Sliding-Cache VLA: Training-Free Acceleration of Vision Language Action Models via Foreground-Background Decoupling
Sliding-Cache VLA: Training-Free Acceleration of Vision Language Action Models via Foreground-Background Decoupling
Yunqing Jiang,Xiangyuan Chen,3 Authors,Chio-in Ieong
2026 · DOI: 10.1109/icassp55912.2026.11464271
IEEE International Conference on Acoustics, Speech, and Signal Processing · 0 Citations