Yongyuan Liang

収録論文 7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

• Failure-Aware RL: Reliable Offline-to-Online Reinforcement Learning with Self-Recovery for Real-World Manipulation
  2026/1/1
• MomaGraph: State-Aware Unified Scene Graphs with Vision-Language Model for Embodied Task Planning
  2025/12/1
• TraceGen: World Modeling in 3D Trace Space Enables Learning from Cross-Embodiment Videos
  2025/11/1
• Magma: A Foundation Model for Multimodal AI Agents
  2025/2/1
• TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies
  2024/12/1
• Robots Pre-train Robots: Manipulation-Centric Robotic Representation from Large-Scale Robot Datasets
  2024/10/1
• Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss
  2024/2/1