Yaobo Liang
Microsoft Research Asia
収録論文 11本 ・ フィジカルAI/ロボット学習
VLA
※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
- 継続か再計画か？適応的実行期間のためのベルヌーイ継続方策学習VLA2026/8/4
固定長のアクションチャンクを実行するVLAモデルにおいて、再計画のタイミングをタスク進捗に応じて適応的に決める軽量フレームワークBCPを提案し、成功率を向上させた。
- Continue or Replan? Bernoulli-Continuation Policy Learning for Adaptive Horizon Execution2026/8/1
- TaskGround: Structured Executable Task Inference for Full-Scene Household Reasoning2026/5/1
- MobileManiBench: Simplifying Model Verification for Mobile Manipulation2026/2/1
- VideoVLA: Video Generators Can Be Generalizable Robot Manipulators2025/12/1
- HiMoE-VLA: Hierarchical Mixture-of-Experts for Generalist Vision-Language-Action Policies2025/12/1
- Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videos2025/10/24
- Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videos2025/10/1
- UniGraspTransformer: Simplified Policy Distillation for Scalable Dexterous Robotic Grasping2024/12/1
- CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation2024/11/29
- CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation2024/11/1