Wei-Chiu Ma

Cornell University

収録論文 22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

• VLA表現からのタスク進捗の解読
  VLA/解釈可能性2026/8/13

  視覚言語行動モデル(VLA)の内部表現からタスク進捗が線形に読み取れることを発見し、それを用いたラベル不要のOOD検出器を提案した。

• Decoding Task Progress from VLA Representations
  2026/8/1
• SAGE: Scalable Agentic 3D Scene Generation for Embodied AI
  2026/2/1
• Imitating What Works: Simulation-Filtered Modular Policy Learning from Human Videos
  2026/2/1
• PolaRiS: Scalable Real-to-Sim Evaluations for Generalist Robot Policies
  2025/12/1
• X-Diffusion: Training Diffusion Policies on Cross-Embodiment Human Demonstrations
  2025/11/1
• Implicit State Estimation via Video Replanning
  2025/10/1
• Prompting with the Future: Open-World Model Predictive Control with Interactive Digital Twins
  2025/6/1
• X-Sim: Cross-Embodiment Learning via Real-to-Sim-to-Real
  2025/5/1
• DRAWER: Digital Reconstruction and Articulation With Environment Realism
  2025/4/1
• UltraLiDAR: Learning Compact Representations for LiDAR Completion and Generation
  2023/11/1
• CADSim: Robust and Scalable in-the-wild 3D Reconstruction for Controllable Sensor Simulation
  2023/11/1
• UniSim: A Neural Closed-Loop Sensor Simulator
  2023/8/1
• MIRA: Mental Imagery for Robotic Affordances
  2022/12/1
• Virtual Correspondence: Humans as a Cue for Extreme-View Geometry
  2022/6/1
• BARF: Bundle-Adjusting Neural Radiance Fields
  2021/4/1
• Deep Feedback Inverse Problem Solver
  2021/1/1
• Deep Parametric Continuous Convolutional Neural Networks
  2021/1/1
• DAGMapper: Learning to Map by Discovering Lane Topology
  2020/12/1
• Recovering and Simulating Pedestrians in the Wild
  2020/11/1
• Exploiting Sparse Semantic HD Maps for Self-Driving Vehicle Localization
  2019/8/1
• Deep Rigid Instance Scene Flow
  2019/4/1