VLA-IAP: Training-Free Visual Token Pruning via Interaction Alignment for Vision-Language-Action Models

Ähnliche Einträge

• EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models
  von: Yang, Yantai, et al.
  Veröffentlicht: (2025)
• ST-Prune: Training-Free Spatio-Temporal Token Pruning for Vision-Language Models in Autonomous Driving
  von: Sha, Lin, et al.
  Veröffentlicht: (2026)
• RobustVLA: Robustness-Aware Reinforcement Post-Training for Vision-Language-Action Models
  von: Zhang, Hongyin, et al.
  Veröffentlicht: (2025)
• Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference
  von: Liu, Ziyan, et al.
  Veröffentlicht: (2025)
• SpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculative Pruning
  von: Wang, Hanzhen, et al.
  Veröffentlicht: (2025)