Siyu Xu

収録論文 12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

• StellaVLA: 文脈構造化デモンストレーションによる汎用視覚言語行動モデル
  VLA2026/8/12

  StellaVLAは、テスト時に単一の構造化デモンストレーションを条件付けすることで、分布外の状況でも適応できる視覚言語行動モデルを提案する。

• StellaVLA: In-Context Structured Demonstration for Generalizable Vision-Language-Action Models
  2026/8/1
• Revisiting Parameter Redundancy in Vision-Language-Action Models: Insights from VLM-to-VLA Adaptation
  2026/6/1
• Seeing Realism from Simulation: Efficient Video Transfer for Vision-Language-Action Data Augmentation
  2026/5/1
• Affordance Field Intervention: Enabling VLAs to Escape Memory Traps in Robotic Manipulation
  2025/12/8
• Affordance Field Intervention: Enabling VLAs to Escape Memory Traps in Robotic Manipulation
  2025/12/1
• Action-aware Dynamic Pruning for Efficient Vision-Language-Action Manipulation
  2025/9/1
• VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching
  2025/2/4
• VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching
  2025/2/1
• A Self-adaptive LSAC-PID Approach based on Lyapunov Reward Shaping for Mobile Robots
  2021/11/1
• A Self-adaptive SAC-PID Control Approach based on Reinforcement Learning for Mobile Robots
  2021/3/1
• Multi-view registration of unordered range scans by fast correspondence propagation of multi-scale descriptors
  2018/4/1