Jiangmiao Pang

Shanghai Artificial Intelligence Laboratory

収録論文 100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

• RoboStriker: 自律型ヒューマノイドボクシングのための潜在空間戦略ゲーム
  強化学習/ヒューマノイド2026/8/17

  ヒューマノイドボクシングを2プレイヤーの潜在空間ゼロサムマルコフゲームとして定式化し、戦略的探索と物理的実現性の矛盾を解決する階層的フレームワークを提案した。

• GAUGE: 物理的忠実性を測定するための実世界基盤ベンチマーク
  シミュレーション評価2026/8/6

  シミュレーションエンジンと生成ビデオワールドモデルの物理的忠実性を、実世界の軌跡に基づいて診断するベンチマークを提案した。

• GAUGE: A Measurement-Grounded Benchmark for Physical Fidelity in Simulation Engines and Video World Models
  2026/8/1
• KAI: A Kinematic-Aware Interface for Data-Efficient Articulated Object Manipulation
  2026/7/1
• RoboInter1.5: A Holistic Intermediate Representation Suite for Embodied World Modeling and Robotic Manipulation
  2026/7/1
• InternVLA-A1.5: Unifying Understanding, Latent Foresight, and Action for Compositional Generalization
  2026/7/1
• X-NavDP: Generalizing Navigation Diffusion Policy to Novel Behavior and Embodiments with Group Q-score Reweighted Matching
  2026/7/1
• Exploratory, Communicative, and Deployable: Vision-Driven Embodied Agents for Open-World Mobile Manipulation
  2026/7/1
• Scaling Behavior Foundation Model for Humanoid Robots
  2026/7/1
• Cortex: A Bidirectionally Aligned Embodied Agent Framework for Long-horizon Manipulation
  2026/7/1
• EBench: Elemental Diagnosis of Generalist Mobile Manipulation Policies
  2026/6/1
• MemoryWAM: Efficient World Action Modeling with Persistent Memory
  2026/6/1
• ReactiveBFM: Reactive Closed-Loop Motion Planning Towards Universal Humanoid Whole-Body Control
  2026/6/1
• Imagine2Real: Towards Zero-shot Humanoid-Object Interaction via Video Generative Priors
  2026/5/1
• STABLE: Simulation-Ready Tabletop Layout Generation via a Semantics-Physics Dual System
  2026/5/1
• HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation System
  2026/4/1
• SIM1: Physics-Aligned Simulator as Zero-Shot Data Scaler in Deformable Worlds
  2026/4/1
• ForceVLA2: Unleashing Hybrid Force-Position Control with Force Awareness for Contact-Rich Manipulation
  2026/3/1
• FutureVLA: Joint Visuomotor Prediction for Vision-Language-Action Model
  2026/3/1
• Towards Human-Like Manipulation through RL-Augmented Teleoperation and Mixture-of-Dexterous-Experts VLA
  2026/3/1
• UltraDexGrasp: Learning Universal Dexterous Grasping for Bimanual Robots with Synthetic Data
  2026/3/1
• Tac2Real: Reliable and GPU Visuotactile Simulation for Online Reinforcement Learning and Zero-Shot Real-World Deployment
  2026/3/1
• Feel Robot Feels: Tactile Feedback Array Glove for Dexterous Manipulation
  2026/3/1
• One-Policy-Fits-All: Geometry-Aware Action Latents for Cross-Embodiment Manipulation
  2026/3/1
• Scalable and General Whole-Body Control for Cross-Humanoid Locomotion
  2026/2/1
• Demystifying Action Space Design for Robotic Manipulation Policies
  2026/2/1
• RoboInter: A Holistic Intermediate Representation Suite Towards Robotic Manipulation
  2026/2/1
• DexImit: Learning Bimanual Dexterous Manipulation from Monocular Human Videos
  2026/2/1
• SoMA: A Real-to-Sim Neural Simulator for Robotic Soft-body Manipulation
  2026/2/1
• ST4VLA: Spatially Guided Training for Vision-Language-Action Models
  2026/2/1
• Embodiment-Aware Generalist Specialist Distillation for Unified Humanoid Whole-Body Control
  2026/2/1
• HumanX: Toward Agile and Generalizable Humanoid Interaction Skills from Human Videos
  2026/2/1
• Robo3R: Enhancing Robotic Manipulation with Accurate Feed-Forward 3D Reconstruction
  2026/2/1
• RoboStriker: Hierarchical Decision-Making for Autonomous Humanoid Boxing
  2026/1/1
• InternVLA-A1: Unifying Understanding, Generation and Action for Robotic Manipulation
  2026/1/1
• Nimbus: A Unified Embodied Synthetic Data Generation Framework
  2026/1/1
• UniCon: A Unified System for Efficient Robot Learning Transfers
  2026/1/1
• RoboVIP: Multi-View Video Generation with Visual Identity Prompting Augments Robot Manipulation
  2026/1/1
• VLNVerse: A Benchmark for Vision-Language Navigation with Versatile, Embodied, Realistic Simulation and Evaluation
  2025/12/1
• LoGoPlanner: Localization Grounded Navigation Policy with Metric-aware Visual Geometry
  2025/12/1
• MM-ACT: Learn from Multimodal Parallel Generation to Act
  2025/12/1
• VL-LN Bench: Towards Long-horizon Goal-oriented Navigation with Active Dialogs
  2025/12/1
• H-Zero: Cross-Humanoid Locomotion Pretraining Enables Few-shot Novel Embodiment Transfer
  2025/12/1
• Ground Slow, Move Fast: A Dual-System Foundation Model for Generalizable Vision-and-Language Navigation
  2025/12/1
• MM-ACT: Learn from Multimodal Parallel Generation to Act
  2025/11/30
• Gallant: Voxel Grid-based Humanoid Locomotion and Local-navigation across 3D Constrained Terrains
  2025/11/1
• InternData-A1: Pioneering High-Fidelity Synthetic Data for Pre-training Generalist Policy
  2025/11/1
• Towards Adaptable Humanoid Control via Adaptive Motion Tracking
  2025/10/1
• X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model
  2025/10/1
• InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy
  2025/10/1
• Expertise need not monopolize: Action-Specialized Mixture of Experts for Vision-Language-Action Learning
  2025/10/1
• PhysHSI: Towards a Real-World Generalizable and Natural Humanoid-Scene Interaction System
  2025/10/1
• Humanoid Goalkeeper: Learning from Position Conditioned Task-Motion Constraints
  2025/10/1
• SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning
  2025/9/11
• InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts
  2025/9/1
• MesaTask: Towards Task-Driven Tabletop Scene Generation via 3D Spatial Reasoning
  2025/9/1
• A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning
  2025/9/1
• Behavior Foundation Model for Humanoid Robots
  2025/9/1
• SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning
  2025/9/1
• F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions
  2025/9/1
• Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies
  2025/8/27
• Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies
  2025/8/1
• Rethinking the Embodied Gap in Vision-and-Language Navigation: A Holistic Study of Physical and Visual Disparities
  2025/7/1
• UniTracker: Learning Universal Whole-Body Motion Tracker for Humanoid Robots
  2025/7/1
• InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulation
  2025/7/1
• StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling
  2025/7/1
• GENMANIP: LLM-driven Simulation for Generalizable Instruction-Following Manipulation
  2025/6/1
• CronusVLA: Towards Efficient and Robust Manipulation via Multi-Frame Vision-Language-Action Modeling
  2025/6/1
• LabUtopia: High-Fidelity Simulation and Hierarchical Benchmark for Scientific Embodied Agents
  2025/5/1
• GLEAM: Learning Generalizable Exploration Policy for Active Mapping in Complex 3D Indoor Scenes
  2025/5/1
• TeleOpBench: A Simulator-Centric Benchmark for Dual-Arm Dexterous Teleoperation
  2025/5/1
• NavDP: Learning Sim-to-Real Navigation Diffusion Policy with Privileged Information Guidance
  2025/5/1
• Towards Latency-Aware 3D Streaming Perception for Autonomous Driving
  2025/4/1
• Novel Demonstration Generation with Gaussian Splatting Enables Robust One-Shot Manipulation
  2025/4/1
• RoboGround: Robotic Manipulation with Grounded Vision-Language Priors
  2025/4/1
• Gripper Keypose and Object Pointflow as Interfaces for Bimanual Robotic Manipulation
  2025/4/1
• Aether: Geometric-Aware Unified World Modeling
  2025/3/1
• A Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning
  2025/3/1
• AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems
  2025/3/1
• HOMIE: Humanoid Loco-Manipulation with Isomorphic Exoskeleton Cockpit
  2025/2/1
• Re$^3$Sim: Generating High-Fidelity Simulation Data via 3D-Photorealistic Real-to-Sim for Robotic Manipulation
  2025/2/1
• VB-Com: Learning Vision-Blind Composite Humanoid Locomotion Against Deficient Perception
  2025/2/1
• BeamDojo: Learning Agile Humanoid Locomotion on Sparse Footholds
  2025/2/1
• Learning Humanoid Standing-up Control across Diverse Postures
  2025/2/1
• A Unified and General Humanoid Whole-Body Controller for Versatile Locomotion
  2025/2/1
• Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulation
  2024/12/1
• Learning Humanoid Locomotion with Perceptive Internal Model
  2024/11/1
• VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding
  2024/10/1
• Open-Vocabulary Object-Goal Navigation by Generalizing Semantic Mapping with Dense CLIP
  2024/7/1
• GRUtopia: Dream General Robots in a City at Scale
  2024/7/1
• CooHOI: Learning Cooperative Human-Object Interaction with Manipulated Object Dynamics
  2024/6/1
• MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language Annotations
  2024/6/1
• Learning H-Infinity Locomotion Control
  2024/4/1
• RoboKeyGen: Robot Pose and Joint Angles Estimation via Diffusion-based 3D Keypoint Generation
  2024/3/1
• RoboDuet: Learning a Cooperative Policy for Whole-body Legged Loco-Manipulation
  2024/3/1
• GenNBV: Generalizable Next-Best-View Policy for Active 3D Reconstruction
  2024/2/1
• EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI
  2023/12/1
• Hybrid Internal Model: Learning Agile Legged Locomotion with Simulated Robot Response
  2023/12/1
• Monocular 3D Object Detection with Depth from Motion
  2022/7/1
• FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection
  2021/4/1