SpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculative Pruning

Documenti analoghi

• SpecDiff: Accelerating Diffusion Model Inference with Self-Speculation
  di: Pan, Jiayi, et al.
  Pubblicazione: (2025)
• SpecEE: Accelerating Large Language Model Inference with Speculative Early Exiting
  di: Xu, Jiaming, et al.
  Pubblicazione: (2025)
• Action-aware Dynamic Pruning for Efficient Vision-Language-Action Manipulation
  di: Pei, Xiaohuan, et al.
  Pubblicazione: (2025)
• RedVLA: Physical Red Teaming for Vision-Language-Action Models
  di: Zhang, Yuhao, et al.
  Pubblicazione: (2026)
• PD-VLA: Accelerating Vision-Language-Action Model Integrated with Action Chunking via Parallel Decoding
  di: Song, Wenxuan, et al.
  Pubblicazione: (2025)