Fengling Li

収録論文 8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

• ActFovea: Runtime Safeguarding for VLA Policies via Spatiotemporal Visual-Action Consistency
  2026/7/1
• DA-PTQ: Drift-Aware Post-Training Quantization for Efficient Vision-Language-Action Models
  2026/4/1
• Non-Markovian Long-Horizon Robot Manipulation via Keyframe Chaining
  2026/3/1
• Self-Correcting VLA: Online Action Refinement via Sparse World Imagination
  2026/2/1
• MOTIF: Learning Action Motifs for Few-shot Cross-Embodiment Transfer
  2026/2/1
• AC^2-VLA: Action-Context-Aware Adaptive Computation in Vision-Language-Action Models for Efficient Robotic Manipulation
  2026/1/1
• A Step Toward World Models: A Survey on Robotic Manipulation
  2025/11/1
• ActDistill: General Action-Guided Self-Derived Distillation for Efficient Vision-Language-Action Models
  2025/11/1