Xiaojian Ma

Beijing Institute for General Artificial Intelligence

収録論文 20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

• パノラマ認識型VLAによる全身遠隔操作を用いた移動操作の学習
  VLA/移動操作2026/8/3

  全身遠隔操作システムとパノラマ認識型VLAポリシーを開発し、移動操作タスクの成功率を大幅に向上させた。

• Learning Panorama-Aware VLA for Mobile Manipulation with Whole-Body Teleoperation
  2026/8/1
• AdaReP:Adaptive Re-Planning under Model Mismatch for Neural World-Model Predictive Control
  2026/6/1
• Chain Of Interaction Benchmark (COIN): When Reasoning meets Embodied Interaction
  2026/4/1
• FlowDreamer: A RGB-D World Model with Flow-based Motion Representations for Robot Manipulation
  2025/5/1
• Falcon: Fast Visuomotor Policies via Partial Denoising
  2025/3/1
• GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents
  2024/12/1
• Multi-modal Situated Reasoning in 3D Scenes
  2024/9/1
• OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents
  2024/6/27
• An Embodied Generalist Agent in 3D World
  2023/11/18
• Adversarial Option-Aware Hierarchical Imitation Learning
  2021/6/1
• Robust Robotic Pouring using Audition and Haptics
  2020/3/1
• A Mobile Robot Hand-Arm Teleoperation System by Vision and IMU
  2020/3/1
• Reinforcement Learning from Imperfect Demonstrations under Soft Expert Guidance
  2019/11/1
• Imitation Learning from Observations by Minimizing Inverse Dynamics Disagreement
  2019/10/1
• Making Sense of Audio Vibration for Liquid Height Estimation in Robotic Pouring
  2019/3/1
• Vision-based Teleoperation of Shadow Dexterous Hand using End-to-End Deep Neural Network
  2018/9/1
• PointNetGPD: Detecting Grasp Configurations from Point Sets
  2018/9/1
• Task Transfer by Preference-Based Cost Learning
  2018/5/1
• Learning and Inferring Movement with Deep Generative Model
  2018/5/1