Learning to Accelerate Vision-Language-Action Models through Adaptive Visual Token Caching

Documenti analoghi

• Inject Once Survive Later: Backdooring Vision-Language-Action Models to Persist Through Downstream Fine-tuning
  di: Zhou, Jianyi, et al.
  Pubblicazione: (2026)
• VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching
  di: Xu, Siyu, et al.
  Pubblicazione: (2025)
• DepthCache: Depth-Guided Training-Free Visual Token Merging for Vision-Language-Action Model Inference
  di: Li, Yuquan, et al.
  Pubblicazione: (2026)
• FreqCache: Accelerating Embodied VLN Models with Adaptive Frequency-Guided Token Caching
  di: Zheng, Zihao, et al.
  Pubblicazione: (2026)
• Adaptive Action Chunking at Inference-time for Vision-Language-Action Models
  di: Liang, Yuanchang, et al.
  Pubblicazione: (2026)