Yandong Guo
収録論文 21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
- 抑制スティック、局所性は脆い：VLAポリシーにおけるタスクベクトル否定の閉ループ標的・制御監査VLA2026/8/5
マルチタスクVLAポリシーからタスクベクトルを引き算したときの行動変化を、全10スキルで監査し、抑制可能・抵抗・全崩壊の3つの様式があることを示した。
- 視覚言語行動モデルは自己受容状態をどう使うべきか？VLA2026/8/4
VLAモデルにおけるロボットの自己受容状態の入力方法（テキスト、視覚言語プレフィックス、行動エキスパートなど）と履歴長が性能に与える影響を、制御実験で体系的に比較し、設計原則を導出した。
- Suppression Sticks, Locality Is Fragile: A Closed-Loop Target-and-Control Audit of Task-Vector Negation in VLA Policies2026/8/1
- How Should Vision-Language-Action Models Use Proprioceptive State?2026/8/1
- Source-Lifted Flow Matching for Intervenable Multimodal Imitation2026/7/1
- Lift3D-VLA: Lifting VLA Models to 3D Geometry and Dynamics-Aware Manipulation2026/7/1
- TACO: TActile World Model as a Self-COrrector forScalable VLA Post-Training2026/7/1
- GeneralVLA-2: Geometry-Aware Reconstruction and Governed Memory for Robot Planning2026/6/1
- MotionVLA: Vision-Language-Action Model for Humanoid Motion2026/6/1
- PHASER: Phase-Aware and Semantic Experience Replay for Vision-Language-Action Models2026/6/1
- Spatial Memory for Out-of-Vision Manipulation in Vision-Language-Action2026/5/1
- A Brain-inspired Embodied Intelligence for Fluid and Fast Reflexive Robotics Control2026/1/1
- Video2Act: A Dual-System Video Diffusion Policy with Robotic Spatio-Motional Modeling2025/12/1
- PosA-VLA: Enhancing Action Generation via Pose-Conditioned Anchor Attention2025/12/1
- RoboCOIN: An Open-Sourced Bimanual Robotic Data Collection for Integrated Manipulation2025/11/1
- SURPRISE3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes2025/7/1
- Fast-in-Slow: A Dual-System Foundation Model Unifying Fast Manipulation within Slow Reasoning2025/6/1
- A Real-Time Fusion Framework for Long-term Visual Localization2022/10/1
- BANet: Motion Forecasting with Boundary Aware Network2022/6/1
- Pose Refinement with Joint Optimization of Visual Points and Lines2021/10/1
- Retrieval and Localization with Observation Constraints2021/8/1