Chen Zhao

Renmin University of China

収録論文 11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

• JEPA-WAM: 共同埋め込み世界モデリングによる視覚・言語・行動ポリシーの学習
  VLA/世界モデル2026/8/10

  事前学習済みV-JEPA空間に基づく潜在世界モデルを導入し、遷移予測と行動生成を共有予測器で結合することで、ロボット制御の性能と汎化を向上させた。

• JEPA-WAM: Learning Vision-Language-Action Policies with Joint-Embedding World Modeling
  2026/8/1
• Training Vision-Language-Action Models with Dense Embodied Chain-of-Thought Supervision
  2026/6/1
• Action Draft and Verify: A Self-Verifying Framework for Vision-Language-Action Model
  2026/3/1
• OpenGaussian: Towards Point-Level 3D Gaussian-based Open Vocabulary Understanding
  2024/6/1
• Gaussian-LIC: Real-Time Photo-Realistic SLAM with Gaussian Splatting and LiDAR-Inertial-Camera Fusion
  2024/4/1
• DVMNet++: Rethinking Relative Pose Estimation for Unseen Objects
  2024/3/1
• 3D-Aware Hypothesis & Verification for Generalizable Relative Object Pose Estimation
  2023/10/1
• LocPoseNet: Robust Location Prior for Unseen Object Pose Estimation
  2022/11/1
• Fusing Local Similarities for Retrieval-based 3D Orientation Estimation of Unseen Objects
  2022/3/1
• Progressive Correspondence Pruning by Consensus Learning
  2021/1/1