Hui Xiong
The Hong Kong University of Science and Technology (Guangzhou)
収録論文 16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。
- Suppression Sticks, Locality Is Fragile: A Closed-Loop Target-and-Control Audit of Task-Vector Negation in VLA Policies2026/8/1
- Source-Lifted Flow Matching for Intervenable Multimodal Imitation2026/7/1
- Just-In-Time Scene Graph Growth: Combating Perceptual Saturation in Long-Horizon Robotics2026/7/1
- LH-AVLN: A Benchmark for Long-Horizon Audio-Visual-Language Navigation2026/7/1
- Spatial Memory for Out-of-Vision Manipulation in Vision-Language-Action2026/5/1
- Tactile-based Multimodal Fusion in Embodied Intelligence: A Survey of Vision, Language, and Contact-Driven Paradigms2026/5/1
- AutoFly: Vision-Language-Action Model for UAV Autonomous Navigation in the Wild2026/2/1
- WaterVideoQA: ASV-Centric Perception and Rule-Compliant Reasoning via Multi-Modal Agents2026/2/1
- A Brain-inspired Embodied Intelligence for Fluid and Fast Reflexive Robotics Control2026/1/1
- Perturbation-mitigated USV Navigation with Distributionally Robust Reinforcement Learning2025/12/1
- Da Yu: Towards USV-Based Image Captioning for Waterway Surveillance and Scene Understanding2025/6/1
- SD-OVON: A Semantics-aware Dataset and Benchmark Generation Pipeline for Open-Vocabulary Object Navigation in Dynamic Scenes2025/5/1
- Open-vocabulary Mobile Manipulation in Unseen Dynamic Environments with 3D Semantic Maps2024/6/1
- HR-INR: Continuous Space-Time Video Super-Resolution via Event Camera2024/5/1
- Talk2Radar: Bridging Natural Language with 4D mmWave Radar for 3D Referring Expression Comprehension2024/5/1