Xiaofeng Wang

収録論文 37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

• GigaBrain-0.7：三系統アーキテクチャによる創発的能力へのスケーリング
  VLA2026/8/16

  視覚言語行動モデルのスケーリングとアーキテクチャ改善により、多様なロボットへの汎化を大幅に向上させた基盤モデルを提案。

• XPolicyLab: ロボットポリシー評価と展開のための統一標準・オープンエコシステム
  ロボットポリシー評価2026/8/10

  ロボットポリシーの評価と展開を統一する標準規格とオープンエコシステムを提案し、N個のポリシーとM個の環境の接続コストをO(NM)からO(N+M)に削減した。

• XPolicyLab: ロボットポリシー評価と展開のための統一標準・オープンエコシステム
  評価基盤2026/8/10

  ロボットポリシーの評価と展開を統一する標準規格とオープンエコシステムを提案し、N個のポリシーとM個の環境の接続コストをO(NM)からO(N+M)に削減する。

• XPolicyLab: A Unified Standard and Open Ecosystem for Robot Policy Evaluation and Deployment
  2026/8/1
• Zero2Skill: Bootstrapping Robot Skills through Autonomous Data Collection, Training, and Deployment
  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
• HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models
  2026/7/1
• ACE-Brain-0.5: A Unified Embodied Foundational Model for Physical Agentic AI
  2026/7/1
• SKIP: Sparse Keyframe Interpolation Paradigm for Efficient Embodied World Models
  2026/6/1
• DVG-WM: Disentangled Video Generation Enables Efficient Embodied World Model for Robotic Manipulation
  2026/6/1
• WAM-Nav: Asymmetric Latent World-Action Modeling for Unified Visual Navigation
  2026/6/1
• R2RDreamer: 3D-aware Data Augmentation for Spatially-generalized 2D Manipulation Policies
  2026/6/1
• iMaC: Translating Actions into Motion and Contact Images for Embodied World Models
  2026/6/1
• MUSE: Multimodal Uncertainty Quantification of State Estimation
  2026/5/1
• DriveDreamer-Policy: A Geometry-Grounded World-Action Model for Unified Generation and Planning
  2026/4/1
• ViVa: A Video-Generative Value Model for Robot Reinforcement Learning
  2026/4/1
• StableIDM: Stabilizing Inverse Dynamics Model against Manipulator Truncation via Spatio-Temporal Refinement
  2026/4/1
• VAG: Dual-Stream Video-Action Generation for Embodied Data Synthesis
  2026/4/1
• TacMamba: A Tactile History Compression Adapter Bridging Fast Reflexes and Slow VLA Reasoning
  2026/3/1
• $\pi$-StepNFT: Wider Space Needs Finer Steps in Online RL for Flow-based VLAs
  2026/3/1
• ACE-Brain-0: Spatial Intelligence as a Shared Scaffold for Universal Embodiments
  2026/3/1
• The RoboSense Challenge: Sense Anything, Navigate Anywhere, Adapt Across Platforms
  2026/1/1
• SwiftVLA: Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal Overhead
  2025/12/1
• Design and Experimental Validation of Closed-Form CBF-Based Safe Control for Stewart Platform Under Multiple Constraints
  2025/12/1
• GigaWorld-0: World Models as Data Engine to Empower Embodied AI
  2025/11/1
• End-to-End Design and Validation of a Low-Cost Stewart Platform with Nonlinear Estimation and Control
  2025/10/1
• GigaBrain-0: A World Model-Powered Vision-Language-Action Model
  2025/10/1
• VLA-R1: Enhancing Reasoning in Vision-Language-Action Models
  2025/10/1
• EgoDemoGen: Egocentric Demonstration Generation for Viewpoint Generalization in Robotic Manipulation
  2025/9/1
• EMMA: Generalizing Real-World Robot Manipulation via Generative Visual Transfer
  2025/9/1
• MimicDreamer: Aligning Human and Robot Demonstrations for Scalable VLA Training
  2025/9/1
• EmbodieDreamer: Advancing Real2Sim2Real Transfer for Policy Training via Embodied World Modeling
  2025/7/1
• Task-Parameter Nexus: Task-Specific Parameter Learning for Model-Based Control
  2024/12/1
• ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration
  2024/11/1
• DiffTune-MPC: Closed-Loop Learning for Model Predictive Control
  2023/12/1
• On the Road with GPT-4V(ision): Early Explorations of Visual-Language Model on Autonomous Driving
  2023/11/1