Xingyu Liu

Beijing University of Technology

収録論文 18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

• EcoVLA: リアルタイム制約下での視覚言語行動モデルのためのエネルギー効率的なデバイス・エッジ協調推論
  VLA/エッジ推論/エネルギー効率2026/8/16

  VLAモデルの推論コストを削減するため、デバイスとエッジサーバー間で協調推論を行い、リアルタイム制約を満たしつつシステム全体のエネルギー効率を最大化する適応型フレームワークEcoVLAを提案した。

• E$^2$DT: Efficient and Effective Decision Transformer with Experience-Aware Sampling for Robotic Manipulation
  2026/5/1
• GFreeDet: Exploiting Gaussian Splatting and Foundation Models for Model-free Unseen Object Detection in the BOP Challenge 2024
  2024/12/1
• Meta-Evolve: Continuous Robot Evolution for One-to-many Policy Transfer
  2024/5/1
• LocoMan: Advancing Versatile Quadrupedal Dexterity with Lightweight Loco-Manipulators
  2024/3/1
• Design and Control Co-Optimization for Automated Design Iteration of Dexterous Anthropomorphic Soft Robotic Hands
  2024/3/1
• Diff-Transfer: Model-based Robotic Manipulation Skill Transfer via Differentiable Physics Simulation
  2023/10/1
• COMPOSER: Scalable and Robust Modular Policies for Snake Robots
  2023/10/1
• HERD: Continuous Human-to-Robot Evolution for Learning from Human Demonstration
  2022/12/1
• Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimation
  2022/3/1
• REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy Transfer
  2022/2/1
• V-MAO: Generative Modeling for Multi-Arm Manipulation of Articulated Objects
  2021/11/1
• KDFNet: Learning Keypoint Distance Field for 6D Object Pose Estimation
  2021/9/1
• StereOBJ-1M: Large-scale Stereo Image Dataset for 6D Object Pose Estimation
  2021/9/1
• GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimator
  2021/2/1
• Time-Efficient Mars Exploration of Simultaneous Coverage and Charging with Multiple Drones
  2020/11/1
• KeyPose: Multi-View 3D Labeling and Keypoint Estimation for Transparent Objects
  2019/12/1
• MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequences
  2019/10/1