupancy Completion and Forecasting
  2023/10/1
• Large Trajectory Models are Scalable Motion Predictors and Planners
  2023/10/1
• GPT-Driver: Learning to Drive with GPT
  2023/10/1
• Boosting Offline Reinforcement Learning for Autonomous Driving with Hierarchical Latent Skills
  2023/9/1
• Robot Parkour Learning
  2023/9/1
• A Universal Semantic-Geometric Representation for Robotic Manipulation
  2023/6/1
• Programmatically Grounded, Compositionally Generalizable Robotic Manipulation
  2023/4/1
• Learning Physically Realizable Skills for Online Packing of General 3D Shapes
  2022/12/1
• P4P: Conflict-Aware Motion Prediction for Planning in Autonomous Driving
  2022/11/1
• InterSim: Interactive Traffic Simulation via Explicit Relation Modeling
  2022/10/1
• ViP3D: End-to-end Visual Trajectory Prediction via 3D Agent Queries
  2022/8/1
• VectorFlow: Combining Images and Vectors for Traffic Occupancy and Flow Prediction
  2022/8/1
• VectorMapNet: End-to-end Vectorized HD Map Learning
  2022/6/1
• M2I: From Factored Marginal Trajectory Prediction to Interactive Prediction
  2022/2/1
• IFR-Explore: Learning Inter-object Functional Relationships in 3D Indoor Scenes
  2021/12/1
• DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries
  2021/10/1
• Learning Practically Feasible Policies for Online 3D Bin Packing
  2021/8/1
• DenseTNT: End-to-end Trajectory Prediction from Dense Goal Sets
  2021/8/1
• DenseTNT: Waymo Open Dataset Motion Prediction Challenge 1st Place Solution
  2021/6/1
• Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset
  2021/4/1
• Predictive Visual Tracking: A New Benchmark and Baseline Approach
  2021/3/1
• Unsupervised Monocular Depth Learning in Dynamic Scenes
  2020/10/1
• CLOUD: Contrastive Learning of Unsupervised Dynamics
  2020/10/1
• SEMI: Self-supervised Exploration via Multisensory Incongruity
  2020/9/1
• TNT: Target-driveN Trajectory Prediction
  2020/8/1